Questions tagged [aic]

AIC stands for the Akaike Information Criterion, which is one technique used to select the best model from a class of models using a penalized likelihood. A smaller AIC implies a better model.

Filter by
Sorted by
Tagged with
0
votes
2answers
37 views

How does AIC vs. LASSO work?

I understand that LASSO and AIC are striking for a balance between model fit and size. However, how do they respectively measure the size/complexity of the model? Does AIC measure the number of ...
2
votes
1answer
20 views

R: Fit Linear Mixed-Effects Model with GAM (mgcv)

Imagine a linear mixed effects model with one random intercept: library(lme4) LMM1 <- lmer(response ~ experience + (1|subject), REML=FALSE, data=train) I'd like ...
1
vote
1answer
19 views

What is the theoretical basis behind counting dispersion as an implicit additional free parameter in R's logLik() function?

Recently I was attempting to calculate the Akaike Information Criterion (AIC) for a set of fitted models in R, using standard packages available on CRAN. A package that I was using seemed to be ...
1
vote
1answer
31 views

How to optimise penalty parameter in ridge regression using AIC

So I know for a ridge regression model, we need to find an optimal $\lambda$ value. I also know that we can achieve this by finding an optimal AIC value, that is, we find the $\lambda$ value that ...
0
votes
1answer
21 views

Does the column ordering matter in the stepwise algorithms used by R?

Suppose I have a large data set with variables $x_1, x_2, \ldots, x_p$ to predict response $y$ where $p$ is very large (however $n >> p$). I would like to perform forward stepwise regression on ...
0
votes
0answers
10 views

When AIC chooses 2 lags, but 2nd lag is insignificant, do I drop it?

If the AIC criterion chose 2 lags, but the 2nd lag is not significant (see p-value), then am I supposed to drop the 2nd lag or leave it?
7
votes
1answer
87 views

GAM: Do shrinkage smooth splines also address for concurvity?

I have a gam model with automatic predictor selection based on cubic splines (bs = cr) and SELECT == T or shrinkage cubic splines (bs = cs) and SELECT == F. Now I'm wondering if predictors affected ...
0
votes
1answer
18 views

How to use the AIC/BIC for overfitting (information criteria) ARIMA

So I am using STATA, I have the log likelihood, AIC and BIC as such: AIC: -112.1838 BIC: -100.2412 log likelihood: 64.23 N= 200 observations So how do I conclude that there is no "over fitting&...
1
vote
1answer
22 views

Negative Log Likelihood for AIC

I was looking at AIC, which is given by AIC = 2K - ln(L). However, to my understanding, and observation, L = Log-Likelihood can be negative. So in the case where L is negative, is AIC not applicable ? ...
2
votes
2answers
67 views

Which statistical test to compare same model with different parameters?

I have two datasets on people buying apples based on weight and price. One dataset in 2019 the other in 2020. I estimate a logit model with Utility = betaWeight * weight + betaPrice * price. Training ...
1
vote
0answers
69 views

What's best? A model with nested random effects supported by AIC, but that validates poorly; or one with a simpler random part that validates better?

I am trying to fit a linear model to understand the factors that influence (marine) plant carbon stocks at a global level. The potential predictors of carbon stocks that I want to include in the model ...
0
votes
0answers
15 views

Outlier detection during non linear regression coupled with unkown model selection - how to pick the best model?

When performing non-linear correlation, I have been using AIC to perform a preliminary selection of what models could be a potential good fit for my correlations. I was toying around with the idea of ...
0
votes
0answers
11 views

Can I use AIC for model selection with same model on data subsets?

I have a class-imbalanced dataset so I divided my data into positive and negative classes (10% pos-90%neg). To model the data I planned to subset the negative data into 8 subsets and then create 8 ...
0
votes
0answers
36 views

negative values for AIC and BIC

I am trying to fit a gumbel distribution using MLE for the following 10 data points. DATA=(3.62,3.76,3.57,3.56,3.61,3.77,3.46,3.6,3.39,3.74) The problem is that the ...
0
votes
1answer
22 views

Reference request: accounting for AIC stepwise model selection with bootstrapped standard errors

The use of the AIC for model selection via comparison over many models is well-known and rightly maligned. But I read an interesting passage from Hastie et. al.'s classic The Elements of Statistical ...
0
votes
0answers
20 views

Picking a suitable performance metric when comparing the same model but using different sets of training data (Causal inference model)

I am comparing the same models prediction accuracy (Causal Impact) using different control variables as predictors and looking for a metric to decide which set of controls to use. Reading into AIC and ...
0
votes
0answers
12 views

AIC of a weighted cox regression model (coxphw)

I have to compare three cox-regression models. However, one of these violates the PH assumption. Stratfying the variable did not work because it is already categorical. Thus, weighted cox regression ...
2
votes
1answer
142 views

Why does AIC select the wrong logistic regression model?

