We performed the siRNA based knockdown assay with 10 different siRNAs and each siRNA with three different concentrations (0.1, 0.5, 1 nM) and repeated three times in triplicates (3-wells) each time. we also took reagents only (i.e. no siRNA) as control and scrambled siRNA as negative control each time.
which statistical significance test will be good for this experimental procedure? Is One way ANOVA good enough for this test?
Thanking in anticipation
Dear Showkat Ahmad,
I believe the number of your data is not big enough to find significant results using ANOVA.
You may want to consider statistical non-parametric methods to validate your results.
Good luck.
Dear Mani Mehraei
Thank you very much for your quick reply...but my question is not answered yet... could you explain it a bit...
Thanks again
Dear Showkat,
Parametric and non parametric analysis are related to the distribution of your data. ANOVA can be used for t-student and normal distributed or the other known distributed population. Since, the number of your data is small, you can't approximate it with those distributions. Most of researchers who are not statisticians keep this mistake, and surprisingly their articles get even acceptance.
Non-parametric methods are not only for testing medians. They can be used for testing the mean of a population as well.
Kind regards,
Mani
To answer this question read:
https://www.amazon.com/Design-Analysis-Experiments-Douglas-Montgomery/dp/1118146921/ref=sr_1_fkmr1_2?keywords=dc+montgomery+design+of+experiments&qid=1564464553&s=gateway&sr=8-2-fkmr1
You should have read this prior to collecting Data. Data is worthless if you don't know or can't find a way to analyze it. D. Booth Moral: Proper Prior Planning prevents poor performance
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Modeling
- Analyses of Variance
- ANOVA