This document discusses different types of descriptive research designs including observation studies, correlational research, developmental designs, and survey research. Observation studies involve quantifying behaviors by counting occurrences or rating dimensions. Correlational research examines relationships between variables but cannot determine causation. Developmental designs study changes over time using cross-sectional or longitudinal methods. Survey research involves asking questions of a sample to make inferences about a population. Validity, reliability, and sampling are important considerations for descriptive research.
Variables, theoretical framework and hypothesesH9460730008
The document discusses variables, theoretical frameworks, and hypotheses in research. It defines different types of variables like dependent, independent, moderating, and intervening variables. It provides examples of each and how they relate in theoretical frameworks. The last section discusses how to develop hypotheses for testing relationships between variables. Hypotheses can be directional or non-directional and involve statements of expected relationships between variables. The document outlines the process of hypothesis testing including determining appropriate statistical tests and analyzing results.
The document discusses steps 4 and 5 of the research process - theoretical framework and hypothesis generation. It defines a theoretical framework as identifying and labeling variables and their relationships. A theoretical framework provides the foundation for developing testable hypotheses. Variables can be dependent, independent, moderating, or intervening. The document provides examples of each variable type. It emphasizes that a theoretical framework must clearly define the variables and their hypothesized relationships, along with explanations for why the relationships are expected to exist. Hypotheses are conjectured relationships between two or more variables expressed as testable statements. The document concludes by providing an example theoretical framework for air safety violations at Delta Airlines, identifying relevant variables and their hypothesized relationships.
This document provides an overview and summary of key concepts from chapters 10 and 11 of the book "How to Design and Evaluate Research in Education". It discusses both descriptive and inferential statistics. For descriptive statistics, it defines common measures like mean, median, standard deviation, and explains how they are used to summarize sample data. For inferential statistics, it outlines statistical techniques like hypothesis testing, confidence intervals, and parametric and nonparametric tests that allow researchers to generalize from samples to populations. It provides examples of how these statistical concepts are applied in educational research.
The document defines a hypothesis as a conjectural statement or tentative explanation about the relationship between two or more variables that can be tested. Several authors contribute definitions stating that a hypothesis makes a specific, testable prediction and must be falsifiable. Key aspects of a hypothesis include identifying variables, having explanatory power, and being testable, quantifiable, and generalizable. The document also distinguishes between statistical hypotheses about population parameters, null hypotheses being tested, and critical regions for rejecting null hypotheses based on sample data.
This document provides an introduction to hypothesis testing. It discusses how hypothesis testing involves both induction and deduction. Researchers use induction to make observations and form hypotheses to explain facts. They use deduction to test hypotheses. The document defines what a hypothesis is and lists its key characteristics. It discusses the classical and Bayesian approaches to hypothesis testing. It also explains statistical significance and how the logic of hypothesis testing involves stating a null hypothesis and alternative hypothesis. Researchers use statistical tests to determine if their data provides enough evidence to reject the null hypothesis.
This document outlines the basic building blocks of social scientific research:
1. It discusses specifying a research question, proposing explanations, and formulating testable hypotheses.
2. It also covers identifying key concepts, variables, and units of analysis to establish relationships between variables.
3. Developing hypotheses involves stating empirical, general, plausible, specific, and testable relationships between independent and dependent variables.
Generalizability in fMRI, fast and slowTal Yarkoni
- The document discusses issues around generalizability in fMRI research and proposes strategies for "fast" versus "slow" generalization.
- It notes that most findings in neuroimaging are only interesting if they generalize broadly, but that statistical models must support desired inferences about new stimuli or subjects.
- The document advocates treating factors like subjects and stimuli as random effects to support generalization, and using large stimulus samples to avoid overgeneralizing findings. It suggests both modeling approaches (e.g. random effects) and study design (e.g. more stimuli/subjects) can help researchers generalize more appropriately.
Variables, theoretical framework and hypothesesH9460730008
The document discusses variables, theoretical frameworks, and hypotheses in research. It defines different types of variables like dependent, independent, moderating, and intervening variables. It provides examples of each and how they relate in theoretical frameworks. The last section discusses how to develop hypotheses for testing relationships between variables. Hypotheses can be directional or non-directional and involve statements of expected relationships between variables. The document outlines the process of hypothesis testing including determining appropriate statistical tests and analyzing results.
The document discusses steps 4 and 5 of the research process - theoretical framework and hypothesis generation. It defines a theoretical framework as identifying and labeling variables and their relationships. A theoretical framework provides the foundation for developing testable hypotheses. Variables can be dependent, independent, moderating, or intervening. The document provides examples of each variable type. It emphasizes that a theoretical framework must clearly define the variables and their hypothesized relationships, along with explanations for why the relationships are expected to exist. Hypotheses are conjectured relationships between two or more variables expressed as testable statements. The document concludes by providing an example theoretical framework for air safety violations at Delta Airlines, identifying relevant variables and their hypothesized relationships.
This document provides an overview and summary of key concepts from chapters 10 and 11 of the book "How to Design and Evaluate Research in Education". It discusses both descriptive and inferential statistics. For descriptive statistics, it defines common measures like mean, median, standard deviation, and explains how they are used to summarize sample data. For inferential statistics, it outlines statistical techniques like hypothesis testing, confidence intervals, and parametric and nonparametric tests that allow researchers to generalize from samples to populations. It provides examples of how these statistical concepts are applied in educational research.
The document defines a hypothesis as a conjectural statement or tentative explanation about the relationship between two or more variables that can be tested. Several authors contribute definitions stating that a hypothesis makes a specific, testable prediction and must be falsifiable. Key aspects of a hypothesis include identifying variables, having explanatory power, and being testable, quantifiable, and generalizable. The document also distinguishes between statistical hypotheses about population parameters, null hypotheses being tested, and critical regions for rejecting null hypotheses based on sample data.
This document provides an introduction to hypothesis testing. It discusses how hypothesis testing involves both induction and deduction. Researchers use induction to make observations and form hypotheses to explain facts. They use deduction to test hypotheses. The document defines what a hypothesis is and lists its key characteristics. It discusses the classical and Bayesian approaches to hypothesis testing. It also explains statistical significance and how the logic of hypothesis testing involves stating a null hypothesis and alternative hypothesis. Researchers use statistical tests to determine if their data provides enough evidence to reject the null hypothesis.
This document outlines the basic building blocks of social scientific research:
1. It discusses specifying a research question, proposing explanations, and formulating testable hypotheses.
2. It also covers identifying key concepts, variables, and units of analysis to establish relationships between variables.
3. Developing hypotheses involves stating empirical, general, plausible, specific, and testable relationships between independent and dependent variables.
Generalizability in fMRI, fast and slowTal Yarkoni
- The document discusses issues around generalizability in fMRI research and proposes strategies for "fast" versus "slow" generalization.
- It notes that most findings in neuroimaging are only interesting if they generalize broadly, but that statistical models must support desired inferences about new stimuli or subjects.
- The document advocates treating factors like subjects and stimuli as random effects to support generalization, and using large stimulus samples to avoid overgeneralizing findings. It suggests both modeling approaches (e.g. random effects) and study design (e.g. more stimuli/subjects) can help researchers generalize more appropriately.
The document discusses the different types of hypotheses used in research, including directional and non-directional hypotheses, declarative hypotheses that state relationships between variables, null hypotheses that state no significant differences exist, question form hypotheses used to raise research questions, alternative hypotheses that anticipate differences between variables, and predication form hypotheses that state expected principles for action research studies.
Problem definition and hypothesis formulationRajThakuri
This document discusses problem definition, hypothesis formulation, and different types of research questions and hypotheses. It defines a research problem as a gap between the actual and desired state. Key points made include:
- Research problems are clearly defined questions or issues to investigate.
- Hypotheses make assumptions about relationships between variables and show the direction of research.
- There are descriptive, relational, directional/non-directional, and null/alternative hypotheses. Relational hypotheses examine correlations or causal relationships between variables.
The document outlines the steps to formulate a hypothesis for research. It defines what a hypothesis is, discusses the types of hypotheses (null and alternative), and lists advantages of developing a hypothesis. The key steps provided are: define the research problem, analyze the problem in-depth, define research objectives, and articulate the hypothesis. Hypotheses can be developed through various means like literature review, observations, and prior studies. The document also provides an example of formulating hypotheses for a study on customer preferences and usage of cashless payments.
