Dfbeta for Negative Binomial and Beta-binomial Models
Produces an approximation, better known as the one-step approximation, of the effect on the parameter estimates of a negative binomial or beta-binomial model of deleting each individual in turn. This function also can produce a plot of those effects for a subset of the parameters in the linear predictor.
## S3 method for class 'overglm' dfbeta(model, coefs, identify, ...)
model |
an object of class overglm which is obtained from the fit of a negative binomial or beta-binomial model. |
coefs |
an (optional) character string which (partially) match the names of some parameters in the linear predictor. |
identify |
an (optional) integer indicating the number of individuals to identify on the plot of dfbeta. This is only appropriate if the argument |
... |
further arguments passed to or from other methods. If |
The one-step approximation of the estimates of the parameters in a negative binomial or beta-binomial model when the i-th individual is excluded from the dataset consists of the vector obtained as result of the first iteration of the Newthon-Raphson algorithm when it is performed using: (1) a dataset in which the i-th individual is excluded; and (2) a starting value which is the estimate of the same negative binomial or beta-binomial model but based on the dataset inluding all individuals.
A matrix with so many rows as individuals in the sample and so many columns as parameters. The i-th row of that matrix corresponds to the difference between the estimates of the parameters using all individuals and the one-step approximation of those estimates when the i-th individual is excluded from the dataset.
Pregibon D. (1981). Logistic regression diagnostics. The Annals of Statistics, 9, 705-724.
fit <- glm(cbind(cells,200-cells) ~ tnf + ifn + tnf*ifn, family=binomial, data=cellular)
dfbs <- dfbeta(fit, coefs="tnf:ifn", col="red", lty=1, lwd=1, col.lab="blue",
col.axis="blue", col.main="black", family="mono", cex=0.8, main="Dfbeta")Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.