Skip to main content
It looks like you're using Internet Explorer 11 or older. This website works best with modern browsers such as the latest versions of Chrome, Firefox, Safari, and Edge. If you continue with this browser, you may see unexpected results.

Burnside: SOC 100: (fall 2020)

Sociology of Everyday Life

Sociology 100: Analysis of Social Survey Data

SOC 100:  Analysis of Social Survey Data

            By now your work in the Sociology of Everyday Life has given you many ideas about relationships between data and variables describing social life in America.  You are ready to do some research and test a hypothesis of your own choosing.

You will be using part of the General Social Survey database from 2014, which consists of questions and responses that describe social life in America.  The variables you can use are found in the GSS Code Manual located on our class Moodle page, and a paper copy will be available in class.

The Statistical Package for the Social Sciences (SPSS) is a computer software package that you will use to analyze the two variables of your choice; it will give you a cross-tabulation that shows the relationship between your two variables of choice, and from this information you will create a table and produce a short summary to present to the class about the relationship between your two variables of choice. 

Your task in class on Friday and Monday is to

 1) understand the difference between independent and dependent variables,

 2) develop a hypothesis about life in the United States using two of the GSS variables,

3) learn how to use the Statistical Package for the Social Sciences (SPSS) to produce frequency 

    tables for variables and produce a cross-tabulation (contingency table) between variables,

 4) produce a set of tables illustrating the relationship you have found,

 5) conclude with a summary of what you found

 (start with a one-sentence summary, support your conclusion with specific data from the table, point out any unexpected or particularly interesting findings, and conclude with a statement that synthesizes everything you’ve done (in two or three paragraphs.)

6) Compile the full assignment which includes the literature review, and submit on Moodle on

 Sept _____, by Noon.  Please see grading rubric for more details (page 6 of Handout.)

As you proceed, review Chapter two in our main text (Ballantine & Roberts) paying attention to the key terms of dependent variable and independent variable, hypothesis, causality and correlations, random sample, and cross-tabulation.

For class, please do the following:

First, Download SPSS on your laptop, this three-step process:

  1. To install SPSS, click the windows key and begin typing “\\kc-entee”,

after the page loads, double click on WinApps,

then Add Remove; find and double click on SPSS 26 and

 then double click on WIN and double click on IBM_SPSS_STATISTICS_CLIENT_64-BIT.exe.


After it is installed, you will need to go back to the SPSS 26 folder and click on SPSS 26 Authorization Codes 2021.pdf, use this code after opening the License Authorization Wizard to enter the Authorization Code and you should be good to go.

  1. After downloading, go next to IBM SPSS 26 License Authorization Wizard.
  2. Choose the Authorized User License instead of Concurrent.
  3. You should be good to go to open SPSS and open the GSS 2014.sav file from our Moodle course site.  Then follow the steps below for “How to Use the SPSS and the GSS data set (see page 3 of this handout).

Note:    Make sure your computer is able to access wireless internet.  If not, contact IS&S about how to bring up wireless on your computer (call ext. 3343).


Group Work aspects of the GSS Research:   Each student will produce his/her individual paper whose hypothesis includes a shared dependent variable but with different independent variables from other group members.  In small groups, you will do data analysis in class, and then complete your research and writing outside of class to compose the final data analysis report (paper w/ GSS data tables).

Variables and Hypotheses in Survey Research

Name _____________________________      Group Members: ______________________________

Dependent variables for your work may be some attitude, opinion, or behavior of Americans in 2014 (see GSS code manual).

Independent Variables for your work may be aspects of American social differentiation (race, age, gender, marital status, etc.) or aspects of American social institution participation (education, religion, income, political party identification:  see GSS code manual).

I am interested in the relationship between these two variables used in the General Social Survey:

My dependent variable name:  VAR: __________________________

This variable was measured by asking the following question:

My independent variable name:  VAR: ____________________________

(the one influencing the dependent variable)

This variable was measured by asking the following question:

My hypothesis is:  _______________________________________________________________


My Rationale is: (What is your reasoning behind your hypothesis? Is there something you learned in class, in something you’ve read, or something from your own experience that’s guiding you? Explain it here.)    ___________________________________________________________________________


How to Use the SPSS 26 and the GSS Data to Test Your Hypothesis

How to generate a frequency distribution:

1. Go under the Analyze menu.

2. Then go under Descriptive Statistics.

3. After that, go under Frequencies.

4. Put in the variables you wish to use by clicking them into the Variable(s) box. (Note that it’s most helpful to use variable names [“VAR” on the previous page] instead of their longer label by right-clicking and selecting “Display Variable Names.” You can also alphabetize your variable names by again right-clicking on the list of variables and selecting “Sort Alphabetically.”

