Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [bic]

BIC is an acronym for Bayesian Information Criterion. BIC is one method of model comparison. See also AIC

1
vote
0answers
20 views

Asymptotic equivalence between cross validation and bayesian information criteria

I heard that Bayesian information criteria and cross validation are asymptotically equivalent when the size of validation set is large enough similar to the relationship between Akaike information ...
1
vote
1answer
38 views

Understanding Intuition for ETS Damping Selection via AIC/BIC

I'm trying to understand how ETS selects whether to use a damped model via information criteria (I'm not sure which of AIC, AICc or BIC are used). I have a time series and I'm comparing two ETS ...
2
votes
1answer
66 views

Selecting between OLS regression and ARIMA for time series, why AIC or BIC for ARIMA is much larger in my data?

My data set is quarterly time seires data (around 140 data points). Method 1: simple OLS regression with 5-6 exogenous variables, which are drivers of the dependent variable. None of the explanatory ...
0
votes
1answer
24 views

AIC calculated in lm(y~1) and stepwise selection in R

http://www.stat.wisc.edu/courses/st333-larget/aic.pdf The AIC calculated with the model lm(SAT~1) was 560.4736, but the AIC calculated with stepwise selection starting with lm(SAT~1) was 419.42. May ...
0
votes
0answers
17 views

How to implement Bayesian Information Criterion (BIC) in a practical problem?

I found a lot of theoretical literature about BIC online, but I had a difficult time when I was trying to find a real case. So I was wondering how do we implement the BIC in a practical problem? Do ...
0
votes
0answers
11 views

Information criterion when model could be mis-specified and data is dependent

Common information criteria (AIC, BIC, etc) require the user to specify the likelihood function, while in practice rarely the user has the luxury to know the correct likelihood function. In the case ...
0
votes
1answer
29 views

How can we calculate AIC from a negative binomial GLMM?

Our problem here described is to calculate AIC from a GLMM negbin. Our data compose by 2 Categorical variables (Yes/Not), 3 Numerical variables and our random factor, all without any NA. We want to ...
0
votes
0answers
54 views

How to optimise Linear Predictive Coding model using AIC/BIC

I am currently using an LPC function in Python that takes a signal x and an order and returns the solution a, the prediction error e, and the reflection coefficients k. The aim is to fit a filter to ...
0
votes
0answers
11 views

Bayesian information criterion (BIC) on KDE?

Consider two datasets, $X$ and $Y$. Both have 2 dimensions with $a$ and $b$ samples respectively. I would like to test whether one kernel density estimate (KDE) on the concatenated data ($XY$, shape $...
1
vote
1answer
123 views

Best BIC value for K-means clusters

I am using code from Using BIC to estimate the number of k in KMEANS (answer by Prabhath Nanisetty) to find BIC values for K-means using different number of components. However, using iris dataset, I ...
1
vote
0answers
15 views

How to use a previously calculated set of clusters to start EM Clustering in R?

I have performed Hierarchical Clustering on a data set. I would now like to compare the BIC of the clustering methods. The process involves using the clusters you have determined to act as your ...
0
votes
0answers
42 views

Calculating BIC for Hierarchical Clusters in R

I'm performing Hierarchical Clustering Analysis on a set of data where I have a cohort of patients, and I am clustering them according to a set of variables. I have used hclust to perform the ...
1
vote
0answers
18 views

AIC and BIC and number of quantization level

I want to test how many quantization levels (discretizing levels) are the best for the given data(time series) set I have. Therefore I am applying different levels of binning (like discretisize data ...
2
votes
0answers
82 views

Time series analysis VAR model: AIC and BIC test criteria

Consider two variables. Imagine you want to analyse the effects of the lags of variable A on variable B. The possiblity you see an effect of variable A on B is reasonable, but there is absolutely no ...
4
votes
2answers
273 views

What is the actual significance of a difference in AIC or BIC values?

Usually, when a difference of a statistic is discussed, that discussion is presented in the context of a significance of that difference. When self-entropy, i.e., information content, is examined, ...
6
votes
1answer
311 views

Elbow Test using AIC/BIC for identifying number of clusters using GMM

How to select number of clusters using GMM when the elbow test (AIC/BIC vs n_components) results in a graph like this?
1
vote
0answers
34 views

AIC and BIC in Latent class analysis

I am using the Latent Class Analysis feature available in Stata 15. The two statistical criterions gave me different indications: $AIC$ suggests me to use 6 classes, instead $BIC$ suggests to use 5 ...
5
votes
1answer
330 views

When is the AIC a good model selection criterion for forecasting and when is it not?

