Dear Scientist,
I kindly plead for any one who has an idea on this to clarify me. I ran a two way ANOVA with data collected from two locations and got no location X genotype interaction, then a reviewer is requesting me to present represent replication within location effect and triplicate within sample effect.
Please, can any one give an idea on this? I use XLSTAT to run the analysis.
Thank you
Hi Difo Voukang Harouna
You can perform pairwise comparisons along with an ANOVA in XLSTAT by selecting Tukey's HSD option. Here is a step-by-step tutorial: https://help.xlstat.com/customer/en/portal/articles/2062434-running-pairwise-multiple-comparisons-after-a-multi-factor-anova?b_id=9283
When interaction is significant in the 2-way ANOVA test, it makes no sense to interpret the main effects of each factor. In this case it is necessary to unfold the interaction. This is done by fixing one of the factors and at each level of the fixed factor, you compare the levels of the other factor with pairwise comparison (Example: Tukey). The link in Usman Rashid answer will be very usefull for you.
Regards!
Dear Usman Rashid and Ouorou Ganni Mariel Guera Thank you very much for your very useful and insightful answer.
However, please, I am still not comprehending very well what to take as replication effect or triplicate effect or interaction. I have actually ran the Tukey test but I Don't know where to read the replication or triplicate interaction. Could it be the LS mean??
Please, can you explain more on how to fix and unfold interaction because it is not explain on the link.
Thank you very much for your help
Waiting to hear from you
Regards!
Dear Difo Voukang Harouna
In the two way ANOVA (location by genotype), what is your outcome variable?
I don't think that replication and triplication effects are statistical tests in this context. Did you study replication and triplication as part of your study?
More on replication and triplication in the context of genotype is discussed in the following articles:
1. Article Replication in Genome-Wide Association Studies
2. Article Impact of triplicate testing on HIV genotypic tropism predic...
Hope it is helpful
Usman R.
Dear Usman Rashid Thank you very much for this additional useful materials.
Please, attached is the outcome.
And here is the question i am trying to answer:
''You should also show the replicate within location effect in this part of the table. You could also report on triplicate within samples to see whether the effort of measuring triplicates would be useful ''.
Could you give any guiding comment?
Can anyone also give me an idea on what he think about the two way ANOVA for the block design in replicates on this link, I just came across this now, trying to analyse.
https://home.ubalt.edu/ntsbarsh/Business-stat/otherapplets/ANOVA2Rep.htm
Thank you, Sir
Regards
Difo Voukang Harouna You already have most of the results you need. There are differences across species. This is also clear from the means presented in the first three rows. I think what the reviewer is asking is: Are there any differences across species within location A and location B? It seems like there are.
This can be answered by performing pair-wise comparisons using Tukey's HSD.
The results will look like following:
Location = A:
Specie 1 - Specie 2 =
Specie 2 - Specie 3 = ...and more
Location = B:
Specie 1 - Specie 2 =
Specie 2 - Specie 3 = ...and more
Did you perform pair-wise comparisons?
This is the type of output (as in attached image) you should be looking at.
Dear Usman Rashid Thank you very much for this very helpful answer. Yeah, I have ran Paire-Wise comparisons and I have this type of output but did not understand that this is what the reviewer is requestion. Thank you very much!
I think you have solved my worry if that is the case. However, please can you explain to me briefly which part could explain the triplicate effect there. I also see that it is comparing between locations A Vs B (contrast) but i found this other attached may be it is the right one, could you advise.
Please, one final issue I kindly wish you to clarify me; As you mentionned th there are some interactions within location B only but could that mean the réplications were wrongly done or have any implication on the interpretation of the réplications.
I am so grateful , Sir
Reagards
Dear Difo Voukang Harouna
The attached image is of model parameters. Presenting this may also be helpful but this is not what the reviewer is asking. The reviewer is asking for differences between pairs of species within location A and differences between pairs of species within location B.
You have not done anything wrong. All you need to do is to provide the output of pair-wise comparisons from XLSTAT.
For example: At cite A. The species differences are:
Specie 1 - Specie 2 = 10.24 - 16.29 = -6. If you get this from XLSTAT, it will also give you standard error, confidence intervals and z-values and p-values.
Dear Usman Rashid Thank you very much.
I highly appreaciate your help!
Regards!
- Badges
- Science topic