daliangning / nst Goto Github PK

Hello, I'm trying compare the NST values between three groups. I got results by using the nst.boot() function implemented in the NST package.

I was wondering about the p-value adjustment in comparing NST bootstrap (& Permanova) results.
Since I have three groups (S1, S2, S3), I wonder whether p.count and p.count.noOut represent p-values that are adjusted for multiple comparisons.

I've looked through the source code for nst.boot() and it seems like there are no adjustments made for p-values. I wonder whether I should adjust them myself (lower significance level like Bonferroni correction).

Thanks a lot!!!

Dear Daling Ning

I am using the NST package to get mean RC and NST within treatments in a community, but considering the pool species. However, when building a null model, Vallend et al, 2007 pointed out a bias when the number of samples varies among treatments. For instance, the species composition of the treatment with a higher sample size will largely determine the regional pool, making sites of that treatment appear more similar to the regional pool, which will potentially tend to have lower mean β RC.

To remove this bias, Vellend et al., 2007 suggest that each species’ frequency in the regional pool should be based on the mean of its frequency within each treatment, rather than its overall frequency. In this way, species frequency could be calculated as the mean of means (that is, each species frequency is the mean of means within treatments).

Thus, I ask you if is possible to include a vector in the null model argument to predefined species frequency. Such fixed species frequency could be externally estimated and included in order to null model argument. Alternatively, I believe that the inclusion of a function where overall species frequency is proportional to sample size within treatments would be the best option.

Thanks
Daniel

VELLEND, M., VERHEYEN, K., FLINN, K.M., JACQUEMYN, H., KOLB, A., VAN CALSTER, H., PETERKEN, G., GRAAE, B.J., BELLEMARE, J., HONNAY, O., BRUNET, J., WULF, M., GERHARDT, F. and HERMY, M. (2007), Homogenization of forest plant communities and weakening of species-environment relationships via agricultural land use. Journal of Ecology, 95: 565-573. https://doi.org/10.1111/j.1365-2745.2007.01233.x

Dear Prof
I trust you are keeping well
I want to know, that is it necessary to have phylogenetic tree for this model, or we can use this with out tree
kindly please let me know
Thanks and Regards

As mentioned in the topic.

Thank you for this quite exciting package. It's really helping me with null model analysis!

I'm exploring pNST and tNST and wonder how to compare different groups best.
In the PNAS paper, it is recommended to do a relative comparison rather than using absolute values.
I have time-series data from three different environments for which I want to check for stochastic effects.
Currently, I'm running NST for each environment with time as a grouping variable, and I use the NST predictions from bootstrapping for statistical analysis.
But I'm struggling with how to make the relative comparison. Do you have any recommendations here?

Hi Daliang,

In the PNAS paper, you mentioned that NST should range from 0 to 1. However, in my results I found that NST.ij.bray/NST.ij.bMNTD does not range from 0 to 1. The MSTij.bray/MST.ij.bMNTD ranges from 0 to 1, though. Should I use MST instead of NST?

Best,

Chen