Questions tagged [nonparametric]
Procedures that rely on relatively few assumptions about underlying probability distributions.
1
vote
0answers
12 views
For what reasons should one use Bootstrap Testing when the sample size is large?
Bootstrap testing is great if we have a small sample size where the Central Limit Theorem does not apply. However, what are convincing reasons we should use Bootstrap if we do have a large sample size....
1
vote
0answers
18 views
Computing Wassertein Distance
For two probability measures $\mu$ and $\nu$, the Wassertein Distance is defined as $$W_p (\mu , \nu) = \left[ \inf\limits_{\gamma \in \Gamma} |x-y|^p \, d\gamma (x,y) \right] ^{\frac{1}{p}} \, , $$
...
0
votes
0answers
23 views
Statistical test for binned proportion data in JMP / MATLAB
I have been trying to determine the proper statistical test for comparing binned proportional data between groups. My data set is individual subjects (4-5 per group) with 76-165 cells per individual. ...
1
vote
0answers
17 views
Pairwise non-parametric test?
I have 5 groups of patients (different sizes), for which I measured some property that is continuous but not normally distributed. I would like to compare every pair of groups in respect to this ...
1
vote
1answer
39 views
I am confused as to which nonparametric procedure I should be performing on my data
My question reads:
"A computer laboratory manager was interested in whether there
was a difference in functioning time for three different branded
battery packs for laptop. The manager took a random ...
0
votes
0answers
14 views
If a dependent sample (pre/post) is not paired (no link between pre & post) are they treated like independent samples? [duplicate]
Trying to run some tests on pre/post survey questions from a small pilot group of n=9. As a fault of the survey, there was nothing to link participants from pre to post. I'm trying to determine what ...
1
vote
0answers
28 views
How can one verify distributional assumptions for testing procedures, if only one draw from each distribution is available
I am currently dealing with a situation in which the Wilcoxon signed rank test (WSRT) is a possible candidate to be applied to the data. So let`s say we have $n$ pairs of Random Variables $(X_i, Y_i)$ ...
0
votes
0answers
11 views
Difference for bandwidth selection between kernel smoothing + KDE
I have random samples of categorical data which are distributed in two- and three-dimensional space. There are between two and ten levels of the category, depending on the dataset. I'm trying to ...
2
votes
1answer
50 views
Construct piece-wise linear mixed effect models
I'm looking at the BMACS dataset(data(BMACS)), and is trying to construct a local constant fit without covariates using base functions B1(t) = 1 for t < 2, B2(t) = 1 for 2 <=t <4 and B3(t) = ...
0
votes
0answers
15 views
Non-parametric test for interaction effect
I have a relatively small data set with quality ratings (dependent var), for different compression methods (independent var 1) applied to different types of video (independent var 2). My first ...
1
vote
0answers
18 views
Imposing orders on distributions based on Wilcoxon test
I am trying to figure out part of a text I am reading about non parametric tests.
In there it is stated that:
The fact that the output of a rank test is driven by the probability that a value ...
0
votes
1answer
26 views
randomization/permutation test for mean > 0
I'd like to know if the following procedure is a valid way to test if the mean of a population is greater than zero, based on a random sample of observations:
1) Calculate the sample mean
2) On each ...
3
votes
1answer
41 views
How is an RNN (or any neural network) a parametric model?
I'm going through this paper A Multi-Horizon Quantile Recurrent Forecaster. The authors state that:
3.1. Loss Function
In Quantile Regression, models are trained to minimize the total ...
24
votes
3answers
3k views
Why does the Kolmogorov-Smirnov test work?
In reading about the 2-sample KS test, I understand exactly what it is doing but I don't understand why it works.
In other words, I can follow all the steps to compute the empirical distribution ...
0
votes
0answers
12 views
Find joint distribution for two different cases Kruskal Wallis
I'm a bit stuck with my homework in a subject called "Non-parametric Statistics". The task is related to Kruskal-Wallis test.
The task is as follows:
Let's look at the comparison of 3 independent ...
2
votes
0answers
17 views
Non-linear regression. Obtain B.spline coefficients using Fourier Transform?
I came up with a idea to estimate the coefficients of a B-spline fit by using the Fourier Transform but I don't know if it makes any sense to estimate them in this way.
