I am measuring the expression of a fluorescent protein over a period of 4 hours (15 min intervals), testing 4 different conditions with 2 control groups (one positive for expression of the protein, one negative), all in triplicate. The purpose of this experiment is to ascertain what effect each condition has on expression of the fluorescent protein over the period of 4 hours. I've considered running a Two Factor Anova with Replication to ascertain whether the test conditions have a statistically significant effect on the expression of the fluorescent protein over the 4 hour time period, however I've read that this test may not be appropriate to apply to time series data. I am wondering if this is the case and if so what statistical analysis might be appropriate to perform on this data?
There are various statistical tests to check stationarity, including the Augmented Dickey-Fuller (ADF) test and the Kwiatkowski-Phillips-Schmidt-Shin (KPSS) test. The ADF test is a widely used test for checking the stationarity of a time series, and it checks for the presence of a unit root in the data.
https://medium.com/analytics-vidhya/time-series-analysis-stationarity-check-using-statistical-test-f106e9045370
If you have a time dependent set of data I suggest looking at regression form ANCOVA. David Booth also see Marie Davidian work on longitudinal models.
A starting point here could be to reduce each four hour period to a single value, say the sample mean, together with an in-sample estimate of the variance of that estimated mean (based on simple time-series theory). You could then compare these variances with the variances derived from your replications
- Badges
- Science topic
- Similar topics
- Biological Science
- Molecular Biology
- Molecular Methods
- Cloning