Technical replicates vs. biological replicates

#1
I've done a lot of reading on hypothesis testing and I can't find the answer to this question: What is the standard way to handle variation in technical repeats (i.e. repeated measurements of the same thing)?

T-tests, etc. , are great at using single measurements (measuring a quantity once per individual in a sample) to determine if there's a difference between two samples. But what if you measure the quantity several times per individual, and see significant variation between those measurements? You'd want your significance test to take this variation in measurement into account, right? How do you do that?
 

Dragan

Super Moderator
#2
I've done a lot of reading on hypothesis testing and I can't find the answer to this question: What is the standard way to handle variation in technical repeats (i.e. repeated measurements of the same thing)?

T-tests, etc. , are great at using single measurements (measuring a quantity once per individual in a sample) to determine if there's a difference between two samples. But what if you measure the quantity several times per individual, and see significant variation between those measurements? You'd want your significance test to take this variation in measurement into account, right? How do you do that?

If I'm understanding you correctly try looking into intraclass correlation coefficients. There are different kinds, but perhaps, Cronbach's alpha being the most popular.
 
#3
In the case of the T-test, you're restricted to k = 2 groups and c = 2 measurements. The repeated measures ANOVA can handle more than 2 groups and more than 2 measurements per individual in the sample.

Did this answer your question?:confused: