Procedures that rely on relatively few assumptions about underlying probability distributions.

learn more… | top users | synonyms

0
votes
1answer
11 views

Multiple Comparisons test strategy

I have a test data with 3452 subjects , I have 5 different algorithms that detect the presence or absence of a disease. ...
0
votes
0answers
9 views

Non-normal, related but non-paired data, test for significant difference

i am comparing the profit margins for restaurants prior and post gaining a michelin star. I have all the profit margins for each restaurant up to 2-5 years prior and post. I want to compare all of ...
0
votes
0answers
17 views

Transformation of dependent variable for MARS algorithm?

I am just wondering if its necessary to transform a dependent variable as it is a large monetary value? I'm unsure if its necessary with a non-parametric methods such as MARS. When I do a log ...
2
votes
0answers
11 views

Explanatory power of variable

To clarify from the very beginning, I expect relations between my variables to be very non-linear, so usual correlation and PCA approach may not work here. Also, for simplicity all the variables are ...
0
votes
2answers
51 views

Statistical test to compare skewed distributions of binary data

I have two positively skewed distributions of binary data (0, 1) I would like to compare. I'm not an expert of non normal distributions. Is there a statistical (R based) test to do this? Thanks in ...
3
votes
0answers
36 views

Regression discontinuity design

I am trying to apply an RRD design to a set of spatial data from rasters. The approach has been widely used in the development economics literature and I know that it is a sound methodological ...
0
votes
1answer
27 views

Nonparametric tests and binary data?

I'm having data which represent two groups, one that used tool 1 and the other that used tool 2. I asked a series of questions (10 questions). The questions were true or false. I also measured the ...
0
votes
0answers
8 views

Time evolving non parametric data model

I have data points $(x_i, y_i)$ in each iteration of my algorithm on which I build a non-parametric model using local linear regression with a Gaussian kernel. Using this model, I estimate the ...
0
votes
1answer
27 views

Machine Learning Procedure for Fractional/Proportional Data?

I am looking for some suggestions of machine learning procedures that work to predict fraction outcomes where the outcome variables $\in [0,1]$. Can you provide me with any suggestions? I thought ...
0
votes
2answers
42 views

How do I get which experiment is doing better using the Mann-Whitney U Test?

The material I got only described how to test if there is difference (null hypothesis: H0 = H1). However, what I want to test is if the test version is doing better than control: null hypothesis: H0 ...
0
votes
0answers
11 views

3 groups to compare, non-normal, unequal variance. What to do

I'm comparing three groups by Julian Date. Group 1 (n=173), Group 2 (n=47), Group 3 (n=126). All three distributions are non-normal and the variance is not equal. I've tried transforming the data six ...
3
votes
1answer
34 views

How to analyze this positively skewed data?

I am having trouble analyzing my dataset consisting of the sumscores of a questionnaire. For each item, subjects had to indicate whether they performed this behavior 'never', 'sometimes', or 'often', ...
0
votes
0answers
12 views

Testing for dependence of unpaired and unequally-sized samples

I've seen several similar questions, but I haven't been able to find an answer. I have two unpaired samples of unequal size and of equal population variance. One concern is that these samples are ...
0
votes
0answers
4 views

Unexpected results with non-parametric multiple comparison of means (R package nparcomp functions nparcomp and mtcp) [migrated]

I am currently trying to perform a non-parametric simultaneous relative contrast effects using the R package nparcomp (https://cran.r-project.org/web/packages/nparcomp/index.html). I am getting some ...
3
votes
1answer
37 views

What does “significant rank correlation” mean in the context of Kendall Tau-B?

I am trying to understand how to correctly interpret "significant rank correlation" in the context of Kendall Tau-B. What can I conclude if the correlation is 1? The relationship is monotonic? Edit: ...
0
votes
0answers
13 views

How to check if two samples come from the same population? [duplicate]

I was wondering if or which tests can be used to test if two samples come from the same population for data that is not normally distributed?
1
vote
0answers
17 views

R package for non parametric G*E interaction

Is there any R package to find out non parametric G*E interaction tests like Kubinger's Hildebrand's and De Kroon and Van der Laan test?
0
votes
0answers
4 views

Can I use Bray-Curtis distance when performing MRPP or MRBP?