This document provides an overview of research methodology in psychology. It discusses key concepts like variables, hypotheses, experimental design, and methods of data collection and analysis. Research methods can be descriptive, correlational, or experimental. Experimental research involves manipulating an independent variable and measuring its effects on a dependent variable while controlling for other influences. Critical aspects of research like controlling for biases, ensuring validity and reliability are also covered.
Different methods of research are applied in different areas of research. Different Scholars and researchers have classified the research methods in different ways. Summary of all kinds of classifications is given here.
This is me Sonia Azam from university of the Punjab. this presentation is knowledgeable for all those students whose field related to Research, engineering or business. So enjoy my Presentation Dear fellows!
God Bless you All !!!!
Rethinking the Teaching and Definition of the Practical Significance of Quant...CPEDInitiative
This document proposes redefining how practical significance in quantitative research is determined for leadership decision making. It argues that solely relying on statistical significance and effect sizes can be misleading. Instead, it recommends evaluating the actual performance of the experimental group to see if it meets target goals. Guidelines are provided for EdD students to critically analyze research findings based on practical significance rather than just reporting researcher conclusions. The goal is to make quantitative research more applicable to leadership practice and EdD work.
The document discusses key concepts in developing a theoretical framework and hypotheses for research. It defines a theoretical framework as identifying the important variables and relationships between them. Hypotheses are testable statements developed based on this framework. Variables can be dependent (outcome), independent (predictor), moderating, or intervening. The theoretical framework forms the basis of the research by conceptualizing these relationships between variables.
This document discusses hypothesis in educational research. It defines a hypothesis as an assumption made to solve a problem or predict the relationship between variables, which is then tested. It outlines the characteristics of a good hypothesis, including that it can be tested and proven true or false. The document also explains the importance of hypotheses in focusing research and deriving findings. It identifies three main types of hypotheses: declarative/research hypotheses made based on expectations, question hypotheses, and null hypotheses which assume no relationship or difference.
Hypothesis is a formal statement that represents the expected relationship between an independent and dependent variable.
It is an assumption about the relationship between two or more variables and is predictive in nature
The document defines and describes different types of hypotheses. An hypothesis is a tentative explanation of the expected outcome of an investigation and serves to guide research. Hypotheses can be classified based on their derivation (inductive or deductive) or formulation (directional, non-directional, null). A null hypothesis states there is no association between variables, while the alternative hypothesis proposes an association. Directional hypotheses predict a positive or negative relationship. Well-formulated hypotheses are testable, clear, simple, and relevant.
This tutorial corresponds with Module A Lesson 2 and should be completed by students enrolled in Professor Hokerson's Psychology 300 online class at American River College.
The document defines and discusses hypotheses in research contexts. It provides that a hypothesis is a formal, testable statement of the expected relationship between independent and dependent variables. The document outlines several definitions of a hypothesis provided by authors and discusses the key characteristics of a good hypothesis. It also differentiates between different types of hypotheses such as universal, existential, null, alternate, non-directional, directional, and research hypotheses. The purpose, components, and process of hypothesis making and testing are described.
The document discusses various types of research including exploratory research, descriptive research, diagnostic research, hypothesis-testing research, and applied research. It also covers research methods such as qualitative research, quantitative research, experimental research, and survey research. The overall purpose of research is to gain knowledge and reduce uncertainty for making effective business decisions.
This document discusses hypothesis testing and related statistical concepts. It defines a hypothesis as a statement that can be tested, and distinguishes between the null hypothesis (H0) and alternative hypothesis (Ha). It explains how to select a significance level, commonly 1%, 5% or 10%, and how this relates to Type I and Type II errors. It also covers one-tailed and two-tailed tests, and when to use z-tests or t-tests to test hypotheses about population means based on sample data. The document provides examples of hypotheses for research topics and how to carry out the statistical tests.
This document provides an overview of exploratory factor analysis (EFA). It defines EFA as a technique used to identify clusters of inter-correlated variables and empirically test theoretical data structures. The document outlines the assumptions, steps, and examples of EFA. It discusses determining the number of factors, rotating factor loadings for interpretation, and interpreting the factor structure. The goal of EFA is to simplify data and develop theoretical models through identification of underlying factors.
A hypothesis is an assumption or proposed explanation made on limited information to guide further investigation. It provides the basis for investigation by establishing the direction of inquiry. A good hypothesis is specific, testable, and related to existing theory. There are two main types - crude hypotheses indicate what data to collect, while refined hypotheses state empirical relationships. Hypotheses come in descriptive, explanatory, null, and alternative forms and serve important functions such as explaining facts, directing inquiry, and enabling deductions.
Student Affairs Assessment Committee Training Part 2Stan Dura
The document outlines a training agenda for assessment fellows that includes a review of foundational statistical concepts such as univariate, bivariate, and multivariate models. It discusses how to use descriptive statistics, correlations, regression, and factor analysis to increase understanding of variables and their relationships through increasingly complex models. The training aims to help fellows better predict, control for, and understand variables in assessment through applying these foundational statistical techniques and concepts.
Hypothesis is a tentative statement about the relationship between two or more variables that is tested for reliability and validity. There are several types of hypotheses including null, alternative, descriptive, relational, non-directional, causal, statistical, and complex hypotheses. Hypotheses should be clear, testable, specific, consistent with known facts, and explain the phenomenon under investigation. Common sources of hypotheses include observation, analogies, intuitions, previous study findings, and theories.
This document provides an overview of key concepts for developing a valid and reliable language test, including criteria like relevance, representativeness, and authenticity. It discusses the importance of qualitative and quantitative analyses, explaining various types of validity like content and construct validity. Factors that influence reliability are outlined, such as test length and difficulty. Statistical analyses of test scores are described, including descriptive statistics, correlations between scores, and item reliability analyses to identify poorly discriminating questions. The goal is to improve tests by evaluating them against these criteria.
The document discusses the different types of hypotheses used in research, including directional and non-directional hypotheses, declarative hypotheses that state relationships between variables, null hypotheses that state no significant differences exist, question form hypotheses used to raise research questions, alternative hypotheses that anticipate differences between variables, and predication form hypotheses that state expected principles for action research studies.
Problem definition and hypothesis formulationRajThakuri
This document discusses problem definition, hypothesis formulation, and different types of research questions and hypotheses. It defines a research problem as a gap between the actual and desired state. Key points made include:
- Research problems are clearly defined questions or issues to investigate.
- Hypotheses make assumptions about relationships between variables and show the direction of research.
- There are descriptive, relational, directional/non-directional, and null/alternative hypotheses. Relational hypotheses examine correlations or causal relationships between variables.
The document outlines the steps to formulate a hypothesis for research. It defines what a hypothesis is, discusses the types of hypotheses (null and alternative), and lists advantages of developing a hypothesis. The key steps provided are: define the research problem, analyze the problem in-depth, define research objectives, and articulate the hypothesis. Hypotheses can be developed through various means like literature review, observations, and prior studies. The document also provides an example of formulating hypotheses for a study on customer preferences and usage of cashless payments.
This document provides an overview of research methodology in psychology. It discusses key concepts like variables, hypotheses, experimental design, and methods of data collection and analysis. Research methods can be descriptive, correlational, or experimental. Experimental research involves manipulating an independent variable and measuring its effects on a dependent variable while controlling for other influences. Critical aspects of research like controlling for biases, ensuring validity and reliability are also covered.
Different methods of research are applied in different areas of research. Different Scholars and researchers have classified the research methods in different ways. Summary of all kinds of classifications is given here.
This is me Sonia Azam from university of the Punjab. this presentation is knowledgeable for all those students whose field related to Research, engineering or business. So enjoy my Presentation Dear fellows!
God Bless you All !!!!
Rethinking the Teaching and Definition of the Practical Significance of Quant...CPEDInitiative
This document proposes redefining how practical significance in quantitative research is determined for leadership decision making. It argues that solely relying on statistical significance and effect sizes can be misleading. Instead, it recommends evaluating the actual performance of the experimental group to see if it meets target goals. Guidelines are provided for EdD students to critically analyze research findings based on practical significance rather than just reporting researcher conclusions. The goal is to make quantitative research more applicable to leadership practice and EdD work.
