1
vote
0answers
4 views

Feature that is numeric if true, or single value if false

In regards to feature engineering for machine learning models. I would like to engineer a feature that encodes the following: value can be true and if so it will measure a numeric (maybe ...
0
votes
0answers
2 views

Survival Analysis/Frailty Model

I am trying to build a probability model for the following situation: I have a very large dataset, whose rows are users and columns are the features. All the users visit a particular store X (once ...
0
votes
0answers
4 views

Fitting data with interdependence

I have an issue, of which I'm not sure how can be solved. I'm trying to do so with Mathematica (and their stack exchange recommended I try here), but other solutions are also possible of course. ...
0
votes
1answer
10 views

sigmoid threshold for neural network

I've trained a NN for a few logical linear logical functions. I've used the sign(positive=1, negative=0) function to threshold the hypothesis. (That makes a Perceptron right?) Now I want to use the ...
0
votes
0answers
4 views

Calculating the formulas in a 2x2 contingency table?

If I was given: The total sample size The overall proportion of the sample with the exposure (risk factor) The overall proportion of the sample with the disease (outcome)The odds ratio (=ad/bc) How ...
-1
votes
0answers
8 views

Recurrence or transience of countable state space markov chain

Consider a discrete time Markov Chain with countable state space S={...,-1,0,1,...} and transition probabilities $p_{i,i+1}= p_{i,i-1},i \in$ S. Show that chain is recurrent if p=1/2 and transient if ...
0
votes
0answers
3 views

Checking for compatible conditional models

I am trying to implement MICE in R, using the package mice. I keep reading in papers that if the full conditionals we specify are compatible (they factor into a joint), then our inference is valid. ...
0
votes
0answers
4 views

Plotting error vs weights for neural networks

What is the better estimate of how well your NN is doing? Plotting how weights change with the number of iterations or Plotting how the error changes with the number of iterations ?!
3
votes
0answers
28 views

How many sides does a die have? Bayesian inference in JAGS

Problem I would like to do some inference on a system analogous to die with an unknown number of sides. The die is rolled several times, after which I would like to infer a probability distribution ...
0
votes
0answers
4 views

Under what circumstances will the log of a variable be normal, given that the variable is not normal

Let us say there is a variable that is not normally distributed. Under what circumstances will the natural logarithm of the variable be normally distributed? I have seen many articles and papers ...
0
votes
0answers
8 views

How much memory do I need to filter through dictionaries in python of 5million?

I am creating a program that has a lot of data. I am currently running it and its been 10 minutes and its still running probably about to stop it. Anyways, I am trying to make my computer faster at ...
0
votes
0answers
4 views

Optimization algorithm for dependent outcome variables

I'm in need of an (optimization) algorithm in R that can deal with dependent outcome variables. Let me give you a little example: Lets define some input variables x1, ... , xn and some categorical ...
0
votes
0answers
20 views

What are the key steps in solving Machine Learning Problem

I am trying to make a summary to myself, what are the key steps for solving a Machine Learning problem. I tried to read good books, talked with peer, discussed many issues here, checked many web based ...
0
votes
0answers
10 views

When is the scatter matrix in linear discriminant analysis singular?

In linear discriminant analysis (LDA), when there are fewer data instances than the number of dimensions, the within-class scatter matrix $S_W$ is of order $n \times m$ where $n$ is less than $m$ and ...
0
votes
0answers
3 views

Multilevel moderated mediation with multiple mediators in MPLUS

I'm trying to assess a 1-1-1-1 multilevel model with a cross-level interaction at path a. The moderator is the group mean of one of the level-1 predictors. I'm confused about how to model this and how ...
0
votes
0answers
5 views

Rank of Between Class Scatter Matrix in Linear Discriminant Analysis

In the derivation for Fisher's linear discriminant (the 2 class problem in particular), I notice that the between-class scatter matrix $S_B$ is said to have rank of at most 1. What is the significance ...
0
votes
1answer
7 views

Calculating p-value from beta and se_beta

I have a set of beta and se_beta values that I would like to calculate p-values for. I know this should be possible via a z-test, but I don't understand how it works and how to implement it. Any help ...
0
votes
0answers
9 views

Axes having different scales on a q q plot

I was trying to learn linear regression in SAS using this example When I came to the part about the q-q plot: ...
0
votes
0answers
9 views

3-way ANOVA to 2-way ANOVA

I have an experimental design with 3 factors of 2 levels each, which are temperature (a1 & a2), pH(b1 & b2) and food (c1 & c2), so I first ran a 3-way anova. Since in 2x2x2 experimental ...
1
vote
0answers
7 views

is it ok to check normality for individual groups seperated by within-subject variables in a mixed model rather than the entire dataset?

