1

I have data on leukocyte aggregation (a percentage) in two different conditions (A= control, B= Verum). Blood was sampled 8 times throughout the day in 2h intervals.

I'm fairly new to statistics and I'm not really sure which direction to go here. Some posts here point to ARIMA, but that is usually for longer time spans.

What I did up to this point was an unpaired t-test for every time point. This only tells me if there is a statistical difference at every time point, not on the overall series.

ANOVA testing of two regression models is not possible, since they are un-nested (correct?).

What is the best way to see if there is a significant difference between conditions?

I'm working in R.

mariachi
  • 213
  • 1
  • 3
  • 7
  • you would like to test for whether there is mean differences for series or not, right? – Math-fun Jul 06 '16 at 11:28
  • yes. Another example of data I have is glucose concentration from an oral glucose test (basically you sample blood 8 times during 2h). I've seen papers testing every time point individually, but to me that doesn't make much sense, because the important thing is that there's a general difference. Is doing a t-test using the time points as.factors what I actually want here? – mariachi Jul 06 '16 at 13:03
  • does this discussion help? https://stats.stackexchange.com/questions/135061/best-method-for-short-time-series#135146 – Steve Nov 01 '17 at 13:21

0 Answers0