Error in tab_model html table generation for glmmTMB with tweedie distribution

[cjpratt94]

I am having issues getting tab_model to work on a glmmTMB object with a tweedie error distribution - I receive the following error:

Error in dimnames(x) <- dn : length of 'dimnames' [1] not equal to array extent

The real model I've been working with is more complex, but the following example reproduces the error and shows that tab_model still works fine with glmmTMB objects fit using other error distributions (e.g. nbinom2):

`library(glmmTMB) library(sjPlot)

generate data

set.seed(10) y <- rnbinom(n = 1000, size = 7, prob = 0.5) x <- rnorm(n =1000)

df <- data.frame(y, x)

nbinom2

mod <- glmmTMB(y ~ x, data = df, family = nbinom2)

summary(mod)

tab_model(mod) #runs fine

tweedie

mod1 <- glmmTMB(y ~ x, data = df, family = tweedie)

summary(mod1)

tab_model(mod1) #returns error`

[strengejacke]

Which package versions do you use? For me, both models work fine. See reprex below (ignore the rendering):

library(glmmTMB)
library(sjPlot)

#generate data
set.seed(10)
y <- rnbinom(n = 1000, size = 7, prob = 0.5)
x <- rnorm(n =1000)

df <- data.frame(y, x)

#nbinom2
mod <- glmmTMB(y ~ x, data = df, family = nbinom2)
tab_model(mod) #runs fine
#> Random effect variances not available. Returned R2 does not account for random effects.

	y
Predictors	Incidence Rate Ratios	CI	p
(Intercept)	7.14	6.91 – 7.38	\<0.001
x	0.98	0.95 – 1.01	0.252
Observations	1000
R2 conditional / R2 marginal	NA / 0.000

#tweedie

mod1 <- glmmTMB(y ~ x, data = df, family = tweedie)
tab_model(mod1) #returns error`

	y
Predictors	Estimates	CI	p
(Intercept)	7.14	6.92 – 7.37	\<0.001
x	0.98	0.95 – 1.01	0.241
Observations	1000

^{Created on 2022-06-05 by the reprex package (v2.0.1)}

[cjpratt94]

Hi Daniel. Thanks for your response. I'm using the latest versions of both packages and of R, and have made sure not to load any other packages. Here is my sessionInfo:

R version 4.2.0 (2022-04-22 ucrt)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 10 x64 (build 19043)

Matrix products: default

Random number generation:
 RNG:     Mersenne-Twister 
 Normal:  Inversion 
 Sample:  Rounding 

locale:
[1] LC_COLLATE=English_Canada.utf8  LC_CTYPE=English_Canada.utf8    LC_MONETARY=English_Canada.utf8 LC_NUMERIC=C                    LC_TIME=English_Canada.utf8    

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] sjPlot_2.8.10 glmmTMB_1.1.3

loaded via a namespace (and not attached):
 [1] sjlabelled_1.2.0    xfun_0.31           tidyselect_1.1.2    TMB_1.8.1           performance_0.9.0   purrr_0.3.4         splines_4.2.0       lattice_0.20-45     parameters_0.17.0  
[10] colorspace_2.0-3    vctrs_0.4.1         generics_0.1.2      utf8_1.2.2          rlang_1.0.2         nloptr_2.0.1        pillar_1.7.0        glue_1.6.2          DBI_1.1.2          
[19] modelr_0.1.8        effectsize_0.6.0.1  emmeans_1.7.4-1     lifecycle_1.0.1     sjmisc_2.8.9        munsell_0.5.0       gtable_0.3.0        bayestestR_0.12.1   mvtnorm_1.1-3      
[28] coda_0.19-4         knitr_1.39          datawizard_0.4.1    fansi_1.0.3         broom_0.8.0         Rcpp_1.0.8.3        xtable_1.8-4        backports_1.4.1     scales_1.2.0       
[37] ggeffects_1.1.2     lme4_1.1-29         ggplot2_3.3.6       insight_0.17.1      dplyr_1.0.9         numDeriv_2016.8-1.1 grid_4.2.0          sjstats_0.18.1      cli_3.3.0          
[46] tools_4.2.0         magrittr_2.0.3      tibble_3.1.7        tidyr_1.2.0         crayon_1.5.1        pkgconfig_2.0.3     MASS_7.3-56         ellipsis_0.3.2      Matrix_1.4-1       
[55] estimability_1.3    assertthat_0.2.1    minqa_1.2.4         R6_2.5.1            boot_1.3-28         nlme_3.1-157        compiler_4.2.0   

[strengejacke]

Please try https://github.com/strengejacke/sjPlot/issues/769#issuecomment-1491384638, that should resolve this issue. Still cannot reproduce the errors, works fine for me. If you still encounter problems, please re-open or open a new issue. :-)