# All Questions

3 views

### Should we predict residual of ensemble model and add it to final prediction?

We have been doing a time series project on daily wise data. We built 5 different models SVM, XGBoot, ARIMA, KNN, ANN. We then built predictive models for residuals for all of these models and got ...
8 views

### optimise sharpe ratio with caret package

I am trying to see if what I used to do manually can fit into the caret package framework. Given a set of potential signals (=features), I need to select a subset that optimises the out of sample ...
9 views

### How to provide a score value to an image based on pattern information in it?

I have a say 30 two-dimensional arrays (to make things simple, although I have a very big data set) which form 30 individual images. Many of these images have similar base structure, but differ in ...
16 views

### Poisson regression with different exposures dependent and predictor variables

I am trying to fit a Poisson regession in R, using rates: $\ln(\mathrm{rate}_i) ~= a + bx_i + c \ln(\mathrm{old\_rate})_i$ My issue is that the predictor variable $(\mathrm{old\_rate})$ is also a ...
15 views

### Neural Network with General Topology

I would like to construct a neural network that has $n+m$ inputs and $k$ outputs. For example $n=5$, $m=2$, $k=2$. The topology is as follows: there are several layers that process the first $n$ ...
17 views

### Time Series Forecasting, Log or non-Log

I have read that you should use log transformations when the fluctuations on your data are increasing over time, but what do you do if the fluctuations level out over time? A plot of the time ...
7 views

### Merge a set of probabilistic statements

I have a machine learning problem for which I would like to split the mostly binary variables in groups of independent variables (independent across groups, dependent within). Then, I can learn the ...
10 views

### PDF from standard deviations plot

I must consider a plot like this that shows the bounds on $x$ (in this case $\sin^2\theta_{12}$), in terms of standard deviations $N\sigma$ from the best fit. How can I extract the PDF of the $x$ ...
7 views

### Circularity of Gaussian kernels and infinite dimensionality [on hold]

I'd like to know more about this statement: Gaussian kernels are circular (which leads to the above-mentioned infinite dimensionality?) Questions: in image processing the issue of ...
13 views

### Why classification accuracy in validation set gets lower if validation cost also gets lower?

I'm training neural network for some simple classification task using tensorflow and have 2 output neurons, using softmax classification. My question is why accuracy on validation set gets lower when ...
7 views

### Time Series Modelling[Issue with modelling the residuals]

I am doing the sales forecast. I found the trend and seasonality manually for my time series data. Regressed time series data against the trend and seasonality and found the residuals. The residuals ...
8 views

### SAS: choosing the right model

I'm getting a bit lost in alle the possible ways to find association... I have a dataset in which my subjects are categorized 1, 2 or 3 (depending on genotype polymorphisms). I want to know the ...
6 views

### How does the caffe mnist_autoencoder work?

This is about the Caffe mnist_autoencoder example provided in ./examples/mnist/ From what I've read an autoencoder uses similar weights between the upgoing and downgoing stages. That is, the ...
5 views

### What models for Rahbek and Mosconi method for exogenous variables in VECM?

I'm not very good at algebra, wich caues problems for me when reading econometric articles. Now, I'm reading the Rahbek and Mosconi (1998) paper on how to introduce exogenous variables in VEC models. ...
17 views

### Interpreting multiple fixed effects interactions

I have the following model (mcmcglmm in R with data based on this paper). Sex is a two level factor (M or F), Group a three ...
32 views

### Multiple comparisons - adjusting p values when some variables are correlated

I'm working with 400+ variables (mostly 2D gel data) across 2 conditions for which I've calculated p values. Some of the variables are highly correlated. I'm wanting to adjust the p values to allow ...
24 views

### Linear Regression bias not converging

I am writing a program to perform a linear regression. The actual function I am trying to estimate (for testing purposes) is as follows: f(x) = 3x + 100 The ...
21 views

### What are some clustering algorithms in which I can define no of clusters I require?

Is there some other clustering algorithms apart from K-means in which I can define no of clusters I require ?I have a data set of large and skewed data points and K-Means is not providing quite ...
11 views

### how i transform data from high dimension (feature space) to euclid space of original data

suppose i have X= 2^11 data with D=3 applying polynomial kernel function (kernel trick)to find kernel matrix K as kn*n kernel matrix ,solve eigen value problem to find principal axis and PC ...
9 views

### Assessing random forest results

I'm trying out a random forest regression model for my metabolomics data. I'm using cforest from the party ...
43 views

### Sample size for multinomial distribution

Suppose we have multinomial distribution with $k$ outcomes having the same probability $1/k$. What sample size do we need to guarantee with the probability $95\%$ that $m$ of the oucomes occur at ...
13 views

### Idiosyncratic error term in fixed effects Poisson

Cameron and Trivedi (2013: 346) and Wooldridge (2010) suggest fixed-effects Poisson with multiplicative heterogeneity.E[y_it│x_it,α_i ]=α_i exp⁡(x_it'β), where α_i is the unobserved heterogeneity. If ...
8 views

### statistical significant deviation cut off point

I have a question with regards to finding a statistical significant difference between two variables. I have 9765 observations of three categories which are "Observed", "Expected" & "Residuals". ...
11 views

