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

learn more… | top users | synonyms

0
votes
0answers
10 views

searching for appropriate outlier method

I have data with the following summary: min: 7.59e-08 max: 67.1887 median: 0.03451017 mean: 0.1763083 estimated sd: 1.191953 estimated skewness: 39.27065 ...
0
votes
0answers
8 views

chisquare outlier test assumptions

what are the assumptions of the chisquare outlier test? ( in R: chisq.out.test()) Is it only applicable if the data follow a certain Distribution? What is the idea of ist Definition of outliers? ...
0
votes
1answer
21 views

Rookie question about non parametric and parametric tests

I am a very rookie statistical test user and I want to better understand how to choose between a non parametric and parametric test based on my data. I read several statistical tests tutorials but I ...
0
votes
0answers
12 views

Bootstrap comparison of group means instead of ANOVA/tukeyHSD

I have several groups (~30, >100 data points per group) and would like to see if there are differences between the group means and where. Both ANOVA and Kruskal-Wallace say yes and I'd like to see the ...
0
votes
0answers
12 views

Permutation test for repeated measures (in time)

I have the measurements of a quantity, observed every day for 60 days Usually, this quantity is really near to 0, apart from 3 days where it is (significantly?) greater than 0 I thought it would be ...
0
votes
0answers
9 views

How to assess the significant level of a sample difference per number of element

I have 3 samples of 28 paired elements which have been tested for normality and they are not normal due to biomodal distributions. I carried out a Friedman test and is not significant. However I know ...
0
votes
0answers
25 views

When to use Median test and Mann-Whitney test?

I know that both uses to find whether the two sample medians are equal or not. But I want to know when should I use them? Under which conditions these two tests can be applied separately?
0
votes
0answers
8 views

Dunnett T3 test interpretation

i have result from a Dunnett T3 test using package DTK in R. The result do not give me any p-value but only "Diff", "lower CI" and "upper CI". i can understand the difference between groups as the ...
8
votes
5answers
161 views

How to test an interaction effect with a non-parametric test (e.g. a permutation test)?

I have two categorical / nominal variables. Each of them can take only two distinct values (so, I have 4 combinations in total). Each combination of values comes with a set of numerical values. So, I ...
0
votes
1answer
18 views

Comparing capture rates in 2 groups: which test?

I am comparing rate of capture (animal captures per hour) between two years. I'm interested in determining whether there is a difference between rate of capture between the two years. A survey night ...
3
votes
2answers
347 views

The correct way to display non-normal data?

In my university we learned a lot about normal data, but handling non-normal data wasn't really covered. For some benchmarking of an application I have data has a very high frequency around one value ...
1
vote
0answers
18 views

Maximizing a non-parametric Probability Density

Assume we have a set of samples and estimate the underlying distribution with a non-parametric density estimator like the Kernel Density Estimator. Lets assume with a gaussian kernel. In my case it ...
0
votes
0answers
10 views

Non-parametric paired data: several Wilcoxon signed-rank tests? Other?

Scenario: I've taken blood samples from a group of patients (n = 15) and measured the expression of one marker on three cell populations within each sample (transitional B, naive B, memory B). I'm ...
0
votes
0answers
37 views

p-value interpretation of Jonckheere Terpstra:one-sided or two-sided

I am using the Jonckheere-Terpstra test in order to validate the pooled t-test results. Basically, I like the JT test because of its non-parametric nature. Basically, I am now trying to understand ...
0
votes
0answers
9 views

Non-parametric analogue of a one-way MANOVA

What is the best test to perform a non-parametric multivariate analysis of variance? I have 4 levels of 1 factor, $n=60$ statistical units and 30 dependent variables.
0
votes
0answers
7 views

Is there a more improved fitting regression than some local regression methods?

I think that some methods in the local polynomial regression ended issues in terms of curve fitting. That is, these methods almost perfectly seem to fit the data given. Whenever I fit the curve using ...
0
votes
1answer
17 views

Betadisper and adonis in R: Am I interpreting my output correctly?