The document discusses key concepts in developing a theoretical framework and hypotheses for research. It defines a theoretical framework as identifying the important variables and relationships between them. Hypotheses are testable statements developed based on this framework. Variables can be dependent (outcome), independent (predictor), moderating, or intervening. The theoretical framework forms the basis of the research by conceptualizing these relationships between variables.
This document discusses hypothesis in educational research. It defines a hypothesis as an assumption made to solve a problem or predict the relationship between variables, which is then tested. It outlines the characteristics of a good hypothesis, including that it can be tested and proven true or false. The document also explains the importance of hypotheses in focusing research and deriving findings. It identifies three main types of hypotheses: declarative/research hypotheses made based on expectations, question hypotheses, and null hypotheses which assume no relationship or difference.
Hypothesis is a formal statement that represents the expected relationship between an independent and dependent variable.
It is an assumption about the relationship between two or more variables and is predictive in nature
The document defines and describes different types of hypotheses. An hypothesis is a tentative explanation of the expected outcome of an investigation and serves to guide research. Hypotheses can be classified based on their derivation (inductive or deductive) or formulation (directional, non-directional, null). A null hypothesis states there is no association between variables, while the alternative hypothesis proposes an association. Directional hypotheses predict a positive or negative relationship. Well-formulated hypotheses are testable, clear, simple, and relevant.
This tutorial corresponds with Module A Lesson 2 and should be completed by students enrolled in Professor Hokerson's Psychology 300 online class at American River College.
The document defines and discusses hypotheses in research contexts. It provides that a hypothesis is a formal, testable statement of the expected relationship between independent and dependent variables. The document outlines several definitions of a hypothesis provided by authors and discusses the key characteristics of a good hypothesis. It also differentiates between different types of hypotheses such as universal, existential, null, alternate, non-directional, directional, and research hypotheses. The purpose, components, and process of hypothesis making and testing are described.
The document discusses various types of research including exploratory research, descriptive research, diagnostic research, hypothesis-testing research, and applied research. It also covers research methods such as qualitative research, quantitative research, experimental research, and survey research. The overall purpose of research is to gain knowledge and reduce uncertainty for making effective business decisions.
This document discusses hypothesis testing and related statistical concepts. It defines a hypothesis as a statement that can be tested, and distinguishes between the null hypothesis (H0) and alternative hypothesis (Ha). It explains how to select a significance level, commonly 1%, 5% or 10%, and how this relates to Type I and Type II errors. It also covers one-tailed and two-tailed tests, and when to use z-tests or t-tests to test hypotheses about population means based on sample data. The document provides examples of hypotheses for research topics and how to carry out the statistical tests.
This document provides an overview of exploratory factor analysis (EFA). It defines EFA as a technique used to identify clusters of inter-correlated variables and empirically test theoretical data structures. The document outlines the assumptions, steps, and examples of EFA. It discusses determining the number of factors, rotating factor loadings for interpretation, and interpreting the factor structure. The goal of EFA is to simplify data and develop theoretical models through identification of underlying factors.
A hypothesis is an assumption or proposed explanation made on limited information to guide further investigation. It provides the basis for investigation by establishing the direction of inquiry. A good hypothesis is specific, testable, and related to existing theory. There are two main types - crude hypotheses indicate what data to collect, while refined hypotheses state empirical relationships. Hypotheses come in descriptive, explanatory, null, and alternative forms and serve important functions such as explaining facts, directing inquiry, and enabling deductions.
Student Affairs Assessment Committee Training Part 2Stan Dura
The document outlines a training agenda for assessment fellows that includes a review of foundational statistical concepts such as univariate, bivariate, and multivariate models. It discusses how to use descriptive statistics, correlations, regression, and factor analysis to increase understanding of variables and their relationships through increasingly complex models. The training aims to help fellows better predict, control for, and understand variables in assessment through applying these foundational statistical techniques and concepts.
Hypothesis is a tentative statement about the relationship between two or more variables that is tested for reliability and validity. There are several types of hypotheses including null, alternative, descriptive, relational, non-directional, causal, statistical, and complex hypotheses. Hypotheses should be clear, testable, specific, consistent with known facts, and explain the phenomenon under investigation. Common sources of hypotheses include observation, analogies, intuitions, previous study findings, and theories.
This document provides an overview of key concepts for developing a valid and reliable language test, including criteria like relevance, representativeness, and authenticity. It discusses the importance of qualitative and quantitative analyses, explaining various types of validity like content and construct validity. Factors that influence reliability are outlined, such as test length and difficulty. Statistical analyses of test scores are described, including descriptive statistics, correlations between scores, and item reliability analyses to identify poorly discriminating questions. The goal is to improve tests by evaluating them against these criteria.
This document discusses various methods for portfolio assessment and grading student work, including self-reports, rating scales, checklists, and portfolios. It describes different types of rating scales like Likert scales, semantic differential scales, and Thurstone scales. The document provides guidelines for developing grading systems, assigning letter grades, conducting parent-teacher conferences, and reporting test results to parents. It discusses decisions around what to include in grades, how to combine assessments into a composite grade, and using portfolio assessment to evaluate the learning process.
This document discusses correlational research, which aims to describe relationships between variables and measure their strength. Correlational research observes how variables change together without manipulation. A correlation indicates the direction, form, and consistency of a relationship. Positive relationships involve variables changing in the same direction, while negative relationships involve opposite direction changes. Correlational designs can be explanatory, relating co-varying variables, or predictive, identifying predictors of an outcome variable. Correlational research allows investigating relationships but cannot determine causation due to low internal validity.
The document discusses key elements of research design, including:
1. It defines a research design as a plan for investigating research questions and problems.
2. Key components of a research design are identified as the problem definition, theoretical framework, hypothesis generation, research methodology, data collection and analysis, and reporting.
3. Different types of research designs are explored, including exploratory, descriptive, and hypothesis testing designs. Factors like the level of researcher interference and study settings (contrived vs. non-contrived) are also discussed.
This document discusses steps 4 and 5 of the research process - developing a theoretical framework and hypotheses. It defines key terms like variables, hypotheses, and theoretical frameworks. Variables can be dependent, independent, moderating, or intervening. A theoretical framework shows the relationships between variables and informs hypotheses development. Hypotheses are testable statements about the relationships between variables. The document provides examples of theoretical frameworks and hypotheses to illustrate these concepts.
This document discusses correlational research, which examines relationships between variables without manipulating them. It defines correlational research and describes its non-experimental design, purpose to test associations between variables with limited control, and high external validity. Examples of positive, negative, and no correlations are provided. Characteristics like being non-experimental and backward-looking are outlined. Common data collection methods include surveys, observations, and secondary data. Correlation and regression analyses can quantify and predict relationships between variables, though correlation does not imply causation due to directionality and third variable problems.
This document provides an overview of common types of quantitative research methods, including descriptive research, correlational research, causal-comparative (ex post facto) research, and experimental research. Descriptive research aims to describe characteristics of a population or phenomenon. Correlational research examines relationships between variables without determining cause. Causal-comparative research investigates possible cause-and-effect relationships by observing existing conditions and searching for plausible causal factors. Experimental research tests hypotheses by manipulating independent variables and measuring effects on dependent variables in a controlled environment.
Transitioning to the Common Core is not going to be easy. Hear what we've learned from educators across the country about what's different and what you should look for in new materials.
This tutorial corresponds with Module A Lesson 2 and should be completed by students enrolled in Professor Hokerson's Psychology 300 online class at American River College.
Factor analysis is a statistical technique used to reduce a large number of variables into fewer factors. It analyzes the relationship between observable variables and how they are affected by smaller sets of unobservable variables. The main goal is to summarize information from many variables into a few factors. There are three main types: exploratory factor analysis identifies underlying factors without predefined structure, confirmatory factor analysis confirms predetermined factor structures, and structural equation modeling tests hypothesized relationships between variables and factors.
