Difficulty reproducing example from paper

[gavinmdouglas]

micropower seems like a great tool and I've been trying to use it to get the general range of effect sizes that could be detectable with power 90% at different sample sizes for detecting differences in weighted Unifrac distances between 2 groups.

I've been trying to reproduce example 2 from the 2015 paper to make sure I'm using the tool correctly, but I'm having a few problems.

Firstly, in section 3.2 it's mentioned that "the mean within-group distance was simulated as 0.2, and the standard deviation of within-group distances as 0.07". Is there a way to specify this with the simPower function? I haven't seen any other function that seems like it could do this.

Also, did it make a difference what max depth / rarefaction parameter was used for the weighted analyses?

I ask these questions since after running the bootPower function on the Unifrac weighted distance matrices I am getting high power based on quite low "simulated_omega2" values, which makes it difficult to fit a loess since there are basically just two values for power: 0 and 1.

Thanks for your help in advance!

[gavinmdouglas]

I wasn't able to figure it out and didn't end up using it for my project

• you might have better luck though!

On 11/20/2018 7:19 PM, Xiaotao JIANG (姜小濤) wrote:

Hello, gavinmdouglas, I read this paper and interested about this paper and want to have a try of this tool on one of my dataset. However, it seems that that the author do not reply any question for the use of this tool. I am hesitating about whether I need to invest my time for this tool. Did you get the result you want or not? What's your comment for this tool? @gavinmdouglas https://github.com/gavinmdouglas

Thank you very much!

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub

[biofuture]

Thanks for your reply. Gavin Douglas Regards,

Xiao-Tao Jiang, Ph.D. Postdoc Research Fellow Microbiome Research Centre St George and Sutherland Clinical School UNSW Sydney

Level 2, Clinical Sciences Building (WR Pitney) Short Street, St George Hospital KOGARAH NSW 2217 T: +61 402 943 681 Email: biofuture.jiang@gmail.com/xiaotao.jiang@unsw.edu.au MRC web: https://microbiome.org.au/

Gavin Douglas notifications@github.com 于2018年11月21日周三 上午11:27写道：

I wasn't able to figure it out and didn't end up using it for my project

• you might have better luck though!

On 11/20/2018 7:19 PM, Xiaotao JIANG (姜小濤) wrote:

Hello, gavinmdouglas, I read this paper and interested about this paper and want to have a try of this tool on one of my dataset. However, it seems that that the author do not reply any question for the use of this tool. I am hesitating about whether I need to invest my time for this tool. Did you get the result you want or not? What's your comment for this tool? @gavinmdouglas https://github.com/gavinmdouglas

Thank you very much!

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub < https://github.com/brendankelly/micropower/issues/6#issuecomment-440464250>,

or mute the thread < https://github.com/notifications/unsubscribe-auth/AL6T00eE9AX_6t-0DkpPQ1J1mz3NJEPpks5uxI3rgaJpZM4Ngl2Z .

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/brendankelly/micropower/issues/6#issuecomment-440480007, or mute the thread https://github.com/notifications/unsubscribe-auth/ABaxoN21qrrb5Zod60soJJYgRfDmZJcFks5uxJ3tgaJpZM4Ngl2Z .

[brendankelly]

Hi all, Unfortunately, I don't have the resources to actively maintain this package.

And, despite my best intentions, I never included a vignette with the package.

The best I can offer is this example workflow, which (I hope) helps clarify how the package can be used:

https://gist.github.com/brendankelly

Brendan