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

learn more… | top users | synonyms

0
votes
0answers
35 views

Confused about whether to use t-tests or ANCOVA or ANOVA

I am investing whether vitamin C supplementation can attenuate creatine kinase increases after a strenuous workout. My participants are divided into two groups, VitC group and a Control (no ...
0
votes
0answers
46 views

Kruskal Wallis: Effect size

I analyse 4 algorithms and 3 sets of metrics for each algorithm in which I apply the non-parametric Kruskal-Wallis test for each metric to detect any differences in performance between these ...
0
votes
0answers
11 views

repeated non-parametric Anova with a normal covariate options, best approach?

I'm looking for input on the best approach to a problem. I have data where each person experienced three conditions during a testing session (different priming stimuli for a memory test). There was ...
2
votes
0answers
25 views

upper bound for expected maximum of difference of two kernel-Estimations

I'm searching for an upper bound for a function like $$ E\left[ \max_{x \in R} \left( \frac{ \sum_{i=1}^n K(\frac{x-X_i}{f(x,X_1, \dots X_n)}) \cdot Y_i } { \sum_{i=1}^n ...
0
votes
0answers
23 views

Z Score for Non Normal Data [duplicate]

I am looking for some direction to see if there is an equivalent metric to a z score that could be used to quickly identify individual values in a non-normal distribution that are not likely to occur ...
0
votes
0answers
25 views

Non parametric test for ANOVA and coefficient of variation

Which is equivalent non parametric test for one way ANOVA ? Is quartile coefficient of dispersion for non parametric test equivalent to coefficient of variation (COV)? Among them which measures are ...
1
vote
0answers
12 views

How do I interpret significant Dunn's test results when the medians are the same?

Long time listener, first time caller... So I am looking at data with five subgroups. Data is negatively skewed in the group as a whole and in all subgroups. Kruskal-Wallis tells me there is some ...
0
votes
0answers
18 views

Bayesian process with noise?

Does anyone know of any research considering Dirichlet processes (or other Bayesian nonparametric models), where sample points have a known gaussian noise attached to their input? I.e. I have a set ...
4
votes
0answers
72 views

Are all models useless? Is any exact model possible — or useful?

This question has been festering in my mind for over a month. The February 2015 issue of Amstat News contains an article by Berkeley Professor Mark van der Laan that scolds people for using inexact ...
1
vote
0answers
38 views

Non parametric test/ANOVA/Parametric test?

My study design is a pre-post test measurements with a control group. My study design is Creatine Kinase being measured before and after exercise, and my subjects are divided into two groups; either a ...
0
votes
0answers
11 views

False discovery rate from non-parametric tests with small n

I have a bunch of paired readings of bacterial abundance, sampled from two different places in the same patient and divided by total bacterial cells found in each location. Thousands of species were ...
1
vote
0answers
23 views

Non-parametric test for repeated measures that are not independent

Seacucumbers were counted at the same 63 survey sites in three successive years (3 x 63 = 189 surveys in total). The distribution of counts per site are non-normal for each year. (Some sites have ...
0
votes
0answers
23 views

Comparing means between two groups if dependent variable is a percentage

I have data on recovery rates from several hospitals across the country. The recovery rates are in percentages. I want to compare the mean recovery rate between two groups of hospitals, one that uses ...
0
votes
0answers
6 views

creating a 3D kernel regression fit from a pool of predictors

i have a ~1k data set that has one response column(z) and 4 hypothesized predictors(x1-x4). i wish to create a 3D plot of the response surface, for example z ~ x1+x1 or z~x2+x4 i know that i need ...
0
votes
0answers
10 views

how to transform non-normal data for downstream statistical analyses [duplicate]

I have a dataset that look at the effect on photosynthesis and respiration. When i checked to see if the data looks normal or not, i find that for both the variables the distributio is non-normal. In ...
2
votes
2answers
79 views

Comparing frequency distributions

Quick rundown of my data: I have depth measurements from fish with implanted transmitters from two sites (reference and hypoxic) and two seasons (spring and summer). All data is in an Excel ...
10
votes
2answers
132 views

Why is Pearson parametric and Spearman non-parametric

Apparently Pearson's correlation coefficient is parametric and Spearman's rho is non-parametric. I'm having trouble understanding this. As I understand it Pearson is computed as $$ r_{xy} = ...
0
votes
1answer
46 views

Dunn.test in R: are adjusted p-values corrected for number of comparisons?