Given that
$$s(x)=\sum_kc(k)\...
0
votes
0answers
11 views
Non-parametric equivalent to Z-factor?
It seems that all the ways of calculating standardized effect sizes assume a normal distribution: Z-factor, Cohen's d, SSMD, ...
I wonder if there is a non-parametric equivalent to these. In ...
1
vote
0answers
30 views
Test for occurrences of pairs from samples with different distributions?
I have two collections of data, A and B, each containing a large number of 10-digit binary strings. For instance, an element of A could be a=1011001111, and an element of B could be b=1001010000. I ...
1
vote
1answer
85 views
Estimating conditional probability with many samples
I am confused about the estimation of conditional probabilities. Suppose I want to predict a binary outcome variable $Y = 0,1$ given $n$ categorical features $X = (X_1, \ldots, X_n)$, i.e. to ...
0
votes
0answers
23 views
Is it okay to use non-parametric tests on normalized data?
I'm doing experiments with 3 conditions: A, B, and C. I have done the experiment 3 times, so each condition gets 3 values for a total of 9 values. Each value is actually an average of 5 measurements. ...
0
votes
0answers
20 views
Fitting quadratic model for non-normal data
I am regressing between the body size and eye size values of different bat species. They are not linearly related (picture attached) and I want to fit a quadratic model to it but the values are non-...
0
votes
0answers
23 views
Alternatives to logistic regression when dataset can't meet 10 events per predictor variable
I have a dataset with a binary outcome I'd like to model, but have many more parameters than events, probably ~100 categorical parameters to test, in a dataset with 20 events in ~600 observations.
As ...
2
votes
1answer
17 views
Meta analysis Cliff's delta
Cliff's delta is an effect size typically recommended whenever the normality and homogeneity assumption do not hold---and thus, Cohen's d cannot be used.
However, I cannot see any reference ...
3
votes
2answers
45 views
Suppose is is stated that $X_i \sim \mathcal{P}_X$ is a non-parametric model. What does this actually imply?
I read in a book that sometimes one can specify a non-parametric model. It stated that:
$X_i \sim \mathcal{P}_X$ for $i = \{1, \ldots, n\}$ was a non-parametric model.
My understanding of a non-...
1
vote
0answers
21 views
Alternative test to paired t-test? [duplicate]
I need to compare data from paired groups, but my distributions are non-normal, and my sample size is small. Are there any tests I could apply?
I've been looking into non-parametric alternatives like ...
7
votes
2answers
597 views
What will happen if I use a nonparametric test with normally distributed data?
I was asked if a type I error in the Shapiro-Wilk test would impact the main analysis and if the wrong test was used if it would matter or not if my data was normally distributed...
2
votes
0answers
41 views
How to prove variance of Spearman's Rho
How does one derive the variance of Spearman's Rho?
The result is $\frac{1}{n-1}$.
I simplified the formula into the last line shown in the picture but how does one proceed from then? ($R(X_i)$ and $R(...
0
votes
0answers
71 views
How to interpret Friedman's rank sum test?
I'm unfamiliar with non-parametric tests and
I have this data
...
0
votes
1answer
7 views
compareGroups p.overall missing p-value
I was doing a non-parametric test across multiple groups in compareGroups. What is strange is my p-overall is missing after showing <.01 before. AND the distribution of the data in the clusters ...
0
votes
0answers
7 views
Is there a parametric counterpart for KS two sample test?
My data is normally distributed for two sample. I wanted compare these two distribution if they are different i.e. if one sample is skewed to right or left compared to another.
1
vote
0answers
32 views
Prove the relation between two distribution functions
I have been given a homework in a subject called "Non-Parametric Statistics" and I'm a bit stuck with it. I would be very thankful if you could give me any advice or help, which would lead to a ...
0
votes
0answers
18 views
Example of an non-symmetrical Wilcoxon Rank Sum test statistic value
I have been given a homework in a subject called "Non-Parametric Statistics" and I'm a bit stuck with it. I would be very thankful if you could give me any advice or help, which would lead to a ...
1
vote
0answers
39 views
Possible questions on testing on hypothesis in A/B testing for a position of a data scientist (EDITED)
What are some possible machine learning and statistics questions on the subject of A/B testing for a position of a data scientist in Ad Tech industry working in retargeting? I'm interviewing for such ...
