Cant find the right test for my dissertation. Please Help!!

#1
Hi i am currently at the end of a summer break and am starting my final year at university within the next few weeks. The title of my dissertation is "The effects of sleep deprivation on aerobic performance". I will have two conditions, "aerobic performance after a good nights sleep" and "aerobic performance after 36 hours of sleep deprivation". I arent sure what sort of statistical test i would need to use to make a comparison between the two sets of data i will recieve. I have looked at websites and have the names of plently of tests (spearman rho, one tailed, two tailed etc) and cant seem to find one that would suit my study. I wont actually do my study until the beginning of next year but would love to get a head start on it if possible. My hypothesis states that "sleep deprivation will have a detrimental effect upon aerobic performance". Any help would be greatly appreciated, if anyone could point me in the right direction. Thank you in advance. Alex
 
#2
You would have to take the mean of your performace measure of case 1 and mean of the performance measure of case 2 and compare them to see if they are significantly different i.e Is the variation significantly greater than what can be explained by noise.
Ho: mean 1= mean 2
H1: not H0.

depending on the sample size i would do either a z or a t test .
 
#5
A t-test is correct, but the type of t-test you use is dependent on whether or not you are sampling the same group of individuals (i.e., between- or within-subjects design)

For example:

One group (n=10) for sleep deprivation and group two (n=10) for no sleep deprivation (independent samples)

--or--

One group (N=10) tested at two separate occasions...once with full sleep and then again after sleep deprivation (paired samples)