New answers tagged

0 votes

Statistical test for small non-parametric dataset with more than 2 dependent groups

With censored response, survival analysis is useful and probably the more appropriate one. See https://stackoverflow.com/questions/41968606/left-censoring-for-survival-data-in-r for both left and ...
DrJerryTAO's user avatar
  • 1,325
1 vote

Parametric vs Non-parametric test recommendation

I would not run any parametric (e.g. t-test, because data is ordinal - Likert), or non-parametric test (e.g. Mann-Whitney U, because there are way too many ties: the vast majority of the comparisons ...
jginestet's user avatar
  • 219
0 votes

nonparametric test for statistical significance for control and treatment

I am not sure why you think you need a non-parametric test? Because the histogram does look skewed? Who cares? In your case, with 100 samples per group, CLT would apply and a t-test would work. But ...
jginestet's user avatar
  • 219
1 vote

About regression analysis with categorical variables

This really depends on what your research question is. If you're simply interested in the effect of the continuous variable, you can just run a regression and look at the Wald test for the coefficient....
Demetri Pananos's user avatar
2 votes

About regression analysis with categorical variables

You can attempt to build a multiple regression model. A standard approach to perform regression with categorical variables is called one hot encoding. You encode each categorical variable with $k$ ...
Marko Lalovic's user avatar
2 votes

About regression analysis with categorical variables

Multiple linear regression analysis could be an option. For polytomous nominal predictor variables, you would have to use binary code variables in the regression model (e.g., using dummy coding [0, 1] ...
Christian Geiser's user avatar
1 vote

Is there a robust test for stochastic dominance between two random variables?

You could rank your observations and report the proportion of ranked values in each of the group and say something like, Proportion of higher ranked values in A > Proportion of higher ranked values ...
Rohan Sarkar's user avatar
1 vote

Mann Whitney Test: Clearing Up Confusion

The best way to see that the Mann-Whitney test does not compare medians is to see two data sets with identical medians (horizontal lines) but a small p-value (0.03) from the Mann-Whitney test: Source
Harvey Motulsky's user avatar
3 votes

Mann Whitney Test: Clearing Up Confusion

The Mann-Whitney U test (MWUt from now on) does not compare medians, nor compares distributions. Why it is used this way in many published papers, presented this way in many textbooks or web sites is ...
jginestet's user avatar
  • 219
1 vote

Business use cases for Wilcoxon signed-rank test

The OP was a bit "loose" with words when writing "When the sample gets large, the data will be approximately normally distributed." What should have been said is that "When ...
jginestet's user avatar
  • 219
4 votes
Accepted

Deriving Sample version of Anderson Darling test statistic from the theoretical version

Let $U_{in}:= F(X_{in});$ for brevity though, we would write $u_i$ in place of $u_{in};$ take $u_0=0,~u_{n+1} = 1.$ Define $\psi(x):= [x(1-x)]^{-1}.$ Anderson-Darling statistic is given by $W_n^2:= n\...
User1865345's user avatar
  • 7,922

Top 50 recent answers are included