Questions tagged [nonparametric]
Use this tag to ask about the nature of nonparametric or parametric methods, or the difference between the two. Nonparametric methods generally rely on few assumptions about the underlying distributions, whereas parametric methods make assumptions that allow data to be described by a small number of parameters.
2,127
questions
2
votes
0
answers
49
views
Kruskal-Wallis statistical power
Given that the Kruskal-Wallis $H$-test has been computed, the epsilon-squared estimate of effect size can be calculated as
$$E_R^2=\frac{H}{(n^2 - 1)/(n+1)},$$
the number of the compared groups, the ...
- 73
0
votes
0
answers
18
views
Give the distribution of an asymptotically Normal statistic, conditional on a function of sample ranks, and describe regression parameters
I'd like to write the following, about conditioning a normal r.v. on a rank statistic, but I'm unable to recall a specific theorem or theorems I can cite:
"Let $\hat{\rho}$ be an asymptotically ...
- 642
0
votes
0
answers
39
views
Data is not normal, want to test for interaction too Any non-parametric test? [duplicate]
I have a sample size of $310$ individuals that comprises samples collected along the elevation gradient and at different times. I want to see how the variables differ along the elevation, and with ...
- 73
0
votes
0
answers
25
views
Model fitting with Chinese Restaurant Process
I am trying cluster a trajectory, consisting of (state, action) sequences, by assigning them to the most likely model that generated them using Chinese Restaurant Process. Basically my goal is to ...
- 51
0
votes
0
answers
18
views
Friedman test for small sample single arm trial?
I am looking at a single arm clinical study with a small sample size (n=14), where each patient was assessed 5 times (weeks 1-5, once a week). I have constructed linear models to see if the change-...
- 1
0
votes
0
answers
9
views
Basic question regarding before and after intervention analysis on groups of different sample size
Apologies for the basic nature of this question. I have collected data before and after an intervention and assessed response to the intervention using a survey. This was a basic survey using a 1-5 ...
- 1
0
votes
0
answers
14
views
References: convergence rates of kernel regression, exchangeable data
I have been studying Kernel estimation; in particular, the Nadaraya-Watson estimator. I am interested in studying the rate of convergence in L^p of the NW (or similar) estimators for subgaussian ...
0
votes
0
answers
19
views
Comparability of means for non-normal distribution and small sample size
I have to perform a comparability study between pre and post change of a production process.
I'm using the final purity to measure comparability and wanted to compare medians between pre (n=40 runs) ...
- 1
1
vote
0
answers
67
views
Confidence interval for sum of product of scaled binomial random variables
I have discrete, independent, but not necessarily identically distributed random variables $X_1,\dots,X_n$ that take on non-negative integer values. Each random variable has unknown distribution ...
- 53
1
vote
1
answer
182
views
What do these Wilcoxon values tell me?
I did a pre and post-test with a small number of students ($n=12$).These values came after a science intervention that took $4$ weeks. I used a Wilcoxon test for 2 related samples as there was not a ...
- 11
0
votes
0
answers
149
views
Comparing the output distribution of two ML models
Consider a regression task (e.g. predicting house prices) with a given train and test sets.
We start with constructing a linear regression model, in which we assume $y_i=X^T\beta+\epsilon$ with $E[\...
- 4,022
0
votes
0
answers
26
views
BART with non-parametric heteroscedastic noise?
Is there a variant of BART that robustly captures noise that is both heteroscedastic and non-parametric (or has an a-priori unknown parametric form)?
For example, a BART that could fit this test data:
...
- 467
1
vote
1
answer
36
views
Estimate multivariate distribution with several variables on real data (continuous and categoricals) and sample from it
I have a complex dataset, collected through a survey, with both continuous (such as Age, Body mass index, etc..) and categorical variables (i.e. Gender, Education, etc..). I want to estimate their ...
- 11
0
votes
1
answer
23
views
Choice of test for Comparing Chatbot vs. Group of Humans on Ordinal Scale
Background
I want to compare chatbot (e.g. ChatGPT) performance on medical questions with a group of human doctors. Each question will be answered and scored on an ordinal scale 1, 2, 3, 4 or 5. I ...
- 123
2
votes
2
answers
248
views
non-parametric-ANOVA
I have a dataset containing angles. They represent the bending angle that a seedling makes to go toward light. Genotype A is WT and A is the one we are testing. We removed a PKS gene, wich is ...
