Replies: 2 comments
-
|
Thank you for your interest in our library. I’m afraid I don’t have much knowledge about statistics itself. I only rewrote QUEST+, a well-known method, as a JavaScript library. One possible idea is to estimate the threshold for each participant as a point estimate, treat the collection of these estimates as a sample, and fit it to a t-distribution. In other words, it’s the same as calculating the confidence interval for the population mean. I’m not very confident whether this is the appropriate approach. Best, |
Beta Was this translation helpful? Give feedback.
-
|
Alternatively, if you are unsure of the population distribution of your estimate, consider a bootstrapped confidence interval. A nice R-package for this purpose is https://cran.r-project.org/package=boot |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hello,
How can I calculate the 95% confidence intervals around a threshold estimate?
Thank you
Beta Was this translation helpful? Give feedback.
All reactions