I need to open a new question regarding the already largely discussed "standard error".

I have performed twice the same experiment on the same area. Each experiment includes the measurements of two replicates. Such that:

Experiment A -> A.1 - A.2

Experiment B -> B.1 - B.2

I have learnt that when I average within the same experiment I have to calculate the standard deviation because it represents how much the samples differ from their mean.

Mean(A) +- SD

Mean(B) +- SD

Now, I want to compare the two experiments. I want to obtain an average that represents the actual population present in the area, and I think I should calculate the standard error of the mean.

How should I calculate the standard error here? should I use the values of the 4 replicates in this way?

mean = (A.1+A.2+A.3+A.4)/4

SE = SD(A.1+A.2+A.3+A.4)/sqrt(4)

or, I should calculate from the averages?

mean = [average(A)+average(B)]/2

SE = SD(average(A)+average(B))/sqrt(2)



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.