Soc. 920:502, Sociology of Research Methods
Patricia A. Roos
Rm. A-342, Lucy Stone Hall
Phone: (732) 445-5848
Email: roos@rutgers.edu
Office Hours: Wednesday 11:30-1 p.m. (or by appointment)

It's an experience like no other experience I can describe, the best thing that can happen to a scientist, realizing that something that's happened in his or her mind exactly corresponds to something that happens in nature. It's startling every time it occurs. One is surprised that a construct of one's own mind can actually be realized in the honest-to-goodness world out there. A great shock, and a great, great joy. Leo Kadanoff, Chaos

I. Goals: This is a course on how to do theoretically informed quantitative social research. The emphasis will be on data analysis, interpreting, and writing up the analytic results. By the end of the course, you should be fairly adept at making sociological sense out of a body of quantitative data. Techniques we will discuss will include: tabular analysis; regression analysis in its various forms, including dummy variable regression analysis, and decomposition of R-square into component parts; factor analysis (for scale construction); logistic regression; and multinomial logit. This is good basic preparation for more advanced courses in time series analysis, Lisrel, and so forth.

Because this is a capstone course, the emphasis is on using statistical tools to link theory and data to draw substantive conclusions, and presenting and writing up results. The focus is not on learning statistics per se. A graduate-level statistics course through multiple regression is a prerequisite for this course. I will assume that you have a statistics text to which you can refer. If you don't, you might want to buy Agresti and Finlay, which is more accessible to social scientists than many statistics books:

Agresti, Alan, and Barbara Finlay. 1997. Statistical Methods for the Social Sciences. Third edition. San Francisco, CA: Dellen.

II. Books: There is one required book for the course (available at the Livingston bookstore):

Jane E. Miller. 2004. The Chicago Guide to Writing About Numbers. The Effective Presentation of Quantitative Information. Chicago: University of Chicago Press.

This book is a well written description of some of the important "tools of the trade" for those who want to think, write, and speak about quantitative data.

Re: SAS or SPSS or STATA: I recommend you use SAS as your statistical package, but if you are already familiar with SPSS or STATA feel free to use either (although you'll be on your own). Each of you will have access to Sociology's Computing Lab, which has documentation for both SAS, SPSS, and STATA. If you don't have a userid, contact Shan Harewood at the Lab, and let him know you're in my class. If you want to order SAS, SPSS, or STATA for your home computer, see Shan as well. The department has a site license for all three packages, which makes it relatively inexpensive.

SAS has a dizzying array of manuals, and most are much more complex that you need for this class (or even probably for your whole career!). If you plan to use SAS, I'd recommend you order two basic manuals, and then use others as needed in the Sociology Lab:

The Little SAS Book: A Primer (Lora D. Delwiche and Susan J. Slaughter, 2003, 3rd edition) [I have a few extra copies of this, check with me]
A Step-by-Step Approach to Using the SAS System for Univariate and Multivariate Statistics (Larry Hatcher and Edward J. Stepanski, 1994)

The Little SAS Book is a basic primer about the SAS system. The Step-by Step Approach volume provides most of what you need through multiple regression, but not more sophisticated models. Other SAS volumes available in the Lab provide additional details on SAS Procedures (e.g., FREQ, MEANS, PRINT, TABULATE, UNIVARIATE); SAS/STAT volumes provide all the gory details on more advanced statistical techniques (e.g., FACTOR, REG, CATMOD); still other volumes provide information on SAS Language. IF YOU PLAN TO ORDER MANUALS, DO SO AS SOON AS POSSIBLE.

There is little required reading for this course. I do, however, provide a bibliography of readings for the course, which I'll continue to update as I find new references. I include these so that you will have background reading on the techniques we discuss, and examples of how they are used in practice. A number of the illustrative articles are written by our own faculty. I'd advise you to read a number of applications of the technique(s) you use. There will also be additional readings associated with the particular topic you choose for your final paper. The emphasis will be on learning by doing. This means lots of computer work and lots of writing up results.

III. Course Requirements: The core of the course is a series of six assignments, which will constitute 60 percent of the grade (see attached calendar). It is important to keep up to date, since you must understand previous material to follow what comes next. These assignments will be due in class a week or two after they are assigned. You must complete all the assignments to get a grade for the course.

The rest of the grade (40 percent) will be based on a final paper (on a topic of your choice), in which you carry out a quantitative analysis of some substantive issue using the technical and analytical skills you're developoling in the course. I strongly urge you to choose a topic early so that you can structure your assignments around your final paper. The final paper proposal is due March 9th (Assignment 4), the literature review is due March 30th (Assignment 5), and the final paper is due May 2nd. To move you along on the literature review, we will spent part of the class on February 23rd in the Sociology Computer Lab, where a Rutgers librarian will give you some pointers on electronic data bases and other library sources. I don't like incompletes, and you shouldn't either, so plan to get that paper (and those assignments) in on time!

