Bootstrapping for regression models
This function provides a simple front-end to the
boot function in the
package also called
boot is very general and therefore
has many arguments, the
Boot function has very few arguments, but should
meet the needs of many users.
## S3 method for class 'default': Boot(object, f=coef, labels=names(coef(object)), R=999, method=c("case", "residual")) ## S3 method for class 'lm': Boot(object, f=coef, labels=names(coef(object)), R=999, method=c("case", "residual")) ## S3 method for class 'glm': Boot(object, f=coef, labels=names(coef(object)), R=999, method=c("case", "residual")) ## S3 method for class 'nls': Boot(object, f=coef, labels=names(coef(object)), R=999, method=c("case", "residual"))
- A regression object of class
nls. The function may work with other regression objects that support the
updatemethod and have a
- A function whose one argument is the name of a regression object that will be applied to the updated regression object to
compute the statistics of interest. The default is
coef, to return to regression coefficient estimates. For example,
- Provides labels for the statistics computed by
f. If this argument is of the wrong length, then generic labels will be generated.
- Number of bootstrap samples. The number of bootstrap samples actually computed may be smaller than
this value if either the fitting method is iterative, or if the rank of a fittle
glmmodel is different in the bootstrap
- The bootstrap method, either
casefor resampling cases or residualsfor a residual bootstrap. See the details below. The residual bootstrap is available only for
nlsobjects and will re
boot function is
Boot is very specific. It takes the information from a
regression object and the choice of
method, and creates a function that is
passed as the
statistic argument to
boot. The argument
is also passed to
boot. All other arguments to
kept at their default values.
The methods available for
nls objects are
nls objects ordinary residuals are used
in the resampling rather than the standardized residuals used in the
method. The residual bootstrap for
generalized linear models has several competing approaches, but none are
without problems. If you want to do a residual bootstrap for a glm, you
will need to write your own call to
An attempt to model fit to a bootstrap sample may fail. In a
glm fit, the bootstrap sample could have a different rank from the original
fit. In an
nls fit, convergence may not be obtained for some bootstraps.
In either case,
NA are returned for the value of the function
The summary methods handle the
bootfor the returned value from this function. The car package includes additional generic functions summary, confint and hist that works with boot objects.
Davison, A, and Hinkley, D. (1997) Bootstrap Methods and their
Applications. Oxford: Oxford University Press.
Fox, J. and Weisberg, S. (2011) Companion to Applied Regression, Second Edition.
Thousand Oaks: Sage.
Fox, J. and Weisberg, S. (2012) Bootstrapping,
m1 <- lm(Fertility ~ ., swiss) betahat.boot <- Boot(m1, R=199) # 199 bootstrap samples--too small to be useful summary(betahat.boot) # default summary confint(betahat.boot) hist(betahat.boot) # Bootstrap for the estimated residual standard deviation: sigmahat.boot <- Boot(m1, R=199, f=sigmaHat, labels="sigmaHat") summary(sigmahat.boot) confint(sigmahat.boot)