### Random Forest Logloss question [on hold]

I am learning how to use random forest. When I use logloss function to compare my predict model with test data, I got a number greater than 1. Here is my model: ...
19 views

I'm relatively new to simulations, R, and multiple imputation. I am writing a simulation to better learn multiple imputation on my own. Here is my simulation of MCAR: ...
5 views

### Model name for regression with square root transformation on the response variable

Consider different transformations on the response variable. If log transformation is used: $$\log{Y} = \alpha + \beta X + \epsilon$$ The model is called log-linear model or semi-log model. My ...
4 views

### how to find principal vector and prencipal component from kernel matrix?

i have kernel matrix n*n it as gram matrix how i find U as principal vector as alpha and V as principal component PC by solving eigen value problem as lamda ?how i normalize them ?how i project the ...
8 views

### Mean comparison multiple groups

I’m not sure if this question has been asked before as I don’t know how to phrase it in a search. But essentially I’m trying to test if there are differences between store locations that have trained ...
9 views

### Basic RNN not converging to zero

I'm writing a basic RNN in Java using JBLAS. My function for generating the hidden state is: tanh(xU + sW) Where x is the input vector and s is the previous ...
25 views

### Is it possible to train neural network to draw picture in a certain style?

Is it possible to train neural network to draw picture in certain style? (So it takes an image and redraws it in a style it was trained for.) Is there any approved technology for such kind of a ...
11 views

### R , code execution no to stop even after getting error [on hold]

Need some clarifications for my R code execution stops / terminates after getting error inside while loop but i want my code to run next line which is 2nd while loop and subsequently 3rd loop , The ...
3 views

### Winbugs error Multiple definitions of node V[1,2] [migrated]

Can anyone see anything immediately wrong with my code that would give this error? ...
5 views

### Identifying sequential patterns and deciding which ones are useful

So, basically I have a problem in which I have, over time, the appearance of different features, each feature containing different categories (where categories belonging to the same feature cannot ...
7 views

### how to classify short text sentences?

I have a very large dataset that looks like ...
20 views

### How to perform SVD to impute missing values, a concrete example

This might be a very stupid question, but I have read the great comments regarding how to deal with missing values before applying svd, but I would like to know how it is going to work, if I apply it ...
8 views

### How to solve eigen value problem in kernel pca? [on hold]

If I have kernel matrix $K_{n*n}$, where $\alpha$ is an eigen vector, and $\lambda$ is an eigen value, how can I solve the eigen value problem to find principal vector and principal component?
14 views

### What to do if a categorical variable has some components that are not statistically significant?

I'm trying to construct a univariate prediction model using logistic regression in order to predict credit default likelihood from overdue level in telecommunication companies: ...
18 views

### GLM: Is it necessary to include lower-order interactions when testing higher-order interactions

It appears to be a general principle that one should include all main effect terms when modelling interactions in (generalized) linear models (as argued here, for example: Including the interaction ...
36 views

### Why would I use any MC technique other than basic sampling

I'm trying to learn sampling techniques. Lots of tutorials say that they are useful when "you can't sample directly from the pdf...." q1) If I have the algebraic form of the pdf can't I always sample ...
12 views

### Prediction of vertex scores in a bipartite graphs

I have a bipartite graph with two sets, A and M, of nodes. Every vertex in M has a score associated with it. I have two tasks: To every vertex a in A, I have to assign a score based on the scores of ...
38 views

### Regression: What is the utility of R squared compared to RMSE?

Suppose I'm doing regression with training, validation, and test sets. I can find RMSE and R squared (R^2, the coefficient of determination) from the output of my software (such as R's lm() function). ...
5 views

### Converting logarithmically transformed negative binomial coefficients to effect size at mean

I have logarithmically transformed coeficients, from a negative binomial regression, and am looking to calculate from these the unit change in y from a one-unit change in x. It is my understanding ...
10 views

### How to mix known and unknown features in timeseries RNN?

Consider the following data: ...
8 views

### Pre/Post Intervention Evaluation

I need help identifying the appropriate statistical test to use, if any. I am helping design a project where well-visit screening rates will be compared before and after a change in pediatric ...
11 views

### Selection Bias and Controlling Covariates

I am currently performing a retrospective study that is comparing a surgical procedure vs a modified version of the same procedure. There is obvious selection bias because of the selection criteria ...
3 views

### How to calculate autovariate from fitted values of a logistic model to include in a autologistic model? [on hold]

I need to account for spatial autocorrelation in my dataset and I would like to apply a autologistic regression model. I read some papers where they first run a ordinary logistic regression and then ...
6 views

### How to improve the fit of a zero-inflated, negative binomial glmmADMB model

I have been trying to fit count data that is zero-inflated and overdispersed using generalized linear mixed models. My research led me to the glmmadmb function in the glmmADMB package. I am fitting ...
48 views

### Is there a formula for an s-shaped curve with domain and range [0,1]

Basically I want to convert similarity measures into weights which are used as predictors. The similarities will be on [0,1], and I will restrict the weights to also be on [0,1]. I'd like a ...