The document discusses research objectives, questions, and hypotheses. It begins by stating that research objectives are derived from the overall study aim and provide direction for the study by helping to focus its scope and prevent unnecessary data collection. Objectives should be specific, measurable, achievable, relevant, and time-bound. Research questions are sometimes rewordings of the objectives and aim to interrogate rather than declare. Hypotheses predict relationships between variables and can be directional, non-directional, null, or alternative. The document provides examples and guidelines for effectively writing objectives, questions, and hypotheses to structure an informative study.
Non experimental%20 quantitative%20research%20designs-1jhtrespa
The document discusses different types of non-experimental quantitative research designs, including descriptive studies, relationship studies, comparative studies, correlational studies, prediction studies, causal-comparative/ex-post facto studies, and surveys. Relationship studies are important in non-experimental designs because they allow researchers to identify possible causes, variables to study, and ways to predict the value of one variable based on others. The key difference between cross-sectional and longitudinal surveys is that cross-sectional surveys collect information from samples at one time, while longitudinal surveys study the same group of subjects over an extended period of time.
The document discusses different types of validity in psychological measurement:
1. Content validity refers to how representative the items on a test are of the domain being measured. It is determined through expert judgment of item relevance.
2. Criterion-related validity examines the correlation between test scores and external criteria. It focuses on a test's ability to predict outcomes. Obtaining appropriate criteria can be difficult.
3. Construct validity seeks to explain variance in test performance through the theoretical constructs or factors underlying them. It involves suggesting constructs, deriving hypotheses from theory, and empirical testing. Construct validity is concerned with validating the theory behind a test.
The document discusses different types of hypotheses used in research studies, including simple, complex, empirical, null, alternative, statistical, directional, non-directional, causal, and associative hypotheses. It defines each type of hypothesis and provides examples. The document also covers the functions, characteristics, and contributions of hypotheses in structuring research problems and guiding the research process.
The document discusses correlational research, which examines relationships between two variables without manipulating them. Correlational research can establish that variables are related but cannot prove one causes the other. Key points covered include:
- Correlation coefficients measure the strength and direction of relationships between variables.
- Positive correlations indicate variables increase together, while negative correlations mean one decreases as the other increases.
- Correlational research has advantages like lower cost but cannot prove causation like experiments can.
- Common data collection methods are naturalistic observation, surveys, archival data, and secondary data. Correlation and regression analyses are frequently used to analyze correlational data and make predictions.
This document provides an overview of descriptive research. Descriptive research describes characteristics or phenomena as they naturally occur without influencing or manipulating variables. It can be used to identify problems, develop hypotheses for further research, and make predictions. The key types of descriptive research discussed are survey research, which collects data from populations to describe trends or opinions; interrelationship research including case studies, causal-comparative research, and correlational research; and developmental research which studies phenomena over time. Descriptive research is useful in education for identifying issues, gathering data to inform decision making, and establishing baseline information.
Magindren Kuppusamy is a certified project management and big data trainer with qualifications including a PMP certification and MBA. They have received several awards for their work including an Asia Pacific Entrepreneurship Award. Their training covers topics such as big data analytics, data visualization, and data storytelling over three days. Big data analytics involves examining large datasets to uncover hidden patterns, correlations, market trends, and customer preferences that can help organizations make business decisions. Correlations refer to relationships between two or more variables in data, which can be positive, negative, zero, or spurious. Market trends analyze past market behavior and consumer preferences to provide insights.
This document summarizes key aspects of different types of scales used in research methodology. It discusses nominal, ordinal, and interval scales. For nominal scales, it describes how they are used for classification but cannot determine distances between categories. Ordinal scales allow ranking or ordering but do not assume equal distances between ranks. Interval scales assume equidistant points between scale elements and are useful for calculating differences and performing statistical analyses. Questionnaires can employ different scale types to reliably measure social cognition and manage unpredictable factors in decision making.
1. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 1
DESCRIPTIVE RESEARCH
• To behold is to look beyond the fact; to observe, to
go beyond the observation
• Look at the world of people, and you will be
overwhelmed by what you see
• But select from that mass of humanity a well-
chosen few, and observe them with insight, and
they will tell you more than all the multitudes
together
2. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 2
Descriptive Quantitative
Research
• Involves either identifying the characteristics of an
observed phenomenon or exploring possible
correlations among two or more phenomena
• In every case, descriptive research examines a
situation AS IT IS
• It does not involve changing or modifying the
situation under investigation, nor is it intended to
determine cause-and-effect relationships
• Strategies include sampling, making observations,
interviewing – take on a very different form when
we want them to yield quantitative data
3. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 3
Descriptive Research Designs
• Include observation studies, correlational
research, developmental designs, and survey
research
• All of these approaches yield quantitative
information that can be summarized through
statistical analyses
• Survey research is the most frequently used
in all disciplines
4. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 4
Observation Studies
• In qualitative studies, observations are usually recorded in great detail,
perhaps with fieldnotes or videotapes that capture the wide variety of
ways in which people act and interact
• From these data, the researcher constructs a complex yet integrated
picture of how people spend their time
• In quantitative research, an observation study is quite different
• Typically, the focus is on a particular aspect of behaviour
• Furthermore, the behaviour is quantified in some way
• In some situations, each occurrence of the behaviour is counted to
determine its overall frequency
• In other situations, the behaviour is rated for accuracy, intensity,
maturity, or some other dimension
• But regardless of approach, the researcher strives to be as objective as
possible in assessing the behaviour being studied
5. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 5
Observation Studies
• To maintain such objectivity, he or she is likely to use strategies
such as the following:
1) Define the behaviour being studied in a precise, concrete manner
so that the behaviour is easily recognised when it occurs
2) Divide the observation period into small segments and then
record whether the behaviour does or does not occur during each
segment
3) Use a rating scale to evaluate the behaviour in terms of specific
dimensions
4) Have two or three people rate the same behaviour independently,
without knowledge of one another’s ratings
5) Train the rater(s) to follow specific criteria when counting or
evaluating the behaviour, and continue training until consistent
ratings are obtained for any single occurrence of the behaviour
6. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 6
Observation Studies
• Despite the extensive investment (time and
energy), an observational study can yield
data that portray much of the richness and
complexity of human behaviour
• In some situations, then, it provides a
quantitative alternative to such approaches
as ethnographies and grounded theory
studies
7. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 7
Correlational Research
• A correlational study examines the extent
to which differences in one characteristic or
variable are related to differences in one or
more other characteristics or variables
• A correlation exists if, when one variable
increases, another variable either increases
or decreases in a somewhat predictable
fashion
8. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 8
Correlational Research
• Simple correlation – researchers gather data about
two or more characteristics; numbers that reflect
specific measurements of the characteristics in
question – test scores, CGPAs, ratings, …
• Each has two numbers, used to calculate
correlation coefficient (r)
• If perfectly correlated r = +1.00 or r = -1.00
• If unrelated or remotely related, r is close to 0
• Moderate correlations are common
9. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 9
Correlational Research
• Examining only two variables – helpful to plot on
scatterplot (also known as scattergram) to allow a
visual inspection of the relationship between the two
variables
• Refer to page 181 of the textbook for the scatterplot
• The diagonal line running through the middle of the
dots is called the line of regression reflects a
hypothetical perfect correlation
• If all the dots fell exactly on this line, r would be
+1.00, dots below the line show children whose
reading level is advanced for their age, and dots above
the line show children who are lagging a bit in reading
10. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 10
Correlational Research
Can make 3 statements from the scatterplot.
