Tagged Questions

A statistical model is a formalization of relationships between variables in the form of mathematical equations. A statistical model describes how one or more random variables are related to one or more random variables. The model is statistical as the variables are not deterministically but ...

52 views

Does it makes sense to keep a 5-way interaction model?

I collected the following variables, as I thought they might be in some relationship, but without any strict hypothesis. Note: this is a repeated measures design. phy = continuous DV (a ...
9 views

Distribution for modelling return times with inflated zeros

I have data on people's return times which I wanted to fit a distribution to using maximum likelihood estimation. I was planning on using a Weibull or Gamma but there are a high number of return ...
7 views

Causes of change in satisfaction

We have a call center that dropped 10% in customer satisfaction since last month. We want to know the factors that led to the 10% decrease not the factors that affect satisfaction. How can I model ...
22 views

Too many models to choose from

I'm trying to find a good evaluation function to approximate the score of a position of the game Reversi. That is the score of mutually perfect play. A position of Reversi has 64 fields, with each one ...
22 views

Setting up maximum likelihood estimation with multi-response data

I was trying to fit the parameters of a time-dependent system coupled of ODES related to a kinetic experiment with multi response data. Example: A->B+H A+H->C+H A->D dcA(t)/dt=-k1Ca(t)-k2Ca(t)*Ch(t)-...
7 views

How to model GEE (generalized estimating equation) in data coming from two datasets?

I would like to model X (sentiment score, continuous between -1 and 1) and Y (smoking status, either 0 or 1). Individuals can be clustered by the "State" variable. It would be the most ideal if I ...
18 views

drop1 LRT is zero in R

So for my current binomial model I am dropping some components and I found out that for one variable the results look a bit different. For 'hurseason' (class factor with two levels Y/N), the LRT is ...
9 views

Converting from Log - Difference to Levels

My problem is as follows: I've built a regression model using the log- difference of both the dependent and independent variable. The model seems to perform fairly well when I plot the results in log-...
19 views

How to simulate a dataset for linear modelling with a 3-level factor?

I am trying to simulate a dataset with a 3-level factor, and I hoped I could run some code by others to make sure I've not done anything wrong. The dataset is analysed in GLM with in R. The model ...
14 views

Choosing polynomial expansion complexity [duplicate]

Here's a specific question I haven't seen asked/answered. Motivation: if you're doing linear regression of two terms plus their interaction, and only the interaction is significant, you keep the ...
16 views

Sample size needed for prediction modeling/validation with logistic regression

I have a dataset with about 30 potential predictors and 115 observations. I'm looking into building a prediction model with the data using logistic regression. From what I have read - the typical ...
23 views

Bayesian model and Jensen inequality [closed]

We estimate a Bayesian model which has transforms in it $y \sim normal(\beta t(\theta, x), \sigma)$, where t() is a nonlinear transform, we then want to translate the many chains and iterations into a ...
15 views

Can we skip this continuous variable main effect in the interaction?

Suppose I have a simple model like this: y ~ alpha_1*x_1 + alpha_2*x_2 + beta*x_1*x_2 x_1 is a dummy variable, x_2 is a continuous variable. If alpha_2 is insignificant, but beta is significant. ...
22 views

Model free reinforcement learning with subgoals: how to reinforce learning with only one reward?

This is a question about reinforcement learning with subgoals related to this post: Reinforcement learning with subgoals In the link above, we gave an assumption that a transition probability ...
20 views

Weights in Loess

I have a good working knowledge of how the loess model works but am curious as to how weights work in conjunction with the model. Obviously, this method weights locally, but many statistical packages (...
12 views

HMM with random process that determines how long you stay in a state

I have a situation that is reasonably well-modelled by a discrete Hidden Markov Model (HMM), but with one twist: when you enter a state, the amount of time that you spend there is given by some ...
9 views

What else I can try to model preferential data?

I have a dataset that has User data and corresponding targets as number of desktop logins, mobile app logins, web logins. Now based on the counts, we clustered the 3 logins to form 3 target classes: 1....
105 views

Classification: Selecting final label using prior information on class distribution

Using R, let's say that I have the following (dummy) data. ...
9 views

Stochastic individual based model

I was going through the article here and can someone please explain what a stochastic individual based model is. Could this be used to model at a population level? Does this model look at each and ...
13 views

Importance of weights parameter while building model

A sample model code written in R is given below: ...
83 views

Comparing SVM Models using Different Methods for Data Generation

I have a set of SVM models that I am trying to compare. Each of the models is trained on a variation of the original data: The original data The original data using resampling scheme A The original ...
27 views

Linear or non-linear model for social interaction with R

The question here is whether the cooperation of people with equal or similar abilities leads to better results than the cooperation of people with different abilities. The setting is a group of ...
11 views

Projection Pursuit Regression

I am trying to use Projection Pursuit Regression to fit a model to my data set, but I am running into some difficulties. I have a few questions: 1. Can PPR only be used when you have many predictors? ...
9 views

Predicting End Year based on Beginning Year - weighting time-based feature values

I apologize if this has been answered in the past, but I have not been able to find anything relative to this type of scenario. Our goal is to predict when an owner of an asset will sell that ...
68 views

Difference in Difference with multiple treatments with paired data observations (twin studies)

I have a data set of identical twins, such that the data can be considered as paired observations. The data is composed of a survey that was conducted on two separate years, and all twins answer the ...
13k views

How to know that your machine learning problem is hopeless?