Choosing a data set: In choosing a data set, feel free to use your own data (either data you collected yourself, data you have access to from other sources, or ICPSR data, or whatever). This is really the best option for those of you far enough along to be working on your dissertation or papers for meetings. The only criterion for using your own data set is that the quality of the data must be sufficient to meet the requirements of the multivariate techniques we use. Check with me if you have any questions!! If you do not have your own data, you can get data from other sources. For example, there are the 1972-2000 General Social Surveys. Check out the GSS website (click "Analyze" on the top for the codebook, and statistical procedures). Other data sets are available through ICPSR. The best source for ICPSR and other data is the Humanities and Social Sciences Data Center on the 4th floor of Alexander Library (Ronald Jantz, Director). Another good local source of data is the Eagleton Poll Archives.

You must have the data set you plan to use ready for use by week 2 of class. Otherwise you won't be able to complete your assignments.

IV. Miscellaneous:

1) All of you will need to undergo IRB review for this class, if you haven't done so already. If you are using existing data, you can probably get a waiver. Read through the IRB annual memo to understand the rules and to find the appropriate forms.

2) All assignments and the final paper must be typed. Use Word or Excel to prepare tables.

3) We have only 14 meetings, three of which are given over to student presentations. Attendance and participation is critical. The norm for graduate courses is: thou shalt not miss class!

4) For Assignment 4 I will ask each of you to write a brief proposal of your final project, as well as to present the proposal to the class on March 9th. These will be due a few days early, in the form of electronic copies to all class members. During the last two weeks of class you will present your ongoing work to the class. As with the proposal, you will send around electronic versions of your preliminary tables and writings to class members several days before the presentation. The class discussion will focus on comments and suggestions for revisions.

V. Course Outline (see attached schedule of readings and due dates):

Week 1 (January 19): Crosstabs, computer info, IRB's

Week 2 (January 26): Basics, simple regression

Week 3 (February 2): Multiple regression/computer printouts/presentation of results

Week 4 (February 9): Example: Quantitative Analysis/Dummy variable regression

Week 5 (February 16): Dummy variable regression

Week 6 (February 23): Related topics/Library review (Sociology lab)

Week 7 (March 2): Decomposition of means

Week 8 (March 9): Proposal presentations

Spring Break: No class March 16th!

Week 9 (March 23): Factor analysis for scale creation

Week 10 (March 30): Logistic regression

Week 11 (April 6): Logistic regression (cont).

Week 12 (April 13): Multinomial logit

Week 13 (April 20): Final paper presentations

Week 14 (April 27): Final paper presentations

FINAL PAPERS DUE: Monday, May 2nd

VI. Selected readings from calendar (See attached bibliography for additional readings.)

Babbie, Earl. n.d. "Notes on Percentaging Tables. Unpublished notes. [click here]

Gatta, Mary L., and Patricia A. Roos. 2005. "Rethinking Occupational Integration." Forthcoming, Sociological Forum. [click here]

IRB Reading: Rutgers Human Subjects Research Annual Memo: [click here]

Miller, Jane E. 2004. The Chicago Guide to Writing About Numbers. Chicago: University of Chicago Press.

Shea, Christopher. 2000. "Don't Talk to the Humans: The Crackdown on Social Science Research." Lingua Franca 10 (6). [click here]

Research and Writing Citations (for your writing pleasure):

Alford, Robert T. 1998. The Craft of Inquiry: Theories, Methods, Evidence. New York: Oxford University Press.

Becker, Howard S. 1998. Tricks of the Trade: How to Think About Your Research While You're Doing It. Chicago: University of Chicago Press.

Becker, Howard S. 1986. Writing for Social Scientists: How to Start and Finish Your Thesis, Book, or Article. Chicago: University of Chicago Press.

Miller, Jane E. 2004. The Chicago Guide to Writing About Numbers. Chicago: University of Chicago Press.

Miller, Jane E. 2005. The Chicago Guide to Writing About Multivariate Analysis. Chicago: University of Chicago Press.

Strunk, William Jr., and E.B. White. 2000. The Elements of Style, Fourth Edition. New York: Allyn & Bacon.

Lee Clarke, "Notes on Proposing" and "On Writing and Criticism"

Sarah Rosenfield, "Some Things To Think About While Reading Papers"

James Jasper, "Why So Many Academics are Lousy Writers"

American Sociological Association, "Writing an Informative Abstract"

And, for some humor: "How to Write Good"