R2 for binomial data is sensitive on the grouping scheme

 Try to use these data to calculate Nagelkerke R2:

library(fmsb)
data_grouped <- data.frame(x=c(3, 4, 5), y=c(2, 1, 0))
cof_grouped <- c(10, 7, 2)
res_grouped <- glm(cbind(x,y) ~ cof_grouped, data=data_grouped, family=binomial())
summary(res_grouped)
or

data_splited <- data.frame(x=c(1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1), 
                           y=1-c(1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1))
cof_splited <- rep(c(10, 7, 2), each=5)
res_splited <- glm(cbind(x,y) ~ cof_splited, data=data_splited, family=binomial())
summary(res_splited)

These data are exactly the same and indeed the fitted model is the same.

But...

> NagelkerkeR2(res_grouped)$R2

[1] 0.9538362

> NagelkerkeR2(res_splited)$R2

[1] 0.2879462

You will conclude for a very strong link and a weaker link in the second case.

Note that you have the same problem with a common R2:

> cor(x = data_grouped$x/(data_grouped$x+data_grouped$y), y=res_grouped$fitted.values)^2

[1] 0.964555

> cor(x = data_splited$x/(data_splited$x+data_splited$y), y=res_splited$fitted.values)^2

[1] 0.1607592


This problem is also indicated here:

https://thestatsgeek.com/2014/02/08/r-squared-in-logistic-regression/

The conclusion of the author is:

The low R squared for the individual binary data model reflects the fact that the covariate x does not enable accurate prediction of the individual binary outcomes. In contrast, x can give a good prediction for the number of successes in a large group of individuals.

See also:

Mittlböck M, Heinzl H (2001) A note on R2 measures for Poisson and logistic regression models when both models are applicable. Journal of Clinical Epidemiology 54: 99-103 doi 10.1016/S0895-4356(00)00292-4


Commentaires

Enregistrer un commentaire

Posts les plus consultés de ce blog

Standard error from Hessian Matrix... what can be done when problem occurs

An Hessian matrix is a square matrix of partial second order derivative. From the square-root of the inverse of the diagonal, it is possible to estimate the standard error of parameters. Let take an example: val=rnorm(100, mean=20, sd=5) # Return -ln L of values in val in Gaussian distribution with mean and sd in par fitnorm<-function(par, val) {   -sum(dnorm(val, par["mean"], par["sd"], log = TRUE)) } # Initial values for search p<-c(mean=20, sd=5) # fit the model result <- optim(par=p, fn=fitnorm, val=val, method="BFGS", hessian=TRUE) # Inverse the hessian matrix to get SE for each parameters mathessian <- result$hessian inversemathessian <- solve(mathessian) res <- sqrt(diag(inversemathessian)) # results data.frame(Mean=result$par, SE=res)   library(MASS) (r<-fitdistr(val, "normal")) It works well. However, the inverse of the matrix cannot be calculated if the second order derivative for some paramete
Lire la suite

stepAIC from package MASS with AICc

Due to a bug in dropterm() and addterm() in package MASS, it is impossible to use AICc with stepAIC() . Here is a solution. Enter these commands and now you can use: stepAIC(g0, criteria="AICc") or stepAIC(g0, criteria="BIC") For example: datax <- data.frame(y=rnorm(100), x1=rnorm(100),                     x2=rnorm(100), x3=rnorm(100), x4=rnorm(100)) g0 <- glm(y ~ x1+x2+x3+x4, data=datax) gx_AICc <- stepAIC(g0, criteria="AICc") gx_AIC <- stepAIC(g0, criteria="AIC") gx_AIC <- stepAIC(g0, criteria="BIC")
Lire la suite

Install treemix in ubuntu 20.04

Informations are available here  https://bitbucket.org/nygcresearch/treemix/downloads/ In terminal, enter for  Ubuntu 20.04: wget https://bitbucket.org/nygcresearch/treemix/downloads/treemix-1.13.tar.gz tar -xvf treemix-1.13.tar.gz sudo apt-get install libgsl-dev sudo apt install libboost-dev sudo apt install libboost-all-dev cd treemix-1.13/ ./configure make sudo make install And it works: $ treemix TreeMix v. 1.13 $Revision: 231 $ Options: -h display this help -i [file name] input file -o [stem] output stem (will be [stem].treeout.gz, [stem].cov.gz, [stem].modelcov.gz) -k [int] number of SNPs per block for estimation of covariance matrix (1) -global Do a round of global rearrangements after adding all populations -tf [file name] Read the tree topology from a file, rather than estimating it -m [int] number of migration edges to add (0) -root [string] comma-delimited list of populations to set on one side of the root (for migration) -g [vertices file name] [edges file name] read the g
Lire la suite