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
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
|
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/boys.R
\docType{data}
\name{boys}
\alias{boys}
\title{Growth of Dutch boys}
\format{
A data frame with 748 rows on the following 9 variables: \describe{
\item{age}{Decimal age (0-21 years)}
\item{hgt}{Height (cm)}
\item{wgt}{Weight (kg)}
\item{bmi}{Body mass index}
\item{hc}{Head circumference (cm)}
\item{gen}{Genital Tanner stage (G1-G5)}
\item{phb}{Pubic hair (Tanner P1-P6)}
\item{tv}{Testicular volume (ml)}
\item{reg}{Region (north, east, west, south, city)} }
}
\source{
Fredriks, A.M,, van Buuren, S., Burgmeijer, R.J., Meulmeester JF,
Beuker, R.J., Brugman, E., Roede, M.J., Verloove-Vanhorick, S.P., Wit, J.M.
(2000) Continuing positive secular growth change in The Netherlands
1955-1997. \emph{Pediatric Research}, \bold{47}, 316-323.
Fredriks, A.M., van Buuren, S., Wit, J.M., Verloove-Vanhorick, S.P. (2000).
Body index measurements in 1996-7 compared with 1980. \emph{Archives of
Disease in Childhood}, \bold{82}, 107-112.
}
\description{
Height, weight, head circumference and puberty of 748 Dutch boys.
}
\details{
Random sample of 10\% from the cross-sectional data used to construct the
Dutch growth references 1997. Variables \code{gen} and \code{phb} are ordered
factors. \code{reg} is a factor.
}
\examples{
# create two imputed data sets
imp <- mice(boys, m = 1, maxit = 2)
z <- complete(imp, 1)
# create imputations for age <8yrs
plot(z$age, z$gen,
col = mdc(1:2)[1 + is.na(boys$gen)],
xlab = "Age (years)", ylab = "Tanner Stage Genital"
)
# figure to show that the default imputation method does not impute BMI
# consistently
plot(z$bmi, z$wgt / (z$hgt / 100)^2,
col = mdc(1:2)[1 + is.na(boys$bmi)],
xlab = "Imputed BMI", ylab = "Calculated BMI"
)
# also, BMI distributions are somewhat different
oldpar <- par(mfrow = c(1, 2))
MASS::truehist(z$bmi[!is.na(boys$bmi)],
h = 1, xlim = c(10, 30), ymax = 0.25,
col = mdc(1), xlab = "BMI observed"
)
MASS::truehist(z$bmi[is.na(boys$bmi)],
h = 1, xlim = c(10, 30), ymax = 0.25,
col = mdc(2), xlab = "BMI imputed"
)
par(oldpar)
# repair the inconsistency problem by passive imputation
meth <- imp$meth
meth["bmi"] <- "~I(wgt/(hgt/100)^2)"
pred <- imp$predictorMatrix
pred["hgt", "bmi"] <- 0
pred["wgt", "bmi"] <- 0
imp2 <- mice(boys, m = 1, maxit = 2, meth = meth, pred = pred)
z2 <- complete(imp2, 1)
# show that new imputations are consistent
plot(z2$bmi, z2$wgt / (z2$hgt / 100)^2,
col = mdc(1:2)[1 + is.na(boys$bmi)],
ylab = "Calculated BMI"
)
# and compare distributions
oldpar <- par(mfrow = c(1, 2))
MASS::truehist(z2$bmi[!is.na(boys$bmi)],
h = 1, xlim = c(10, 30), ymax = 0.25, col = mdc(1),
xlab = "BMI observed"
)
MASS::truehist(z2$bmi[is.na(boys$bmi)],
h = 1, xlim = c(10, 30), ymax = 0.25, col = mdc(2),
xlab = "BMI imputed"
)
par(oldpar)
}
\keyword{datasets}
|