Imagine a standard machine-learning scenario: You are confronted with a large multivariate dataset and you have a pretty blurry understanding of it. What you need to do is to make predictions ...
383 views

When have I to stop looking for a model?

I'm looking for a model between stockprices of energy and the weather. I have the price of the MWatt bought between the countries of Europe, and a lot of values on the weather (Grib files). Each hours ...
20 views

Are RSS and R^2 related to training error only?

While reading An Introduction to Statistical Learning, I stumbled across the following (p. 210): [...] the model containing all of the predictors will always have the smallest $RSS$ and the ...
109 views

Am I introducing bias by assuming birthdate is middle of month?

I have a dataset containing dichotomous disease measures as well as some continuous anthropometric measures on a cohort of patients, and includes their month and year of birth as well as the exact ...
39 views

How to prove the reliability of a predictive model to executives?

I trained data from 500 devices to predict their performance. Then I applied my trained model to a test data set for another 500 devices and show pretty good prediction results. Now my executives want ...
83 views

UK Exit EU Poll

Since it is the topic of the day, let's turn it into a statistical question. Preliminary polls are showing 52 to 48 in favor of staying in the EU in terms of vote. However bookies are giving a 80%+ ...
65 views

Suggestions for appropriate regression models? [closed]

The image is like a larger version of the one posted, but not as clear. I am trying to find a model that can fit to that pattern so that I can identify when there is a break in the pattern. I am ...
9 views

Scaling parameters to lie in unit hypercube — how to understand this notation?

I am attempting to emulate a simulation in a paper I am reading. The model includes two parameters $\theta_1,\theta_2$. These parameters are scaled to lie in the unit hypercube. That is, where the ...
11 views

Modeling : How do I learn how a discrete function with some smoothness properties evolves over time?

I have a function f over an equi-spaced grid. The function is somewhat smooth, and I can make it smoother (e.g. by doing some type of nearest neighbor averaging), but it will have several peaks and I ...
34 views

Deciding Optimal Cutoff for a Prognostic Index derived from Cox Proportional Hazards

I am planning to develop a prognostic model that would identify a particular group of head neck cancer patients who will do better if chemotherapy is added to standard radiation therapy. The data for ...
40 views

How does a Biased Interviewer Behave?

Suppose three equally capable candidates are interviewed for a job. One candidate is female, the other two male. The interviewer is biased. What is the probability that the female candidate is ...
8 views

Sort or cluster experimental 2D data crossplots with respect to common shape/model

I have a quantity of tabular data, let us say $E=200$ experiments, and $V=20$ variables (all positives). I am trying to find EDA-like dependencies or "correlations" between some of the variables, at ...
20 views

Gibbs Sampling for LDA example

Can someone provide an example of 1 (or more) iteration(s) of Gibbs sampling for LDA using real values? I have been searching for a while and I can't seem to find any good examples. Thank you.
19 views

Compound poisson gamma model and biomass data

I have some biomass data (total count -discrete- of individuals and total dry weight -continuous-) that I would like to model with environmental parameters recorded at different spatial scales (...
10 views

Herfindahl–Hirschman index for data accumulation

I'm checking the data accumulation in segments with Herfindahl–Hirschman index, the idea is to get segments with low index. Do you think this is a good way to detect this accumulation? and do you see ...
77 views

Using R to create a predictive analysis model [closed]

I'm an intern for a movie studio and my boss has said to use what I know about R and predictive modelling (which is 2 edX courses) and make some sort of predictive model. The data I have available is ...
11 views

Are models within 2 deltaDIC of each other considered equivalent?

I think its a rule when using AIC that should the best model be within 2 unit AIC of the second best model, both are considered with equal weight. Does the same rule-of-thumb apply to Deviance ...
9 views

1k views

Variable selection for predictive modeling really needed in 2016?

This question has been asked on CV some yrs ago, it seems worth a repost in light of 1) order of magnitude better computing technology (e.g. parallel computing, HPC etc) and 2) newer techniques, e.g. [...
47 views

Measuring the effect of weather on retail sales

I'm currently working on modeling this as an ad hoc. Sr mgmt want to know how much of our sales growth during the year can be attributed to weather. I chose to investigate "weather" as temp & ...
26 views

Is the likelihood statistic applicable for model selection in machine learning?

Minimising the likelihood ratio statistic is often used as a criterion for model selection in connection with linear and related models and statistics such as as AIC are an extension of this practice, ...