UUPharmacometrics/xpose

[Feedback wanted] Documentation update !!

bguiastr opened this issue ยท 2 comments

Hi everyone,

I realize that some work needs to be done on the xpose documentation and I would like your opinion on what aspects of the package YOU find confusing and/or poorly documented.

I believe that the vpc(), vpc_data() are among the most confusing ones but please send me your feedback and I will try to make things better!

Don't be shy ๐Ÿ˜„ !

a topic that comes around often is how to handle vpc with multiple lloq ( several studies where lloq is study specific) this is a good candidate of the workflow approach where you filter your data run the vpc with the nbins and loq specif to the study then at the end stitch everything together.
also a good liston what is missing from the old xpose.
also example of theming for those not very familiar with ggplot versus lattice.

library(xpose)
#> Loading required package: ggplot2
#> 
#> Attaching package: 'xpose'
#> The following object is masked from 'package:stats':
#> 
#>     filter
xpdb_ex_pk %>% 
  vpc_data(vpc_type = 'continuous', obs_problem = 1, sim_problem = 2) %>%
      vpc(xp_theme=c(point_alpha=0.3,area_alpha=0.2,line_size=1.5) )+
  scale_fill_manual(values=c("red","blue","red"))+
  scale_linetype_manual(values=c("dotted","solid","dashed"))+
  theme_bw2()
#> 
#> VPC continuous --------------------
#> 1. Gathering data & settings
#> Using xpdb simulation problem 2 and observation problem 1.
#> 
#> 2. Computing VPC data
#> Configuring and initializing...
#> Parsing observed data...
#> Filtering rows where EVID not 0
#> Parsing simulated data...
#> Filtering rows where EVID not 0
#> Binning: 0 0.66667 1.25 1.75 2.1667 3 4.3333 5 6.25 7 9
#> Calculating statistics for simulated data...
#> Calculating statistics for observed data...
#> 
#> VPC done
#> Scale for 'fill' is already present. Adding another scale for 'fill',
#> which will replace the existing scale.
#> Scale for 'linetype' is already present. Adding another scale for
#> 'linetype', which will replace the existing scale.

Created on 2019-04-02 by the reprex package (v0.2.1)

I think an example of stratifying by endpoints would be nice.