Procedures that rely on relatively few assumptions about underlying probability distributions.
2
votes
0answers
18 views
Kernel density estimator that doesn't collapse in the tails
I have iid datapoints $x_1, \dots, x_n$, generated by an unknown density $f(x)$.
So far I have approximated $f(x)$ with a normal $N(\hat{\mu}, \hat{\sigma}^2 )$, where $\hat{\mu}$ and $\hat{\sigma}^2$ ...
1
vote
0answers
23 views
Causal identification and penalized splines
I just got a rejection from an economics journal. Among the reasons cited for rejection were:
the benefits of using the semi-parametric method are not clearly
brought out compared to ...
2
votes
0answers
27 views
How to test group difference between nominal and ratio data with nonparametric tests?
In my data the dependent variable ‘vocabulary uptake’ is measured as scores ranging from 0-10 and the independent variable is yielded from a ‘reading intervention’ with 4 different reading conditions ...
0
votes
0answers
21 views
Estimation of conditional CDF vs PDF, practical differences
I'm trying to figure out where and when one would opt to work with the conditional cdf $F(y|X=x)$ rather than the pdf $f(y|X=x)$. I am thinking of $y$ as being a real valued response, and $x$ as being ...
1
vote
1answer
32 views
Checking autocorrelation in non-parametric methods
I would like to forecast short-term electric load by using Artificial Neural Network and Support Vector Regression. However, there's one question that sticks in my mind. In such forecasting with ...
5
votes
2answers
199 views
Is logistic regression a non-parametric test?
I recently received the following question via email. I'll post an answer below, but I was interested to hear what others thought.
Would you call logistic regression a non-parametric test? My ...
2
votes
1answer
45 views
Mean squared error definition
I'm currently working through (part of) a textbook on non-parametric regression techniques. Regarding the choice of smoothing parameter the book starts out explaining the MSE which is defined as:
...
1
vote
0answers
32 views
Two-way anova with interaction term: what is the point of a post-hoc test?
I have a statistics interpretation question. I've recently performed a two-way anova to identify an interaction term between my categorical independent variables (genotype + temperature) that ...
1
vote
0answers
23 views
Distributions whose domain are themshelves a distribution
Dirichlet process, Pitman Yor processes and their variants are special types of distributions whose domain are themshelves a distribution. Is there a name to refer to these distributions in general? ...
1
vote
0answers
16 views
Characterizing uncertainty in empirical PMF of unknown discrete random distribution
Suppose a discrete random distribution $X$ which takes integer values in some small (but not binary) range, e.g. $[0, 255]$ and whose true pmf is unknown (however, the null hypothesis is that it is ...
0
votes
0answers
19 views
Is it justified to say after U Mann-Whitney test that there is a “possibility to differentiate”?
I have 2 variables (similar measurement of 2 structures in same individual) with non-normal distribution, so I compared ranks with U Mann-Whitney test. The result was significant (p=.01). Is it ...
2
votes
1answer
57 views
Can I use 95%CI for mean for non-normal distribution if there is a natural limit?
I have problem with real basics. I have variable that has p=.000 in Shapiro-Wilk. As I looked on the histogram it appears that the cause is natural limit for this measurement (value 0, skewness > ...
1
vote
1answer
32 views
All vs One non-parametric test?
I am currently analyzing several repeated measures with several treatments. That is: 33 individuals and 4 different conditions. The box plots that are shown from left to right indicate the treatments ...
2
votes
1answer
76 views
Introductory textbook into nonparametric Bayesian models?
I'd like to wrap my head around this topic but learning from white-papers and tutorials is hard because there are many gaps which are usually filled in textbooks.
If it is important I have ...
1
vote
0answers
33 views
Computing a bootstrap confidence interval for the prediction error with the percentile and the BCa method
I have two related questions regarding the computation of a non-parametric bootstrap confidence interval for the prediction error.
Setting: I have a sample S from a data population P and a learner L, ...
1
vote
0answers
27 views
Learning parameters of non-parametric Bayesian models
I have a sample of Chinese restaurant process which I want to model as Pitman–Yor process. How do I determine parameters of Pitman-Yor model from given sample?
For Dirichlet process I would just use ...