Can I use Bray-Curtis distance when performing MRPP (Multi-response Permutation Procedures) or MRBP (Blocked Multi-response Permutation Procedures)? [See Ch 24 of McCune & Grace (2002) for ...
2
votes
1answer
46 views

Why do we resample in bootstrap estimation? [duplicate]

Why do we need to resample from an initial set of samples when using bootstrapping? Why don't we just take fresh sets of samples from the original distribution? What is the justification behind ...
1
vote
0answers
25 views

How to discriminate among different post hoc friedman tests

I had to carry out several Friedman test comparing different yields. I also wanted to conduct a Post-hoc test to distinguish among different systems. I used the R function ...
1
vote
0answers
37 views

Gaussian processes and kernels

What is the difference between Gaussian process regression and non-parametric regression using kernels? I think that there is some connection between the two, however my main question is if we can ...
1
vote
1answer
41 views

How to show that the general parzen window provides a probability distribution?

According to the solution above, the integral of the kernel over x is the volume of the hypercube. However, I do not understand why. Can someone explain to me please?
0
votes
0answers
16 views

Clustered Data and Kruskal–Wallis

I have a data set of loan amounts that is naturally clustered into 3 groups: 0 - 5 year loan 10 - 15 year loan 20 - 30 year loan The 3 groups are not normally distributed. Since I don't need to ...
1
vote
1answer
37 views

Kernel nonparametric regression

One of the methods for nonparametric regression is using kernels. My question is what are the conditions on the kernels functions in this method? In other words how can I decide if a given function ...
1
vote
1answer
38 views

Smooth Non Normally Distributed Data

I have ~16,000 probability sets of goals scored [maximum of 12] like below [some % are rounded hence do not add up to 100%]: ...
5
votes
1answer
132 views

Estimate the number of failing components in a changing population

I'm working on a problem (using R) which involves estimating the number of failures in a population of components. I have information on the number of components that were added to the population in ...
0
votes
0answers
12 views

Number of Dimensions in a CHAID Decision Tree

I am thinking of running a CHAID decision tree to understand which factors play an important role towards a store being highly profitability (1) or low profitability (0). I have 500 such stores being ...
0
votes
0answers
17 views

Determing Probability Distribution of PCA Values

I am trying to determine the best distribution for PCA values. I did an experiment where I have a lot of response variables and I think they're best interpreted through using a PCA. I want to use a ...
5
votes
1answer
84 views

“Inverse” Q-Q plot?

Suppose we have two real-valued random variables $X,Y$. Let $cdf_X$ and $cdf_Y$ be the corresponding cumulative distribution functions. We are interested in graphically comparing the distributions ...
0
votes
0answers
15 views

What test to use for non-parametric repeated measures data?

I've been having trouble finding the correct test to use for my data. I measured the response of subjects to two treatments across three different time periods (e.g. beginning, middle, end). I want to ...
0
votes
0answers
20 views

Chi-Square value in Kruskal Wallis test very large

I am comparing measurements of 12 different groups to one another. My distributions are not normal and my Levene's test is significant - even after data transformation. I am therefore doing a ...
0
votes
1answer
32 views

How can I conduct a non-parametric version of MANCOVA in R?

Is it possible to transform my variables to their ranks and apply MANCOVA to the transformed data, just like how it is done in rank ANCOVA?
0
votes
1answer
35 views

Suitable non parametric test

I am trying to determine which type of non-parametric test is most suitable in this situation: Public and private sector organisations were sampled in a study which aimed to determine what percentage ...
3
votes
2answers
59 views

How to interpret Mann-Whitney's statistical significance if median is equal?