I've performed a post-hoc Dunn's test with Sidak adjustment using the dunn.test code for R. There are three groups in my comparison and I understand from the R help files that the lower number in the ...
3
votes
1answer
59 views

Find test statistic for sign test

I'm investigating if people are walking more than they bicycle. I have $n = 55$. $30$ of them are walking more and $25$ are bicycling more. I need to 1) find the test statistic for the sign test ...
0
votes
0answers
2 views

Comparing change in lateral root densities between treatments for different genotypes

I have been growing 4 genotypes of the same plant and been recording their lateral root density under both control conditions and a salt treatment. I have calculated the decrease in lateral root ...
2
votes
0answers
61 views

How many people initially had apples?

Story problem: Assume 10 apples are distributed across $X$ unknown people, where each person has at least one apple. For each apple a biased coin is flipped to see if that apple should be kept or ...
0
votes
0answers
25 views

Kruskal-Wallis post hoc comparisons different results in different software used

I'm having some trouble analyzing my data because when I use StatSoft Statistica and run a Kruskal-Wallis, I get one set of values for multiple comparisons, but when the same analysis is run in XLSTAT ...
0
votes
0answers
6 views

Data set distribution by state compared to US pop distribution by state

thanks in advance for your help. -I have a survey data set in which people reported which US State they are from. -I have the proportions of the entire data set comprised of people from each state, ...
0
votes
1answer
57 views

Is dunn.test a suitable alternative to kruskalmc in pgirmess package?

I'm trying to run the krushkalmc method after running kruskal.test as part of my analysis with the Kruskal-Wallis rank sum test. I have data with a small sample size that also does not have a normal ...
1
vote
1answer
58 views

Probability that randomly chosen value from one distribution is greater than randomly chosen value from another distribution

Say I have $n$ values sampled from two distributions, $A$ and $B$ . That is, I have a sample $A_1, A_2, \dots, A_n$ and a sample $B_1, B_2, \dots, B_n$. How would I go about finding ...
0
votes
0answers
10 views

Correlation between ordinal and dichotomous variable with repeated measurements

I ask say 50 people to rate 10 statements whether they are true of false (dichotomous answer). The 10 statements were rated concerning the occurrence of specific cues (such as details or emotional ...
3
votes
1answer
54 views

Convergence rate: $E\|\hat f - f\|^2 = O(\psi_n)$ vs $\|\hat f - f\| = O_p(\psi_n^{1/2})$

I have seen two types of results on convergence rates for some estimator $\hat f$: $E\|\hat f - f\|^2 = O(\psi_n)$ and $\|\hat f - f\| = O_p(\sqrt{\psi_n})$. The first result seems to be stronger, ...
2
votes
1answer
68 views

Excess Bunching - Bunching Estimator (Saez 2010)

Saez (2010) defines excess bunching at the kink as the area under the density in the dominated region: $$ B = \int^{z^*+d z^*}_{z^*} h(z)dz \approx h(z^*)dz^* $$ where income $z$ is distributed ...
1
vote
0answers
23 views

Confidence intervals for a curve with bootstrapping

I am estimating y= az + f(x) in a semi-parametric way. I want to compute the standard error for the estimated coefficient for a ...
2
votes
1answer
79 views

How can I measure difference between non-parametric data with many zeros?

I'm comparing two groups of students by their course activity and I'm struggling a little to determine the best way to test for significant difference. The data is non-normal, and very prevalent with ...
0
votes
0answers
22 views

Correlation to use for non-scale data( counts)

In our college we run some extra non-required sessions that we hope help the students. To decide whether they help, I wanted to correlate the number of sessions attended with the cumulative gpa of ...
0
votes
0answers
14 views

What is the complexity of locally linear regression on many grid points?

