【R】jstable
2021年7月21日
1. はじめに
jstable
は、‘GLM’, ‘GEE’, ‘GLMM’, ‘Cox’のRegression tableを表示してくれるパッケージです。
2. インストール
CRANからインストールできます。
install.packages("jstable")
3. つかってみる
まずは、GLMのRegression tableです。
library(jstable) library(modeldata) data("penguins") head(penguins) glm_gaus <- glm(body_mass_g~flipper_length_mm + bill_length_mm, data = penguins) glmshow.display(glm_gaus, decimal = 3)
$first.line
[1] "Linear regression predicting body_mass_g\n"
$table
crude coeff.(95%CI) crude P value adj. coeff.(95%CI) adj. P value
flipper_length_mm "49.686 (46.709,52.662)" "< 0.001" "48.145 (44.203,52.087)" "< 0.001"
bill_length_mm "87.415 (74.867,99.963)" "< 0.001" "6.047 (-4.105,16.2)" "0.2438"
$last.lines
[1] "No. of observations = 342\nR-squared = 0.75996\nAIC value = 5063.48249\n\n"
attr(,"class")
[1] "display" "list"
GEE tableの例です。
library(geepack) data(dietox) dietox$Cu <- as.factor(dietox$Cu) dietox$ddn <- as.numeric(rnorm(nrow(dietox)) > 0) head(dietox) gee01 <- geeglm (Weight ~ Time + Evit , id = Pig, data = dietox, family = gaussian, corstr = "ex") geeglm.display(gee01)
> head(dietox)
Pig Evit Cu Litter Start Weight Feed Time ddn
1 4601 Evit000 Cu000 1 26.5 26.50000 NA 1 0
2 4601 Evit000 Cu000 1 26.5 27.59999 5.200005 2 0
3 4601 Evit000 Cu000 1 26.5 36.50000 17.600000 3 1
4 4601 Evit000 Cu000 1 26.5 40.29999 28.500000 4 0
5 4601 Evit000 Cu000 1 26.5 49.09998 45.200001 5 0
6 4601 Evit000 Cu000 1 26.5 55.39999 56.900002 6 0
> geeglm.display(gee01)
$caption
[1] "GEE(gaussian) predicting Weight by Time, Evit - Group Pig"
$table
crude coeff(95%CI) crude P value adj. coeff(95%CI) adj. P value
Time "6.94 (6.79,7.1)" "< 0.001" "6.94 (6.79,7.1)" "< 0.001"
Evit: ref.=Evit000 NA NA NA NA
100 "1.81 (-1.93,5.56)" "0.343" "2.03 (-1.65,5.7)" "0.28"
200 "-1.3 (-4.97,2.38)" "0.489" "-1.17 (-4.83,2.49)" "0.531"
$metric
crude coeff(95%CI) crude P value adj. coeff(95%CI) adj. P value
NA NA NA NA
Estimated correlation parameters "0.771" NA NA NA
No. of clusters "72" NA NA NA
No. of observations "861" NA NA NA
4. さいごに
いろいろ機能があるようですが、今日はここまで。