lccdf of beta overflows at reasonably normal values

Dear all,

I am sorry for giving reference to Claude AI in advance, but it was flagged by it recently.

transformed data { real y = 0.865169; }
generated quantities {
  real lccdf = beta_lccdf(y | 1, 19);   //   -inf
  real truth = 19 * log1m(y);           //  -38.0709
}

Analytically that's beta_lccdf(y | 1, 19) = 19·log1m(x) = −38.07, entirely finite. Stan evaluates it as log(1 − inc_beta(...)), and (1−0.865)^19 = 3e-17 vanishes against 1.0 in double precision, so it returns log(0), which leads to initialization error.

Technically, I have also had similar problems working with log_diff_exp for _lcdf. So I replaced it with log(CDF1 - CDF2) and it worked quite fine.

Sorry if I disturbed you without a good reason in advance.

Best wishes,
Andrei

Thanks for this! This has come up in a few cdf functions and I think we need to do a bigger review of extreme values for all of them. This would be a nice thing for a swarm of claude agents to look at since it would just be researching extreme values for each distribution and putting those into our expect_ad testing framework.

I have fix for this, but that fix depends on #3409. After that is merged, I can make a PR to fix this.

Also I have done a bigger review and I have other PRs waiting, but don't want to flood before earlier have been reviewed

Oh well, I made the PR. This is fixed by #3433 (not yet merged)

Navigation Menu

Repository navigation

lccdf of beta overflows at reasonably normal values #3377

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

lccdf of beta overflows at reasonably normal values #3377

Description

Activity

SteveBronder commented on Aug 28, 2026

avehtari commented on Oct 6, 2026

avehtari commented on Oct 6, 2026

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions