A statistical model is a formalization of relationships between variables in the form of mathematical equations. The model is statistical as the variables are not deterministically but stochastically related.

learn more… | top users | synonyms

0
votes
0answers
14 views

Do Precision-Recall vs Sensitivity-Specificity represent two cultures?

Why favor Sensitivity-Specificity over Precision-recall for model selection?
0
votes
0answers
7 views

Validation for Household Relocation Model without validation set

We are working on several household relocation models based on census data. This data contained the location of many households over the course of three years, along with several other variables. The ...
1
vote
1answer
46 views

How to add an interaction term in JAGS?

I'm trying to add an interaction term to a JAGS model. I found this where it shows some interaction terms. But I don't understand what's the guide lines to create an interaction term, which is ...
0
votes
0answers
21 views

Is there a minimal percentage of a data set to have the property to be modelled?

We have a data set of about 45,000 observations. Around 2 % of these have the property that we're interested in modelling. We have made a probit model fitted to all 45,000 observations and get ...
0
votes
0answers
15 views

Bayesian Dirichlet equivalent (BDe), Bayesian Dirichlet equivalent uniform (BDeu) and Mutual Information Test (MIT)

To estimate structures of Bayesian networks, I am thinking about three score functions, BDe, BDeu and MIT. I have several questions. What are the differences between BDe and BDeu? Can I convert BDe ...
0
votes
0answers
18 views

Purposeful model building for prediction and inference

What are some of the best practices and steps to building models for prediction and or inferences? What have been taught to me during my classes was the steps outlined in Chapter 4 of Hosmer et al. ...
0
votes
0answers
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 ...
0
votes
0answers
5 views

What are some viable models for all factor variables?

I have a dataset where everything, including my target dependent variable(s) are factors. Maybe I'm lacking creativity on this one, but what are some viable, predictive, models for something like this?...
0
votes
0answers
8 views

How to deal with model misspecification - linktest

I am running an OLS model to examine to what degree is the physical quality of life (SF-12 scale) is associated with depression (HADS scale), adjusting by age and the presence of an acute illness (yes/...
0
votes
0answers
38 views

confirmatory factor analysis for survey

I'm pretty new to confirmatory factor analysis and hope you can help me clear some questions. We are doing a workplace engagement survey in our organization. Our team chose approximately 150 ...
0
votes
0answers
10 views

Is it accepted to fit model with standardized data and predict on non-standardized data? [duplicate]

If you standardize your training data, then can it work on unstandardized data during predictions accurately? Many algorithms require the feature data to be standardized and I am wondering how/why/...
0
votes
0answers
19 views

Calculate AIC for random model (0 parameters)

I want to compare some action-selection models (e.g. soft-max and epsilon-greedy) to the simplest model I can think of. A random model, one that picks an action randomly among the available ones. To ...
0
votes
0answers
14 views

Determining intentions on synonym phrases

I am building an app that works with the Stanford NLP Parser in order to annotate all the parts of the sentence. I can use those chunks to (more or less) understand what the user wants. Now, my ...
1
vote
0answers
29 views

Predicted values in negative binomial model with 0-inflation

My count data are zero-inflated, for which I utilized glmmADMB. ...
0
votes
0answers
29 views

How to build model given data only?

Given data only and without any (prior) knowledge or information about the data, how to construct a model for the data and predict new data? There are many statistical models but I have no idea which ...
0
votes
0answers
29 views

Model for predicting Gentrification

I am looking for a way to design a model, which can in some way predict a gentrification process. I am using various indicators such as age structure, income, real estate prices etc. over a time ...
1
vote
1answer
55 views

How to improve model by Bayesian Statistics/Inference? [closed]

I am puzzled about model improvement in implementing Bayesian statistics/inference. Normally, we will use a fixed model in bayesian statistics, e.g. normal distribution with parameter mean and sd. ...
-1
votes
1answer
14 views

Warnings using lme with a binomial distribution

Good morning all!I am trying to run a binomial gmler model. My response variable is a binomial variable: extra pair paternity -->( 1 or 0) I am looking at several continuous variables like weight, ...
3
votes
0answers
13 views

Model to determine how many actions someone needs to continue

I need to think of a model to determine how many liked recommendations does a user need to come back to the site the next day. Until now, I did a model to determine the probability that each user ...
0
votes
1answer
21 views

transition matrix for urn model

There are slides regrading to urn model I have two questions if a Species A dies and a Species A is born, the original text says the probability is 0.4*0.4, but since a Species A has died , ...
0
votes
0answers
15 views

Power Model & linear regression model

What does it mean if linear regression coefficients and power model coefficients (using Log transformed value of explanatory variable) are same and only difference in intercept value? Thanks, Meera
0
votes
0answers
12 views

Appropriate form of regression for gender pay modelling: The LASSO?

I'm aiming to identify which factors best explain the difference in hourly wages for men and women. The dataset contains 10-15 potential predictors which are of varying data types. Some examples: ...
0
votes
0answers
6 views

Impulse response function of a SARIMA model

I really appreciate if someone could help me with some tips/Rcode to obtain the IRF of a SARIMA model estimated for a time series. What I want is to interpret the model estimated after an intervention ...
0
votes
0answers
14 views

what other models are used to predict system resource needed to server increase in volume for an application

I am trying to use models to predict underlying cpu or memory needed to serve an application volume. For example, I have a data set like this: ...
0
votes
1answer
34 views

Dealing with Unbalanced categorical data for prediction in R

I'm currently working on a predictive model concerning a dataset of 180521 observations for ~10 variables (including the predicted class). The predicted class is caracterized as below : True : 8058 ...
0
votes
1answer
14 views

Building a Regression Tree with one Gaussian Mixture Model at each node

I am trying to build a regression tree that outputs both a mean and a covariance matrix for each leaf of the tree. Ideally I would be able to have a Gaussian Mixture Model at each leaf. A first ...
0
votes
1answer
24 views

Fitting a model on continuous response variable using lme4 package in R? Factorial or Nested design?

