Research method ch04 research topic and design

8,833 views
8,666 views

Published on

Published in: Health & Medicine, Technology
3 Comments
13 Likes
Statistics
Notes
No Downloads
Views
Total views
8,833
On SlideShare
0
From Embeds
0
Number of Embeds
2,186
Actions
Shares
0
Downloads
0
Comments
3
Likes
13
Embeds 0
No embeds

No notes for slide

Research method ch04 research topic and design

  1. 1. 1 Research Methods in Health Chapter 4. Research Problem and Design Young Moon Chae, Ph.D. Graduate School of Public Health Yonsei University, Korea ymchae@yuhs.ac
  2. 2. Table of Contents Research problem and topicResearch problem and topicI Research DesignResearch DesignII 1. Descriptive design 2. Experimental design 1. Research problem 2. Research sub-problem
  3. 3. 3 Research problem and topicResearch problem and topicII Research DesignResearch DesignII 1. Descriptive design 2. Experimental design 1. Research problem 2. Research sub-problem
  4. 4. 4 Research Problem • Problem is the heart of research project • Researchable problems fit the requirement s of the scientific method • For a problem to be researchable it must demand an interpretation of the data leading to a discovery of fact. Simple comparison, of itself, cannot be the end of a research effort • Each word of the problem should be expressive and stated be stated in a complete grammatical sentence • Degree to which study meets its aims is determined by relevance and completeness of research questions addressing the research problem • Divide problem (or purpose) into sub-problems (specific purposes) in order to have clear and global view of the problem
  5. 5. 5 Characteristics of Research Sub-problem • Each sub-problem should be a completely researchable unit • The solutions of the sub-problems, taken together, combine to resolve the main problem of research • Pseudo sub-problems are not researchable sub-problems. They are problems that the researcher must resolve by deciding on a course of action to be followed as a part of the research procedure - Example: What is the best way to choose a sample? What instruments should be used to gather the data? How large should a representative sample be? • Within the sub-problems, interpretation of the data must be apparent • The sub-problems must be add up to the totality of the problem • Proliferation of sub-problems is circumspect
  6. 6. 6 Components Comprising the Setting of the Problem • The delimitations of the problem The statement of the problem indicates what the researcher will include and will not include in the research endeavor • The definitions of the terms Without knowing explicitly what a term means, we cannot evaluate the research • The assumptions Assumptions are what the researcher takes for granted • The hypotheses Hypotheses are tentative guesses posited for the purpose of assisting the researcher in directing one’s thinking toward the solution of the problem • The importance (or significance) of the study Within the research paper, the researcher frequently sets forth the reason for undertaking the study based on literature review
  7. 7. 7 Finding Research Topic • Timely topic (current research issue) • Scientifically significant topic (through literature review) - Originality - Contribution to the field - Different from other studies (e.g. sample, methods) - Important issues • Interdisciplinary approach to find research topics - Healthcare specialized fields are closed related - Since each field has its own research problems and methods, you can find good topic by combining research problems and/or methods from other field (see next figure)
  8. 8. 8 Epidemiology Health Statistics Health Informatics Health Promotion Health Administration Environmental Health Industrial Health Workplace Health Promotion Information system for Health promotion Change management Environmental health Information system Disease surveillance system Industrial epidemiologyEnvironmental epidemiology Disease management Environmental policy Community participation Evaluation of industrial health programs Interdisciplinary Nature of Healthcare Sub-fields
  9. 9. 9 Review Points • Topic • Originality • Research methods • Formats (tables, figures, references) • Literature review • Relevance to the journal
  10. 10. 10 Research problem and topicResearch problem and topicI Research DesignResearch DesignIIII 1. Descriptive design 2. Experimental design 1. Research problem 2. Research sub-problem
  11. 11. 11 What is Research Design? • A plan for selecting the sources and types of information used to answer research questions • A framework for specifying the relationships among the study variables • A blueprint that outlines each procedures from the hypothesis to the analysis
  12. 12. 12 Key Considerations to Design Your Research Approach • What question do you want to answer? • For what purposes is the research being done? i.e., what do you want to be able to do or decide as a result of the research? • Who are the audiences for the information from the research, e.g., teachers, students, other researchers, members of a disciplinary community, corporate entities, etc.? • From what sources should the information be collected, e.g., students, teachers, targeted groups, certain documentation, etc.? • What kinds of information are needed to make the decisions you need to make and/or to enlighten your intended audiences? • Select a research design from the large variety of methods, techniques, procedures, protocols, and sampling
  13. 13. 13 Assessing Methods • Research Question(s) is/are key • Methods must answer the research question(s) • Methodology guides application • All must include “rigor”
