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

learn more… | top users | synonyms

1
vote
1answer
10 views

non parametric or parametric test for means of groups?

I have a series of experiments that are done in a series of blocks(groups). When comparing the means of group 1 and group 2 that arent statistically significant p=0.84. However looking at the group 1 ...
1
vote
0answers
9 views

Different kinds of minimax convergence rates

Stone (1980) provides a minimax rate of convergence $a_n$ for pointwise estimation of a regression function, defining it as $\lim \inf_n \sup_{\theta \in \Theta} P_\theta( \hat{T}_n - T(\theta) > ...
0
votes
1answer
18 views

Wilcoxon signed-rank test for proportion variable response?

My response variable is a proportion. The explanatory variable is categorical with two levels which are not independent. The distribution of the response variable is different from normal. ...
0
votes
0answers
12 views

Inaccuracy of Non-Parametric Bootstrap for great sample sizes in Excel-VBA

My aim is to evaluate the performance of parametric and non-parametric Bootstrap under specific circumstances; and particularly their ability to capture the population mean within their produced ...
0
votes
1answer
18 views

Wilcoxon signed-rank test

While reading Wikipedia, and my teacher's notes, I found that Wilcoxon signed rank test for n>10 is given like below: Under null hypothesis, W follows a specific distribution with no simple ...
0
votes
0answers
9 views

Comparing accuracy of two non-parametric predictors

I have a quantity x_i that I have n measurements for. I also have for every point two separate non-parametric and non-symmetric distributions A_i and B_i that are supposed to predict the quantity ...
2
votes
2answers
106 views

Is there a non-parametric Coefficient of Variation?

I was reading a paper where the author mentions: "The coefficient of variation is primarily a descriptive statistic, but it is amenable to statistical inferences such as null hypothesis testing or ...
0
votes
0answers
18 views

Nonparametric data (Friedman)

Suppose you have data as follows: ...
0
votes
1answer
31 views

Non-parametric test of difference for zero-inflated data

I have zero-inflated (~90% zeros) data which is distributed like the left-hand figure above (the right-hand figure shows how when log-transformed, the non-zero component of the distribution is ...
1
vote
0answers
97 views

What statistical analysis should I use for this (attached) dataset?

I have a dataset of 815 positive examples and 9492 negative examples for a certain class. Each example is represented by 12 features and a target label (i.e. TRUE/FALSE). The dataset is in a CSV file ...
2
votes
0answers
92 views

Question about the answer to “Local polynomial regression: Why does the variance increase monotonically in the degree?”

I appreciated Marco's elegant answer explaining why the variance of a local polynomial regression increases monotonically in the degree. However, in the end of the proof, I find difficult to calculate ...
0
votes
0answers
16 views

Is the Fisher's exact test “parametric” or “non-parametric”?

It is not clear to me whether we can consider the Fisher's exact test as a "parametric" or "non-parametric" one. My gut feeling is that it should be defined as "parametric" as it involves a fully ...
0
votes
0answers
13 views

Questions about Data Envelopment Model Mean-time values?

I'm planning to do a Data envelopment model with one quality input and one economic input. It's input oriented and with constant returns of scale (CRS) I wounder first: Is it possible to restrict ...
1
vote
1answer
59 views

Probability of an unknown distribution

I have the sample of a variable $X$ whose distribution is unknown and I would like to know how to estimate the probability of $X$ taking some values. How can I do that? I assume that there's a non ...
0
votes
1answer
28 views

Assumptions of additive model

An additive model takes the form: $y=\alpha+f_1(x_1)+f_2(x_2)+...+f_p(x_p)+\epsilon$ If I've understood correctly, there are only two assumption on the errors: - errors have mean zero - errors are ...
0
votes
0answers
19 views

Coefficient of variation for non-normal populations?