1) Can describe the homogeneity or heterogeneity of the two
variables (the extent to which the children are similar to or
different from one another with respect to age and reading
level. Eg. group of only age 6 and 7 has greater
homogeneity than group of age 6 - 13)
2) Can describe the degree to which the two variables are
intercorrelated by computing the correlation coefficient r
3) The most important, we can interpret the data and give
them meaning – children’s reading level improves as they
grow older, without hesitation as shown by the upward
trend of the dots from left to right
11. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 11
A Caution About Interpreting
Correlational Results
• In all correlational studies, be alert for faulty logic
• Correlation does not, in and of itself, indicate
causation
• Although in some cases, influence may indeed be
present, for example, chronological age influences
mental development, including their reading
ability
• But ultimately we can never infer a cause-and-
effect relationship on the basis of correlation alone
12. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 12
A Caution About Interpreting
Correlational Results
• One variable correlates meaningfully with
another only when a common causal bond
links the phenomena of both variables in a
logical relationship
• Increase in the population of birds in Tasik
Serdang has no meaningful relationship
with the increase of the population of
elephants in Thailand – the correlation is
simply a fluke and meaningless
13. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 13
A Caution About Interpreting
Correlational Results
• In the example, the faulty logic is readily apparent,
yet we often see similarly faulty reasoning
proposed in correlational research reports
• Imagine that a researcher finds a correlation
between socioeconomic level and academic
performance - it would be all too easy to draw the
conclusion that socioeconomic status directly
affects academic achievement – also if we could
improve the family’s economic status, then the
learning ability of the family’s children would also
improve
14. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 14
A Caution About Interpreting
Correlational Results
• No, no, no! We cannot make an inference about causation
on the basis of correlated data alone
• It is possible that salary does have an impact on children’s
grades, BUT it is equally possible that it does not
• May be an undetermined third variable influences BOTH
the salary and the children’s school performance
• If we were to infer that socioeconomic status directly
affects academic achievement, not only would we be going
far beyond the data we have, but we would also have
trouble accounting for all of the world’s geniuses and
intellectual giants, some of whom have been born of
indigent parents and grown up in poverty
15. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 15
A Caution About Interpreting
Correlational Results
• The data may not lie, but the causal conclusions
we draw from the data may, at times, be extremely
suspect
• Nevertheless, a good researcher must not be
content to stop at the point of finding a
correlational relationship, because beneath the
correlation lie some potentially quite interesting
data whose interpretation may conceivably lead to
the discovery of new and exciting information
• r is just a signpost pointing to further findings
16. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 16
A Caution About Interpreting
Correlational Results
• The forces of the correlated data will
determine the ultimate meaning of the
correlation
17. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 17
How Validity and Reliability
Affect Correlation
• We will not find correlation if the
measurement instruments have poor validity
and reliability
• For example, if the reading test used is
neither a valid (accurate) nor reliable
(consistent) measure of reading
achievement, therefore we will not find
correlation
18. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 18
Developmental Designs
• To study how a particular characteristic
changes, use either 1) a cross-sectional (X-
S) study or 2) a longitudinal (LG) study
• In a cross-sectional study, a developmental
psychologist might study the nature of
friendships for children at ages 4, 8, 12, and
16. A gerontologist might consider how
retired people in their 70s, 80s, and 90s, are
most likely to spend their leisure time
19. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 19
Developmental Designs
• In a longitudinal study, a single group of people is
followed over the course of several months or
years, and data related to the characteristic(s)
under investigation are collected at various times
• For example, an educational psychologist might
get measures of academic achievement and social
adjustment for a group of Year Four students and
then, 10 years later, find out which students had
completed high school and which ones had not
20. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 20
Developmental Designs
• Obviously, cross-sectional studies are easier to
conduct than longitudinal studies, because the
researcher can collect all the needed data at a
single time, and don’t have to worry tracking
down people
• An additional disadvantage of a longitudinal
design is that when people respond repeatedly to
the same measurement instrument, they are likely
to improve simply because of their practice with
the instrument, even if the characteristic being
measured hasn’t changed at all
21. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 21
Developmental Designs
• A disadvantage of cross-sectional designs is that
the different age groups sampled may have been
raised under different environmental conditions
• Groups of 20-year-olds and 70-year-olds –
different education standards
• A second disadvantage of a cross-sectional design
is that we cannot compute correlations between
characteristics at different age levels
22. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 22
Survey Research
• Survey means “to look or see over or beyond”
• “Looking” or “seeing” is not restricted to perception
through the physical eye only
• Survey research involves acquiring information about one
or more groups of people – perhaps about their
characteristics, opinions, attitudes, or previous experiences
– by asking them questions and tabulating their answers
• The ultimate goal is to learn about a large population by
surveying a sample of that population
23. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 23
Survey Research
• This approach is called a descriptive survey or
normative survey
• Reduced to its basic elements, a survey is quite
simple in design: The researcher poses a series of
questions to willing participants; summarises their
responses with percentages, frequency counts, or
more sophisticated statistical indexes; and then
draws inferences about a particular population
from the responses of the sample
• It is a common approach, used with more or less
sophistication in many areas of human activity
24. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 24
Survey Research
• This is not to suggest, however, that
because of its frequent use, a survey is any
less demanding in its design requirements or
any easier for the researcher to conduct than
any other type of research
• Quite the contrary, the survey design makes
critical demands on the researcher that, if
not carefully respected, may place the entire
research effort in jeopardy
25. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 25
Survey Research
• Survey research captures a fleeting moment in time
• By drawing conclusions from one transitory collection of
data, we may extrapolate about the state of affairs over a
longer time period
• At best, the extrapolation is a conjecture, and sometimes a
hazardous one at that, but it is our only way to generalise
from what we see
• So often, survey reports that we read seem to suggest that
what the researcher found in one sample population at one
particular time can be accepted for all time as a constant
26. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 26
Survey Research
• An additional consideration in survey research is that we
are relying on self-report data
• People are telling us what they believe to be true or,
perhaps, what they think we want to hear
• People’s memories for events are often distortions of
reality: What they think happened isn’t always what did
happen
• Furthermore, people’s descriptions of their attitudes and
opinions are often constructed on the spot – often times,
they haven’t really thought about certain issues until a
researcher poses a question about them – and so may be
coloured by recent events or the current context
27. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 27
Survey Research
• An additional problem is that some people
may intentionally misrepresent the facts (at
least, the “facts” as they know them) in
order to present a favourable impression to
the researcher
• Survey research typically employs a face-
to-face interview, a telephone interview, or
a written questionnaire
28. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 28
Face-to-Face and Telephone Interviews
• In survey research, interviews are fairly structured
• In a structured interview, the researcher asks a standard
set of questions and nothing more
• In a semi-structured interview, the research may follow
the standard questions with one or more individually
tailored questions to get clarification or probe a person’s
reasoning
• The interview tends to be informal and friendly in a
qualitative study but more formal and emotionally neutral
in a quantitative one
• Participants in a qualitative interview may feel as if they’re
simply engaging in a friendly chat with the researcher, who
is typically someone they’ve come to know and trust
29. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 29
Face-to-Face and Telephone Interviews
• In contrast, participants in survey research are continually
aware that, yes, this is an interview, and that the temporary
relationship they’ve formed with the researcher will end
once the interview is complete
• This is not to say, however, that a survey researcher
shouldn’t strive to establish rapport with participants
• Quite the contrary, the researcher is more likely to gain
participants’ cooperation and encourage them to respond
honestly if he or she is likable and friendly and shows a
genuine interest in what they have to say
30. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 30
Face-to-Face and Telephone Interviews
• Face-to-face interviews have the distinct
advantage of enabling the researcher to establish
rapport with potential participants and therefore
gain their cooperation; thus, such interviews yield
the highest response rates – the percentages of
people agreeing to participate – in survey research
• However, the time and expense involved may be
prohibitive if the needed interviewees reside in a
variety of states and countries
31. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 31
Face-to-Face and Telephone Interviews
• Telephone interviews are less time-consuming and less expensive
(they involve only the cost of long-distance calls), and the researcher
has ready access to virtually anyone on the planet who has a telephone
• Although the response rate is not as high as for a face-to-face
interview (many people are apt to be busy, annoyed at being bothered,
or otherwise not interested in participating), it is considerably higher
than for a mailed questionnaire