I've noticed a phenomenon with logistic regression: when the probability of success is small and number of trials large the AIC consistently selects the wrong models. In fact the more wrong the model ...
0
votes
0answers
45 views

How to Calculate Degrees of Freedom for a Polygon with Correlated Arcs?

I'm running a bit in circles on this, so hopefully someone has ideas. Problem: I am trying to calculate the degrees-of-freedom (DOF; for purposes of calculating AIC) for a polygon. I am fitting an ...
0
votes
0answers
16 views

Can you compare AIC to WAIC?

This may be a simple question, but I'm at a bit of a loss. Can I compare AIC to WAIC for the same model, one estimated using general linear models and one using Bayesian estimation? Or do I need to ...
1
vote
0answers
27 views

What counts as a parameter for AIC?

I know this question has been asked before (e.g. here Meaning of 'number of parameters' in AIC), but I am still confused. What exactly makes something as a parameter for the AIC penalty, ...
1
vote
0answers
23 views

Is the model with the lowest AIC value always the preferred one? [duplicate]

I have a question regarding model selection based on the AIC criterion. I have 5 predictor variables that I include in my models (no interactions are included) and create all possible model ...
1
vote
0answers
20 views

Do conventional thresholds for global fit indices (e.g. AIC) hold for models based on very large data sets?

Problem/Question in short: I have estimated 5 generalized linear mixed models and subsequently compared their levels of relative fit according to AIC. These models are based on a very large dataset of ...
1
vote
0answers
34 views

Is it possible to calculate AIC on LSTM?

I'm doing a forecast on returns of stocks using ARMA-GARCH models and LSTM. Because of the nature of the data, RMSE, MSE cannot be used. I instead found MAAPE. Now what I'm trying to understand if I ...
1
vote
1answer
24 views

Multiple comparisons correction, for alpha-less criteria like AIC

When performing multiple hypothesis tests, for example in stepwise model selection, we need to apply something like the Bonferroni correction to the alpha/significance value in order to avoid too many ...
0
votes
1answer
94 views

How to calculate AIC and BIC?

I should find formula of BIC and AIC which is used in statsmodels. I have array with values: ...
0
votes
0answers
18 views

How can I determine what value of k to use for an AIC/BIC of a fractional power equation?

I have two equations of which I am trying to determine which is the better fit using AIC and BIC: a quadratic equation of the formula $$\ y = β_{1}x^2+β_{2}x+β_{0}$$ and a fractional power equation ...
0
votes
0answers
21 views

AUC and test MSE as metrics to compare models for zero- and zero-one-inflated data?

I am creating models for 3 response variables, two of which have zero and one-inflated distributions between 0 and 1, and the other has zero-inflated data between 0 and 3. I would like evaluate the ...
0
votes
0answers
14 views

Two (related) questions about forecasting multivariate models with multi-period lags

I am estimating a bunch of different linear or quasi-linear models on several hundred observations of the same multivariate (economic) time series data set. I hope to use the results both for insight ...
0
votes
0answers
12 views

Can I use AIC to compare a random-effects model to a fixed-effects model?

In my project, I want to study certain aspects about individuals. These individuals are clustered into households. First, I did an analysis without taking this clustering into account (linear model). ...
0
votes
0answers
13 views

Nested Model Comparison via AIC

As you know, Log likelihood Ratio Test(LRT) for nested model is well orgarnized. Especially, we can test whether null model is rejected or not by using the fact that LRT test statistics follow chi-...
1
vote
0answers
8 views

What to use deviance or aic for a measure of fitting

I know that the model which has small AIC or small deviance is preferred. But it often occurs that AIC and deviance does not argree. In this case, what measure do I follow? My gratitude goes to any ...
2
votes
1answer
78 views

How to choose a model? Residual deviance or AIC

I have two models of logistic regression with the same variables in the first model I got: Residual deviance: 61.097 on 73 degrees of freedom AIC: 79.097 in the ...
2
votes
0answers
35 views

Comparing fits of linear models that use different data spans of a curve (and why does AIC seem to work)

Several related questions have been asked. This one is similar, but it does not match this question exactly. Also, i seem to have results that contradict the accepted answer there. Data An imperfect ...
0
votes
0answers
11 views

Checking a GLM model using plots, Hoslem test and AIC

I am testing a GLM model from a set of categorical and continuous variables on the incidence of an event. I have first included all variables, then checked for co-linearity. Then did a step-down ...
0
votes
1answer
32 views

Linear mixed model high AIC

I try to create a Linear mixed model by comparing different combinations of random effects. However my AIC score is much higher then I find in tutorials (best 6541.42). Can I still use such a model to ...
0
votes
0answers
63 views

Simple explanation of Takeuchi’s information criterion?

Takeuchi’s information criterion is said to be the generalization of AIC to misspecified models. That publication presents DEGREES OF FREEDOM FOR NONLINEAR LEAST SQUARES ESTIMATION. From that source: ...
1
vote
0answers
23 views

AIC and BIC for wrong models! [closed]

If the models we consider for the data are wrong, what happens to the model selection with AIC or BIC as the data increases? Any hint?
0
votes
0answers
24 views

Stepwise AIC - on which model is the forward- and backward step performed

After I have read on different websites different claims, I hope that someone could may help me with the following question. :) I refere to stepwise AIC w.r.t regression models. In fact, I wonder on ...
3
votes
1answer
255 views

Can I use AIC/BIC to compare a Poisson model to a negative Binomial model?

I would please like to enquire if it's appropriate for me to compare the fit of a Poisson vs. a negative Binomial model for my data, given that the two models are nested, i.e. the negative Binomial ...
1
vote
1answer
67 views

Is there a range of values in the Akaike information criterion (AIC) score that tells us that the model is correct?

I know that when choosing a model, the AIC and BIC criteria are considered since the one with the lowest value will be the one corresponding to the best model, however, I would like to know if; Is ...
0
votes
0answers
22 views

Are information criteria (AIC and SIC) comparable between a linear regression model and a time series model?

I have a problem in which I have to choose the best model between an AR(3) and a MA(3) by comparing the Akaike and Schwarz information criteria. That is fine and easy. The problem comes when I have to ...
0
votes
0answers
11 views

Negative AIC value (R) [duplicate]

When im making a forward selection and looking for the AIC, I get some large negative numbers. My code: ...
0
votes
0answers
36 views

I am trying to fit multiple distributions to my data in R, but can't find out how to do that. Can anyone help me?

I'm doing research on plastic pollution in urban areas. The data represents the amount of plastics for certain segments. To get uniform data, the data is divided by the area where the plastic is found,...
0
votes
0answers
7 views

Is there any criteria to compare different regression methods/models?

I am trying to make a comparison between the lm, gam(mgcv) and lme(nlme) models. The problem is I am not able to find a single criterion on which these 3 models are comparable with each other. I am ...
0
votes
0answers
19 views

Model fit across methods

I have one dataset and I would like to compare analytic methods. The data have to do with risk factors predicting functioning in multiple domains (multiple IVs, multiple DVs). All variables are ...
8
votes
2answers
183 views

Does automatic model selection via AIC bias the p-values of the selected model? [Looking for simulation-based evidence]

Let's say I run a procedure where I fit every possible model given some set of covariates and I select the model with the minimum AIC. I know that if my selection criteria was based on minimizing p-...
3
votes
1answer
64 views

Calculating AIC

I have following data Model 1: Y ∼ B1 + B2 + B3 + B4: log L = −213.4 Model 2: Y ∼ B1 + B2 + B3 + B5: log L = −567.1 The question that i have is "Calculate AIC ...
0
votes
0answers
41 views

Backwards stepwise model building in R

I have been working my way through some data to build a logistic model. I screened variables (most of them categorical) through an unconditional analysis, letting variables with a p-value of <0.2 ...
1
vote
2answers
91 views

AIC calculation with very low negative log likelihood

I am using AIC formula (AIC=2k−2lnL) to compare different exponential models. I know that this formula is used to penalize complexed models (with high number of parameters). The problem I have is that ...

1
2 3 4 5
18