1
vote
1answer
20 views

Method of moments for skew-t distribution

I'm trying to work out how to apply the method of moments to estimate the parameters of the skew-t distribution. From slide 12 of the following presentation: ...
0
votes
2answers
40 views

Convergence of Sequence Random Variables

I'm a bit confused by the definition of convergence of a sequence of random variables. I'm reading Wasserman's All of Statistics and at the start of Chapter 5, he writes: "Suppose that $X_1, X_2...$ ...
0
votes
0answers
13 views

Separation problem in GLM

So I think I have a separation problem in my logistic regression model. The response variable (that only takes 0 or 1 values) takes 99.2% of its cases as 0 and only 0.8% as 1. This is the ROC curve ...
1
vote
1answer
57 views

Why is my density plot just a line on the bottom?

Basically, I'm just trying to plot a curve over my histogram for the weight of a few students. lines(density(weight), lwd = 2, col = "red") However, what I get ...
0
votes
0answers
7 views

Do I have endogeneity problem if I use year-over-year change data in AR(1) model?

My dependent variable is y(t)=data(t)/data(t-4)-1 with quarterly data and the model is standard AR(1) : y(t)=a*1y(t-1)+ b*x(t)+e(t). I 1was told that due to overlapping I should have endogeneity ...
1
vote
1answer
13 views

Model matrix for linear model with multiple contrasts

I don't fully understand the concept of a model.matrix. Assume I have the following experimental design: ...
3
votes
0answers
27 views

What assumptions are made about the link function in GLM's?

There are posts in similar vein about this topic, but what I want to know exactly is whether there is a list of properties/assumptions about link functions in generalized linear models, or if the link ...
0
votes
1answer
22 views

aggregate all data by Date and ID

I have a dataset with 20 different columns and i want to aggregate all of the columns by the first two columns (Date and ID). Is there a way to say aggregate all instead of typing the names of the ...
0
votes
0answers
17 views

Likelihood function for Missing data [on hold]

I am looking for information about likelihood function for missing data. I was wondering you could help me.
0
votes
0answers
5 views

Using alternative normalization method in DESeq analysis of gene enrichment

I'm using DESeq to identify differentially expressed genes in a next-gen sequencing dataset. (DESeq: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3218662/). In my experiment, the normalization of read ...
0
votes
1answer
15 views

Preprocessing via PCA in Caret, then fitting PLS

I am dealing with quite highly-dimensional data, and am using (in R) Caret's preprocessing 'pca' method to reduce the dimensionality. However, dependent on the number of components I choose, I seem to ...
1
vote
1answer
15 views

How to connect groups if they are not large enough?

I am new at statistics and I have problem that I have no idea how to solve. I have biological data, which includes expression levels (130 patients) for different alleles (I'm analysing SNP's) of ...
0
votes
0answers
3 views

Some dependent variables repeated and others measured at one time

I am running a one-way repeated measures ANOVA where I have three variables that are collected at two time points and four dependent variables that were only measured at the end. I can't figure out ...
2
votes
1answer
20 views

Loess in gene enrichment analysis using DESeq

Often MA plots (Bland-Altman style representations of gene enrichments) are corrected using the LOESS method. Will a LOESS correction significantly affect the results of gene enrichment analysis? More ...
0
votes
0answers
14 views

How to calculate distribution of (X1, X2) conditional on (C1, C2) in statistical model?

Say that $X_{1}$ = $a_{1}$$X_{2}$ + $B_{1}$$C_{1}$ + $E_{1}$ and $X_{2}$ = $a_{2}$$X_{1}$ + $B_{2}$$C_{2}$ + $E_{2}$ where $E_{1,2}$ are jointly distributed normal with 0 mean and variance ...
1
vote
1answer
37 views

How should I test for autocorrelation in this time series context?

