2
$\begingroup$

I am unsure about how to analyze some data of my PhD project and could use some input. I am analyzing data from a Phase I clinical trial where we have scRNAseq + Histology of paired PRE and POST biopsies. However, as the clinical trial was stopped early due to outside reasons (adverse effects in a different trial in a different condition), I am left with "only" 5 paired samples. Now, I want to compare fractions (e.g. Number of CD8+ T cells/mm2, or %of stromal coverage, or % of total population) between PRE and POST to see where the treatment induced changes. In some cases, it seems quite clear as there is a strong difference, however I don't know which statistical test to apply.

Normally I would say the Wilcoxon matched-pairs signed rank test, since I don't think I can assume normality for fractions. However, with 5 paired samples, the power is too low to reach significance threshold (lowest attainable p value with wilcoxon with N=5 is 0.0625), which in principle I don't care about since I think there is still a pretty strong message when I see the same effect in scRNAseq and histology, but I am worried that it will make submission more difficult. I have also seen people use the paired t-test for these kinds of fractions in the literature in good journals (e.g. Cell), but I think that would be cheating (but I'm hoping to be wrong here - please tell me).

If you have other ideas, feel free to let me know. If there's some special test for low N paired samples not assuming normality that is not available in Graphpad, I am fine with R as well.

Thank you all!!

$\endgroup$

1 Answer 1

2
$\begingroup$

You don't have enough data for traditional statistical hypothesis testing. No statistical test will get you around this fact.

I'd recommend just reporting the raw data when there are so few numbers. Let your audience decide what they want to believe or not regarding the data.

$\endgroup$
1
  • $\begingroup$ Thank you, I guess I needed a bit of tough love so to speak. I had hoped that maybe there's some more advanced statistics that can make sense of the situation but I guess not. $\endgroup$ Oct 24, 2023 at 9:02

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .