[R-sig-ME] Testing Random Effects--On the Boundary

[James Grecian]

Hi all,

Have you tried Scheipl's RLRsim package? http://cran.r-project.org/web/packages/RLRsim/index.html

I found it really useful for testing the importance of random effects. It will simulate a p value based on LRT for you.

Best,

James


-----Original Message-----
From: r-sig-mixed-models-bounces at r-project.org [mailto:r-sig-mixed-models-bounces at r-project.org] On Behalf Of Thompson,Paul
Sent: 21 November 2013 20:22
To: AvianResearchDivision; Philippi, Tom; r-sig-mixed-models at r-project.org
Subject: Re: [R-sig-ME] Testing Random Effects--On the Boundary

I have never heard of a rule of "dividing the p values in half". There are corrections like Bonferroni but these depend on the number of tests. 

-----Original Message-----
From: r-sig-mixed-models-bounces at r-project.org [mailto:r-sig-mixed-models-bounces at r-project.org] On Behalf Of AvianResearchDivision
Sent: Thursday, November 21, 2013 2:07 PM
To: Philippi, Tom; r-sig-mixed-models at r-project.org
Subject: Re: [R-sig-ME] Testing Random Effects--On the Boundary

Hi Tom,

I have read that page.  I see there are 6 options, but I am curious about using LRT in particular and using a corrected p value, rather than other options.  I see people floating around the suggestion to divide the p value in half, but there has to be a more exact calculation maybe?  Then again, maybe not because of the nature of the issue.

Jacob


On Thu, Nov 21, 2013 at 3:04 PM, Philippi, Tom <tom_philippi at nps.gov> wrote:

> Jacob--
> Have you read the r-sig-mixed-models FAQ and the references it points to:
> http://glmm.wikidot.com/faq
>
> I don't know if you can do the parametric bootstrap tests for random 
> effects using PBmodcomp in package pbkrtest, as I only test for fixed 
> effects.
>
> I hope that this helps...
> Tom
>
>
> On Thu, Nov 21, 2013 at 11:47 AM, AvianResearchDivision < 
> segerfan83 at gmail.com> wrote:
>
>> Hi all,
>>
>> I've read multiple times that using LRT to test the significance of 
>> random effects terms in mixed models yields conservative p-values and 
>> that one way to correct this is to divide the p value in half.  Is 
>> this a hard fast rule or is there a script for R that gives an actual 
>> corrected value?
>>
>> Thank you,
>> Jacob
>>
>>         [[alternative HTML version deleted]]
>>
>> _______________________________________________
>> R-sig-mixed-models at r-project.org mailing list 
>> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>>
>
>
>
> --
> -------------------------------------------
> Tom Philippi, Ph.D.
> Quantitative Ecologist & Data Therapist Inventory and Monitoring 
> Program National Park Service
> (619) 523-4576
> Tom_Philippi at nps.gov
> http://science.nature.nps.gov/im/monitor
>

	[[alternative HTML version deleted]]

_______________________________________________
R-sig-mixed-models at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
-----------------------------------------------------------------------
Confidentiality Notice: This e-mail message, including a...{{dropped:11}}