  14. 14. 14 Categorization of Research Design by Design Typology 1. The degree of formulation of problem a. Exploratory or Formulated b. Descriptive, Diagnostic, Analytical 2. The topical scope a. Historical study b. Survey, Delphi Study c. Case study (History, Material), Accounts, Episodes, Story of experience d. Statistical study 3. The search environment, I.e., the field or lab setting a. survey or lab experiment 4. The time dimension a. Cross Sectional (One time) b. Longitudinal, Trend, Developmental (Follow up or Cohort Studies, Panel Studies)
  15. 15. 15 (cont.) 5. The mode of data collection a. Survey b. Observational 6. The manipulation of the variables under study a. Experimental (Hypothesis Testing ) b. Ex post facto 7. The nature of the relationship among variables a. Causal/ Prediction b. Descriptive/ Relational (i) Association (ii) Correlation 8. a. Conceptual ( Fundamental, Basic, Pure) b. Empirical (Applied, Action) 9. a. Qualitative b. Quantitative
  16. 16. 16 Categorization of Research Design by Descriptive or Experimental 1. Descriptive (Qualitative) • Case Study • Survey/Sampling • Focus Groups • Quantitative Description • Prediction/Classification 2. Experimental (Quantitative) • True Experiment • Quasi-Experiment Source: Lauer and Asher, Composition Research: Empirical Designs and MacNealy, Empirical Research in Writing
  17. 17. 17 1. Descriptive Design • Simplest method of scientific inquiry • Describe behavior and mental processes • Most widely used - Survey method – ask people’s opinions - Naturalistic observation – watch, describe - Clinical method – observe in clinic setting • All have advantages and disadvantages
  18. 18. 18 Case Studies • Focus is on individual or small group • Able to conduct a comprehensive analysis from a comparison of cases • Allows for identification of variables or phenomenon to be studied - Time consuming - Depth rather than breadth - Not necessarily representative
  19. 19. 19 Survey Research • An efficient means of gathering large amounts of data • Can be anonymous and inexpensive - Feedback often incomplete - Wording of instrument can bias feedback - Details often left out
  20. 20. 20 Distinctiveness of survey research • The purpose of the survey is to produce quantitative descriptions of some aspects of the studied population.. requires standardized information from and/or about the subjects being studied - relationships between variables - projecting findings descriptively to a predefined population • The main way of collecting information is by asking people structured and predefined questions. Their answers constitute the data to be analyzed. • Information is generally collected about a fraction of the study population--a sample--but it is collected in such a way as to be able to generalize the findings to the population-such as service or healthcare organizations, line or staff work groups
  21. 21. 21 Purposes of Survey Research • Exploratory - Little is known about a population - Further information is desired about research variables - Prelude to a costlier, larger research endeavors • Descriptive - Focus on who, what, when, how - Existence of opinions and attitudes • Explanatory - Cause and effect, focus on why - Reasons for existence of facts and opinion is of interest
  22. 22. 22 Techniques and Key problems with Survey Research • Survey research combines three techniques - Collection of answers to standardized questionnaires - Random sampling from a known population - Statistical analysis of a quantified representation of the survey answers • Each focus makes different demands of the data which are to be collected. Three key problems : - Measurement - Control - Representation
  23. 23. 23 Focus Groups • Aid in understanding audience, group, users • Small group interaction more than individual response • Helps identify and fill gaps in current knowledge re: perceptions, attitudes, feelings, etc. - Does not give statistics - Marketing tools seen as “suspect” - Analysis subjective
  24. 24. 24 Quantitative Descriptive Studies • Isolates systematically the most important variables (often from case studies) and to quantify and interrelate them (often via survey or questionnaire) • Possible to collect large amounts of data • Not as disruptive • Biases not as likely - Data restricted to information available
  25. 25. 25 Prediction and Classification Studies • Prediction forecasts and interval variable • Classification forecasts a nominal variable −Important in healthcare, education to predict behaviors −Need substantial population −Restricted range of variables can cause misinterpretation −Variables cannot be added together; must be weighted and looked at in context of other variables
  26. 26. 26 Positive Aspects of Descriptive/Qualitative Research • Naturalistic; allows for subjects to interact with environment • Can use statistical analysis • Seeks to further develop theory (not to influence action); Pre-scientific • Coding schemes often arise from interplay between data and researcher’s knowledge of theory
  27. 27. 27 Problems with Descriptive/Qualitative Research • Impossible to impose control • Subject pool often limited, not representative • Seen as more “subjective,” less rigorous • Beneficial only in terms of initial investigation to form hypothesis
  28. 28. 28 2. Experimental Design • Tests relationship of two or more variables - Allows conclusions about cause-and-effect - Quantitative measures of behavior compared in different conditions created by researchers - Evidence supports or rejects hypothesis • Elements - Independent variable – gets manipulated - Dependent variable – amount of change - Experimental group – exposed to independent variable or conditions expected to create change - Control group – presents normal behavior used for comparison - Random assignment - Experimental control
