- 1. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 1 Quantitative Research In quantitative research, the investigator identifies a research problem based on trends in the field or on the need to explain why something occurs. Describing a trend means that the research problem can be answered best by a study in which the researcher seeks to establish the overall tendency of responses from individuals and to note how this tendency varies among people. For example, you might seek to learn how voters describe their attitudes toward a bond issue. Results from this study can inform how a large population views an issue and the diversity of these views (Cresswell, 2001, p-13) Characteristics of Quantitative Research In quantitative research the major characteristics are (Cresswell, 2001, p-13): Describing a research problem through a description of trends or a need for an explanation of the relationship among variables. Providing a major role for the literature through suggesting the research questions to be asked and justifying the research problem and creating a need for the direction (purpose statement and research questions or hypotheses) of the study. Creating purpose statements, research questions, and hypotheses that are specific, narrow, measurable, and observable. Collecting numeric data from a large number of people using instruments with preset questions and responses. Analyzing trends, comparing groups, or relating variables using statistical analysis, and interpreting results by comparing them with prior predictions and past research. Writing the research report using standard, fixed structures and evaluation criteria, and taking an objective, unbiased approach. Quantitative Analysis Quantitative analysis involves the techniques by which researchers convert data to numerical forms and subject them to statistical analyses (Babbie, 2001). It involves the numerical representation and manipulation of observations for the purpose of describing and explaining the phenomena that those observations reflect.
- 2. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 2 • Involves techniques • Involve task of converting data into knowledge. 1. Quantification of data It is the process of converting data to a numerical format. This involves converting social science data into a machine-readable form—a form that can be read and manipulated by computers and similar machines used in quantitative analysis. Today, quantitative analysis is almost always handled by computer programs such as SPSS and Micro Case (Babbie, 2011, page, 422). 1.1 Coding To conduct a quantitative analysis, researcher often must engage in a coding process after the data have been collected. For example, open-ended questionnaire items result in non-numerical responses which need to be coded before analysis. Suppose, for example, that a survey researcher asks respondents, ―What is your occupation?‖ The responses to such a question will vary considerably. Although he or she can assign a separate numerical code to each reported occupation, this procedure will not facilitate analysis. The variable occupation has many pre- established coding schemes which differentiate and combines both to compare research results with other studies. One coding scheme distinguishes Professional and managerial occupations Clerical occupation Semi-skilled occupations Another coding scheme distinguishes sectors of economy Manufacturing health education commerce
- 3. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 3 1.2 Developing code categories It means the categorization of data into distinct field. For example, if we are willing to conduct a survey in a self-administered campus about the existing problems facing by students. We can categorize the responses from students as financial concern, academic concern and non academic concern. Financial concern Academic concern Non-academic concern 1.3 Codebook construction The end product of the coding process is the conversion of data items into numerical codes. These, codes represent attributes composing variables. A codebook is a document that describes the locations of variables and lists the assignments of codes to the attributes composing those variables. For example, if we conduct a survey on then it will be the following: 1.4 Data entry Transforming data into quantitative form, researchers interested in quantitative analysis need to convert data into a machine-readable format, so that computers can read and manipulate the data. Tuition is too high Books cost too much Not enough financial aid Not enough classes offered Advisors are not available Too many requirements Cafeteria food is infected Not enough parking spaces Cockroaches in the dorm How often do you attend religious services? 0. Never 1. Less than once a year 2. About once or twice a year 3. Several times a year 4. About once a month 5.Every week
- 4. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 4 Data-entry specialists (including yourself) could enter the data into, say, an SPSS data matrix or into an Excel spreadsheet to be imported later into SPSS. Types of Variables Analysis 2.0 Univariate analysis Univariate analysis is the analysis of a single variable for purposes of description. Frequency distribution, averages, and measures of dispersion would be examples of univariate analysis, as distinguished from bivariate and multivariate analysis. Univariate analysis covers the following points: 2.1 Frequency Distribution A description of the number of times that the various attributes of a variable are observed in a sample is called a frequency distribution. The report that 53 percent of a sample were men and 47 percent were women would be a simple example of a frequency distribution. It gives researcher some general picture about the dispersion, as well as maximum and minimum response. 2.2 Central Tendency A measure of central tendency is a single value that attempts to describe a set of data by identifying the central position within that set of data. As such, measures of central tendency are sometimes called measures of central location. Univariate analysis One variable E.g. Age, gender, income etc. Bivariate analysis Two variables E.g. gender & CGPA Multivariate analysis Several variables E.g. Age, education, and prejudice
- 5. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 5 2.2.1 Mean An average computed by summing the values of several observations and dividing by the number of observations. If you now have a grade number of observations point average of 4.0 based on 10 courses, and you get an F in this course, your new grade point (mean) average will be 3.6 2.2.2 Mode An average representing the most frequently observed value or attribute. If a sample contains 1,000 Protestants, 275 Catholics, and 33 Jews, Protestant is the modal category. 2.2.3 Median An average representing the value of the ―middle‖ case in a rank-ordered set of observations. If the ages of five men are 16, 17, 20, 54, and 88, the median would be 20. (The mean would be 39) Figure: Three averages (Babbie, 2001, page, 430)
