2
votes
1answer
30 views

What is the duality relationship between eigensystems of X X' vs X' X?

I want to know the relationship between the eigensystems of two non-negative-definite (covariance-like) matrices. Both are derived from X which is a T-by-K real matrix (wlog say K > T). I avoid ...
2
votes
1answer
9 views

Filtering to avoid the Slutsky-Yule effect in a moving window average?

Can anyone suggest a generally accepted method of filtering time series data to avoid the appearance of artifactual oscillations when smoothing the data using a moving window average? Is it simply a ...
0
votes
1answer
27 views

Daily data, different dates

I have downloaded two different daily data sets, both for the same period. Together I want to use them to construct data for another variable. However, the problem is that the dates do not exactly ...
0
votes
0answers
12 views

How to Schedule R Activity [on hold]

I am having following requirement, 1. Run R regression techniques on mainframe Data 2. Do visualization and save it for business users My questions are, What is the best way to integrate R with ...
0
votes
0answers
5 views

Training an Elman Recurrent Neural Network?

I have few doubts related to training Elman RNN using Backpropagation Through Time Algorithm. Assume, I present a sequence to the network and the network adapts the parameters based on the error ...
3
votes
1answer
21 views

Metropolis : Set first sample value instead of randomly generate an arbitary value

According to Metropolis-Hasting algorithm, the first sample is an arbitrary value generated randomly at the Initialization step. ( http://en.wikipedia.org/wiki/Metropolis%E2%80%93Hastings_algorithm ) ...
2
votes
1answer
19 views

What are some standard bimodal distributions?

I have plotted this curve using the default kernel density estimate function in R I am looking for some standard distribution which could be close to this. Is there any standard bimodal distribution ...
1
vote
1answer
8 views

Does VECM use the stationary series or the originals ones?

I have some cointegrated series and I decided to build a VECM model. (I differentiated them twice in order to get stationary series and that led me to believe that they might be cointegrated - I ...
1
vote
1answer
15 views

What is the right way of computing baseline hazard rate

What is the right way of computing baseline hazard rate? To my understanding hazard rate at time t is simply #events / #AtRisk ...
4
votes
1answer
28 views

Why exactly is normality an assumption in a T-test but not a Wilcox rank sum/Mann Whitney U test when obtaining a p-value?

In addition to the question, please do correct anything below that I have incorrect. I understand how the test statistics for a t-test and WRS/MWU test are calculated. In a t-test, $t=\frac{\bar ...
3
votes
1answer
24 views

Stein's estimator vs James-Stein estimator

I read a lot of sources concerning stein's estimator and James-Stein estimator. Unfortunately, a lot of sources do not write the correct formulas of each estimator. And so I am now confused!! Kindly, ...
0
votes
0answers
31 views

Using Dirac Delta functions for estimating a probability distribution

I'm having some trouble understanding this slide. It's mentioned in the context of gaussian distributions. I sort of understand the Dirac delta "function". The main difficulty I'm having is with ...
0
votes
0answers
8 views

Calculating the covariance of effect sizes for multiple-treatment multiple-enpoint studies

I'm interested in finding the covariance of effect sizes for multiple-treatment multiple-outcome design given the scenario below. Gleser and Olkin (2009) provided the formula for the estimating the ...
1
vote
0answers
9 views

online bin packing and machine learning

I am trying to optimize scheduling disk allocation in data centers. In nature it is an online bin packing problem. But, since each customer has it's own behavior or kind of workload I was wondering, ...
0
votes
0answers
7 views

Obtaining wide Confidence Intervals from a fitting of a model with 2x2 Crossover trial data. Where am I going wrong?

I am doing an analysis of a 2x2 crossover experiment with ordinal output. And it seem that the effect of the treatment (trt) is statistically significant. However my CI are very wide [1.05, 364.23]. ...
1
vote
0answers
12 views

How to treat different (multiple) measurements on the same subject over time?

