Quartiles instead of IQR in summary_factorlist ?

[LukaszDerylo]

Hello,

I think, it would be nice to have option to include quartiles along with median (instead of IQR).

IQR tells little about location of "middle half" of data, whereas quartiles do.

I mean something like Median (Q1-Q3) e.g. 20.7 (14.5-22.5).

What do you think?

Regards, and thanks for great work,
Lukasz

[ewenharrison]

Thanks. This is done.

devtools::install_github('ewenharrison/finalfit')
library(finalfit)
explanatory = c("age", "age.factor", "sex.factor", "obstruct.factor")
dependent = "perfor.factor"
colon_s %>%
  summary_factorlist(dependent, explanatory, p=TRUE, 
                     cont = "median", cont_range = TRUE)

        label       levels                  No                 Yes     p
1 Age (years) Median (IQR) 61.0 (53.0 to 69.0) 60.0 (50.0 to 68.0) 0.578
2         Age    <40 years            68 (7.5)             2 (7.4) 1.000
3              40-59 years          334 (37.0)           10 (37.0)      
4                60+ years          500 (55.4)           15 (55.6)      
7         Sex       Female          432 (47.9)           13 (48.1) 0.979
8                     Male          470 (52.1)           14 (51.9)      
5 Obstruction           No          715 (81.2)           17 (63.0) 0.018
6                      Yes          166 (18.8)           10 (37.0)   

[LukaszDerylo]

Great!

Although, I'd change "Median (IQR)" in levels column to something like "Median (quartiles)".

[ewenharrison]

Thanks. Yes please change in your own work, but I'm comfortable with the definition of "range" being the limits as well as the difference.

[LukaszDerylo]

I agree that "range" can be understood as the limits as well as the difference, but IQR is special case of range that is strictly defined as difference between quartiles. So I think, using the name "IQR" for limits can lead to confusion: person, who sees "IQR" label expects a single value, just like he/she read in his/her textbook.