Which Stats Test... Help!

#1
Hi All,

I've just taken on a masters as a (very) mature student and have no experience of running stats... help!

I need to analyse the results of a questionnaire looking at peoples fitness habits.

For example, I would like to compare the time of day that males and females work out - during working hours, during lunch or after work - and determine if there is a significant difference. So I guess my null hypothesis is that "there is no significant difference between the time of day that males and females work out"...?

Second example... I would like to explore if there is any relationship between age and participation frequency. I have the age of all my respondents and how often they participate (once a month or less, once a week, twice a week, three times a week or more). Is this a correlation?

IS there a reliable online resource i can use for advice?

Thank you for any advice ;)
 
Last edited:

hlsmith

Not a robit
#2
What is your response rate and sample size?

Your first question may be addressed using Fisher's Exact test (if you have small sample) or chi-square test.

Your second question is trickier given the time units aren't constant in the time measures. If you order them you may be able to get away with a Spearmen Rank-Order correlation or Gamma correlation, given you aren't publishing or changing the world with these data.

What program are you in?