Thread: Which statistical test to use for the following scenario?

1. Which statistical test to use for the following scenario?

Firstly, thanks for taking the time to read my post.
The scenario:

I have 20 novice darts players- split into 5 teams. They're told it's a darts competition between teams, where they throw 6 darts each. They throw 6 darts each, 1 at a time, and each individual (and overall team) score is calculated. They then fill in a sports anxiety questionnaire (CSAI-2) to get measures for cognitive anxiety, somatic anxiety, and self-confidence.
Each team then goes away and learns a different anxiety management technique (imagery, self-talk, breathing, or a combination of all 3, and a control group). They then complete the same procedure again- 6 darts each, scores calculated, and a questionnaire to measure differences in anxiety.

Basically I want to compare:
Changes in darts scores pre-intervention and post intervention (and compare which intervention resulted in the greatest improvement in darts scores).

And also do the same for:
Cognitive anxiety
Somatic anxiety
Self-confidence
(i.e. see which intervention resulted in the greatest improvements for cognitive anxiety, somatic anxiety and self-confidence)

Which statistical test should I use- and how should I go about this? (I.e. should I compare players individuals scores, or teams total scores).

Many thanks again for reading my post.

Sam

2. Re: Which statistical test to use for the following scenario?

You've posted this in two places which actually decreases the chances of getting an answer rather than increases. I'd recommend you delete one.

3. The Following User Says Thank You to trinker For This Useful Post:

CowboyBear (04-09-2013)

4. Re: Which statistical test to use for the following scenario?

I've deleted OP's other post.

5. Re: Which statistical test to use for the following scenario?

Repeated measures ANOVA would probably be the usual way to go if you assumed normal errors*. I don't know enough about darts to say much about what kind of error distribution is plausible though.

*Errors in the regression model I mean, not errors in the sense of darts thrown haphazardly into the wall.

6. The Following User Says Thank You to CowboyBear For This Useful Post:

03turnerS (04-10-2013)

 Tweet

Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts