0
votes
0answers
2 views

Mutual information for two soft clustering results?

I understand that mutual information (MI) of two distributions $X$ and $Y$ is defined as In the case of clustering analysis, say we are looking for two clusters out of 3 data points. We have two ...
0
votes
0answers
3 views

Scatterplot with edgeR DESeq Voom

I am new in RNAseq and I started using edgeR, DESeq and Voom from Limma package to do differential analysis. I have a data frame of 30 couples of Normal and Tumoral tissues Since each method is ...
0
votes
0answers
8 views

Extension of Median to big data integer distributions?

I am analysing big samples of integer values. Because they come from a non-symmetrical distribution, I prefer to use the median to characterise central tendency, not the mean. However, due to the ...
0
votes
0answers
2 views

Forecasting a ARIMA(1,1,1) model

ARIMA(1,1,1) process with constant term $\mu$ is $X_t=\alpha X_{t-1}+\mu+Z_t+\beta Z_{t-1}$ where $Z_t$ is white noise with mean zero variance $\sigma ^2$. Find one step and two step ahead forecast ...
1
vote
0answers
9 views

Is there a known bias with telephone polls in the U.S.?

I was looking at a WashingtonTimes/ABC poll, and the results breakdown, especially by age, seemed surprising to me. So I went looking for bias. It said: "poll was conducted by telephone Dec. 11-14, ...
2
votes
1answer
34 views

Dimensionality reduction when number of samples is much larger than number of features

I was wondering what happens when the number of samples is much larger (e.g. $\times 200\:000$ times more) than the number of features? Is there any recommended way of reducing the samples' ...
2
votes
0answers
8 views

Diferrencing vs Moving Average

Moving Average and differencing a series can both be used to remove seasonality. Does the difference of these two lie in the model they are used? Moving Average used in classical decomposition and ...
3
votes
1answer
22 views

What is the problem with post-hoc testing?

My statistic professor says so, all the books that I look at state it: post-hoc-testing is unscientific. You must derive a hypothesis from theory first, and then collect data and analyse it. But I ...
2
votes
1answer
27 views

Why doesn't measurement error in the dependent variable bias the results?

When there is measurement error in the independent variable I have understood that the results will be biased against 0. When the dependent variable is measured with error they say it just affects the ...
3
votes
1answer
41 views

Definition of exponential family

I was reading these lecture notes and came accross the definition of GLM using exponential family of distribution. The latter seemed to have a bit of ambiguity, so I've checked that's it indeed the ...
0
votes
0answers
7 views

How to combine Gaussians in a two-dimensional data

I have two-dimensional data which can be summarized by a sample matrix M'(X,Y) , where each data point M'(x,y) consists of a set of numbers which I assume is generated by an underlying Gaussian ...
0
votes
0answers
8 views

Understand mixed models SPSS

On a mixed model on SPSS I got the following results: in the table called "Type III Tests of Fixed Effectsa" ...
2
votes
1answer
12 views

Confidence interval for polynomial linear regression

I have a model which is not linear but rather polynomial, and I have to estimate the parameters by giving a 95% confidence interval. There are plenty of formulas for regression of the type $Y = ...
0
votes
0answers
6 views

algorithms for color image edge enhancement using potential function

I want to use the method based on the use of weighting function also known as Parzen Kernels and form estimation of the probality density function (pdf) based on ...
0
votes
0answers
6 views

Omnibus test for several incidence rate ratios

Is there an omnibus test for comparing several incidence rate ratios, for example, irr1, irr2, irr3 with null hypothesis irr1=irr2=irr3 against alternative hypothesis irr1 ne irr2 ne irr3? Here are ...
1
vote
1answer
16 views

Interactions - using ratio of variables

I have 3 variables, colony size, colony age and growth rate (colony size/age). I am interested to predict various other properties ($y$) of a colony using these 3 variables; $y = a_1 \text{ size} + ...
0
votes
0answers
11 views

I have to know about the tslm function in r [on hold]