I am currently analyzing next generation sequencing bacterial data and trying to figure out whether bacterial communities differ between regions (seems to exhibit this in nMDS). When running adonis ...
0
votes
0answers
22 views

Non parametric multivariate analysis

I need some help with my statistical analysis. I have two different pharmacokinetic parameters. They result from two different models applied on the same data. These data are baseline and follow up ...
1
vote
2answers
39 views

Most appropriate analysis for non-normal, right-censored response variable?

I conducted an experiment with human subjects in which the independent variable has 3 treatment levels and the dependent variable is the duration of time that passes before the subject engages in a ...
1
vote
1answer
34 views

Why run a post hoc wilcoxon signed rank test after Friedman test, why not just skip to Wilcoxon sign test instead?

I understand that one is required to run post hoc tests after the Friedman test. For example, while the Friedman test may find a statistically significant change amongst 3 treatments, one may follow ...
0
votes
1answer
43 views

Survival analysis with multiple factors

I want to do survival analysis in a situation where I expect the survival time depends on two factors: Environment. Each person is in one of three environments, $E_1,E_2,E_3$. I expect that the ...
5
votes
1answer
35 views

Are parametric tests on rank transformed data equivalent to non-parametric test on raw data?

Many non-parametric tests are identical to their parametric equivalent on ranked data. At least, that's what I learned from this blog post on Friedman's test and skimming this 1981 article.. This ...
0
votes
0answers
16 views

Non Parametric test for ranked data

I am working on a project on multi criteria decision modelling. The technique applied (Analytical Hierarchy Process) provides me with data in the form of normalised weights (sum=1) to a set of ...
1
vote
0answers
11 views

Is there any test, like Mann Whitney U test or Kruskal Wallis test, that allows me to include a categorical covariate (like an ANCOVA)?

Here is my question: I want to know if there is a test that allow me to do an nonparametric ANCOVA. Let me explain: I am looking for a Mann-Whitney-U and a Kruskal-Wallis, but I want to include a ...
0
votes
0answers
9 views

How are the values of knots in MARS calculated?

I'm wondering how the MARS algorithm decides on the specific values for the knots which are included in the hinge functions. Thank you very much.
0
votes
0answers
12 views

Nonparametric test for discovering a unimodal distribution?

I am doing a literature review. I want to count how many times a given HCI concept has been found to have some effect (strong, medium, weak or none, with negative effects that's an ordinal scale with ...
1
vote
0answers
25 views

Paired or non-paired data? comparing two sets of scores from same individuals

I have data from four companies, W, X, Y and Z. For each company, three groups of 5 individuals (15 individuals total) take part in a test. Every individual takes two tests, test A and test B, with A ...
1
vote
0answers
28 views

How do I check data for normality, then what next…?

I am currently undertaking a hypothesis test for some financial returns data. I'm getting slightly confused on parametric versus non-parametric testing. I am testing a market portfolio of 305 stocks ...
1
vote
0answers
129 views

Testing difference between two portions of a time series with Chebyshev Theorem

I have a time series which presents two different patterns during time. These patterns are related to two different events that happen during the experiment. I can manually select the temporal ...
0
votes
1answer
26 views

Kernel Regression with Multiple Predictors

I know Kernel regression is a type of local regression, i.e., we consider nearby points/observations to predict the value at a particular point. In other words, we see which of the already existing ...
0
votes
1answer
30 views

Version of Mann-Whitney U test, for right-censored data

Is there an equivalent of the Mann-Whitney U test, but for right-censored data? I have right-censored numerical data from two different groups. The mean for one group is higher than the other. I'd ...
5
votes
0answers
28 views

Dirichlet process mixture MCMC

I'm reading Markov Chain Sampling Methods for Dirichlet Process Mixture Models by Radford M. Neal. Equation (3.6) states that If $c=c_{j}$ for some $j\neq i $: $P\left(c_{i}=c\;|\;c_{-i}, y_{i}, ...
1
vote
0answers
30 views

Four standard deviation rules in relation to normality testing

Within our department we were given a set of guidelines for how we might decide whether to proceed with parametric or non-parametric testing (for continuous data). These were drawn up in consultation ...
0
votes
0answers
17 views

Unsure what test to use for my non-parametric data

I would like some help choosing the most appropriate stats test to use for my data. I have two different types of organism, four different treatments and then the dependent variable is yes/no did they ...
1
vote
0answers
31 views

Is there an online way to compute additive, kernel or spline regressions?

