Beginner: Issues with a simple regression test.

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

hardwiredstudios
Posts: 1
Joined: Wed May 31, 2017 12:26 pm

Beginner: Issues with a simple regression test.

Postby hardwiredstudios » Wed May 31, 2017 12:58 pm

Hey all, I'm brand new to this forum and to statistics generally, so hello and hope you're all good.

For my undergrad thesis, i'm comparing the effect of gaming audio styles to game immersion.
For this i tested 18 people who had to play 2 levels of a game i created and fill in a likert scaled questionnaire after each level thus showing the immersion for each level.

The audio delivery systems (2 styles) were randomised for each participant; so say procedural audio (one of the styles) featured on either their first or second level and i want to compare if using that method made a more immersive experience compared to the other style (sample-based). For the immersion level i used a likert scale and from this the total for each level is out of 60.

I've tried a simple t-test and as the audio level variable (1st or 2nd) isn't population based it won't compare it. So i tried a regression test but i'm confused on what variable goes where.

Everything i try won't work. The main variable (the audio style level) is set out a 1st = 1 and 2nd = 2. So in effect its the same as Male = 1 and Female = 2 for gender.

Because i'm clueless about stats, i'm not sure if its something i'm doing fundamentally wrong (like i've allocated the wrong var in the wrong place or i'm not doing the right test) or is it as simple as how i've done the variable (1st=1, 2nd=2).

I hope i'm being kind of clear on my issue haha.
I could upload my SPSS project if it helps.

Many Thanks,

Paul..

Who is online

Users browsing this forum: No registered users and 3 guests

cron