0
votes
1answer
28 views
How to know which two hyperparameters are more important in SVM, KNN and MLP?
I am trying to limit myself to a maximum two hyper-parameters that are important in KNN, SVM and ...
0
votes
1answer
22 views
Uniform kernel estimator
For practice, I'm trying to provide an estimation for a nonparametric model on dataset BMACS from library (npmlda). I'm having trouble to set up a kernel estimator with Uniform(-1/2,1/2) kernel and ...
0
votes
0answers
4 views
Perform non parametric test for continuous spectrum of data
I am having continuous spectrum of data which is calculated after fixed interval. I need to check its correlation with the categorical data.
Eg;
Data explanation:
NMR_NO: sample number.
...
0
votes
2answers
46 views
Which statistic test should I use in this situation?
There are 10 questions in which we are comparing peoples' opinion about two conditions, "X"and "Y". Every question was answered by about 90 people who were different than other questions' respondents. ...
0
votes
0answers
14 views
Comparison between one qualitative variable and a quantitative non-parametric one
I have a dataset composed of 85 observations. Each observation represents a lymphoma diagnosis. For each diagnosis I have a clinical classification (indolent, aggressive and very aggressive) and a ...
2
votes
0answers
34 views
Which test to use to detect if a process has significantly more errors than another?
A have a set of machines running a particular software. I want to do something that's called "canary deployment".
This consists of deploying the new version of the software to a subset of machines ...
0
votes
1answer
30 views
Non-parametric tests for interaction effects
I have two datasets that are both organised as follows: an algorithm calculated a quality score (Q) of a specific image (image) that was processed using a certain algorithm (method). One has 315 ...
0
votes
0answers
30 views
Covariate adjustment of non-normal traits for subsequent two-sample analysis
My dataset is composed of two populations, and I have numerous continuous traits that I’d like to compare between the two populations. All the traits are non-normal. The covariates for each of these ...
0
votes
1answer
47 views
Estimating Expected Order Statistics
I have a fairly basic question that I'm looking for a reference for.
First, a couple definitions. Let's say $X_1,\ldots,X_n$ are IID samples from a distribution $F$ over $[0,1]$. For any $k\in\{1,\...
0
votes
1answer
29 views
non-parametric test: proof of Friedman's statistic
I am asked to prove that the Friedman statistic has two equivalent forms, namely:
This is my attempt at a solution starting from LHS and trying to arrive at RHS. I feel like there are some ...
1
vote
2answers
46 views
How can I obtain a function that describes the expected value of data based on monthly data throughout different years?
I know this question is kind of complicated to understand at first. Here's the deal:
I've got organized, monthly sales data from various years, and when I graphed it I saw there's (obviously) a ...
0
votes
1answer
35 views
Paired t-test of a non-normal data with sample size 66
I have a paired data with n=66. I understand that normality condition of differences data should be met to conduct a paired t-test. However, from the histogram, it doesn't appear so normal. The p-...
0
votes
0answers
11 views
non-normal censored outcome, high dimensional predictors
I have an outcome that is non-normal (multimodal) and has an upper limit of detection giving censored values at an upper bound. I have several hundred observations and wish to predict these non-normal ...
0
votes
0answers
31 views
Multivariate plug-in bandwidth estimator local constant regression
Has someone good references for multivariate plug-in bandwidth estimators in local constant regression? All I'm finding is for the univaraite case.
And is there maybe already an implementation in R? ...
1
vote
0answers
25 views
Determining the number of simulations in non-parametric classification simulation
I am currently working on setting up a simulation study that compares the effectiveness of k-nearest neighbours and gradient boosted trees.
I have checked these two sources. Both refer to p-values ...
0
votes
0answers
7 views
Nonparametric classification of a sample of values — is my approach correct?
Suppose I have a machine with a number of different labelled settings. The labels go from $1$ up to $L$. When I choose a setting on the dial, let's say setting $j$, I can have it output i.i.d. samples ...
1
vote
0answers
15 views
What among location, scale and shape is Kolmogorov–Smirnov test statistic sensitive to and why?
I understand that the Kolmogorov–Smirnov test statistic for a given cumulative distribution function $F(x)$ is $D_n = \sup_x |F_n(x) - F(x)|$. However, if I have to rank its sensitivity to location, ...
