While the project will require some time, it is not that difficult. The project will interest you more if you can come up with some well thought out hypotheses. The examples provided are not complex and, therefore, not particularly theoretically exciting. You will discover that theory and method go together. If you start with a simple hypothesis, you will get a simple and obvious answer (most of the time). Personally – I always like picking variables like religiosity, politics or age and seeing how they impact beliefs about the society we live in.
For Example, Hyp 1 Reliousity (as measured by the frequency of attendance at church) will be positively correlated with more conservative political viewpoints as measured by (anti-abortion beliefs, concealed gun permits, belief in the after life, etc.) Another version would be – The higher the attendance at church on a monthly basis – the more likely subjects will identify with conservative politics. (GSS Question: I align myself with very conservative, moderately conservative, moderatately liberal or very liberals politics). Just look up the variables in your GSS data base.
SUMMARY
Your exercise should follow these STEPS. It should consist of:
1. A brief paragraph or two about the GSS. What is it, what does it do, why is it important for social research, how will you use it?
2. Your theory, three hypotheses with accompanying rationales.
3. Your variables, descriptions with a table.
4. Your original or first-order findings with a chart or table.
5. Your control variable and results (charts or tables).
6. Conclusions about what you find and how your control variable affected the results.
Make sure and run a true statistical test on your variables… Gamma’s, TOS, MOA, Pearson’s r… ANOVA’s … something to let me know you see WHY we make you take stats. You have to know how to interpret those stats and that is easy. For TOS or Tests of Significance – you simply state whether there is or is not a statistically significant relationship between the IV and DV and at what level (.05 or .01 etc). If you have some issue with employing Pearson’s r… Use the following correlations as guidelines. Anything less than .20 would suggest a minimal or NO correlation between those variables selected. .20- .40 shows there is weak to mild correlation with the selected variables. .41- .65 – A strong correlation between those selected variables. .65- .90… you have a very strong correlation and are getting close to TRUTH! These regression stats like Pearsons r are much more powerful that TOS or MOA because they actually measure how STRONG or WEAK the relationship actually is. Also, remember that correlations may be negative or positive so if there is a -.45 for example – that means there is an INVERSE relationship between the IV and DV.