Testing the difference between the observations of two groups by using Mann-Whitney Test has given the following output (from minitab): ...
0
votes
0answers
49 views

Is this wikipedia article about KNN contradicting itself regarding “non-parametric”?

I understood that KNN (K-Nearest-Neighbors) was non-parametric, after reading the beginning of the wikipedia article here: ...
2
votes
2answers
133 views

What test is appropriate for comparing the difference in accuracy between recognition tools?

I have developed a tool that recognizes a set of six classes, and then tested and evaluated its ability to recognize these classes by using the F-score (aka F-measure). I then tested two other tools ...
1
vote
0answers
15 views

Evaluation of effectiveness of linear filtering on nonlinear processes

I was across the following problem recently. I have a nonlinear bivariate process, where $X$ is causing $Y$, i.e. $$ y_i=f(x_i) + \varepsilon_i, $$ where $f$ is a nonlinear function. To evaluate the ...
1
vote
0answers
22 views

Empirical multivariate probability integral transform

Is there a 'simple' way to obtain a non-parametric empirical multivariate probability integral transform? Univariate case The probability integral transform relates to the transform of any random ...
1
vote
2answers
39 views

Different definitions of Epanechnikov-Kernel

I was just wondering why there are 2 definitions of the Epanechnikov-Kernel. In the first paper, Epanechnikov introduced his kernel [1] with: $K\left(y\right) = \frac{3}{4 \sqrt{5}} - \frac{3 y^2}{20 ...
1
vote
1answer
78 views

Kernel density estimation bandwidth selection

I've just started using Kernel Density Estimation for my study, and encountered a problem. In KDE, we have to select a proper bandwidth $h$ according to the data. If we don't, it could lead wrong ...
1
vote
2answers
46 views

Help with kernel regression calculation

(This is a really basic question, so I appreciate your patience.) I'm trying to do a Nadaraya-Watson kernel regression on a set of $(x,y)$ data points to predict the value at a particular $x$. I ...
20
votes
2answers
206 views

Is there a reliable nonparametric confidence interval for the mean of a skewed distribution?

Very skewed distributions such as the log-normal do not result in accurate bootstrap confidence intervals. Here is an example showing that the left and right tail areas are far from the ideal 0.025 ...
2
votes
2answers
116 views

Parametric vs nonparametric methods [duplicate]

Are non-parametric methods preferable to parametric methods since the former do not force the model to have a parametric structure?
0
votes
0answers
3 views

How would I apply non parametric tests when testing for interactions?

I have a research design where I am interested in testing four strategies with N=87. Each strategic approach involves independent variables, two interactions and one dependent variable. Is it possible ...
2
votes
0answers
17 views

Intuition behind kernel density estimation in Bishop 2006

I have been wondering about this passage from Bishop 2.5.1 Kernel density estimators (p. 122). The passage follows an explanation of how a density function $p$ could be approximated, based on the ...
0
votes
0answers
10 views

About locally linear regression (as a nonparameter regression)

I use package loess in R to build a local linear regression model, but loess can only predict the data that is in the range of training data, when the new data is outside of the range of training ...
3
votes
3answers
69 views

Why is Kernel Density Estimation still nonparametric with parametrized kernel?

I am new to kernel density estimation (KDE), but I want to learn about it to help me calculate probabilities of outcomes in sequencing data. I watched this https://www.youtube.com/watch?v=QSNN0no4dSI ...
1
vote
0answers
16 views

How can I control for a variable while conducting Wilcoxon Rank Sum Test?

I did a Wilcoxon rank sum test to figure out if there is any difference in the distribution of Variable X1 for two groups. The test results showed that the difference does exist. I, however, suspect ...
0
votes
1answer
22 views

Ordinary sign test

Values of pressure of 10 patients before and after the administration of aspirin is given. Using sign test it is to be tested if aspirin was effective. There problem I am facing is that all the after ...
9
votes
1answer
117 views

How to choose between sign test and Wilcoxon signed-rank test?

I am trying to pick one from these two tests to analyze paired data. Does anyone know any rules of thumb about which one to pick in general?