Let's say I am interested in some microscopic measurements on a subject, for example, the pore sizes on my hand. I want to see how putting my hand under a humidifier changes the pore size over time, ...
0
votes
0answers
7 views

Signal detection theory: optimal criterion with unequal variances

Is there a formula for the optimal cut-off for signal detection theory with unequal variances? To put this in another way, if I assume two approximately normal distributions with different means and ...
0
votes
2answers
23 views

Clustering methods based off set membership

So most of the clustering algorithms I've looked at are based on the distance between points. I was wondering if anyone knows any simple clustering algorithms based off points making up a set. ...
1
vote
1answer
19 views

Why pnorm function and sum of dnorm function differs for same input?

Data is height of men in 'inches'. Mean is 70. SD is 3.3 I wanted to compute the probability of men whose height is in between 69 inches and 74 inches. The following methods gave me different ...
0
votes
0answers
4 views

Determining a fit test for a interupted stochastic data

I have 10s of thousands of linear data tracks (DNA sequence abundances) which I am attempting to classify by their adherence to a theoretical model. My first pass approach was quite naive, defining ...
3
votes
1answer
45 views

Simulating non-normal correlated data for Bayesian regression

I'm interested in generating data for three separate datasets where each contains three IVs and a single DV that are correlated with one another based on meta-analytic data. For example, I would like ...
0
votes
0answers
7 views

Where is the Vowpal Wabbit SGD objective function specified? [on hold]

I am new to Vowpal Wabbit, and have been reviewing everything I can find on it. I am interested in using SGD to optimize a fairly large problem with a few hundred parameters several hundred prediction ...
0
votes
1answer
18 views

AIC values “Without Covariates” in R [on hold]

I've been using SAS but I'm now transitioning to R. When doing cox-regression in SAS (proc phreg) the output included AIC values "Without Covariates" and "With Covariates": The difference between ...
0
votes
0answers
9 views

interpretation negative binomial

I have a question towards an analysis of purchasing decisions. I have a data set where I investigate the amount of previous purchases last week (predictor) on the amount of purchases today (response ...
3
votes
1answer
22 views

R lmer confint: theta values not the same as summary values

I've been using lmer's confint procedure to compute bootstrapped confidence intervals for random effects. I noticed that extracting the theta values using "getME" produces estimates that are slightly ...
0
votes
0answers
12 views

Estimating transition probabilities from the sequences without repeated states

Is it possible to estimate transition probabilities of the continuous process if we observe only the first occurence of the state? For example, if the real transition sequence was 1 - 5 seconds; 2 - ...
2
votes
3answers
21 views

Non-normal univariate distribution — how to define “low” to “high” subsets of values?

Sorry for the dumb question: it's been a million years since I took basic stats. I have a set of 48, non-normally distributed values ranging from 1 to 100. I'd like to be able to apply a (valid) ...
0
votes
0answers
14 views

Negative coefficient for expected return, what does it mean?

I'm estimating a set of parameters in a utility function $U=\alpha\ \text{payment} -\beta\ \text{investCost}+ \text{error}$ The payment and investCost are expected return (payment) and cost, and ...
0
votes
1answer
25 views

Citing articles as references for the Leave-One-Out Method

I wish to know which work(s) should be cited as reference(s) for the Leave-One-Out method.
0
votes
0answers
20 views

How to Conduct a Multi-Level (3 levels) SEM in R

I've been told that there isn't a way of conducting a multilevel (3 levels) SEM analysis in R. I then found the package xxM http://xxm.times.uh.edu/get-started/ while searching online for a solution. ...
0
votes
0answers
30 views

R function for Matrix Multiplication and Addition [migrated]

After performing SVD on a matrix, I would like to create a function (I'm not good with functions in R yet) that creates a reduced matrix per my specified n-value. For instance, here is the R code for ...
-1
votes
0answers
20 views

Project Success Probability [on hold]

If there are two years of projects, the first year project has probability 0.7 of being high, and there is a .30 probability that both years will have success, but a 0.10 probability that both ...
1
vote
0answers
23 views

What is “the best” way to approximate moments of two distributions if they cannot be matched exactly?