- 6. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 6 2.3 Dispersion Dispersion refers to the way values are distributed around some central value, such as an average. The simplest measure of dispersion is the range: the distance separating the highest from the lowest value. Range The simplest measure of dispersion is the range: the distance separating the highest from the lowest value. The range is a simple example of a measure of dispersion. Thus, we may report that the mean age of a group is 37.9, and the range is from 12 to 89 (Babbie, 2001, page, 431) Variance To describe the variability of the distribution. Standard deviation A measure of dispersion around the mean. It is an index of the amount of variability in a set of data. Higher SD means data are more dispersed. Lower SD means that they are more bunched together. Figure 14-4 illustrates the basic idea. Notice that the professional golfer not only has a lower mean score but is also more consistent represented by the smaller standard deviation. The duffer, on the other hand, has a higher average and is also less consistent: sometimes doing much better, sometimes much worse (Babbie, 2001, page, 432) Dispersion Range Variance Standard Deviation
- 7. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 7 2.4 Continuous & Discrete Variables Continuous variable: A variable whose attributes form a steady progression, such as age or income. Thus, the ages of a group of people might include 21, 22, 23, 24, and so forth and could even be broken down into fractions of years. E.g. Income & age Scale: Interval & Ratio Discrete Variables: A variable whose attributes are separate from one another, or discontinuous, as in the case of gender or religious affiliation. Thus, in age (a continuous variable), the attributes progress steadily from 21 to 22 to 23, and so forth, whereas there is no progression from male to female in the case of gender. E.g. Marital status, gender & nationality. Scale: Nominal & Ordinal
- 8. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 8 Modes should be calculated for nominal data, medians for interval data, and means for ratio data, not for nominal data. 2.6 Sub group comparison Univariate analyses describe the units of analysis of a study and, if they are a sample drawn from some larger population, allow us to make descriptive inferences about the larger population. The subgroup comparisons tell us how diﬀerent groups in the population response to questions and see a pattern in the result (Babbie, 2011, page: 433). For example table represents whether marijuana should be legalized or not by age of respondents: Marijuana Legalization by Age of Respondents Source: General Social Survey, 2004, National Opinion Research Center. In response, 33.4 percent said it should and 66.6 percent said t.it shouldn‘t. 2.7 Collapsing” Response Categories It means combining the two appropriate range of variation to get better picture or meaningful analyses. Consider an example: Attitudes toward the United Nations: How is the UN doing in solving the problems it has had to face? Source: ―5-Nation Survey Finds Hope for U.N.,‖New York Times, June 26, 1985, p. 6 Under 21 21-35 36-54 55 & older Should be legalized 27% 40% 37% 24% Should not be legalized 73 60 63 76 100%= (34) (238) (338) (265)
- 9. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 9 Part of the problem with Table lies in the table relatively small percentages of respondents selecting the two extreme response categories: the UN is doing a very good or a very poor job. This procedure is inappropriate in that it ignores all those respondents who gave the most positive answer of all: ―very good job.‖ In a situation like this, you should combine or ―collapse‖ the two ends of the range of variation combine ―very good‖ with ―good‖ and ―very poor‖ with ―poor.‖ If you were to do this in the analysis of your own data, it would be wise to add the raw frequencies together and recompute percentages for the combined categories (Babbie, 2011, page, 434) After collapsing extreme categories Source: ―5-Nation Survey Finds Hope for U.N.,‖New York Times, June 26, 1985, p. 6 2.8 Handling “Don’t Knows” option Whether to include or exclude the ‗don‘t knows‘ is harder to decide. It‘s usually a good idea to give people the option of saying ―don‘t know‖ or ―no opinion‖ when asking for their opinions on issues. In any event, the truth contained within your data is that a certain percentage said they didn‘t know and the remainder divided their opinions in whatever manner they did (Babbie, 2011, page, 436). 3.0 Bivariate Analysis The analysis of two variables simultaneously, for the purpose of determining the empirical relationship between them. The construction of a simple percentage table or the computation of a simple correlation coefficient are examples of bivariate analyses. However, as with univariate analysis the purpose of subgroup comparisons is largely descriptive. Most bivariate analysis in social research adds on another element: determining relationships between the variables
- 10. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 10 themselves (Babbie, 2011, page, 436-37). For example: Religious Attendance Reported by Men and Women in 2004. Table describes the church attendance of men & women as reported in 1990 General Social Survey. It shows: comparatively & descriptively – that women in the study attended church more often as compared to men. Source: Babbie, 2011, page, 437 3.1 Constructing and Reading Bivariate Tables Steps involved in constructing of explanatory bivariate tables: 1. The cases are divided into groups according to attributes of the independent variable. 2. Each of these subgroups is then described in terms of attributes of the independent variable. 3. Finally, the table is read by comparing the independent variable subgroups with one another in terms of a given attribute of the dependent variable. Table: Gender and attitudes toward equality for men and women. Source: (Babbie, 2011, 439)
- 11. Tahmina Ferdous Tanny, Lecturer, Dept. of Public Administration, Jagannath University, Dhaka-1100 Page 11 4.0 Multivariate analysis The analysis of the simultaneous relationships among several variables. Examining simultaneously the effects of Religious Attendance, Gender, and Age would be an example of multivariate analysis (Babbie, 2011, page, 441). . Source: General Social Survey, 1972 – 2006, National Opinion Research Center 5.0 Sociological diagnostics Sociological diagnostics is a quantitative analysis technique for determining the nature of social problems such as ethnic or gender discrimination (Babbie, 2011, page, 442) It can be used to replace opinions with facts and to settle debates with data analysis. For example Issues of gender and income. Because family pattern, women as group have participated less in in the labor force and many only begin outside the home after completing certain child-rearing tasks. Reference Babbie E. (2011). The Practice of Social Research, (Twelfth ed.). California: Wadsworth Cengage Learning. http://www.slideshare.net/asmasemma/quantitative-data-analysis Religious attendance Gender Age