Is it a bug? When adding variable "extent" from colon_s into finalfit() model, the odds ratio cannot be displayed correctly.

[zhaohongxin0]

explanatory = c("age.factor","extent" , "sex.factor", "obstruct.factor", "perfor.factor")
dependent = "mort_5yr"

t<-colon_s %>%
  finalfit(dependent, explanatory)

t

The results are:

<style> </style>

Dependent: Mortality 5 year		Alive	Died	OR (univariable)	OR (multivariable)
Age	<40 years	31 (46.3)	36 (53.7)	-	-
	40-59 years	208 (61.4)	131 (38.6)	0.54 (0.32-0.92, p=0.023)	0.54 (0.31-0.93, p=0.027)
	60+ years	272 (53.4)	237 (46.6)	0.75 (0.45-1.25, p=0.270)	0.77 (0.45-1.31, p=0.340)
extent	1	16 (80.0)	4 (20.0)	-	-
	2	78 (75.7)	25 (24.3)	-	-
	3	401 (53.5)	349 (46.5)	-	-
	4	16 (38.1)	26 (61.9)	-	-
Sex	Female	243 (55.6)	194 (44.4)	-	-
	Male	268 (56.1)	210 (43.9)	0.98 (0.76-1.27, p=0.889)	0.97 (0.74-1.28, p=0.852)
Obstruction	No	408 (56.7)	312 (43.3)	-	-
	Yes	89 (51.1)	85 (48.9)	1.25 (0.90-1.74, p=0.189)	1.20 (0.86-1.69, p=0.284)
Perforation	No	497 (56.0)	391 (44.0)	-	-
	Yes	14 (51.9)	13 (48.1)	1.18 (0.54-2.55, p=0.672)	0.98 (0.45-2.16, p=0.970)
NA	NA	NA	NA	2.22 (1.64-3.07, p<0.001)	2.25 (1.64-3.14, p<0.001)

it seems that the last row is the OR for "extent" as a continuous variable, but in the table, extent is considered as a factor but the OR is not displayed.
If I changed “extent” to a factor, it can be corrected. But how can I do when I want to do it as a continuous variable? cont_cut seems not work in finalfit().

[ewenharrison]

Many thanks for this. Apologies I didn't get a notification when this was posted.

It's kind of a bug, yes, in that a continuous variable with very few distinct values is being passed to a regression model. This would often be treated as a factor (see extent.factor).

A fix for this has been pushed with version 1.0.55.

Many thanks again,

[HoangAVu]

Hi! Can this be extended to or_plot() as well (adding a cont_cut arg)? My finalfit and or_plot are showing incohesive results, most likely because of this reason which causes one of my cont variables to be treated as factor.

[zhaohongxin0]

I also want to know the updates.
cont_cut now is available in finalfit(), but it doesn't work in glmuni() or glmmulti(). That means we cannot get right results from a poisson model