• The researcher cannot establish the same kind of rapport that is
possible in a face-to-face situation, and the sample will be biased to the
extent that people without phones are part of the population about
whom the researcher wants to draw inferences
• Personal interviews, whether they be face-to-face or over the
telephone, allow the researcher to clarify ambiguous answers and,
when appropriate, seek follow-up information
• Because such interviews take time, however, they may not be practical
when large sample sizes are important
32. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 32
Questionnaires
• Data lie deep within the minds or attitudes, feelings, or reaction of
men/women
• Instrument for observing the data beyond the physical reach is the
questionnaires since paper-pencil questionnaires can be sent to a large
number of people, including those who live thousands of miles away
• Thus, they may save the researcher travel expenses, and postage is
typically cheaper than a lengthy long-distance telephone call
• The social scientist who collects data with a questionnaire and the
physicist who determines the presence of radioactivity with a Geiger
counter are at just about the same degree of remoteness from their
respective sources of data: Neither sees the source from which the data
originate
• The Geiger counter and questionnaires are impersonal probe
• They are governed by practical guidelines
33. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 33
Questionnaires
• From the perspective of survey participants, this distance becomes an
additional advantage: Participants can respond to questions with assurance that
their responses will be anonymous, and so they may be more truthful than they
would be in a personal interview, particularly when they are talking about
sensitive or controversial issues
• Yet questionnaires have their drawbacks as well
• Typically, the majority of people who receive questionnaires don’t return them
– in other words, there may be a low return rate – and the people who do
return them are not necessarily representative of the originally selected sample
• Even when people are willing participants in a questionnaire study, their
responses will reflect their reading and writing skills and, perhaps, their
misinterpretation of one or more questions
• Furthermore, by specifying in advance all of the questions that will be asked –
and thereby eliminating other questions that could be asked about the issue or
phenomenon in question – the researcher is apt to gain only limited, and
possibly distorted, information
34. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 34
Using Checklists and Rating
Scales
• Observation studies look at people’s behaviours, and developmental
studies, correlational studies, and survey research frequently use
questionnaires to learn about people’s behaviours, characteristics,
attitudes, and opinions
• Behaviours and attitudes are often quite complex and so not, at least on
the surface, easily evaluated or quantified
• Two techniques that facilitate both evaluation and quantification in
such circumstances are the checklist and the rating scale
• A checklist is a list of behaviours, characteristics, or other entities that
a researcher is investigating. Either the researcher or participants
(depending on the study) simply check(s) whether each item on the list
is observed, present, or true; or else not observed, present, or true
35. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 35
Using Checklists and Rating
Scales
• A rating scale is more useful when a behaviour, attitude, or other
phenomenon of interest needs to be evaluated on a continuum of, say,
“inadequate” to “excellent”, “never” to “always”, or “strongly
disapprove” to “strongly approve”
• Rating scales were developed by Rensis Likert in the 1930s to assess
people’s attitudes; accordingly, they are sometimes called Likert
scales
• Experts have mixed views about letting respondents remain neutral in
interviews and questionnaires
• If you use rating scales in your own research, you should consider the
implications of letting your respondents”straddle the fence” by
including a “no opinion” or other neutral response, and design your
scales accordingly
36. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 36
Using Checklists and Rating
Scales
• Whenever you use checklists or rating scales, you
simplify and more easily quantify people’s
behaviours and attitudes
• In the process, however, you may lose valuable
information
• Ultimately you will have to determine whether the
trade-offs is worth it for the particular research
problem you are investigating
37. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 37
Planning and Conducting
Interviews
• Interviewing involves much more than just
asking questions
• The questions for the interview should be
carefully planned and precisely worded to
yield the kinds of data the researcher needs
to answer his or her research question
38. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 38
Guidelines for Conducting
Interviews in a Quantitative Study
1. Make sure your interviewees are representative of the group
2. Find a suitable location
3. Get written permission
4. Establish and maintain rapport
5. Focus on the actual rather than on the abstract or hypothetical
6. Don’t put words in people’s mouths
7. Record responses verbatim
8. Keep your reactions to yourself
9. Remember that you are not necessarily getting the facts
But interviews are typically more structured in quantitative studies
than they are in qualitative studies. The following are additional
guidelines for conducting interviews in quantitative research
39. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 39
Guidelines for Conducting
Interviews in a Quantitative Study
10. As you write the questions, consider how you can quantify the
responses, and modify the questions accordingly. Remember, you
are conducting a quantitative study. Thus, you will, to some extent,
be coding people’s responses as numbers and, quite possibly,
conducting statistical analyses on those numbers. You will be able
to assign numerical codes to responses more easily if you identify an
appropriate coding scheme ahead of time
11. Consider asking questions that will elicit qualitative information as
well. You do not necessarily have to quantify everything. People’s
responses to a few open-ended questions may support or provide
additional insights into the numerical data you obtain from more
structured questions
40. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 40
Guidelines for Conducting
Interviews in a Quantitative Study
12. Pilot-test the questions. When you plan your interview, you will, of
course, be trying hard to develop clear and concise questions.
Despite your best intentions, however, you may write questions that
are ambiguous or misleading or that yield uninterpretable or
otherwise useless responses. You can save yourself a great deal of
time over the long run if you fine-tune your questions before you
begin data collection. You can easily find the weak spots in your
questions by asking a few volunteers to answer them in a pilot study
13. Restrict each question to a single idea. Don’t try to get too much
information in any single question; in doing so, you may get
multiple kinds of data – “mixed messages”, so to speak – that are
difficult to interpret
41. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 41
Guidelines for Conducting
Interviews in a Quantitative Study
14. Save controversial questions for the latter part of the
interview. If you will be touching on sensitive topics
(e.g., attitudes about AIDS, opinions about gun control),
put them near the end of the interview, after you have
established rapport and gained the person’s trust
15. Seek clarifying information when necessary. Be alert for
responses that are vague or otherwise difficult to
interpret. Simple probes such as “Can you tell me more
about that?” may produce the additional information you
need
42. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 42
Constructing and Administering a
Questionnaire
• Questionnaires seem so simple, yet in our
experience they can be tricky to construct and
administer
• One false step can lead to uninterpretable data or
an abysmally low return rate
43. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 43
Guidelines for Constructing a
Questionnaire
1. Keep it short. Your questionnaire should be as brief as possible and
solicit only that information essential to the research project. You
should test every item by two criteria: (a) What do I intend to do
with the information I am requesting? and (b) Is it absolutely
essential to have this information to solve part of the research
problem?
2. Use simple, clear, unambiguous language. Write questions that
communicate exactly what you want to know. Avoid terms that your
respondents may not understand, such as obscure words or technical
jargon. Also avoid words that do not have precise meanings, such as
several and usually
44. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 44
Guidelines for Constructing a
Questionnaire
3. Check for unwarranted assumptions implicit in your questions. Consider a
very simple question:
“How many cigarettes do you smoke each day?” It seems to be a clear and
unambiguous question, especially if we accompany it with certain choices
so that all the respondent has to do is to check one of them:
How many cigarettes do you smoke each day? (Check one of the
following.)
More than 25 25-16 15-11
10-6 5-1 None
• One obvious assumption here is that the person is a smoker, which probably
is not the case for all participants
• A second assumption is that a person smokes the same number of cigarettes
each day, but for many smokers, this assumption is not true
• At work, if under pressure, they may be chain smokers and may smoke
more
45. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 45
Guidelines for Constructing a
Questionnaire
• But at home on weekends and holidays, they may relax and smoke
only one or two cigarettes a day or go without smoking at all
• How are the people in this group supposed to answer the above
question?
• What box does this type of smoker check?
• First, you have to inspect the assumption underlying the question:
Does it fit the reality?
• Had the author of the question considered the assumptions on which
the question was predicated, he or she might first have asked questions
as these:
“Do you smoke cigarettes?
Yes No (If you mark “no”, skip the next two questions.)
“Are your daily smoking habits reasonably consistent; that is, do you
smoke about the same number of cigarettes each day?”
Yes No (If you mark “no”, skip the next question.)
46. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 46
Guidelines for Constructing a
Questionnaire
4. Word your questions in ways that do not give clues about preferred
or more desirable responses. Take another question: “What
strategies have you used to try to quit smoking?” By implying that
the respondent has, in fact, tried to quit, it may lead him or her to
describe strategies that have never been seriously tried at all
5. Check for consistency. When an issue about which you are asking is
such that some respondents may give answers that are socially
acceptable rather than true, you may wish to incorporate a
“countercheck” question into your list at some distance from the
first question. This strategy helps verify the consistency with which
a respondent has answered questions. For instance, take the
following two items appearing in a questionnaire as items 2 and 30.