1
vote
0answers
33 views
Analysis of computer software performance
I am currently collecting data from a software system that draws conclusions about the nature of certain structures in medical CT chest scans. Structures in the chest can be classified into four ...
1
vote
1answer
41 views
how to analyze pre-post attitudinal data (ordinal) collected from a group of 60 students?
I have a survey with 25 items that were administered pre and post an intervention. Each item had four possible responses: (1) Not Appealing at all; (2) Not Appealing; (3) Somewhat Appealing; and (4) ...
1
vote
1answer
68 views
Parametric vs non-parametric tests
How to test statistical difference of a mean (or median?) concentration of an enzyme between two groups of patients where distribution in one group is normal, whereas in other is non-normal? ...
1
vote
0answers
17 views
Nonparametric analysis of continuous variable from matched case control
I have a continuous variable which is measured for cases and controls, which have been matched in a 3 to 1 fashion. The distribution of this variable is very skewed, so mixed models won't seem to cut ...
2
votes
2answers
66 views
Estimation of the density/distribution
Let $(x_i,y_i,z_i)_{i=1,\dots,n}$ be an i.i.d. sample of $(X,Y,Z)$. How one can estimate the following object
$$\int_{-\infty}^xf(\bar x,y|z)\mathrm{d}\bar x$$
where $f(x,y|z)$ is a density of $X,Y$ ...
0
votes
1answer
52 views
Naive Bayes with Density estimation
The way I understand the Naive Bayes estimators is that the characteristic (or naive) assumption is that all Features are conditionally independent.
Now on top of this assumption, for continuos ...
4
votes
3answers
214 views
How to test my data against an specific normal distribution?
I need to test my data to see if it follows a normal distribution with specific mean and std like N~(mu, std) I know that this can be done by Kolmogorov-Smirnov test which has a function in both ...
0
votes
0answers
25 views
non-parametric equivalence /non-inferiority for ratio variable?
I'm comparing subjects' success rates in two conditions A and B. All subjects run both conditions, so the data is paired. Each subject runs say 8 trials in both conditions, with 0 or 1 as output. The ...
4
votes
1answer
85 views
Histogram with uniform vs non-uniform Bins
This question describes the basic difference between a uniform and a nonuniform histogram. And this question discusses the rule of thumb for picking the number of bins of a uniform histogram that ...
3
votes
0answers
81 views
Kolmogorov-Smirnov and bootstrap
The KS test uses the statistic
$$
D_n=\sup_x |\hat{F}_n(x)-F_0(x)|
$$
where $F_0(x)$ is the distribution to be tested and $\hat{F}_n(x)$ the empirical distribution. Under the null hypothesis $D_n$ is ...
2
votes
0answers
39 views
Two uneven groups (101 vs 21) measured twice; what repeated measures ANOVA equivalent can help?
I have a question that I have difficulties in answering:
I have two groups of patients tested twice at the same continuous variable.
Group A=104 & GroupB=21.
So two groups, one continuous ...
0
votes
1answer
41 views
Ranks test problem
This is a questions I got for homework in test planning and variance analysis. I apologize in advance for the way my professor phrases things :D
I would love to hear hints or tips on how to approach ...
2
votes
1answer
46 views
Repeated measures, between-groups non parametric test?
I have read a few posts on related topics but can't seem to figure out which test would best apply in my study. What I have is ordinal data from the same questions taken at two points(W1 and W2). ...
1
vote
1answer
75 views
Data-driven removal of extreme outliers with Naive Bayes or similar technique
I have a large set of location data from a social network and would like to conduct a mobility study with it. For each object, I have up to several thousand locations where this object posted from. I ...
2
votes
0answers
104 views
How to interpret results from non-parametric ANCOVA?
I 'm new to the CV and not very good at statistic:) I would much appreciate some help on a non parametric ANCOVA in R sm package.
I do a pre post analysis on a set of pre/post variables of two groups ...
1
vote
1answer
46 views
Randomization Tests
The following data are mandible lengths (mm) of 10 male and 10 female golden jackals Canis aureus in the collection at the British Natural History Museum. The two samples are independent.
...
0
votes
1answer
119 views
Kolmogorov Smirnov conflicts with visual data
I recorded the length of 197 nursing care episodes. My normalised data $(x-\mu)/\sigma^2$ looks like this:
Kolmogorov-Smirnov gives me a p-value of 0.14. Can't be right surely?! Am I ...
