Introduction to PropTestR

The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

Vinodhkumar Obli Rajendran

Keerthi Aaradhana

Overview

PropTestR provides a common interface for independent two-proportion inference. The principal function is compare_2prop().

library(PropTestR)
r <- compare_2prop(82, 100, 75, 100, method=c("wald","score","fisher","miettinen_nurminen"))
print(r)
#> PropTestR: comparison of two independent proportions
#> Group 1: 82/100 (0.8200)
#> Group 2: 75/100 (0.7500)
#> Risk difference: 0.0700; null margin: 0.0000
#> 
#>              method estimate    conf.low conf.high statistic   p.value
#>                Wald     0.07 -0.04345805 0.1834580  1.209235 0.2265724
#>               Score     0.07 -0.04432278 0.1823656  1.204839 0.2282655
#>        Fisher exact     0.07          NA        NA        NA 0.3017227
#>  Miettinen-Nurminen     0.07 -0.04479568 0.1844067        NA        NA
#>                                                                           note
#>                             Large-sample Wald test; null difference is margin.
#>                                     Score test with constrained null variance.
#>  Exact conditional 2x2 test; Fisher CI is for odds ratio, not risk difference.
#>                      Confidence interval method; no separate p-value reported.

Non-inferiority

For a non-inferiority margin of 10 percentage points, use a null difference of -0.10 and a one-sided greater alternative.

farrington_manning(82, 100, 85, 100, margin=-0.10, alternative="greater")
#> 
#>  Farrington-Manning score test
#> 
#> data:  x1 = 82, n1 = 100; x2 = 85, n2 = 100
#> Z = 1.3198, p-value = 0.09345
#> alternative hypothesis: true difference in proportions is greater than -0.1
#>  percent confidence interval:
#>  -0.135012  0.074556
#> sample estimates:
#> difference in proportions 
#>                     -0.03

Equivalence

equivalence_2prop(80, 100, 78, 100, margin=0.10, conf.level=0.90)
#>   estimate    conf.low conf.high margin equivalent
#> 1     0.02 -0.07557697 0.1155364    0.1      FALSE
#>                                                       method
#> 1 Miettinen-Nurminen CI / two-one-sided equivalence decision

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.