Comparing responses by gender (or another demographic var)

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

jdyson
Posts: 4
Joined: Sat May 03, 2014 8:15 pm

Comparing responses by gender (or another demographic var)

Postby jdyson » Sat May 03, 2014 8:19 pm

It seems like this should be intuitive, but I'd like to see (for example) if males and females answered a specific dependent variable question differently. I'd like to compare male and female responses to see if there is a statistically significant differences between responses. I'm not sure how to do this. I've tried to click on "explore," but that will only give me means--it won't actually tell me whether the difference is significant. Thanks in advance for your help.
statman
Administrator
Posts: 2721
Joined: Tue Jun 12, 2007 12:08 pm
Location: Florida, USA

Re: Comparing responses by gender (or another demographic va

Postby statman » Sun May 04, 2014 11:01 am

So you have 2 columns of data responses, 1 male and the other female and you want to test if a difference?

If so then a simple t-test should but, how many observations?

Also ...
See the note below

NOTE: Please read the Posting Guidelines and always tell us your OS, the SPSS version and information about your study and data!

Statman
Statistical Services
jdyson
Posts: 4
Joined: Sat May 03, 2014 8:15 pm

Re: Comparing responses by gender (or another demographic va

Postby jdyson » Sun May 04, 2014 2:41 pm

"Males" and "females" aren't in two columns, they are just in one column. Here is an example: In one of my studies, my student created a hypothetical applicant scenario. In one scenario, the applicant was introverted and in the other scenario, the applicant was extraverted. So, I conducted an independent samples t test to see if there were differences between these groups. There are statistically significant differences between the groups. However, I'd like to know if the females had different preferences for a particular applicant than did males. I'm not sure how to do this.
statman
Administrator
Posts: 2721
Joined: Tue Jun 12, 2007 12:08 pm
Location: Florida, USA

Re: Comparing responses by gender (or another demographic va

Postby statman » Mon May 05, 2014 12:18 am

Check into a test of Independence
jdyson
Posts: 4
Joined: Sat May 03, 2014 8:15 pm

Re: Comparing responses by gender (or another demographic va

Postby jdyson » Mon May 05, 2014 1:21 am

Thanks.
jdyson
Posts: 4
Joined: Sat May 03, 2014 8:15 pm

Re: Comparing responses by gender (or another demographic va

Postby jdyson » Mon May 05, 2014 1:52 am

I did what you suggested and it gave me a nice little chart, so I know I'm in the right "neck of the woods." The chart compared the means of males and females. Perfect! However, when I clicked on Chi square, it said I didn't have enough data to run the analysis. Then, I tried clicking on a T test and it gave me two blank columns. Humm. Am I missing something obvious.
statman
Administrator
Posts: 2721
Joined: Tue Jun 12, 2007 12:08 pm
Location: Florida, USA

Re: Comparing responses by gender (or another demographic va

Postby statman » Mon May 05, 2014 12:24 pm

What is your case count (exclude missing responses)

Who is online

Users browsing this forum: No registered users and 2 guests

cron