Error: Family 'zero_one_inflated_beta' requires response smaller than or equal to 1

Interfaces brms
,
1

I have a zero-one-inflated dependent variable:
Min. 1st Qu. Median Mean 3rd Qu. Max.
0.00000 0.06002 0.16456 0.25052 0.35714 1.00000

However, when I run the model, I receive an error message: Error: Family ‘zero_one_inflated_beta’ requires response smaller than or equal to 1.

I have run the model before without any issues; the only change I made was adding observations to the dataset.

code_to_run_your_model(if_applicable)
f1<-bf(DV ~ 1 + IV1* Group+I(IV1^2)+I(IV1^3)+IV2+IV3+
       +IV4 + IV5 +IV6+IV7+IV8+IV9+IV10+ IV11+IV12
       +IV13*IV4+(1|R1)+(1|R2)+(1|R3),
 zoi~1 + IV1* Group+I(IV1^2)+I(IV1^3)+IV2+IV3+
       +IV4 + IV5 +IV6+IV7+IV8+IV9+IV10+ IV11+IV12
       +IV13*IV4+(1|R1)+(1|R2)+(1|R3),   
coi~1 + IV1* Group+I(IV1^2)+I(IV1^3)+IV2+IV3+
       +IV4 + IV5 +IV6+IV7+IV8+IV9+IV10+ IV11+IV12
       +IV13*IV4+(1|R1)+(1|R2)+(1|R3),
       family=zero_one_inflated_beta())


Model <-brm(f1, data=data, chains = 8, cores=8, warmup = 500, iter = 1000, family = zero_one_inflated_beta(),
                   prior = prior,
                   thin = 1, control = list(adapt_delta = 0.9, max_treedepth = 12),init = 0,
                   seed = 123,threads = threading(2),
                   backend = "cmdstanr")```


* Operating System: Windows 10
* brms Version: 2.19

Any tips or suggestions are appreciated, thank you!
2

What is the output of identical(0, max(data$DV - 1))?

What happens if you run data$DV[data$DV > 1] <- 1 and then try re-running?

1 Like
3

@jsocolar Thanks, it worked…It must be the post-holiday brain fog…

1 Like