What test do i use?

[hamii0]

Hi...

i'm a doctor... and im currently in the process of writing a paper detailing the results of some research i've been conducting over the past 3 months.

I'd like to know what would be the statistical test to use on my data.

Example:

Diagnosis 1:

Patient 1 12.3mmHg
Patient 2 13.1mmHg
Patient 3 12.5mmHg
Patient 4 12.3mmHg

Diagnosis 2:

Patient 5 6.3mmHg
Patient 6 5.9mmHg
Patient 7 6.5mmHg
Patient 8 6.1mmHg

I understand that the sample size isn't large. The diagnosis isn't a particularly common one. Would a student t test suffice? if i run a test on more than 2 groups... would an ANOVA be needed? what parameters do i need to apply to each test?

[IronMan]

What kind of inference do you want to make about your data?


If you're trying to show that the means (or medians) are different, you could use a t test, but the sample size is extremely small... You may want to look at Non parametric tests.

i.e.

http://en.wikipedia.org/wiki/Mann-Whitney_U