Wikipedia mentions that it is crucial to ensure normality for within-subject variables in a mixed model. I am interpreting this as I should check normality for my within-subject variables and not ...
0
votes
0answers
10 views

R - Same Density but different QQ-Plot?

I have data variable corresponding to quotation amount and I want to find which statistic law this variable follow if there is one. It seems that the ...
0
votes
1answer
5 views

Variance estimator of quadratic term of Cox PH model

I have a failure time data set. I want to fit Cox PH model with quadratic term like $h(t;x)=h_0(t)*exp(x\beta_0+x^2\beta_1)$ What will be the mathematical formula for variance of quadratic term? ...
0
votes
0answers
5 views

Determining if coordinates in a distribution are significant/goodness of fit

I have a non-normal set of data that has x and y coordinates (a non normal distribution). I'm trying to determine if I can include a few particular data points in my analysis or if I should exclude ...
0
votes
0answers
3 views

output of doParallel workers [migrated]

Suppose I have a code that does various calculations in a foreach loop, for simplicity let it be this: ...
1
vote
0answers
9 views

adjusting ties for kruskal.wallis

I would like to perform a Kruskal-Wallis test on my data. I chose this test because my data is not normally distributed. As I have identical values in my data I tried to adjust the ties for ...
0
votes
0answers
6 views

Gaussian Process: How to use GPML toolbox for multi-dimensional input?

I am using MATLAB 2014_a student version I have 198 x 9 training data x (X1,X2,...,X9) and 198 x 1 target data y For now, I got linear equation among training data and target data ,for example, ...
0
votes
1answer
16 views

HMM with final or absorbing state

I am reading about HMMs and it's unclear to me if they are required to have a final state. In particular I have seen examples of HMMs that have an absorbing state and other examples with no final ...
1
vote
0answers
13 views

Subset based on maximum difference for one variable, minimum for others

This seems like it should be an easy problem to solve, but I can't think of anything nor can I find anything to help me. I'm working with multiple data sets where I have a series of sometimes ...
0
votes
1answer
9 views

Confusion about Cross-Validation for Hierarchical Bayesian Regression Models

I had two questions regarding model selection for a Hierarchical Bayesian (HB) Regression Model and the purpose of Cross-Validation. 1). I understand cross-validation as one way to perform model ...
4
votes
0answers
16 views

what are the assumptions of ridge regression and how to test them?

Consider the standard model for multiple regression $Y=X\beta+\varepsilon$ where: (1) X is $n\times p$ of rank p (non collinearity of predictors) (2) $\varepsilon \rightsquigarrow N(0, \sigma^2I_n)$ ...
1
vote
1answer
9 views

What test do I use comparing pre and post intervention data? [on hold]

I am doing a health related project at at hospital where a policy was implemented for patients on certain therapy. Data was collected for the number of patients and days of therapy pre-implementation, ...
0
votes
0answers
5 views

How can get F-measure, precision and re call and also Cluster labels in R

I am new to R. I want to use hierarchical clustering of R to cluster following distance matrix. ...
0
votes
0answers
11 views

Different results in estimating 3PL model parameters in IRTPRO and mirt(R)

Can someone explain why I obtain different a, b, and c parameters estimates when I use IRTPRO3 and the package mirt from R? The method both uses are Bock and Aiken (1981) - IRTPRO calls BAEM and R ...
1
vote
0answers
11 views

fixed vs random regression in panel data

Anyone could explain me the differnce between fixed and random effects concerning panel data regressions? With examples? I have actually used panel data regressions for some of my predictive models ...
1
vote
0answers
15 views

Is this alternative hypothesis possible?

