Regression Analysis for Survey Data on SPSS (For a beginner)

#1
Hello Everyone,

I am very new to SPSS so forgive me if my questions seem overly simple. I am conducting a survey based research project.

My dependent variable contains 2 response options: Likely or Not Likely (0 or 1)

The independent Variables I am interested in are:
Age Category (20-29, 30-39, 40-49,50-59,60-69)
Gender (Male, Female)
Highest level of education (Bachelor, Masters, PHD, Other)

The question I want to answer is how each category in the independent variable predicts the dependent variable. For instance, for the Gender category, I want to identify if the option Male is predictive of the dependent value (and identify the P-value for this). I would like to be able to describe the P-value of all individual options within each independent variable category in this manner, if possible.

Can anyone help me to get started with this type of analysis? Mostly looking for the best way to set up this regression. Always happy to answer any further questions. Thank you so much!
 

hlsmith

Less is more. Stay pure. Stay poor.
#2
Not an SPSS user, but in logistic regression when you have a categorical variable, you select a reference group. Then in the output you get the increased log odds of the other group compared to the reference. So for Gender you will get 1 estimate, Age 4 estimates, and highest ed 3 estimates).

Ideally you should focus on the odds ratios with confidence intervals as your estimate not the pvalue, which does not really convey directionality of estimate or magnitude.