I am trying to find the effect of plant traits on water infiltration and did some analysis using lme4 with the help of 2 statisticians, both of them suggest different models to check it. I can't ...
1
vote
0answers
9 views

Using Conditional random field for many valued labels

I want to use the CRF for labeling a corpus of annotated text. Each word in the corpus has its own set of labels. More specifically, the labels are the pronunciations of each word: some words like "...
0
votes
2answers
24 views

How to select automatically the best GLMM?

I have a set of 14 variables and I want to construct GLMM's. I want to include at first each variable and then add all the others, one at the time. This will require a lot of combinations of ...
0
votes
0answers
15 views

Modelling dependence between two groups but not within effects in ANOVA

I have two conditions and in each condition, the same participants took part. however, I am not interested in how the value of an observation changes between the two conditions for each participant (i....
0
votes
2answers
43 views

What is lm() compared to VAR()

What's the difference between # Fit Model # fit1 = lm(var$1 ~ var$2, data=data) and ...
1
vote
1answer
16 views

Where can I find sound information about Periodic Autorregressive Multivariate models?

I am reading an article that mentions Periodic Autorregressive Multivariate Models and their noises; however, in no section have the authors explained or shown references to these models. I looked ...
0
votes
0answers
23 views

Why would the intercept coefficient be higher than the the coefficients of the independent features?

I am a beginner in statistics and I can't seem to figure this out.. I have two models. Model 1, that contains all my independent features and model 2, that only has the features that show ...
0
votes
0answers
9 views

Linear probability model and multinomial logit inconsistent signs

I have a dependent variable with three potential outcomes. When I run linear probability models independently on the dependent variables and compare the results to that of a multinomial logit model ...
1
vote
0answers
16 views

Stacking/Blending Predictive Models with More than Two Outcomes

I've been experimenting with stacking predictive models recently. I've mainly been focused on looking at making meta-models based off of predictive probabilities of smaller models while implementing ...
0
votes
0answers
2 views

Modeling periodic deviations for a varying norm

I have a continuous input that's more or less the same, though it varies slightly and somewhat periodically over time. Essentially randomly, a large deviation will occur for a period of time, after ...
1
vote
0answers
9 views

Correlating model with measurements, trend vs absolute accuracy

I'm trying to compare results predicted by a complex model with measured results and don't know what the best method would be to do so. RMSE could give you an idea of the models absolute accuracy, but ...
1
vote
0answers
26 views

Model comparison via AIC or BIC for different likelihood maximization procedures

Maximum likelihood estimation of different models (which all model the same variable and assume the same likelihood function) is done by a different method for each model. Simple numerical ...
0
votes
0answers
8 views

Heteroskedastic errors may still explain more deviance?

Among a population, N = 1,100, you employ 10-iteration, 10-fold cross-validation on 1,000 observations using OLS model #1: $Y_i = \beta X + \epsilon$ This has an Adjusted $R^2$ of Q1 with a standard ...
0
votes
1answer
25 views

Inner / outer model

i have created a SEM model and want to know while reporting which part should be treated as Structural model and which portion as and outer / measurement model . Whether i should take portion A or ...
0
votes
0answers
15 views

simulation and model comparison

I created a simulation to compare a number of regression type models/estimators, lets call them M1, ...,Mn. for each iteration of the simulation run: I generate randomly data set X I generare ...
1
vote
1answer
129 views

Interpreting output of analysis of deviance table from anova() model comparison

0 down vote favorite I have a large multivariate abundance data and I am interested in comparing multiple models that fit different combinations of three categorical predictor variables to my species ...
0
votes
0answers
7 views

Parameter recovery study for a computational model: assessing model slopiness and practical implications

Consider a decision-making computational model with 6 free parameters. The model mimics human behavior: for a given decision-making task, it generates decision times and accuracy. For each parameter, ...
3
votes
1answer
47 views

Suggestions to improve sem results

I wish to check the assumption that physical and mental health for elders are affected by two main latent factors the physical burden (PHB) and the emotional burden (EMB). The measurement model is as ...
0
votes
0answers
13 views

study real-world process with an artificial model

I'm building a predictor for a classification problem. Some of the features are categorical, some are continuous, some are sparse, some are not. Unfortunately, the classes are very imbalanced, with ...
0
votes
0answers
27 views

Specify a mixed effect model for per patient treatment effect and interactors for such effect

I have a study design setting where each patient received a treatment and was assed again after 30 days. the dependent variables are a set of symptoms and clinical values. I thought of a design where ...
0
votes
0answers
4 views

Simulation Model Performance for Flood Quantile Estimation at Ungauged Site

I have proposed a model that is the modified ANN to estimate flood at ungauged site. In order to test the performance of the model, i want to design the simulation for ungauged estimation problem. Did ...
0
votes
0answers
41 views

errors in the orthogonal factor model

I am using R psych package in order to design a factor model. By default, an oblique rotation (oblimin) is performed by fa. The number of factors (fa.parallel$nfact) has been previously estimated. <...
0
votes
0answers
14 views

orthogonal factor model

I have a matrix of data that is clustered in several sets of variables (X1,...,Xn). In order to define these clusters I have used hierarchical clustering to get the desired number of clusters and ...
2
votes
1answer
54 views

How to check permutation testing exchangeability assumption when using a General Linear Model

I have a question on the assumption of exchangeability in permutation tests. Although I read a lot about this topic, I am still confused. For $N$ subjects, I have the value of a clinical measure $Y$ (...