I have an online learning problem where every second (say) I receive a new observation $(x_1,x_2,y)$. I'd like to fit the following models: $$ y = f(x_1) + f(x_2)$$ and maybe $$ y = f(x_1,x_2) $$ In ...
1
vote
0answers
28 views

Rephrasing: Hypothesis Test: normal and non-normal data [closed]

I am rephrasing this question to make it more clear. I have two samples of data, A and B, and I want to perform an hypothesis test to realize about the cost of A and B. Cost, here, it is simply the ...
3
votes
2answers
270 views

Why does using a non-parametric test decrease power?

I am thinking about using the Mann Whitney U test over Student's classic t-test. But I was warned that I'd lose power and would require a higher sample size to compensate. I don't understand: Why ...
0
votes
1answer
63 views

Is likelihood ratio test a nonparametric test?

I have a few doubts about the Likelihood ratio test. I understand that we compute a p-value based on the ratio of likelihoods between two models. I am wondering: Is the likelihood ratio test, a ...
1
vote
1answer
37 views

run test with p-value equals to NA

I am using runs.test() of library lawstat in R. I am getting following output ...
3
votes
1answer
35 views

Distribution-free test for two-sample multivariate distributions

Suppose that $X_1, \cdots, X_n$ and $Y_1, \cdots, Y_n$ are samples of $R^d$ vectors with distributions $X$ and $Y$ respectively. In addition, assume that there is one-to-one mapping between the first ...
0
votes
0answers
45 views

unbalanced non-parametric version of two-way ANOVA

I have a question on deciding which statistical test to use for my thesis research. I am trying to analyse abundance of microbes along time in two groups of oral microbiota samples: oral samples ...
1
vote
1answer
21 views

non-parametric trend analysis with data that is both left and right censored

I am assessing the the presence of monotonic temporal trends in E. coli concentration data using a non-parametric approach. These data are both right and left censored (for example the lower detection ...
3
votes
0answers
19 views

Covariance of two distinct quadratic forms

Let's say that I have two random vectors, that should belong to the same distribution family, but are distinct. I.e. $\mathbf{Y_{1}} = (Y_{11}, ..., Y_{n1})^{T} \sim D(\mu_1, \Sigma_1)$ and ...
0
votes
0answers
30 views

Is it possible to compare unequal sample sizes in a non-parametric paired t-test?

I'm trying to compare counts of species made during the day and during the night. The counts were made in the same location for day and night and were on the same populations. Therefore, I'm assuming ...
1
vote
0answers
20 views

Comparying MLE and Parzen Window based Classifier?

I am trying to compare a classifier that uses either MLE or Parzen in the training stage. MLE is a parametric method while Parzen is non-parametric. Naturally, CPU time can be used as a comparison ...
3
votes
1answer
135 views

Is Principal Component Analysis a parametric method?

Principal component analysis assumes that the features are distributed by a Gaussian. Does this make Principal Component Analysis a parametric approach? I can't seem to find a concrete answer saying ...
1
vote
0answers
33 views

Reporting the results of Nonparametric regression using kernel weights

I am wondering how I can present the results of nonparametric regression. I performed the nonparametric tests using R, and R package 'np'. The commands used for this are freq <- npreg(Respno ~ ...
1
vote
1answer
29 views

Nonparametric censored trend analysis: When using cenken (package NADA in R), should I use annual medians or all of data

I am using cenken to perform a nonparametric trend test on concentration data with multiple detection limits (the detection limit changed when a change of labs was made). I have seven years of data ...
1
vote
0answers
36 views

Learn a distribution from distributions on samples

There's many good ways to learn a distribution $p_X$ of an r.v. $X$ over $k$ symbols given many i.i.d. samples $X_1,\ldots, X_n$. The simplest is to use the sample relative frequencies $\hat{f}_X$ as ...
3
votes
1answer
34 views

Nonparametric 2-way ANOVA for data with unequal n's due to possibly informative missingness

So my problem revolves around trying to find the right test for my data in R. I've been doing an experiment that is measuring sublethal effects in a toxic environment, and as a result, even though I ...