Multiple imputations

An imputationList object containing five imputations of data from the Victorian Adolescent Health Cohort Study.

data(smi)

Format

The underlying data are in a data frame with 1170 observations on the following 12 variables.

id

a numeric vector

wave

a numeric vector

mmetro

a numeric vector

parsmk

a numeric vector

drkfre

a factor with levels Non drinker not in last wk <3 days last wk >=3 days last wk

alcdos

a factor with levels Non drinker not in last wk av <5units/drink_day av =>5units/drink_day

alcdhi

a numeric vector

smk

a factor with levels non/ex-smoker <6 days 6/7 days

cistot

a numeric vector

mdrkfre

a numeric vector

sex

a numeric vector

drinkreg

a logical vector

Source

Carlin, JB, Li, N, Greenwood, P, Coffey, C. (2003) "Tools for analysing multiple imputed datasets" The Stata Journal 3; 3: 1-20.

Examples

data(smi)
with(smi, table(sex, drkfre))
#> [[1]]
#>    drkfre
#> sex Non drinker not in last wk <3 days last wk >=3 days last wk
#>   0         282            201             105               12
#>   1         207            194             134               35
#> 
#> [[2]]
#>    drkfre
#> sex Non drinker not in last wk <3 days last wk >=3 days last wk
#>   0         282            195             109               14
#>   1         200            200             132               38
#> 
#> [[3]]
#>    drkfre
#> sex Non drinker not in last wk <3 days last wk >=3 days last wk
#>   0         278            202             109               11
#>   1         209            194             131               36
#> 
#> [[4]]
#>    drkfre
#> sex Non drinker not in last wk <3 days last wk >=3 days last wk
#>   0         284            188             114               14
#>   1         203            206             128               33
#> 
#> [[5]]
#>    drkfre
#> sex Non drinker not in last wk <3 days last wk >=3 days last wk
#>   0         288            191             109               12
#>   1         206            192             136               36
#> 
#> attr(,"call")
#> with(smi, table(sex, drkfre))
model1<-with(smi, glm(drinkreg~wave*sex, family=binomial()))
MIcombine(model1)
#> Multiple imputation results:
#>       with(smi, glm(drinkreg ~ wave * sex, family = binomial()))
#>       MIcombine.default(model1)
#>                 results         se
#> (Intercept) -2.25974358 0.26830731
#> wave         0.24055250 0.06587423
#> sex          0.64905222 0.34919264
#> wave:sex    -0.03725422 0.08609199
summary(MIcombine(model1))
#> Multiple imputation results:
#>       with(smi, glm(drinkreg ~ wave * sex, family = binomial()))
#>       MIcombine.default(model1)
#>                 results         se      (lower     upper) missInfo
#> (Intercept) -2.25974358 0.26830731 -2.78584855 -1.7336386      4 %
#> wave         0.24055250 0.06587423  0.11092461  0.3701804     12 %
#> sex          0.64905222 0.34919264 -0.03537187  1.3334763      1 %
#> wave:sex    -0.03725422 0.08609199 -0.20623121  0.1317228      7 %