# All Questions

2 views

### What is a good way for to explain the Granger Causality Test and the Toda Yamamoto Test

I'm due to explain this to an audience that has only basic econometrics knowledge. I'm not entirely sure how I can explain this to them since most of the jargon used here is actually quite advanced. ...
4 views

### Multiclass classification problem: how to analyze data to determine affect on precision?

I have a multiclass text classification problem being solved by SVM. There are $K$ mutually exclusive classes but my task is to improve precision while maintaining reasonable recall of only $k \ll K$ ...
6 views

### Interpretation of Engle-Granger Cointegration Test (Gretl)

How would you interpret following result from running the Engle-Granger cointegration test in Gretl: ...
4 views

### Under what conditions decreasing number of classes increases/decreases precision of multi-class SVM?

I have a multi-class classification problem that is being solved using SVM. I have a set of ground truth data with K different mutually exclusive classes. This is ...
7 views

### Extracting data from S3 file system to R dataframe

We extract the data from S3 file system to MySQl and connect R to MySQl to acces the data. Now, I am trying to extract the data from files of S3 file system directly instead from the mediator MySQl ...
9 views

### How can I calculate a rolling total based on time?

I apologize if this is the wrong place to post this question. I have a series of web requests that i'm analyzing for some sort of pattern. Each entry has a start time and end time in seconds since ...
4 views

### Nonparametric rank correlations with survey package in R

Is it possible to run nonparametric rank correlations (Kendall Tau/Spearman's rank) in the R survey package?
9 views

### Training Accuracy for a Classifier

I am training a Support Vector Machine (or another other classifier, for that matter), and I want to refer to the probability that the classifier predicts the correct class of a new input. What is the ...
4 views

### Use of Forward-Backward algorithm in structured mean field approximation for factorial HMMs

This question is specifically about the Factorial HMM paper of Ghahramani et al. and how to use Forward-Backward recursion for calculating means with respect to variational distribution in section ...
4 views

### Tests for subset containment

My apologies if this has already been asked (I haven't found it). Suppose we are taking measurements over time coming from some source (in my case, data consumption rates, which can have some ...
18 views

### Calculating $R^2$ for exponential regression in R

I am fitting a simple regression model on my data and I am using nls() the only problem is it does not provide the coefficient of determination $R^2$ and adjusted ...
8 views

### AIC in R. How to back-transform model averaged coefficients?

I have run a simple analysis in R for a mixed model (using lmer). go<-lmer(dN~treatment*time+(1|replicate), data=crab, REML=FALSE) I have used AIC model selection to identify a top model set. ...
6 views

### Mixed effects model for partially repeated sampling?

I have a quick question about using mixed effects models for my dataset. Briefly, this is the data structure: I collected data from 8 study plots in 2011 and 18 study plots in 2012. 7 of the study ...
14 views

### Hellinger distance bounds

The squared Hellinger distance is, for two densities $f(x)$ and $g(x)$, $$HD^2(f,g)=\frac{1}{2}\int \left[\sqrt{f(x)}-\sqrt{g(x)}\right]^2dx$$ Using that $\int f(x)dx=\int g(x)dx=1$, we may write ...
9 views

### R: regression with Interaction term but without Intercept

I would like to get a regression of the form: y=b1*x1+b2*x1*d1 (without an Intercept bo), where d1 is a dummy variable which is equal to 1 for all the positive values of x1 and zero otherwise.I ...
9 views

### Calculation of the acceptance ratio (Metropolis-Hastings)

I have a really basic question. But I am a little bit confused about that. How do I calculate the acceptance ratio within a Metropolis-Hasting step? I have something like ...
44 views

### Why does the standard error of $\hat p = \sqrt{p*(1-p)/n}$?

A binomial distribution has the standard deviation $\sqrt{np(1-p)}$. When you find the standard error of $\bar x$, you divide the standard deviation be $\sqrt n$. Analogously, shouldn't I simply take ...
10 views

### Covariance of Time Series

So first I combined them: $Z_t+2Z_{t-1}+Z_{t-2}$ = $a_t+a_{t-2}+0.4a_{t-4}+0.3a_{t-5}+2a_{t-1}+2a_{t-3}+0.8a_{t-5}+0.6a_{t-6}+a_{t-2}+a_{t-4}+0.4a_{t-6}+0.3a_{t-7}$ ...
11 views

### complex data set with mixed effect models in R

I have a quite complex data set. Active time is my response variable. And we have different habitat type, species nested in the habitat type, different treatments, body size as a control factor but ...
10 views

### Why would adding controls decrease the p-value for Durbin's alternative test?

I'm running regressions with time series data. Due to the nature of my data, I am concerned with serial correlation of error terms. Hence, I ran Durbin's alternative test to see if serial correlation ...
22 views

### How can I interpret the results of R kmeans function?

I have a large set of data containing the description for 81432 images. These descriptions are generated by an image descriptor which generates a vector (for each image) with 127 positions. So, I have ...
4 views

### fast sum-of-ranks-between Perl module [on hold]

The sum_of_ranks_between function from the Statistics::Data::Rank Perl module is very slow on large data sets. Is there a faster ...
10 views

### Appropriate hypothesis test/method where numeric target variable

If we are testing different offers on a webpage, where we show alternating offers to different visitors as they land on our site, how can we tell if any of the variants are "truly" better as opposed ...
6 views

### equivalence of equal error rate to accuracy

Suppose that someone reports that he has accomplished an equal error rate from 5 to 15 percent. How can I find the equivalence of this value to an accuracy score, support score and F-score?
6 views