I have data sets in which different people estimate a certain quantity. They potentially can see the estimates of anyone who participated before them, but in practice they're only likely to look at ...
0
votes
0answers
23 views

Scale and normalization of dates

It's common to normalize the different vars before applying some kind of supervised/unsupervised learning. Which algorithm do you use with the dates? You use the day of year (1, 200, 300) and perform ...
0
votes
0answers
12 views

Understanding my serial mediation from R and creating a serial mediation model

I am having trouble understanding my serial mediation results from R. I think that my results are significant, but I'm not sure how to create a model using my results. Can R create the model on its ...
0
votes
0answers
11 views

Homogeneity of multivariate k:th cumulant

I want to show that $c_k[AXB]=(B'\otimes A)c_k[X](B\otimes A')^{\otimes k-1}$ for a random matrix $X$. This is how I started but I am not able to finish: Characteristic function ...
0
votes
1answer
16 views

what is the biological meaning of R nought equal 1 ? endemicity?

From an epidemiological model with differential equation, we can compute the basic reproductive number R0 (the number of expected secondary case per primary case in a disease free population). ...
0
votes
1answer
7 views

Comparison of two different ratings of ten variables

I am rating the quality of a product across ten dimensions D1 to D10, e.g., durability, price, advertising, etc. Each dimension receives a rating from 1 to 10 (1 = lowest, 10 = highest). I have a main ...
1
vote
0answers
44 views

How to simulate this truncated normal?

I am trying to simulate data with two values: Start is a truncated normal with mean mu, sd sigma and min 0. Finish is also truncated normal. But X% are half or less of start. How can I simulate ...
0
votes
0answers
20 views

Z-Test and Normality

Does normality apply when performing a 2-proportion Z-Test? Say for example, you're taking # of student detention/student population for January, and comparing that to # of student detention/student ...
1
vote
0answers
18 views

PLS with more variables than data points

Does it make sense to run partial least squares (PLS) on a data set that has many more columns (variables) than it has rows (data points)? I am using plsr in R. I ...
0
votes
0answers
46 views

Statistics Test Question - Help needed! [on hold]

I am really terrible at statistics and basically don't even know where to begin on answering these. Any help would be appreciated. I've googled but there is some much info that it confuses me and I ...
0
votes
1answer
29 views

k means clustering on sales geolocation data

I have geolocation data (lat and long) per customer per online purchase, and my end goal is to identify common locations per purchase per customer. (basically to see what people typically buy when ...
0
votes
0answers
54 views

Log-likelihood proof and AIC hypothesis

First of all, statistics is just not my thing ... yet (I hope!) I'm having a hard time finding out the log-likelihood equation: Given $Y \rightarrow \mathcal{N}(\mu_1,\sigma_1)$ (observation) and ...
0
votes
1answer
25 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
votes
1answer
28 views

Gaussian processes ordinal regression in R [on hold]

Is there any ordinal regression using gaussian processes implemented in R? I made a research in the Internet, but I didn't find anything.
0
votes
0answers
12 views

Comparing odds ratios - conditional or unconditional MLE

When comparing log(OR) from two contingency tables using Z-test should I use conditional maximum likelihood estimate of odds ratios (as given by fisher.test in R) or simple unconditional?
1
vote
1answer
26 views

Time-dependent variable in survival analysis using R

I am conducting a retrospective study where I have a cohort of cases who underwent the same surgical procedure. The primary outcome of the study is the recurrence incidence rate during a follow up ...
0
votes
0answers
14 views

Different results for chi square and logistic binary regression

When I run chi square and logistic regression for the same two variables I get very different results.The logistic regression is a binary regression so I it is adjusted for any other factor: My ...
1
vote
1answer
23 views

Quasi-experimental design : time series analysis

I am busy designing a medical research for my masters(epidemiology)on time series analysis, comparing the trends of Pulmonary TB bacteriologically confirmed cases before and after the introduction a ...
0
votes
0answers
19 views

Comparing the estimated coefficient in Logit versus Mix Logit, regarding the scale parameter

My question is how can I compare the estimated parameters for a logit model with a mixed logit model? I am using mlogitpackage in R and my code is as follows: ...
5
votes
1answer
85 views

Goodness-of-fit test in Logistic regression; which 'fit' do we want to test?