(Their distance from each other increases the likelihood that a
person will answer the second without recalling how he or she
answered the first.)
47. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 47
Guidelines for Constructing a
Questionnaire
Notice how one individual has answered them:
2. Check one of the following choices:
In my thinking, I am a socialist.
__ In my thinking, I am a capitalist.
30. Check one of the following choices:
__ I believe that major economic activities must be owned by the state.
I believe that major economic activities must be owned by private owners.
The two responses are inconsistent. In the first, the respondent claims to be
a socialist but later, when given the socialist and the capitalist positions in
another form, indicates a position generally thought to be more capitalist
than socialist. Such an inconsistency might lead you to question whether the
respondent is truly the socialist thinker that he or she claims to be
48. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 48
Guidelines for Constructing a
Questionnaire
6. Determine in advance how you will code the
responses. As you write your questions, perhaps
even before you write them, develop a plan for
recoding participants’ responses into numerical
data that you can statistically analyse. Data
processing procedures may also dictate the form a
questionnaire should take. If, for example,
people’s response sheets will be fed into a
computer scanner, the questionnaire must be
structured differently than if the responses will be
tabulated using paper and pencil
49. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 49
Guidelines for Constructing a
Questionnaire
7. Keep the respondent’s task simple. Make the instrument as simple to read
and respond to as possible. Remember, you are asking for people’s time, a
precious commodity for many people these days
• Discussion items – those that present open-ended questions and ask people
to respond with lengthy answers – are time-consuming and mentally
exhausting for both the participants and the researcher. Don’t forget that
you will have to wrestle with the participants’ words to try to determine
exactly what their answers mean. Those who write in the “Yes/no, and I’ll
tell you why” style are few and far between. The usefulness of responses to
discussion items rests entirely on participants’ skill to express in words the
thoughts they wish to convey. Respondents may ramble, engaging in
discussion that doesn’t answer the question or is beside the point
• Save your respondents and yourself from this ordeal. After answering 15 to
20 discussion questions, your respondents will think you are demanding a
book! Such a major compositional exercise is unfair to those from whom
you are requesting a favour
50. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 50
Guidelines for Constructing a
Questionnaire
8. Provide clear instructions. Communicate exactly how you want
people to respond. For instance, don’t assume that they are familiar
with Likert scales. Some of them may never have seen such scales
before
9. Give a rationale for any items whose purpose may be unclear. We
can’t say this enough: You are asking people to do you a favour by
responding to your questionnaire. Give them a reason to want to do
the favour. At a minimum, each question should have a purpose, and
in one way or another, you should make that purpose clear
10. Make the questionnaire attractive and professional looking. Your
instrument should have clean lines, crystal-clear typing (and
certainly no typos!), and, perhaps, two or more colours
51. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 51
Guidelines for Constructing a
Questionnaire
11. Conduct a pilot test. Give the questionnaire to at least half a dozen friends
and colleagues to see whether they have difficulty understanding any items.
Have them actually fill out the questionnaire; this way, you can see the
kinds of responses you are likely to get and make sure that, down the road,
the “real” responses you obtain will be of sufficient quality to help you
answer your research question
12. Scrutinise the almost-final product carefully to make sure it addresses your
needs. Item by item, a questionnaire should be quality tested again and
again for precision of expression, objectivity, relevance, and probability of
favourable reception and return. Have you concentrated on the recipient of
the questionnaire, putting yourself in the place of someone who is asked to
invest time on your behalf? If you received such a questionnaire from a
stranger, what would your honest reaction be? These questions are
important and should be answered impartially
• Above all, you should make sure that every question is essential for you to
address the research problem
52. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 52
Guidelines for Maximising your Return
Rate for a Mailed Questionnaire
• The potential respondents whom you mailed your questionnaires to,
have little or nothing to gain by answering and returning the
questionnaire, and so many of them do not
• As a result, the typical return rate for a mailed questionnaire is 50% or
less, and in recent years, it has steadily declined
• Should you decide that a mailed questionnaire is the most suitable
approach for answering your research question, the following
guidelines can help you increase your return rate:
1. Consider the timing. Consider the characteristics of the sample you are
surveying, and try to anticipate when respondents will be most likely
to have time to answer a questionnaire. As a general rule, stay away
from peak holiday and vacation times
53. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 53
Guidelines for Maximising your Return
Rate for a Mailed Questionnaire
2. Make a good first impression. Put yourself in the place of a potential
respondent. Imagine a stranger sending you the questionnaire you propose
to send. What is your initial impression as you draw the questionnaire from
the envelope? Is it inordinately long and time-consuming? Is it cleanly and
neatly typed? Does it have adequate margins, giving the impression of
relaxation and uncluttered ease? Are the areas for response adequate and
clearly indicated? Is the tone courteous, and are the requests reasonable?
3. Motivate potential respondents. Give people a reason to want to respond.
Occasionally, researchers may actually have the resources to pay people for
their time or offer other concrete inducements. But more often than not, you
will have to rely on the power of persuasion to gain cooperation. Probably
the best mechanism for doing so is the cover letter you include with your
questionnaire. See Figure 9.4 on page 194 and compare it with Figure 9.5
on page 195 of the textbook. The cover letter is extremely important. It
should be carefully and thoughtfully composed and should stress the
concerns of the recipient rather than any selfish interests of the sender.
Some students forget this and, in doing so, unintentionally reveal their own
self-centeredness
54. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 54
Guidelines for Maximizing your Return
Rate for a Mailed Questionnaire
4. Include a self-addressed envelope with return postage. Accompany your
questionnaire with a self-addressed stamped envelope for your respondent’s
convenience in returning the questionnaire. To impose on a person’s time
and spirit of cooperation and then to expect that person also to supply the
envelope and pay the postage is unreasonable
5. Offer the results of your study. In return for the investment of time and the
courtesy of replying to your questions, offer to send your respondent a
summary of the results of your study if he or she wishes it. You might
provide a check space, either at the beginning or at the end of your
instrument, where a respondent can indicate the desire to have such a
summary, together with a place for name, address, and postcode. In
questionnaires for which anonymity is desirable, a separate postcard may be
included to indicate the desire for a summary. It, too, should request name,
address, and postcode, along with the suggestion that it be mailed separately
from the questionnaire to maintain anonymity
55. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 55
Guidelines for Maximizing your Return
Rate for a Mailed Questionnaire
6. Be gently persistent. Experts often suggest that when people do not
initially respond to a questionnaire, you can increase your response
rate by sending two follow-up reminders, perhaps sending each one
a week or two after the previous mailing. But if the questionnaire is
meant to be anonymous, how do you know who has returned it and
who has not?
