You can install the development version from GitHub with:
You can install mice with:
lbp_orig is a dataset that is part of the miceafter package with
missing values. So we first impute them with the mice
function. Than we use the mids2milist function to turn a
mids object, as a result of using mice, into a
milist object with multiply imputed datasets. Than we use
the with function to apply repeated logistic regression
analyses. With the pool_glm function we obtain the results
for the pooled model.
library(mice)
library(miceafter)
imp <- mice(lbp_orig, m=5, maxit=5, printFlag = FALSE)
dat_imp <- mids2milist(imp)
ra <- with(dat_imp, expr = glm(Chronic ~ factor(Carrying) + Gender + Smoking +
Function + JobControl + JobDemands + SocialSupport,
family = binomial))
poolm <- pool_glm(ra, method="D1")
poolm$pmodel
#> term estimate std.error statistic df p.value
#> 1 (Intercept) -2.599678571 2.79904484 -0.9287735 80.72068 0.355775562
#> 2 Gender -0.160779207 0.44648149 -0.3601027 141.96434 0.719305476
#> 3 Smoking 0.088180473 0.36379678 0.2423894 147.14268 0.808815992
#> 4 Function -0.078376259 0.04900571 -1.5993292 115.89698 0.112470142
#> 5 JobControl 0.004606545 0.02150228 0.2142352 94.85725 0.830823487
#> 6 JobDemands 0.008403115 0.03951551 0.2126536 132.04678 0.831925088
#> 7 SocialSupport 0.063177544 0.06015009 1.0503317 130.21219 0.295511087
#> 8 factor(Carrying)2 1.373648173 0.58076934 2.3652216 41.19666 0.022808070
#> 9 factor(Carrying)3 1.949499572 0.61017175 3.1950013 40.94789 0.002691594
#> OR lower.EXP upper.EXP
#> 1 0.07429746 0.0002832468 19.488700
#> 2 0.85148005 0.3522582803 2.058201
#> 3 1.09218521 0.5321866243 2.241448
#> 4 0.92461647 0.8390884552 1.018862
#> 5 1.00461717 0.9626342925 1.048431
#> 6 1.00843852 0.9326155609 1.090426
#> 7 1.06521594 0.9457089771 1.199825
#> 8 3.94973376 1.2225400655 12.760643
#> 9 7.02517111 2.0486582993 24.090415
poolm$pmultiparm
#> p-values D1 F-statistic
#> Gender 0.718780256 0.12967398
#> Smoking 0.808478793 0.05875261
#> Function 0.110170682 2.55785374
#> JobControl 0.830492967 0.04589673
#> JobDemands 0.831618887 0.04522156
#> SocialSupport 0.293713421 1.10319662
#> factor(Carrying) 0.006526093 5.44561744Back to Examples
The lbp_orig is a dataset that is part of the miceafter package with
missing values. So we first impute them with the mice
function. Than we use the mids2milist function to turn a
mids object, as a result of using mice, into a
milist object with multiply imputed datasets. Than we use
the with function to apply repeated linear regression
analyses. With the pool_glm function we obtain the results
for the pooled model.
library(mice)
library(miceafter)
imp <- mice(lbp_orig, m=5, maxit=5, printFlag = FALSE)
dat_imp <- mids2milist(imp)
ra <- with(dat_imp, expr = glm(Pain ~ factor(Carrying) + Gender + Smoking +
Function + JobControl + JobDemands + SocialSupport))
poolm <- pool_glm(ra, method="D1")
poolm$pmodel
#> term estimate std.error statistic df p.value
#> 1 (Intercept) 5.116256747 2.33216453 2.19378036 123.50275 0.030123078
#> 2 Gender -0.543023519 0.41765045 -1.30018660 91.56731 0.196800206
#> 3 Smoking -0.118049319 0.31689773 -0.37251551 140.95274 0.710068592
#> 4 Function -0.045499572 0.04683091 -0.97157131 44.25423 0.336544504
#> 5 JobControl -0.019450157 0.02147524 -0.90570135 27.81561 0.372872805
#> 6 JobDemands 0.036942210 0.03421558 1.07968979 133.37123 0.282228988
#> 7 SocialSupport 0.001670081 0.05193580 0.03215665 140.25373 0.974392841
#> 8 factor(Carrying)2 0.638354466 0.55983313 1.14025847 14.03321 0.273266532
#> 9 factor(Carrying)3 1.755155121 0.57093300 3.07418757 17.36160 0.006747234
#> 2.5 % 97.5 %
#> 1 0.50006673 9.73244676
#> 2 -1.37256559 0.28651855
#> 3 -0.74453624 0.50843760
#> 4 -0.13986577 0.04886662
#> 5 -0.06345334 0.02455303
#> 6 -0.03073315 0.10461757
#> 7 -0.10100816 0.10434833
#> 8 -0.56210162 1.83881055
#> 9 0.55250008 2.95781016
poolm$pmultiparm
#> p-values D1 F-statistic
#> Gender 0.19452222 1.69048520
#> Smoking 0.70952192 0.13876780
#> Function 0.33448888 0.94395082
#> JobControl 0.37072919 0.82029493
#> JobDemands 0.28039628 1.16573005
#> SocialSupport 0.97434832 0.00103405
#> factor(Carrying) 0.01896136 4.87813729Back to Examples
We follow the same procedure as the first example but also apply model selection here.