I am referring to this question and its answers: How to compare (probability) predictive ability of models developed from logistic regression? by @Clark Chong and answers/comments by @Frank Harrell. ...
0
votes
1answer
21 views

Composite similarity of GitHub projects

As a hobby, I'm building recommendation system which finds related projects on GitHub. I'm computing Jaccard index for each repository, based on users who gave stars: $$J(A, B) = \frac{ \left\vert ...
0
votes
0answers
14 views

Comparing categorical and numerical results simultaneously

This question is in regards to options for analysing a dataset. I have a dataset where we have 23 video clips that have been treated using three different algorithms to change how each clips looks. ...
0
votes
0answers
9 views

Graph Edit Distance - strings versus matrix-->vector conversion?

I have two adjacency matrices and I want to find the graph edit distance between them. The only implementations I'm seeing (I need this fast) is edit distances in MATLAB (sigh...) for strings. I have ...
0
votes
3answers
53 views

how to calculate R-squared in glm?

I came up with below for my glm analysis but I need to calculate R-squared to cite in the paper? anyone can help me with this please? summary(lrfit) Call: ...
0
votes
0answers
9 views

Discrepancy between Wald test and score test in Type-3 analysis in PROC GENMOD

My logistic regression model has a binomial response and 3 categorical predictors, A, B and C. A is binary B is ternary C is ternary The observations are clustered under a factor R. There are ...
0
votes
1answer
14 views

Multi-class logistic Generalized Additive Models [on hold]

I am looking for a package for three-class logit and probit GAM. I have searched and found out that ZeligGAM in R works for this but it seems that it is only applied to binary dependent variables. In ...
0
votes
0answers
30 views

Quantile of a conditional cumulative bivariate normal distribution and R Implementation

I would like to compute a quantile Z of a conditional cumulative bivariate normal distribution. I have two questions: 1) Do I formulate the problem correctly? 2) How would I compute this quantile Z ...
3
votes
1answer
38 views

What are good introductory papers on recommender systems?

I am beginning to build a recommendation system. I have users on a website and they purchase services, so I'll recommend services that commonly go along - i.e. are purchased by a single user (not ...
0
votes
2answers
34 views

Why it is popular to use stochastic gradient descent in neural networks rather than the BFGS algorithm?

I have made two solvers to implement neural networks, one is based on stochastic gradient descent (SGD) while the other is based on the BFGS (Broyden-Fletcher-Goldfarb-Shanno) algorithm. I have read ...
1
vote
3answers
61 views

Variance of an average of random variables

This seems like it should be a pretty common problem. I have four estimates of fishing effort, each with its own variance. For subsequent calculations, I want the mean of the four estimates, and a ...
0
votes
0answers
14 views

Statistical validity of association rules with low support

We have data sample with 10,000 observations. We are using association analysis to find segments with low support (< 4%) and high(er) confidence. Our rules are always in such way that on the right ...
0
votes
1answer
14 views

recode function [on hold]

Two sections of an introductory statistics class took a quiz. The highest possible regular score was 20. Some students got one point of extra credit from a bonus question. A passing grade is 60% or ...
2
votes
0answers
20 views

Allocation of design points in an experiment

I would like some hints with the following problem. Thanks for any help in advance. An experimenter wants to design an experiment for estimating the rate of change in a dependent variable Y as an ...
0
votes
2answers
47 views

Building a regression Tree with R FROM SCRATCH

I am trying to build a basic regression Tree in R FROM SCRATCH (I know of rpart, tree, RandomForest,etc.). But it is just something that I would want to code myself for my culture. In terms of ...
0
votes
0answers
10 views

Can it be as accurate to model child-variables to estimate a parent-variable instead of modeling the parent-variable directly?

With time series data, let's say you want to model the return of the S&P 500. Could you get as good or better results by modeling each stock, and aggregating them to estimate the return of the ...

15 30 50 per page