Most appropriate statistical test(s)

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

catiscot
Posts: 3
Joined: Thu Jan 04, 2018 7:35 pm

Most appropriate statistical test(s)

Postby catiscot » Tue Jan 09, 2018 9:31 pm

I have data on nine different behaviours when a woman is pregnant. I have asked respondents to rank them in order of importance, most important to least important. Scale is 1 to 9.

The behaviours are things like:
Eating 5 a day; Exercising moderately ; Reducing caffeine intake; Reducing alcohol intake

I also have a number of predicator variables like age, do you smoke, do you drink, do you have children etc. Do you consider yourself physically active etc.

I am hoping for advice from someone with a more indepth understanding of statistical analysis than I have of what would be the most appropriate type of statistical test for significance.

Basically, if you were looking for significant differences in fields that have been ranked from 1 to 9 in importance, which tests you would go to first.
statman
Administrator
Posts: 2750
Joined: Tue Jun 12, 2007 12:08 pm
Location: Florida, USA

Re: Most appropriate statistical test(s)

Postby statman » Wed Jan 10, 2018 12:58 pm

So you want to test the diff between the behaviors? Or, behavior by predictor? Or ................? what

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
catiscot
Posts: 3
Joined: Thu Jan 04, 2018 7:35 pm

Re: Most appropriate statistical test(s)

Postby catiscot » Wed Jan 10, 2018 2:13 pm

Thank you for your response.

I had not read anything before regarding posting guidelines, thank you for making me aware of it.

The project is a student project for my daughter who is postgraduate Psychology. My background has been in survey analysis but nearly all projects did not have much of a statistical analysis part to them.
The short answer to

So you want to test the diff between the behaviours? Or, behaviour by predictor?

Is both. I think my main focus will be differences between the importance of the behaviour for different groups (predictor groups i.e. do you smoke). But I think she will also have to look at differences between the behaviours.
statman
Administrator
Posts: 2750
Joined: Tue Jun 12, 2007 12:08 pm
Location: Florida, USA

Re: Most appropriate statistical test(s)

Postby statman » Wed Jan 10, 2018 4:40 pm

Might look at one of the independence test, e.g., Independent Means Test or its equivalent Nonparametric version depending on response base

ANOVA can give an overall perspective

Hope this sets you in the right direction

BTY, your "background has been in survey analysis," are you independent or a company? If want to talk off-line send me a PM or see my Web site

Who is online

Users browsing this forum: No registered users and 3 guests

cron