I am trying to approximate one distribution with another by matching their first two moments. However, due to a discrete (integer) nature of parameters of the approximating distribtuion, it is not ...
1
vote
0answers
17 views

Interactions and PCA

I have a linear model that requires a large number of interactions (there are as many interactions as there are IVs) and I want to reduce colinearity using PCA, then regressing the DV on the principal ...
3
votes
1answer
56 views

How to detect noisy datasets (bias and variance trade-off)

Studying the bias-variance trade-off: expected loss = bias + variance + noise I understand that we minimize this quantity by finding the "best" balance between ...
0
votes
1answer
20 views

Relative Importance of categorical variables

My question concerns management issues more than statistical theory. I am searching for a way to measure the relative importance/influence of categorical variables in a logistic regression model with ...
1
vote
0answers
18 views

Directed acyclic graphs in regression model

I am using DAGs to select best set of variables for my logistic regression analysis. Assessment of DAG includes one exposure, number of covariates and an outcome variable. I have not found any ...
0
votes
0answers
23 views

lme4: Why won't lsmeans output my fixed effects?

I'm trying to plot confidence intervals for linear mixed effects models trained with lme4 and lmerTest in R. I am using this data file, which I've shared via Google Drive. Here is my trained model. ...
0
votes
1answer
13 views

Smoothing a particle filtered 2D trajectory

I am currently developing a very basic particle filter for a 2D robot localization task. My process is defined by a really simple velocity / steering angle based motion model. I am re-weighting the ...
1
vote
0answers
22 views

Median-computation (“grouped median”). Problem with gmedian-computation in SPSS

In my basic-statistics course I wanted to delve deeper into the problem of the (grouped) median-computation and did some computations using SPSS. The protocol seems to indicate either a different ...
1
vote
0answers
38 views

Imposing a model on a pdf

(This question is an attempt to zoom in on the key issue in this question using as little information as possible.) Lets say I want to derive the likelihood function of $\beta$ given $x$ and $y$ for ...
1
vote
1answer
14 views

Johansen cointegration test: interpretation of results in EViews

I am not sure whether I am interpreting the cointegration test correctly. This is the test result: Because of the probability of the test I understand that my series are cointegrated of order 2. ...
0
votes
1answer
40 views

Understanding neural networks and classes

I want to know if this argumentation is valid or not of my algorithm. I'm trying to implement a CBIR (Content-Based Image Retrieval) where I've used the basics on CBIRs (colour, texture, shape, ...
1
vote
1answer
42 views

What makes the recommendation problem unable to be solved by traditional machine learning algorithms directly?

We have collaborative filtering and content based algorithms there for recommendation. What stops traditional algorithms from directly being used to find missing values in the Utility matrix ...
2
votes
1answer
27 views

Is continuous inputs an assumption of factor analysis?

Should we use only continuous inputs for factor analysis (FA)? My data is a mix of continuous and categorical inputs: one of the inputs has only 600, 700 and 1000 as values. I found that principal ...
0
votes
0answers
12 views

Lowering C parameter increases the number of support vectors

I know that the C (cost) parameter controls the trade-off between model complexity and misclassification. A large C should increase the error weight, and therefore the model complexity. Nevertheless, ...
2
votes
1answer
26 views

What are the formulae used in R by predict.lm when interval= a) 'none', b) 'prediction', and c) 'confidence'?

The references provided in the R documentation for predict.lm, taken together, actually leave open a number of possibilities for the formulae for confidence and prediction intervals (including the ...
0
votes
2answers
21 views

How do I calculate clustering of symptoms?

I am trying to assess whether a risk factor (A) has an impact on clustering of 3 types of symptoms (B, C, D). I know that A has a significant association with B, C, and D. So first I did a ...
0
votes
0answers
28 views

Double hierarchical GLM reports non-conformable arguments error [on hold]

I am new modeling and I am trying to analyse my data using the package Double Hierarchical Generalized Linear Models. However, I always get the same sort of error: ...
1
vote
0answers
12 views

Running Latent Dirichlet Allocation (LDA) on word counts

I have difficulties understanding the VB implementation lda-c. In particular, the method expects as input a bag-of-words representation of documents, where distinct words appearing in a document are ...

15 30 50 per page