Showing 1 - 10 of 10
Persistent link: https://www.econbiz.de/10003455986
Persistent link: https://www.econbiz.de/10008663766
Persistent link: https://www.econbiz.de/10008663504
Persistent link: https://www.econbiz.de/10008663768
Persistent link: https://www.econbiz.de/10009545946
We present an exact test for whether two random variables that have known bounds on their support are negatively correlated. The alternative hypothesis is that they are not negatively correlated. No assumptions are made on the underlying distributions. We show by example that the Spearman rank...
Persistent link: https://www.econbiz.de/10012723709
The stochastic inequality test is an exact non-parametric test that can be used to infer whether values in one random sample tend to be higher than in another. In addition it can be used to derive a confidence interval around an intuitive measure of effect size that is readily interpretable...
Persistent link: https://www.econbiz.de/10013281266
Persistent link: https://www.econbiz.de/10010189877
We introduce tests for finite-sample linear regressions with heteroskedastic errors. The tests are exact, i.e., they have guaranteed type I error probabilities when bounds are known on the range of the dependent variable, without any assumptions about the noise structure. We provide upper bounds...
Persistent link: https://www.econbiz.de/10014197050
Small sample properties are of fundamental interest when only limited data is available. Exact inference is limited by constraints imposed by specific nonrandomized tests and of course also by lack of more data. These effects can be separated as we propose to evaluate a test by comparing its...
Persistent link: https://www.econbiz.de/10014214813