  29. 29. 29 Formal Experiments • Placebo control - Placebo effect: provides no active effect - Use in identical conditions for control and experimental groups • Blind experiment - Researchers blind to group membership of participants to rule out experimenter bias • Strongest experiments – double blind - Researchers and participants kept blind
  30. 30. 30 Experimental Research: True Experiment • Random sampling, or selection, of subjects (which are also stratified) • Introduction of a treatment • Use of a control group for comparing subjects who don’t receive treatment with those who do - Adherence to scientific method (seen as positive, too) - Must have both internal and external validity - Treatment and control might seem artificial
  31. 31. 31 Types of Experimental Design • The pretest-posttest control group design - Experimental group will chosen through appropriate randomization procedures and control group similarly selected - The experimental group is evaluated, subjected to the experimental variable, and reevaluated. The control group is isolated from all experimental variable influences and is merely evaluated at the beginning and at the end of the experiment. • The posttest-only control group design - This design is used when you cannot pretest group (such as growing children or crops) - Randomness is critical in the posttest-only design
  32. 32. 32 (cont.) • Correlational and Ex Post Facto Designs - Correlational design üCorrelational design are usually attempts to establish cause-effect relationships between two sets of data üCorrelation is too simple an answer for most of the complex realities of life, and its simplistic approach disarms the researcher. It is extremely deceptive tool, and one that the researcher needs to employ with the utmost caution - Ex post facto studies üThis is experimentation in reverse. Instead of taking groups that are equivalent and exposing them to different treatment with a view to promoting differences to be measured, this design begins with a given effect and seeks the experimental factor that brought it about üThe obvious weakness of this design is that we have no control over the situations that have already occurred and we can never be sure of how many other circumstances might have been involved üExample: Medical researches. Physicians discover a pathological situation, then inaugurate their search “after the fact”. They sleuth into events and conditions antecedent in order to discover the cause for the illness
  33. 33. 33 33
  34. 34. 34 Source: Leedy PD. Practical research. Third Edition. Macmillan Publishing Co., 1985
  35. 35. 35 Experimental Research: Quasi-Experiment • Similar to Experiment, except that the subjects are not randomized. Intact groups are often used (for example, students in a classroom). • To draw more fully on the power of the experimental method, a pretest may be employed. • Employ treatment, control, and scientific method - Act of control and treatment makes situation artificial - Small subject pools
  36. 36. 36 Types of Quasi-experimental Design • The time-series experiment - It consists of taking a series of evaluations and then introducing a variable or a new dynamic into the system, after which another series of evaluations is made - If substantial change results in the second series of evaluations, we may assume with reasonable experimental logic that the cause of the difference in observational results was because of the factor introduced into the system - The weakness of this design is in the probability that a major event that may be unrecognized may enter the system along with, before, or after the introduction of the experimental variable • Control group, time series - A variant of the time-series design and it is the equivalent time-sampling design except that the different materials are introduced throughout the course of the experiment - The object of its construction is to control history in time designs
  37. 37. 37 Positive Aspects of Experimental Research • Tests the validity of generalizations • Seen as rigorous • Identifies a cause-and-effect relationship • Seen as more objective, less subjective • Can be predictive
  38. 38. 38 Problems with Experimental Research • Generalizations need to be qualified according to limitation of research methods employed • Controlled settings don’t mirror actual conditions; unnatural • Difficult to isolate a single variable
  39. 39. 39 Quantitative and Qualitative Research QUANTITATIVE • Measured & expressed in terms of quantity • Expression of a property or quantity in numerical terms • Quantitative research helps: − Precise measurement − Knowing trends or changes overtime − Comparing trends or individual libraries / units QUALITATIVE • Involves quality or kind • Helps in having insight into problems or cases
  40. 40. 40 Conceptual and Empirical Research CONCEPTUAL • Related to some abstract idea or theory (for thinkers & philosophers) • Relies on literature EMPIRICAL • Relies on experience or observation alone, i.e., data based research • Capable of being verified by observation or experiment • Experimenter has control over variables
  41. 41. 41 References Dane, F.C. (1990). Research methods. Brooks/Cole Publishing Company. Leedy PD. (1985) Practical research. Third Edition. Macmillan Publishing Co. Polgar, S., Thomas, S.A. (1991). Introduction to research in the health sciences. Churchill Livingston.

×