Yet another question about selecting the proper statistical test - (Jul/10/2013 )

I would greatly appreciate if you could point me out in the right direction. In my experiments I have two conditions: newborn and adult. And from both of them I have 24 samples which value can be positive or negative for the presence of a gene. So I have a discrete variable and I want to know if the frequency of appearance of this gene is different in newborns with respect of adults, but I do not if it´s proper to apply a non parametric test like Ji square. Thanks a lot guys!

Best,

Zazek84

Are you sure your observation is yes or no? How can some do not have the gene? If it is discrete variable, Chi-square is appropriate.

are you looking for presence or expression of the gene?

the G-test and Fisher's Exact test are the modern alternatives for Chi-Square and often preferable.

pcrman on Thu Jul 11 06:41:44 2013 said:

Yes, the cells can suppress the expression of a certain gene according to their developmental stage, that is our general hypothesis. Thanks a lot to all for your quick response! It´s of great help!