### Calculating a CI for predicted probabilities

I have data with a binary variable Y (success/failure) and an explanatory variable X, which is in nature continuous, but in my data has only 5 different numerical values. I am interested in estimating ...
21 views

### How to print loop values in R [on hold]

I have 2 data frames in R called d3 and d4. d3 contains: ...
2 views

### Correct GLMM model for unreplicated factorial design

My experimental design is as follows: Three sites (Treatments) that were not replicated (Healthy Control [HC], Untreated [U], and Treated [T]). Six independent measurements (Samples) of a response ...
6 views

### Intraday satisfaction estimation from end-of-day response

My business partners currently measure customer satisfaction at end of day for their sponsored events. I have developed a model to help them extrapolate from their sample to the universe at large ...
5 views

### Finding ideal hypothetical data according to a regression model

Analogy We have 10 athletes. Each athlete is represented as a binary feature vector. We make these athletes compete in a 100 metre race. We get real value numbers corresponding to the time they took ...
4 views

### Iterative generalized least squares procedure in SPSS?

I want to test the 'poolability' of my data set for a logit regressions. Gatingnon and Reibstein (1986), proposed an iterative generalized least squares procedure to do so. Anybody has an idea how I ...
18 views

### How to include control variables in an Intervention analysis with ARIMA?

I want to conduct an Intervention Analysis using SPSS. Thereby, I want to find out if a specific regulation introduced in 2013 has an effect on leveraged loan volume. Thus, the dependent variable is ...
7 views

### Getting churn rate / probability with only the status of an account?

I have limited sources. I just wanna get the churn rate even if its not too accurate or it not too conclusive. I only have the details of all the activated sim card of customers for 2 months. I have ...
13 views

### Hierarchical K-Means structure and nearest neighbor search

I have just recently begun looking into data structures and their use. The two that stood out the most were k-d tree and Hierarchical K-Means. K-d tree was quite straight forward with search as it's ...
18 views

### Scale variable as count data - correct or not?

In this paper (freely available via PubMed central), the authors use negative binomial regression to model the score on a alcohol use disorders screening instrument, using various baseline variables ...
9 views

### Mann-Whitney significance and multiple hypothesis testing significance

I am performing various comparisons using the Mann-Whitney U test. Because I'm comparing various groups simultaneously, I would am also correcting the p-values for multiple hypothesis testing using ...
28 views

### Beta of transformed gamma variable

I'm trying to transform a gamma distributed variable with $\alpha=n$ and $\beta=15$ using the following formula: $$U=\frac{2S}{\beta}$$ S is actually a summation of n exponential variables ($Y_i$), ...
11 views

### Generating a new conditional variable in Stata/SPSS [on hold]

I am new with Stata and trying to figure out a rather simple task of coding a new variable. (Any tips how to deal with this easily in SPSS are also welcome!) I´m generating a new variable newvar that ...
5 views

### Sum of ordinal items, treated as non-parametric?

I have a survey which seeks to quantify the amount of experience with performing arts. Each item as the person questions like "estimate the numbers of experience you have had playing an instrument ...
7 views

### Error normality test in case of least square Dummy regression

I hv used a Least square Dummy Variable Regression model for panel data. I want to test d error normality for which i used Shapiro-Wilk Test and found two variables against which d null hypothesis ...
15 views

### creating random variable with certain auto-correlation in R

I want to create a random variable with a given autocorrelation in R. The target autocorrelation is defined by: $$acf_{target}=(lag+1)^{(-b)}$$ with $b=1.41519$ which I derived from a natural ...
31 views

### Estimate the tuning parameter in Ridge logistic regression

I need to know how can we estimate the tuning parameter in penalized likelihood? I write my own code but there is a mistake I could not find it.!! Could you please help, I do my best to make the code ...
121 views

### Statistical anecdotes [on hold]

I was inspired by this question on statistics jokes and wanted to start a similar thread on statistical anecdotes. These are famous stories from the past where statistics have been used to solve some ...
11 views

### Multiple controls per case test (dichotomous responses) - How to take into account the multiple match design?

In matched pair-study (1:1 ratio) with dichotomous responses I use McNemar's Test to take into account the matched pairs. But what test do you use to take into account multiple controls per case ...
34 views

### Standard logistic regression post-Lasso

The situation I'm interested in is logistic regression for a binary response variable with lots of predictors (500 to 1000), lots of which are correlated. I would like to use a logistic LASSO approach ...
7 views

### r - Definition of random effects in repeated-measures designs using lme() as described in Field et al. (2012): Discovering statistics using R

This question is related to this other question. Introduction of the problem In Field et al. (2012): Discovering statistics using R, the following implementation of repeated-measures designs using ...
49 views

### Why randomForest in R limits the number of levels for categorical predictors?

It's a pity for randomForest in R. But, for instance, if we have a categorical predictior with 100 categories, there is a solution in which we create 100 ...
9 views

### Best approach to analyze time series data for two data sets with 2 different scales

I would like to know the best methodology to analyze two different data sets when they have alternative scaling (without rescaling the data). I've read that plotting 2 vectors along two separate y ...
33 views

### ARIMA(2,1,3) - insignificant coefficients?

I estimated an ARIMA (2,1,3) model and found that AR(1), AR(2) had both significant coefficients however my MA tests were unexpected - both the MA(2) and MA(3) were significant yet the MA(1) was ...
I would like to learn how to calculate the expected value of a continuous random variable. It appears that the expected value is $$E[X] = \int_{-\infty}^{\infty} xf(x)\mathrm{d}x$$ where $f(x)$ is the ...