2
votes
0answers
44 views
How do you think about the central estimate when the confidence interval is asymmetric?
I'm using a wild bootstrap to create confidence intervals around fitted values of the following model, for a specific combination of the factors, as x varies across its range.
...
1
vote
1answer
39 views
Non-parametric test for 3 matched-pairs?
I showed a video to 3 groups, and they answered questions before and after the test.
Control group watched it with no ads
Group A watched it with ad A
Group B watched it with ad B
The sample is such ...
0
votes
1answer
203 views
Kruskal-Wallis test of groups with unequal sample sizes matlab
I can't seem to work out why I can't perform a 5 grouped Kruskal-Wallis test on unequal sample sizes in matlab. Any thoughts how to do this?
Also as a post-hoc analyis using Wilcoxon Rank sum is this ...
1
vote
1answer
87 views
All my observations are identical. Use a non-parametric test?
I was doing test for normality on variables and came across one that had identical values for each observation. I can't do a normality test. I plotted the kernel density and it looks normal, however ...
1
vote
1answer
79 views
Nelson-Aalen estimator and interval censoring/tied events
I just noticed that the Nelson-Aalen estimate of the cumulative hazard changes depends on the existence of tied events. As a toy example, consider a study with 3 patients. The patients die on day 1, ...
0
votes
1answer
84 views
Alternative nonparametric test for chi-square test for independence
suppose we have a table like this:
\begin{array}{ |l | c | r |}
\hline
& \mathrm{win} & \mathrm{lose} \\ \hline
\mathrm{male} & X_{11} & X_{12} \\ \hline
...
1
vote
1answer
80 views
Is ETA a good measure for computing the efect size between an ordinal and a nominal variable?
I have a nominal and an ordinal variable and I would like to look measure the association that is between the two. For now, I have done Chi-square test and non-parametric Kruskall-Wallis Test and I ...
2
votes
0answers
71 views
Bayesian approach to trend detection in non-parametric data
I have a series of data points, and I want to see how much evidence there is that the points are getting bigger over time. The data themselves are counts, but for various reasons I don't want to build ...
3
votes
2answers
94 views
curse of dimensionality & nonparametric techniques
I have seen it many times in a number of articles that nonparametric techniques are subject to the curse of dimensionality, which may lead to the failure of these methods. Why does this happen? Could ...
1
vote
0answers
49 views
Post-hoc analysis when variable effect is non-significant
In a dataset with 3 related measurements for each case, I ran a Friedman test, and found no significant effect.
Is it appropriate to now run (and report) pairwise tests, as I had planned initially?
...
0
votes
0answers
41 views
which test to use if you only have summary statistics? (non-normal)
Here's the basic problem: visiters to our website were randomly put into one of 7 different groups, and we want to compare the activity of users in the different groups on a downstream site. The ...
0
votes
2answers
68 views
How to correct for gender in Mann-Whitney U test?
My statistical knowledge is very limited.
I have two groups (patients and controls) and a measured concentration value for each indivdual. Not normally distributed: Mann-Whitney
How do I correct for ...
0
votes
1answer
82 views
Modeling a outcome variable heavily skewed toward 0
I am working with a data set to model student performance with various variables from the class/school/district/provincial level. Student performance is extremely low though--~70% of reading ...
3
votes
3answers
226 views
Normality assumption and sample size
I know this is a very debated topic, even on this site, but I still couldn't find an answer to my problem.
Recently I am working with large samples (300, 400 and more). For now, I am trying to use ...
0
votes
0answers
76 views
What test of independence of sample proportions is appropriate when n is very large and p is very small?
I have the (not necessarily veridical) impression that typical textbook independence tests of proportions are intended for use the proportions involved are not super small.
In my case n may be 10^8 ...
0
votes
0answers
48 views
Can you use Cox regression for more than just modeling time to event data?
Can you use Cox regression as a general regression modeling choice not just for modeling time to event data? That is, couldn’t you use a Cox regression to model any (positive) ordinal/interval ...
3
votes
1answer
116 views
Student's t vs Mann-Whitney U
Trying to choose between these two tests for data I've harvested from Android store. Basically, I want to see if there is any difference in the number of dangerous permissions requested by free vs ...
