Systematic Screening of Study Data for Subgroup Effects

Identifying outcome relevant subgroups has now become as simple as possible! The formerly lengthy and tedious search for the needle in a haystack will be replaced by a single, comprehensive and coherent presentation. The central result of a subgroup screening is a diagram in which each single dot stands for a subgroup. The diagram may show thousands of them. The position of the dot in the diagram is determined by the sample size of the subgroup and the statistical measure of the treatment effect in that subgroup. The sample size is shown on the horizontal axis while the treatment effect is displayed on the vertical axis. Furthermore, the diagram shows the line of no effect and the overall study results. For small subgroups, which are found on the left side of the plot, larger random deviations from the mean study effect are expected, while for larger subgroups only small deviations from the study mean can be expected to be chance findings. So for a study with no conspicuous subgroup effects, the dots in the figure are expected to form a kind of funnel. Any deviations from this funnel shape hint to conspicuous subgroups.


subscreen 1.0.0

Bug fixes subscreencalc

  • Fixed the example to make it work properly. Added some data pre-processing and handling of NAs.
  • Fixed the problem with max_comb=1 in combination with nkernel=1. Function sapply needed the option simplify=FALSE to keep the data structure
  • No error anymore if nkernel>1 and par_functions=""

Bug fixes subscreenshow

  • Factor levels 6 to 8 will now be displayed. They had no color assigned before.
  • Reference line for overall result is now exact on the right place. The slider input has been removed as this caused inappropriate rounding in some cases.

Enhancements subscreenshow

  • The slider for the y-range is now improved. It will use nice numbers for the range selection. Thanks to Tommy (662787) from StackOverflow for roundDownNice(). And you can actually give a set of numbers you think of being nice in the new parameter NiceNumbers.
  • Background shading including marks can be set by the new parameter StripesBGplot. The program will aim for the given number of stripes/marks but the actual display may differ to have nice intervals
  • On the x-axis percentages of the total are shown

Editorial changes

  • Updated the description
  • Packages shiny and DT are now imports although only needed in subscreenshow
  • Spelling errors corrected
  • Changed some internal function and variable names for better readability
  • Translated the rest of the German comments into English
  • Deleted unused functions and program code
  • Removed NA from the subgroup filter drop-down selection

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


2.0.1 by Bodo Kirsch, a month ago

Browse source code at

Authors: Bodo Kirsch , Susanne Lippert , Thomas Schmelter , Steffen Mueller , Christoph Muysers , Hermann Kulmann

Documentation:   PDF Manual  

GPL-3 license

Imports utils, plyr, data.table, grDevices, graphics, shiny, DT, stats, shinyjs, bsplus, jsonlite, colourpicker, dplyr, randomForestSRC, V8

Suggests parallel, survival, knitr, rmarkdown

See at CRAN