If samples of prices of different items are taken and I want to compare the variation in prices between the items can I simply use the coefficient of variation to do so? Or, in order to do this ...
0
votes
0answers
17 views

Criteria for comparing parametric and nonparametric approaches

I have a real data set of size n = 50 and I would like to compare some parametric and nonparametric (for example spline function) density estimation. Which measure should I use to assess their ...
0
votes
1answer
41 views

non equal variances alternative for kruskal wallis anova

I have a dataset with a total of about 6 groups set up, and there is a minimum of n=150-200 samples per group. Now when I look at the data, its not normally distributed, and the variances are not ...
1
vote
1answer
69 views

What descriptive statistics to report for non-normal data

Let's say I run an experiment with one dependent variable and three experimental groups. In the end I would like to report both the results of a statistical test to know if there are any group ...
1
vote
0answers
11 views

MANOVA: What to do with a u-shaped DV?

I am hoping to get some advice on my analysis for my MSc dissertation. I will try to keep it short but please let me know if there is more information I can provide to make the situation clearer. ...
0
votes
1answer
20 views

Variance of Wilcoxon Rank-Sum Test (no ties)

$\newcommand{\E}[1]{\mathbb{E}\left[#1\right]} \newcommand{\r}[1]{r\left(#1\right)} \newcommand{\P}[1]{\mathbb{P}\left(#1\right)} \newcommand{\Var}[1]{\text{Var}\left[#1\right]}$ Given two sets of ...
1
vote
1answer
18 views

Wilcoxon Rank-Sum Test $H_1$ notation

This notation is from Nonparametric Statistical Inference, 5th ed., by Gibbons and Chakraborti. On p. 290, it states: Wilcoxon (1945) proposed a test where we accept the one-sided location ...
2
votes
0answers
26 views

Alternative to ANOVA (beginner)

I have run 15 experiments to compare the effect of different hormone combinations on the maturation on Xenopus oocytes (immature eggs). I am hoping to find the best performing variable. I have 4 ...
2
votes
0answers
15 views

Kolmogorov-Smirnov vs. Kuiper test

I would like to compare two 2D distributions with quantitative variables, illustrated here: For each "x", they are several measures "y". I can't assume these distributions are parametric. A ...
0
votes
0answers
27 views

Hypothesis testing: does a single sample belong to the population represented by many other samples

I have categorical data for the abundance of genes involved in particular metabolic pathways, ranging from 0 to 1 for each metabolic pathway. I have 15 samples that belong to a "wild-type" condition, ...
0
votes
0answers
7 views

Two-way ANCOVA with count data— Poisson model in SPSS

I am attempting to compare the number of eating episodes by gender and diagnosis (4 levels), adjusting for BMI and age. I am assuming that a Poisson model would be preferred over a factorial ANCOVA ...
0
votes
0answers
16 views

Non-parametric alternative to a mixed anova?

My data fails assumptions of variance - (norm dist is good though) - and I was wondering if anyone had a suggestion for an alternative to a mixed anova? Three repeated measures (Test 1, Test 2, Test ...
43
votes
14answers
3k views

Why would parametric statistics ever be preferred over nonparametric?

This may be a stupid question but it's been bugging me for years. Can someone explain to me why would anyone choose a parametric over a nonparametric statistical method for hypothesis testing or ...
0
votes
1answer
29 views

How do you do a nonparametric quantile regression in SAS?

I want to do a nonparametric quantile regression in SAS and I can't, for the life of me, figure out how to do it. All the examples I see don't do a good job of explaining the code that is used and why ...
1
vote
0answers
24 views

Combining data from different locations to test difference in populations

I have (irregularly spaced) times series concentration data for four locations and am trying to discern whether or not there has been a change in concentrations after a particular event. To avoid ...
1
vote
1answer
23 views

Kruskall-Wallis test. How many degrees of freedom to report?

I have run a kruskall-wallis test to see if there is a significant difference in the amount of fish at each site. There are three sites (Site1, Site2 and Site3), with 80 observations of fish in each ...
4
votes
1answer
58 views

Rank and z-transform instead of Wilcoxon?

