Summary statistics using rpsychi package
## Settings for RMarkdown http://yihui.name/knitr/options#chunk_options
opts_chunk$set(comment = "", warning = FALSE, message = FALSE, tidy = FALSE,
echo = TRUE, fig.width = 7, fig.height = 7)
options(width = 120, scipen = 10)
setwd("~/statistics/Rmedstats/")
Load rpsychi
library(rpsychi)
Data preparation
data(infert)
infert$case <- factor(infert$case, labels=c("control", "case"))
infert$induced <- factor(infert$induced, labels=c("0","1","2 or more"))
infert$spontaneous <- factor(infert$spontaneous, labels=c("0","1","2 or more"))
summary(infert)
education age parity induced case spontaneous stratum
0-5yrs : 12 Min. :21.0 Min. :1.00 0 :143 control:165 0 :141 Min. : 1.0
6-11yrs:120 1st Qu.:28.0 1st Qu.:1.00 1 : 68 case : 83 1 : 71 1st Qu.:21.0
12+ yrs:116 Median :31.0 Median :2.00 2 or more: 37 2 or more: 36 Median :42.0
Mean :31.5 Mean :2.09 Mean :41.9
3rd Qu.:35.2 3rd Qu.:3.00 3rd Qu.:62.2
Max. :44.0 Max. :6.00 Max. :83.0
pooled.stratum
Min. : 1.0
1st Qu.:19.0
Median :36.0
Mean :33.6
3rd Qu.:48.2
Max. :63.0
head(infert)
education age parity induced case spontaneous stratum pooled.stratum
1 0-5yrs 26 6 1 case 2 or more 1 3
2 0-5yrs 42 1 1 case 0 2 1
3 0-5yrs 39 6 2 or more case 0 3 4
4 0-5yrs 34 4 2 or more case 0 4 2
5 6-11yrs 35 3 1 case 1 5 32
6 6-11yrs 36 4 2 or more case 1 6 36
Summarize
##continuous and categorical variables
groupSummary(infert, group = "case")
total.m/f total.sd/pct total.n control.m/f control.sd/pct control.n case.m/f case.sd/pct case.n
education.0-5yrs 12.000 4.839 248 8.000 4.848 165 4.000 4.819 83
education.6-11yrs 120.000 48.387 NA 80.000 48.485 NA 40.000 48.193 NA
education.12+ yrs 116.000 46.774 NA 77.000 46.667 NA 39.000 46.988 NA
age 31.504 5.241 248 31.491 5.238 165 31.530 5.247 83
parity 2.093 1.249 248 2.085 1.238 165 2.108 1.271 83
induced.0 143.000 57.661 248 96.000 58.182 165 47.000 56.627 83
induced.1 68.000 27.419 NA 45.000 27.273 NA 23.000 27.711 NA
induced.2 or more 37.000 14.919 NA 24.000 14.545 NA 13.000 15.663 NA
spontaneous.0 141.000 56.855 248 113.000 68.485 165 28.000 33.735 83
spontaneous.1 71.000 28.629 NA 40.000 24.242 NA 31.000 37.349 NA
spontaneous.2 or more 36.000 14.516 NA 12.000 7.273 NA 24.000 28.916 NA
stratum 41.871 23.920 248 41.806 23.901 165 42.000 23.958 83
pooled.stratum 33.581 17.237 248 33.521 17.204 165 33.699 17.303 83
##continuous variables only
groupSummary(infert[, c(2,3,7,8, 5)], group = "case")
total.m total.sd total.n control.m control.sd control.n case.m case.sd case.n
age 31.504 5.241 248 31.491 5.238 165 31.530 5.247 83
parity 2.093 1.249 248 2.085 1.238 165 2.108 1.271 83
stratum 41.871 23.920 248 41.806 23.901 165 42.000 23.958 83
pooled.stratum 33.581 17.237 248 33.521 17.204 165 33.699 17.303 83
##categorical variables only
groupSummary(infert[, c(1,4, 6, 5)], group = "case")
total.f total.pct total.n control.f control.pct control.n case.f case.pct case.n
education.0-5yrs 12 4.839 248 8 4.848 165 4 4.819 83
education.6-11yrs 120 48.387 NA 80 48.485 NA 40 48.193 NA
education.12+ yrs 116 46.774 NA 77 46.667 NA 39 46.988 NA
induced.0 143 57.661 248 96 58.182 165 47 56.627 83
induced.1 68 27.419 NA 45 27.273 NA 23 27.711 NA
induced.2 or more 37 14.919 NA 24 14.545 NA 13 15.663 NA
spontaneous.0 141 56.855 248 113 68.485 165 28 33.735 83
spontaneous.1 71 28.629 NA 40 24.242 NA 31 37.349 NA
spontaneous.2 or more 36 14.516 NA 12 7.273 NA 24 28.916 NA
##total sample
groupSummary(infert[, c(1,4, 6, 5)])
total.f total.pct total.n
education.0-5yrs 12 4.839 248
education.6-11yrs 120 48.387 NA
education.12+ yrs 116 46.774 NA
induced.0 143 57.661 248
induced.1 68 27.419 NA
induced.2 or more 37 14.919 NA
spontaneous.0 141 56.855 248
spontaneous.1 71 28.629 NA
spontaneous.2 or more 36 14.516 NA
case.control 165 66.532 248
case.case 83 33.468 NA