Could anyone check that the alternative hypothesis is valid? I wanted to prove that the "Mahalanobis distance ($\mathbf{T_i} = \mathbf{(x_i - \bar{x})^T \Sigma^{-1}(x_i - \bar{x})}$)" is a Log ...
0
votes
0answers
11 views

Difference in significance of variables between bootstrap based and usual glm regression

I'm using bootstrap regression lately to get confidence intervals and assess variability of coefficients for glm regressions. I'd like to know how to interpretate the results when a variable is ...
0
votes
0answers
8 views

Comparison Category Rating (Pairwise comparision) with SPSS [on hold]

I'am new with SPSS (worked with Excel before) but have to use SPSS for my bachelor thesis and got some problems. I did a Comparison Category Rating with multiple Persons (Playing 2 stimuli and the ...
0
votes
0answers
4 views

WinBUGS - sample from the posterior of exponential distributed survival times

as introduction to WinBUGS, I want to simulate the posterior of the Gamma-Exp-Model. Because the posterior is known, I can varify the result. But the true posterior is always shifted to the right. I ...
0
votes
2answers
15 views

Should I use logistic mixed effects? How?

I've run an experiment in which different subjects had to make a number of decisions, which are stored in the dependent boolean variable Y (0 or 1). I have multiple independed variables which may ...
0
votes
1answer
17 views

What topic model should I use? [on hold]

I want to find out what is the most hot topic which twitter users are speaking about "Cancer". I have downloaded 10000 medical articles abstracts for training and 20000 tweets for test. What topic ...
0
votes
1answer
18 views

Formula for y axis in a plot in R [on hold]

How can one specify a formula for y-axis labels in a plot in R? I need to display exp(y) labels instead of raw y's. Is there a simple way to do that?
1
vote
0answers
19 views

Correlation for a sample with constant dependent variable

Generally, I am trying to calculate correlation coefficients (best case even Pearson r) of several independent variables on one single dependent variable. I am looking at several studies, where some ...
1
vote
0answers
9 views

Comparing normalized and partially normalized quadratic form of normal variables

Suppose $X=(X_1,X_2,\ldots,X_n)' \sim \mathcal{N}(0,\Omega)$, where $\Omega$ is the variance-covariance matrix of dimension $n\times n$ for the vector $X$. Let $a=X'\Omega^{-1}X$. It is known that ...
2
votes
1answer
26 views

What distribution has this non-central Chi-Squared -like moment generating function?

I'm new here so please criticize errors! My moment generating function looks like this (after some tidying): $E[e^{wY(t)}] = \frac{1}{\left(1-2\theta(t) w\right)^{k/2}} ...
1
vote
0answers
13 views

Sample from a quotient of mixture distributions

I want to sample from a random variable $Z=\frac{X}{Y}$, where $X$ and $Y$ are mixtures of distributions. I figured out, how to sample from a mixture distribution (e.g. Simulating random variables ...
0
votes
0answers
11 views

What mean coefficients in autoregressive model and how calculate them?

What mean coefficients in autoregressive model and how calculate them ? yt=c+ϕ1yt−1+ϕ2yt−2+⋯+ϕpyt−p+et, ϕ1, ϕ2 ... This coefficients are "fourier transform"? Can ...
0
votes
2answers
29 views

P-value versus Exp(B) value in Cox regression analysis

I performed Cox regression analysis for two Biomarkers. Both were significant (p<0.05). Biomarker 1 showed higher significance but lower Exp(B)=hazard ratio value than Biomarker 2 (see below). ...
3
votes
0answers
32 views

What explains the correlation between the slope and intercept?

If $R^2$ explains the variation explained by a model, what explains the correlation between the coefficients given for a slope parameter and an intercept? I have been thinking of it in two ways: If ...
6
votes
0answers
28 views

What non-Bayesian methods are there for predictive inference?

In Bayesian inference a predictive distribution for future data is derived by integrating out unknown parameters; integrating over the posterior distribution of those parameters gives a posterior ...
0
votes
0answers
6 views

Why is discrete cosine preferred to FFT in neuroimaging GLM

High-pass filtering is often used in neuroimaging data analysis. Commonly, whenever a general linear model is fitted to the data (as for instance in statistic parametric mapping) a number of columns ...

15 30 50 per page