library(mice)
library(miceafter)
imp <- mice(lbp_orig, m=5, maxit=5, printFlag = FALSE)
dat_imp <- mids2milist(imp)
ra <- with(dat_imp, expr = glm(Chronic ~ factor(Carrying) + Gender + Smoking +
Function + JobControl + JobDemands + SocialSupport,
family = binomial))
poolm <- pool_glm(ra, method="D1", p.crit = 0.15, direction = "BW")
#> Removed at Step 1 is - Smoking
#> Removed at Step 2 is - JobDemands
#> Removed at Step 3 is - JobControl
#> Removed at Step 4 is - Gender
#> Removed at Step 5 is - SocialSupport
#>
#> Selection correctly terminated,
#> No more variables removed from the model
poolm$pmodel
#> term estimate std.error statistic df p.value
#> 1 (Intercept) -0.58603210 0.71646223 -0.8179525 95.34782 0.415423692
#> 2 Function -0.07534636 0.04651968 -1.6196663 127.91028 0.107766927
#> 3 factor(Carrying)2 1.26330472 0.48465748 2.6065928 120.67837 0.010297190
#> 4 factor(Carrying)3 1.84734477 0.55588526 3.3232484 65.43706 0.001459931
#> OR lower.EXP upper.EXP
#> 1 0.5565312 0.1342136 2.307716
#> 2 0.9274222 0.8458662 1.016842
#> 3 3.5370913 1.3549595 9.233497
#> 4 6.3429552 2.0902963 19.247549
poolm$pmultiparm
#> p-values D1 F-statistic
#> Function 0.105579303 2.623319
#> factor(Carrying) 0.002598671 6.103450Back to Examples
We follow the same procedure as the second example but also apply model selection here.
library(mice)
library(miceafter)
imp <- mice(lbp_orig, m=5, maxit=5, printFlag = FALSE)
dat_imp <- mids2milist(imp)
ra <- with(dat_imp, expr = glm(Pain ~ factor(Carrying) + Gender + Smoking +
Function + JobControl + JobDemands + SocialSupport))
poolm <- pool_glm(ra, method="D1", p.crit = 0.15, direction = "BW")
#> Removed at Step 1 is - SocialSupport
#> Removed at Step 2 is - Smoking
#> Removed at Step 3 is - JobDemands
#> Removed at Step 4 is - Gender
#>
#> Selection correctly terminated,
#> No more variables removed from the model
poolm$pmodel
#> term estimate std.error statistic df p.value
#> 1 (Intercept) 7.14316335 1.09008239 6.552866 118.59755 1.529257e-09
#> 2 Function -0.09574888 0.04172459 -2.294783 83.53042 2.425399e-02
#> 3 JobControl -0.03007168 0.01761107 -1.707544 91.52800 9.111104e-02
#> 4 factor(Carrying)2 0.64444136 0.43231177 1.490687 53.38486 1.419292e-01
#> 5 factor(Carrying)3 1.55475765 0.47589180 3.267040 47.14458 2.030604e-03
#> 2.5 % 97.5 %
#> 1 4.9846161 9.301710600
#> 2 -0.1787296 -0.012768141
#> 3 -0.0650512 0.004907834
#> 4 -0.2225203 1.511403061
#> 5 0.5974643 2.512050970
poolm$pmultiparm
#> p-values D1 F-statistic
#> Function 0.022655956 5.266029
#> JobControl 0.088797963 2.915706
#> factor(Carrying) 0.003907592 5.869005Back to Examples