[R-sig-ME] ICC for quasipoisson?

[Dr C B Stride]

Hi

Was wondering if anyone knows of a snippet of R code that will perform 
the ICC calculations recommended in this paper?

cheers
Chris

Jarrod Hadfield said the following on 09/09/2011 16:51:
> Hi,
> 
> You can find the relevant equations in Table 2 of:
> 
> Repeatability for Gaussian and non-Gaussian data: a practical guide for 
> biologists. Biological reviews. 2010. Nakagawa1 & Schielzeth
> 
> Cheers,
> 
> Jarrod
> 
> Quoting Elizabeth Oliva <elizabeth.oliva at gmail.com> on Fri, 9 Sep 2011 
> 08:34:50 -0700:
> 
>> Hi all,
>>
>> I’ve been searching at length for a way to figure out how to calculate 
>> the
>> ICC for a mixed effects quasipoisson model in R from the output below 
>> (i.e.,
>> intercept only model) and can't figure out the correct equation to 
>> use. For
>> example, I've run mixed effects logistic regression models for which I 
>> used
>> the following equation:
>>
>>                c<-a*a
>>
>>                icc<-c/(3.289868+c)
>>
>> [a being the standard deviation of the intercept]
>>
>>
>>
>> I'm not sure what the corollary type of equation is for quasipoisson 
>> mixed
>> models.
>>
>>
>>
>> If you had any suggestions I would greatly appreciate it.
>>
>>
>>
>> Best,
>>
>> Elizabeth
>>
>>
>>
>>
>>
>> womentxengintonly <- glmmPQL(NewSpecOut_SUM ~ 1, random = ~1 |NEPEC3N,
>> family =quasipoisson, data = women)
>>
>>
>>
>>
>>
>> summary(womentxengintonly)
>>
>>
>>
>> Linear mixed-effects model fit by maximum likelihood
>>
>> Data: women
>>
>>   AIC BIC logLik
>>
>>    NA  NA     NA
>>
>>
>>
>> Random effects:
>>
>> Formula: ~1 | NEPEC3N
>>
>>         (Intercept) Residual
>>
>> StdDev:   0.4679934  7.26936
>>
>>
>>
>> Variance function:
>>
>> Structure: fixed weights
>>
>> Formula: ~invwt
>>
>> Fixed effects: NewSpecOut_SUM ~ 1
>>
>>                Value  Std.Error   DF  t-value p-value
>>
>> (Intercept) 3.046308 0.04805773 4960 63.38852       0
>>
>>
>>
>> Standardized Within-Group Residuals:
>>
>>        Min         Q1        Med         Q3        Max
>>
>> -1.0333625 -0.5507037 -0.3717204  0.2138915 12.4856954
>>
>>
>>
>> Number of Observations: 5099
>>
>> Number of Groups: 139
>>
>>     [[alternative HTML version deleted]]
>>
>>
> 
> 
> 
> --The University of Edinburgh is a charitable body, registered in
> Scotland, with registration number SC005336.
> 
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models


-- 
Dr Chris Stride, C. Stat, Statistician, Institute of Work Psychology, 
University of Sheffield
Telephone: 0114 2223262
Fax: 0114 2727206

“Figure It Out”
Statistical Consultancy and Training Service for Social Scientists

Visit www.figureitout.org.uk for details of my consultancy services, and 
forthcoming training courses, which are also available on an in-house basis:
- Data Management using SPSS syntax
- Multiple Regression using SPSS
- Multilevel Modelling using SPSS
- Structural Equation Modelling using MPlus