Say I have $n$ data points and I want to estimate $f(x)$ at $m$ locations, where both $n$ and $m$ are large. Are there any common algorithms for computing locally linear regression estimates at all ...
2
votes
1answer
35 views

Choosing a line/plane to separate two classes of binned data

In high energy physics I know it is common task to find the best separation point between two classes of data, usually signal and noise. This separation point is usually determined by first binning ...
1
vote
2answers
133 views

Inverted nonparametric rank test

I have two related samples, for which I want to prove they are not significantly different (normally you would test for the opposite, i.e. samples are significantly different). If I use Wilcoxon ...
1
vote
1answer
45 views

Critical value for Wilcoxon one-sample signed-rank test in R

I am trying to find the critical value for the Wilcoxon one-sample signed-rank test. Currently, I can find the value using tables. I looked at qwilcox() in R, but ...
2
votes
1answer
106 views

Local polynomial regression: Why does the variance increase monotonically in the degree?

How can I show that the variance of local polynomial regression is increasing with the degree of the polynomial (Exercise 6.3 in Elements of Statistical Learning, second edition)? This question has ...
0
votes
0answers
11 views

Is there a blocked replicate test like Friedman Test, but for data across different populations?

I'm working on my analysis for a thesis project. I have two years of data, where I measured number of bats approaching boxes. The boxes are set into replicates, with each replicate having 5 treatment ...
1
vote
0answers
8 views

Variance decomposition of fixed factors and stochsticity

I am running a model sensitivity analysis of a model that yield results based on several (fixed) input parameters and some randomness (stochasticity). So in order to get the sensitivity of the model's ...
1
vote
0answers
29 views

Non parametric version of Hotelling's $T^2$

Is there a non parametric version for Hotelling's $T^2$ test? Namely, the one group test for location (not the two group).
1
vote
1answer
51 views

Using ANCOVA when the covariate is not normally distributed

I have conducted a repeated-measures ANOVA, but a reviewer suspects that the observed main effect of condition are due to a the difference between hit rates of two conditions (one of them is ...
0
votes
0answers
33 views

Example of parametric and non-parametric method

I have not understood this example from wikipedia. Suppose we have a sample of 99 test scores with a mean of 100 and a standard deviation of 1. If we assume all 99 test scores are random samples ...
2
votes
1answer
59 views

Non-robustness of parametric statistics

Why is parametric test considered to be non-robust ? Or, why is parametric test not considered to be robust?
2
votes
1answer
31 views

Parameters in a non-parametric model

I have not understood this Wikipedia statement: The difference between parametric model and non-parametric model is that the former has a fixed number of parameters, while the latter grows the ...
1
vote
1answer
61 views

Can one do GLM with LOESS transformed variables

I have binary valued classification variables, and predictors that are not really performing great in GLM with probit/logit model. Some of the predictors are also correlated with each other. I am ...
2
votes
0answers
65 views

Where is the maximum bias and variance in a histogram as non-parametric density estimator?

I am a little bit confused about bias and variance of non-parametric density estimators and hope you can help me. Assuming a constant bandwidth and sample size, I am wondering at which points of the ...
0
votes
0answers
31 views

Confidence intervals for median from Wilcoxon signed rank statistic

We are given the sample $X_1, ..., X_n$ from a common distribution with median $\mu$. Using Wilcoxon's signed rank statistic, how can I construct a confidence interval in terms of the order statistics ...
1
vote
0answers
49 views

non normal data - bootstrap pearson r or kendall tau?

This may be a follow up on these questions: Pearson's or Spearman's correlation with non-normal data How robust is Pearson's correlation coefficient to violations of normality? ...
0
votes
1answer
19 views

Test to determine correlation between organism size and concentration?

I have a gamma distribution. I am looking to determine if higher concentrations of a toxin are correlated to larger organism size. I think a non-parametric test would be best, but I'm not sure which ...
3
votes
0answers
20 views

Kolmogorov-Smirnov test: horizontal variant?

The Kolmogorov Smirnov test is based on the maximum vertical distance between the ECDFs of two provided samples. Is there a variant that checks the maximum horizontal distance?
0
votes
0answers
20 views

Nonparametric alternatives to 1-way anova?

Are there non-parametric alternatives to one-way analysis of variance? Ideally, I am looking for something that is easy to understand and can be done in SPSS.