Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 1 down vote favorite

Lets say I run an experiment testing accuracy of hitting targets of two different sizes. I have 10 participants and 40 targets, 15 small and 25 large. I then have the number of misses for each target recorded.

So I end up with 150 small target scores and 250 large target scores. I want to see if there is a difference in the number of misses on small targets vs large targets. Is the degrees of freedom based on the total number of measurements, 150 and 250? Or is it based off of the number of participants, 10?

share|improve this question
Cross-posted: forums.xkcd.com/viewtopic.php?f=17&t=84964 – Dason May 25 '12 at 4:49
Is crossposting not ok? It was fairly time critical so I wanted to throw it out to a few sources. – Justin May 25 '12 at 6:04
1  
Cross-posting on several SE sites is not recommended: there exist facilities to migrate question from one site to another if it happens one site is better suited for the question at hand. Cross-posting on different forums, Q&A sites, mailing, etc., is another issue: It's always a good idea to reference other posts and keep every actors up to date with replies on either site. Otherwise, there is a risk of overlapping threads, incomplete replies due to intervening updates to the question, etc. In all cases, we are messing up google queries, but hopefully CrossValidated will come first :-) – chl♦ May 25 '12 at 11:45
It is usually nice to have an equal number of observations in each cell. If you have not yet collected the data, you might consider using the same number of large and small targets. In any case, what statistical analysis were you planning to use? Also, did you counterbalance the order of presentation of large and small targets? – Joel W. May 25 '12 at 15:22
The data has already been collected. This particular comparison really is not the main point, just something we wanted to run on the side. And the order was fixed, but small targets were reasonably well distributed. I was hoping to run Welch's t-test. (Stats really is not my area... and when all you have is a hammer, it all looks like a nail.) – Justin May 25 '12 at 16:13

Know someone who can answer? Share a link to this question via email, Google+, Twitter, or Facebook.

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.