1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
|
\name{foodstamp}
\title{Food Stamp Program Participation}
\alias{foodstamp}
\docType{data}
\encoding{utf8}
\description{
This data consists of 150 randomly selected persons from a survey
with information on over 2000 elderly US citizens, where the response,
indicates participation in the U.S. Food Stamp Program.
}
\usage{data(foodstamp, package="robustbase")}
\format{
A data frame with 150 observations on the following 4 variables.
\describe{
\item{\code{participation}}{participation in U.S. Food Stamp Program; yes = 1, no = 0}
\item{\code{tenancy}}{tenancy, indicating home ownership; yes = 1, no = 0}
\item{\code{suppl.income}}{supplemental income, indicating whether
some form of supplemental security income is received; yes = 1, no = 0}
\item{\code{income}}{monthly income (in US dollars)}
}
}
\source{
Data description and first analysis: Stefanski et al.(1986) who
indicate Rizek(1978) as original source of the larger study.
Electronic version from CRAN package \CRANpkg{catdata}.
% which wrongly labeled 'income' (='INC') as "log(1 + income)"
}
\references{
Rizek, R. L. (1978)
The 1977-78 Nationwide Food Consumption Survey.
\emph{Family Econ. Rev.}, Fall, 3--7.
%% MM ~/save/papers/robust-GLM/Stefanski_etal-Biometrika-1986.pdf :
Stefanski, L. A., Carroll, R. J. and Ruppert, D. (1986)
Optimally bounded score functions for generalized linear models with
applications to logistic regression.
\emph{Biometrika} \bold{73}, 413--424.
Künsch, H. R., Stefanski, L. A., Carroll, R. J. (1989)
Conditionally unbiased bounded-influence estimation in general
regression models, with applications to generalized linear models.
\emph{J. American Statistical Association} \bold{84}, 460--466.
}
\examples{
data(foodstamp)
(T123 <- xtabs(~ participation+ tenancy+ suppl.income, data=foodstamp))
summary(T123) ## ==> the binary var's are clearly not independent
foodSt <- within(foodstamp, {
logInc <- log(1 + income)
rm(income)
})
m1 <- glm(participation ~ ., family=binomial, data=foodSt)
summary(m1)
rm1 <- glmrob(participation ~ ., family=binomial, data=foodSt)
summary(rm1)
## Now use robust weights.on.x :
rm2 <- glmrob(participation ~ ., family=binomial, data=foodSt,
weights.on.x = "robCov")
summary(rm2)## aha, now the weights are different:
which( weights(rm2, type="robust") < 0.5)
}
\keyword{datasets}
|
