Timeline for Should I report credible intervals instead of confidence intervals?
Current License: CC BY-SA 3.0
11 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Apr 13, 2017 at 12:44 | history | edited | CommunityBot |
replaced http://stats.stackexchange.com/ with https://stats.stackexchange.com/
|
|
Feb 11, 2014 at 6:05 | answer | added | OpenIntro | timeline score: 4 | |
S Feb 11, 2014 at 1:50 | history | suggested | Nick Stauner | CC BY-SA 3.0 |
$\LaTeX$, tags; changed "credibility" to "credible" following @gung's point in Ten fold
|
Feb 11, 2014 at 1:44 | review | Suggested edits | |||
S Feb 11, 2014 at 1:50 | |||||
Feb 11, 2014 at 1:38 | comment | added | Nick Stauner | Some other questions are worth linking here: 1. What's the difference between a confidence interval and a credible interval?, and 2. Are there any examples where Bayesian credible intervals are obviously inferior to frequentist confidence intervals | |
Feb 7, 2014 at 3:58 | history | tweeted | twitter.com/#!/StackStats/status/431637959826493440 | ||
Feb 6, 2014 at 16:22 | comment | added | rumtscho | I may have still have my terms mixed up, but in my textbook, the author is suggesting using a credible interval when estimating the mean of binomial data using a maximum likelihood estimation based on a test statistic derived from standard errors. And I think this is a frequentist approach. Is there maybe a difference between a credible interval and an "actual coverage probability" confidence interval? | |
Feb 6, 2014 at 13:39 | comment | added | Penguin_Knight | As of today there are 154 articles on PubMed mentioning credibility interval and 489 mentioning credible interval. They are not as common as confidence interval (179811 articles and counting), but it's just due to frequentist approach being the dominating method. And yes, credible interval sounds awesome but it's only true if the prior distribution is correctly specified. The devils are all in the assumptions. | |
Feb 6, 2014 at 3:47 | comment | added | Bogdan Lataianu | Confidence intervals are for frequentist and credible intervals for Bayesian approach. "why haven't I seen any publications which use it?" there are plenty (Bayesian) | |
Feb 6, 2014 at 3:38 | history | migrated | from academia.stackexchange.com (revisions) | ||
Feb 5, 2014 at 23:34 | history | asked | rumtscho | CC BY-SA 3.0 |