I need the full details of tslm function in r beacause I have to know this.Can you please give the explanation about the tslm when we use?,why we use?,how it works?
0
votes
1answer
24 views

Correlation between two Likert items with a non-monotonic relationship

One of the assumptions for Spearman correlation is that there is a monotonic relationship between the two variables. I've created a scatterplot for two Likert item variables, but it seems impossible ...
0
votes
0answers
21 views

Determining demographics by restaurant visits

Assume Person X likes to visit different restaurants at different times. We would like to determine the current estimate of their demographic distribution based on all prior information we know from ...
1
vote
0answers
10 views

In R, generating every possible solution to a model, based on constraints [on hold]

In R, I’m trying to generate a matrix that shows results from a model and the values used to solve them- all of which are constrained. Every possible solution. An example model: Model= ...
0
votes
1answer
38 views

Resources for learning R with Statistics [duplicate]

Already read: Resources for learning R I would prefer to have a textbook which covers statistics with R, accessible to a beginning graduate student in statistics. Since I'm not as familiar with R as ...
-1
votes
1answer
18 views

What is the relationship between theta and size in negative binomial distribution?

In negative binomial regression glm.nb(y~x), I got a parameter theta and two coefficients? And then I want to use dnbinom(x, size, prob, mu, log = FALSE) to calculate the predicted probability. can ...
1
vote
0answers
15 views

How to decide which of two distributions a sample is from?

I have two random distributions. How can I get a quantitative estimate of the likelyhood that a particular sample was taken from one or the other of the distributions? To be more precise: Let $I = ...
-1
votes
0answers
25 views

Prerequisite reading before Andrew Ng's machine learning course

I have basic understanding of probability, statistics and matrices. By basic, I mean I can understand the khan academy lectures on these topics. With this understanding , I proceeded to listen to ...
1
vote
3answers
33 views

Remapping the Sum of two Normal Random variables?

I have a problem where I have sum of two random variables 1). Each distributed independently normally with different means ($\mu_1$, $\mu_2$) and sds ($\sigma_1$, $\sigma_2$). $Z=R_1+R_2$ 2). Each ...
0
votes
1answer
9 views

MSEP and R2pred for Linear Model

I have two set of data 1-Training (Calibrating) 2-Test. With these datasets, I Fit the model using first dataset. predict using the second dataset x-variables I have to test the closeness of the ...
3
votes
3answers
74 views

glm in R - which pvalue represents the goodness of fit of entire model?

I am running glms in R (generalised linear models). I thought I knew pvalues - until I saw that calling up a summary for a glm does not give you an overriding pvalue representative of the model as a ...
0
votes
1answer
34 views

glm in R - is the pvalue for Intercept important? Which pvalue represents the goodness of fit of entire model?

I am running glms in R (generalised linear models). I thought I knew pvalues - until I saw that calling up a summary for a glm does not give you an overriding pvalue representative of the model as a ...
2
votes
0answers
14 views

How to derive Gibbs sampling?

I'm actually hesitating to ask this, because I'm afraid I will be referred to other questions or Wikipedia on Gibbs sampling, but I don't have the feeling that they describe what's at hand. Given a ...
0
votes
0answers
10 views

Correlation of One when I simulate [on hold]

When i simulate off a distribution that I have created, I take the correlation between my simulations and end up with 1. What does this indicate? Is the result possible? Edit: By correlation between ...
2
votes
1answer
25 views

When to use a normal approximation of a Bernoulli distribution

What is a practical example where one would want to use a normal approximation of a binomial distribution over using properties of the binomial distribution itself? I.e if I already know that the ...
0
votes
0answers
6 views

Significance of a group of variables

I know how to do a significance contrast of a group of variables but if I see a lack of significance in two variables (for example in R the t test show when you type summary(lm(y~x1+x2+...+xk))) ...
0
votes
0answers
4 views

Fleiss' Kappa alternative for inter-rater reliability with multiple answers

I have a dataset where researchers assign a binary yes/no answers to cells in a matrix. For each row more than one, but at least one, 'x' is allowed. For example, researchers 1 may code: ...
1
vote
0answers
11 views

How does one analytically solve for the contours of an arbitrary bivariate density?