To address this problem, many researchers put a different code
number on each copy they send out and keep a list of which number
they have sent to each person in their sample. When a questionnaire
is returned, they remove the number and person’s name from the
list. When it is time to send a follow-up letter, they send it only to
the people who are still on the list. Researchers should use the list of
names and code numbers only for this purpose. At no point should
they use it to determine who responded in what way to each
question. Courtesy, understanding, and respect for others pay large
dividends in a situation in which a researcher needs others’
cooperation. This is especially true in questionnaire studies
56. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 56
Choosing a Sample in a
Descriptive Study
• The researcher who conducts a descriptive study wants to determine the nature
of how things are
• Especially when conducting survey research, the researcher will want to
describe one or more characteristics of a fairly large population
• In such situations, the researcher will, of course, usually not study the entire
population of interest
• Instead, he or she will select a subset, or sample, of that population
• But the researcher can use the results obtained from the sample to make
generalisations about the entire population only if the sample is truly
representative of the population
• Failure to recognise population parameters and their demands upon research
procedures and research design and resources available is indicative of
inexperience
• A universe of data consists of the totality of those data within certain specified
parameters – too large
• Sampling is a process of selecting the population that is both statistically and
logically sound
57. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 57
Choosing a Sample in a
Descriptive Study
• The sampling procedure depends on the purpose of the sampling
and a careful consideration of the parameters of the population
• The sample should be so carefully chosen that, through it, the
researcher is able to see all the characteristics of the total
population in the same relationship that they would be seen were
the researcher, in fact, to examine the total population
• Ideally, samples are population micrococms (something that
represents a large system on a small scale)
• Unless the sampling procedure is carefully planned, the
conclusions that the researcher draws from the data are likely to
be distorted
• Such distortion is called bias
58. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 58
Sampling Designs
• Different sampling designs may be more or
less appropriate in different situations
• There are eight different approaches to
sampling, which fall into two major
categories: probability sampling and non-
probability sampling
59. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 59
Probability Sampling
• In probability sampling, the researcher can specify in advance that each
segment of the population will be represented in the sample
• This is the distinguishing characteristic that sets it apart from non-probability
sampling
• Generally, the components of the sample are chosen from the larger population
by a process known as random selection
• Random selection means choosing a sample in such a way that each member
of the population has an equal chance of being selected
• When such a random sample is selected, the researcher can assume that the
characteristics of the sample approximate the characteristics of the total
population
• If we have a population with considerable variability in race, wealth,
education, social standing, and other factors, and if we have a perfectly
selected random sample (a situation usually more theoretical than practical),
we will find in the sample those same characteristics that exist in the larger
population, and we will find them in the same proportions
60. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 60
Probability Sampling
• A sample is no more representative of the total population than the
degree to which it has been randomly selected
• There are, of course, many methods of random selection
• For instance, we could assign each person in the population a different
number and then use an arbitrary method of picking certain numbers,
perhaps by drawing numbers out of a hat, or using a computer’s
random number generator
• A tried-and-true, and therefore widely used, method of selecting a
random sample is to use a table of random numbers, such as that
presented in Table 9.2 on page 200 of the textbook
• The researcher typically does not start at the beginning of the table;
instead, he or she identifies a starting point randomly
61. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 61
Probability Sampling
• One fundamental principle must be kept in mind: The purpose of randomness
is to let blind chance determine the outcomes of the selection process to as
great a degree as possible
• Hence, in determining a starting point for the selection of random numbers,
pure chance must always initiate the process
• But how do we find an entry number?
• Look at RM bill
• Ask a friend for his/her last 2 digits of IC number
• Use telephone directory
• Vehicle registration number
• Pure chance dictates the choice
• Next step is to determine the size of the proposed sample
• If it is to be fewer than 100 individuals, we will need only two-digit numbers;
if it is to be fewer than 1,000, we will need three digits to accommodate the
sample size
62. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 62
Simple Random Sampling
• Simple random sampling is the least sophisticated
of all sampling designs
• The sample is chosen by simple random selection,
whereby every member of the population has an
equal chance of being selected
• Simple random sampling is easy when the
population is small and all of its members are
known
63. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 63
Stratified Random Sampling
• Think of students in Years 4, 5, and 6 in a public school
• This is a stratified population
• It has three different layers (strata) of distinctly different types
of individuals
• In stratified random sampling, the researcher samples equally
from each one of the layers in the overall population
• Look at Figure 9.9 on page 203 of the textbook
• Stratified random sampling has the advantage of guaranteeing
equal representation of each of the identified strata
• It is, of course, most appropriate when those strata are equal in
size in the overall population as well
64. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 64
Proportional Stratified Sampling
• In the simple stratified random sampling design,
all the strata of the population are essentially equal
in size
• In the proportional stratified sampling, the sample
is chosen in accordance with the proportions of the
different strata
• Look at Figure 9.10 on page 204 of the textbook
65. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 65
Cluster Sampling
• Sometimes the population of interest is spread out over a large area
• It may not be feasible to make up a list of every person living within the area
and, from the list, select a sample for study through normal randomisation
procedures
• Instead, we might obtain a map of the area showing political boundaries or
other subdivisions
• We can then subdivide an expansive area into smaller units
• For example, a city can be subdivided into precincts, clusters of city blocks, or
school boundary areas; a state can be divided into districts or townships
• In cluster sampling, it is important that the clusters be as similar to one another
as possible, with each cluster containing an equally heterogeneous mix of
individuals
• A subset of the identified clusters is randomly selected
• The sample consists of the people within each of the chosen clusters
• Look at Figure 9.11 on page 204 of the textbook
66. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 66
Systematic Sampling
• Systematic sampling involves selecting individuals (or
perhaps clusters) according to a predetermined sequence
• The sequence must originate by chance
• For instance, we might scramble a list of units that lie
within the population of interest and then select every 10th
unit on the list
• Using the systematic sampling technique, the clusters for
sampling are chosen by predetermined sequence
• Look at Figure 9.12 on page 205 of the textbook which
shows the systematic sampling design as used for sampling
clusters
67. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 67
Population Characteristics and
Probability Sampling Techniques
• At this point, let’s consider the various kinds of populations for which
different probability sampling techniques may be appropriate in a research
study
1. The population may be generally homogeneous. The individual units within
the population may be similar with respect to the characteristics of interest
2. The population may contain definite strata that are roughly equal in size
3. The population may contain definite strata that occupy varying proportions
of the overall population
4. The population may consist of clusters whose characteristics are similar, but
the individual units (e.g., people) within each cluster show variability in
characteristics that is similar to the variability in the overall population
• Table 9.3 on page 205 of the textbook lists these four possibilities and
suggests probability sampling designs appropriate for each one
• A sampling design should not be chosen blindly or willy-nilly
• Each of the designs that has been discussed is uniquely suited to a particular
kind of population, and so you should consider the nature of your
population when selecting your sampling technique
68. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 68
Nonprobability Sampling
• In nonprobability sampling, the researcher has no
way of forecasting or guaranteeing that each
element of the population will be represented in
the sample
• Furthermore, some members of the population
have little or no chance of being sampled
• There are three types of nonprobability samplings,
namely, convenience sampling, quota sampling,
and purposive sampling
69. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 69
Convenience Sampling
• Convenience sampling (also known as accidental sampling) makes no
pretense of identifying a representative subset of a population
• It takes people or other units that are readily available – for instance,
those that arrive on the scene by mere happenstance (a chance
occurrence)
• Convenience sampling may be appropriate for some less demanding
research problems
• Look at the example on page 206 of the textbook
• Not all research data need to be collected through careful, thoughtful
sampling procedures
• But without such safeguards, the conclusions drawn from the research
may not be trustworthy
70. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 70
Quota Sampling
• Quota sampling is a variation of convenience sampling
• It selects respondents in the same proportions that they are
found in the general population, but not in a random
fashion
• Look at the example on page 206 of the textbook
• This type of sampling regulates only the size of each
category within the sample; in every other respect, the
selection of the sample is nonrandom and, in most cases,
convenient
71. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 71
Purposive Sampling
• In purposive sampling, people or other units are chosen, as the name
implies, for a particular purpose
• For instance, we might choose people who we have decided are
“typical” of a group or those who represent diverse perspectives on an
issue
• Agencies that forecast elections frequently use purposive sampling:
They may choose a combination of voting districts that, in past
elections, have been quite useful in predicting the final outcomes
• Purposive sampling may be very appropriate for certain research
problems
• However, the researcher should always provide a rationale explaining
why he or she selected the particular sample of participants
72. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 72
Identifying a Sufficient Sample
Size
• The basic rule is, the larger the sample, the better
• But such a generalised rule is not too helpful to a researcher who has a
practical decision to make about a specific research situation
• The following are guidelines for selecting a sample size:
• For small populations (with fewer than 100 people or other units),
there is little point in sampling. Survey the entire population
• If the population size is around 500, 50% of the population should be
sampled
• If the population size is around 1,500, 20% should be sampled
• Beyond a certain point (at about 5,000 units or more), the population
size is almost irrelevant, and a sample size of 400 should be adequate
• Generally speaking, then, the larger the population, the smaller the
percentage (but not the smaller the number!) one needs to get a
representative sample
73. SAK 5090 MOHD HASAN SELAMAT- chapter 8 Slide 73
Identifying a Sufficient Sample
Size
• To some extent, the size of an adequate sample depends on
how homogeneous or heterogeneous the population is –
how alike or different its members are with respect to the
characteristics of research interest
• If the population is markedly heterogeneous, a larger
sample will be necessary than if the population is fairly
homogeneous
• Important, too, is the degree of precision with which the
researcher wishes to draw conclusions or make predictions
about the population under study
• Statisticians have developed formulas for determining the
desired sample size for a given population