5. Click OK.

How to perform a bivariate analysis:

1. Go under the Analyze menu.

2. Then go under Descriptive Statistics.

3. After that, go under Crosstabs.

4. Put the dependent variable that you want to use in the box labeled Row and the independent variable you want to use in the box labeled Column(s).

5. Click on the Cells box and select your percentages by Column(s).

6. Click Continue.

7. Click OK.


Soc 100

Constructing Contingency Tables (Cross-Tabulations)

1. A table should be numbered and have a heading or a title that describes what is contained in the table.

2. The original content of the variables should be clearly presented in the table itself, or in the text, with a paraphrase in the table.

3. When percentages are reported in the table, the base upon which they are computed should be indicated (i.e. the total n should be included in your “Total” row).

4. If any cases are omitted from the table because of missing data (“no answer,”: for example ) their numbers should be indicated in the table.

5. Typical format of a contingency table:

            Table #: [Title of Heading for Table Contents}

                                                                        INDEPENDENT VARIABLE

DEPENDENT VARIABLE                           (Attribute)       (Attribute)       Total

(Attribute)                                                       (%)                  (%)                  (%)

(Attribute)                                                       (%)                  (%)                  (%)

Total                                                    100% =  total #           total #              total #

                        Number of missing observations =

                        Data source and year: (GSS, 2014)



The hypothesis in the following analysis of General Social Survey (2014) data is that men will report higher levels of happiness than women. My rationale is that women experience higher rates of gender-based discrimination and violence, and these could translate into higher rates of unhappiness. In this analysis, the independent variable is gender and the dependent variable is level of happiness. The results of the analysis are displayed in Table 1 below.

            Table 1: General Happiness by Gender:

Level of Happiness                   Male                Female

Very Happy                            30.6%              32.6%

Pretty Happy                           58.4%              54.3%

Not too Happy                        10.9%              13%___

Total                            100% = 1218               1588

Missing = 2

                                                GSS, 2014      

Considering the data presented in Table 1, it appears that the hypothesis that women will be less happy than men is not supported by the data. About one-third of people, regardless of gender, report being “very happy” and more than half report being “pretty happy.” In fact, while not statistically significant, women are two percentage points more likely to be very happy. However, they are also two percentage points more likely to report that they are “not too happy.” Since these differences aren’t large enough to be statistically significant, the primary conclusion to be drawn from these data is that happiness levels do not vary substantially by gender. Interestingly, a large majority of both men and women report being either “pretty happy” or “very happy,” with only 11% of men and 13% of women reporting are “not too happy.”


Writing up the Data Analysis Paper using the General Social Survey (GSS)

Cover the Following points in an essay format:  DUE: ______

  • Introduction paragraph.
  • Hypothesis: Specific statement of relationship such as “when IV is high, DV will be low”.
  • Dependent Variable (DV): (the one that is influenced); and Independent Variable (IV) (the one that influences the other).
  •  Rationale – statement of how and why the independent and dependent variable are related in history and culture. 
  • Literature review
  •  Survey’s data in cross-tabulations presented as a table (percentage down and compare across).
  •  Analysis – The hypothesis was:  clearly supported? partly supported? the reverse was true?
  • Conclusion and ideas for future research:  “I was right!”  Why? OR“I was not right!”  Why?



Grading Rubric:

SOC 100:  Sociology of Everyday Life                                  Date: _______________

Dr. J. Burnside                           Name ________________________________________

General Social Survey (GSS) Data Analysis

Feedback Scale:  Very Good (A, A-); Good (B+, B, B-); Fair, mostly satisfactory (C+, C, C-);

 Unsatisfactory (D+, D, D-); Poor (F)

______________  Interesting  title and introduction

______________ Definition of basic research question or problem

______________ Literature review (minimum of two articles)

_____________ Discussion =variables (w/ frequency tables) and hypotheses (bivariate table)

_____________  Analysis of research findings using the bivariate (cross-tabulations) table

______________   Conclusions and ideas for further research (uses sociological concepts and


____________   Writing Mechanics: organization, grammar, punctuation, spelling, proper in-

text citations, typed 4-5 pages (includes tables) and works cited list.

_____________  Grade:    ___________________________________________________________



Evaluating Internet Sources with the CRAAP Test

Steps of the Literature Review

  1. Search for scholarly articles using my database recommendations

  2. Repeat your search in multiple databases, mixing and matching keywords

  3. Repeat your search in the book catalog - BANC - for books

  4. "Cite forward" in Science Direct and Google Scholar for further sources

  5. Organize your findings in some way: chronologically, geographically, topically/thematically, or methodologically

Conducting a Literature Review