This slide deck shows how to solve for the contours of a multivariate normal, using an eigendecomposition of the covariance matrix. This seems to rely on the convenient ellipsoid shape of the normal's ...
0
votes
1answer
27 views

Is confidence interval necessary? [on hold]

Why do we want to predict $\mu$ (mean) when we know $\sigma$ (standard deviation). If we know the standard deviation of population, we can calculate $\mu$ (mean) at the same time. Is it necessary ?
0
votes
1answer
28 views

Study design - fresh look!

Need to be advised outside of the circle. I am more a physiologist+mathematician plus-c,c++,java coder/developer. Chart data. From year 2001 till 2012. 89 nursing stations or emergency call ...
0
votes
0answers
7 views

Learning from sparse label products

Consider the following binary classification problem $f(\mathbf{X})\rightarrow\mathbf{Y}$ where: $\mathbf{X}$ = Feature matrix $\mathbf{Y}$ = Product of several label (binary) vectors, i.e. ...
-1
votes
0answers
21 views

How to use gpu in R in Windows 7? [on hold]

As I know, there are packages (like gputools, magma, HiPLARM, ...) for unix OS. Is it possible to use something like gputools in Windows 7? thanks!
0
votes
0answers
14 views

Analysis to assign a categorical var to a ordinal

I have a categorical outcome with > 2 levels and a categorical predictor with many levels. Which model can I use to assign to each predictor level the probability of being in one of the classes of ...
0
votes
0answers
16 views

K-fold Cross Validation. R squared value?

I am using multiple linear regression with a data set of 72 variables and using 5-fold cross validation to evaluate the model. I am unsure what values I need to look at to understand the validation ...
0
votes
0answers
12 views

Generating text data for training for doing named entity recognition and extraction

I'm trying to build an algorithm for doing named entity extraction. It goes like this. There is a large set of text documents [communications], from which specific information has to be extracted. The ...
2
votes
2answers
36 views

How to analyze an inflection point in univariate time series?

I have a univariate time series with 36 data points (monthly data for 3 years). The general trend of this time series is relatively steep decline, but for the most recent one year, it is almost flat ...
-2
votes
0answers
24 views

How to calculate relative risk in R Studio? [migrated]

How to calculate relative risk in R Studio? In input i have names(DS) Tab<-table(DS[,5],DS[,11],DS[,3]) No Yes No 4 16 Yes 40 168 I am new in ...
0
votes
1answer
29 views

Generate correlated continuous and categorical data in R [on hold]

Task at hand: generate a simulated dataset containing both continuous and categorical variables, given a pre-defined correlation matrix. What has been done: this post covers how to generate ...
4
votes
1answer
58 views

Clarifications about probit and logit models

I know that there is a very good explanation of the technical differences of probit and logit model in this question. However, I would appreciate some common sense clarifications which can be very ...
1
vote
1answer
24 views

Predicting the direction of moving a object in R

I am trying to produce a model that classify the direction of a moving object. In the figure we see a single projection of 3D space where an object was moved up and down (red) vs up and down together ...
0
votes
1answer
11 views

Sparse Collaborative Filtering

Does anyone know of any Python code examples for sparse collaborative filtering. Everything I can find revolves around using prebuilt packages (e.g. Mahout, GraphLab), but I'm learning to learn the ...
0
votes
0answers
13 views

Fitting a good model in multiple linear regression cases

We assume to have multiple features and we would like to fit a good model through multiple regression. in the following case I can't graph all the features in a graph because we have many features and ...
0
votes
0answers
9 views

What deviation to choose in the error of the mean? [on hold]

What is the error of the mean of several measurements, if each measurement has some error? When one does $N$ repeated measurements of a particular variable $x$, the resulting set of measurements ...

15 30 50 per page