Andrew Gelman in a recent post in his blog suggests using a rank, transforming the rank to a z-score, and then using parametric tests and tools instead of performing non-parametric tests. I never ...
1
vote
0answers
24 views

Confidence intervals for Kendall's tau-b

I am working on some stats coursework, and have non parametric bivariate data. n=19, so small sample. There are a number of tied ranks, so I'm planning to use Kendall's tau-b rather than Spearman's, ...
0
votes
0answers
20 views

Nonparametric equal variance tests

I have two large, non-normal samples as evidenced by the Kolmogorov-Smirnov test. I now wish to test for equality of variance nonparametrically. I'm confused as to which nonparametric test is ...
0
votes
1answer
36 views

Non parametric: How to detect different groups

I have data sets for different serial numbers of devices. Those data are not following a normal distribution. I would like to know which serial numbers are behaving differently from the overall ...
0
votes
0answers
20 views

Volume for Parzen window and $k_n$ Nearest Neighbors density estimation

In Parzen window estimate, suppose we want to estimate the density at $x_o$, what we do is raise, say a uniform kernel at $x_o$, find number of points falling in the box, which is $k_n = ...
1
vote
0answers
44 views

Comparison between groups with one group normally distributed, and the other skewed

I want to compare continuous numerical variables between two groups. Sample size is small (27 for one group and 43 for the other). I use Shapiro-Wilk test to check for normality of distribution of ...
2
votes
1answer
34 views

Spearman's correlation as a parameter

Spearman's rank correlation for a bivariate sample $\{ (x_1, y_1), (x_2, y_2) , \ldots , (x_n, y_n) \}$ is generally defined as the correlation between the ranks of the observations, but what is the ...
1
vote
0answers
44 views

Comparing several asymmetric distributions

I have constructed 3 toy distributions using R ...
0
votes
1answer
7 views

Detecting outlying distributions of ratio data

I have a dataset consisting of hundreds of repeat observations on thousands of agents. Each observation is a ratio between two distance measures, A and B, where A is always larger than B. Thus, my ...
5
votes
1answer
128 views

Difference between LOESS and LOWESS

What is the difference between LOESS and LOWESS? From Wikipedia I can only see that LOESS is a generalization of LOWESS. Do they have slightly different parameters?
1
vote
0answers
18 views

Choosing to adjust or not after Kruskal-Wallis rejection

I have a series of data (4 numerical variables) and 4 categorical variables (with multiple factors each). I need to test for differences between various subsets based on the categorical variables. ...
4
votes
1answer
66 views

Dunn's test p-values in R are exactly half those in SPSS and GraphPad for the same data

Firstly, this is my first post to Cross Validated, so apologies in advance if I have infringed any conventions. I am writing up a PhD thesis on aspects of biomedical research, and use R for my ...
0
votes
0answers
9 views

Comparing the degree of “spatial clustering” of a response variable across different treatment groups

I have a neuroscience dataset consisting of unpaired data obtained from cells recorded under either control conditions or an experimental manipulation. For each cell I have recorded its spatial ...
0
votes
1answer
21 views

Applying a non-parametric ANCOVA to the interactive effects of multiple explanatory variables.

I am having a few issues processing some data in that the number of samples is far less than originally anticipated. In a control and impacted design, there are 11 samples each. I thought this seemed ...
0
votes
0answers
9 views

what is the most suitable method to compare percentage values if there are no mean (no replicates)

I have a problem with my data analysis part in my final year research thesis. I measured methane generation efficiencies (percentage values) for 3 different biogas reactors for 2 months. But data in ...
0
votes
0answers
17 views

non parametric analysis of variance in small, unbalanced data set

I'm facing a data set composed of five different dependent (1,2,3,4,5) and three independent (I,II,III) variables. 1,2,3,4,5 are continuous but not normally distributed. I,II,III are qualitative, I ...
0
votes
1answer
49 views

Which ones of $n$ random variables have the largest mean (non-parametric way)?

Let us have $n$ random, mutually independent variables $X_1,X_2,\dots,X_n$. Let us have some samples of them such as $x_{i,j}$ where $i=1,\dots,n$. I want to know the maximal variable(s) based on ...
0
votes
0answers
34 views

permanova or non-parametric test for multiple explanatory variables and interaction

Hi I am trying to find a test to analyse the following data set. Response variable is failure or success (0 and 1) measured over 4 time points, under 2 different treatments (light and temperature) in ...
0
votes
1answer
44 views

Non parametric analysis

The my dataset is not normal distributed. In order to apply a non parametric analysis, exist only the Kruskal Wallis test or others? I need to find a test similar to ANOVA to apply a dataset not ...