I'm trying to wrap my head around why the AIC and other similar ICs work as proxies for out of sample error when trying to perform automated forecast generation. So I performed an experiment on the ...
1
vote
1answer
54 views

How to choose the number of steps ahead when comparing time series CV to the AIC or the BIC?

I would like to empirically evaluate the performance of the AIC, BIC and Cross Validation as model selection criteria for time series forecasting, i.e. which one of these criteria leads to the best ...
1
vote
0answers
186 views

Elbow Method or/and Bayesian Information Criterion to select the optimal number of clusters

I am working k-means cluster analysis. I am new in R and even newer with cluster analysis, but happy to learn. I have managed to plot the following two figures to select the optimal number of ...
3
votes
1answer
63 views

As you drop variables, can AIC or BIC go up and then down?

I have some potential spline models and I'm trying to use AIC or BIC to choose variables. I'm seeing that AIC is lower when I use all variables than if I exclude any one or two. However, if I exclude ...
0
votes
0answers
33 views

Clustering with mclust and cluster packages in R [duplicate]

I need to group my data into few buckets and wanted to use clustering with R. It is important that I cluster it right as my downstream processing largely depends on how well the data is clustered ...
0
votes
0answers
12 views

Comparing model fit with different number of choice occasions

I have estimated 2 models, one where each choice is modeled separately, while the other considers panel effects, thus reducing the number of choice occasions. Can I still use BIC to compare the two ...
11
votes
2answers
1k views

Is it possible that the AIC and BIC give totally different model selections?

I'm performing a Poisson Regression model with 1 response variable and 6 covariates. Model selection using AIC results in a model with all covariates as well as 6 interaction terms. The BIC however, ...
0
votes
1answer
31 views

BIC estimate for multidimensional data

I want to use the Bayesian Information Criterium (BIC) to infer the number of clusters in a clustering algorithm, but I have two doubts. Suppose I have $N$ points in a $D$-dimensional space, and that ...
0
votes
0answers
16 views

Statistics for information criteria of a model selection procedure

When applying a binary hypotheses testing, on an additive normal vector of measurements, assuming some regulations (similar variance) and using an information criterion of the form $$\hat{L}+P^{s}(N, ...
1
vote
0answers
249 views

Interpreting negative vs positive BIC values

I have fit time series data to two models using SPSS. Their BIC values are as follows: Normalised BIC, Winters: -.111, ARIMA: .048 I understand I must ...
0
votes
0answers
157 views

Using BIC to determine K in K means on Grayscale and RGB image

I have used the following k-means algorithm Place K points into the space represented by the objects that are being clustered. These points represent initial group centroids. Assign each object to ...
1
vote
0answers
383 views

Correct calculation of BIC (Bayesian Information Criterion) to determine K for K-Means

I am trying to calculate BIC in python. In python, there is no inbuilt library for computing BIC. I referenced the following link to compute variance and BIC further:- Using BIC to estimate the number ...
0
votes
0answers
38 views

How to derive EBIC for sparse linear regression with group lasso penalty for selecting optimum hyper parameter?

I have regression model with sparse group lasso penalty with following loss function: $||Y-\beta X||^2 + \lambda|\beta|_1 + \gamma \sum_1^g ||G_g||_2$ where $G$ is subset of $\beta$ . I have ...
0
votes
0answers
21 views

Significance levels vs Information criterion

Modelling financial time series data. My mean equation was an AR(1) process. Planning to forecast the data in-sample and I have a TGARCH with IC indicating it is a better model, but the p-value for ...
2
votes
2answers
513 views

In Bayesian Information Criterion(BIC), why does having bigger N get penalized?

The Bayesian Information Criterion (BIC) is calculated with: where RSS is resudial sum of suqares and delta squared is estimate of the variance of the error associated with each response measurement. ...
0
votes
0answers
81 views

Using AIC to find a horizontal line (linear vs non-linear models)

I would like to statistically test which of the following functions is best described by a straight horizontal line (slope of 0), rather than another function, e.g. an exponential decay function or ...
2
votes
0answers
435 views

Calculating the AICc and BIC with RSS instead of likelihood

I have found here that that the akaike information criteria, corrected for small sample sizes is: where: And that the likelihood can be replaced with residual sum of squares (RSS) divided by n, the ...
1
vote
0answers
9 views

Bayesian Information Criteria variable penalisation for increasing N

I am trying to understand the Bayesian Information Criteria for model performance, given by the formula below: BIC=−2ln(L)+kln(n) I understand the aim is to minimize this function. I can see that ...
0
votes
0answers
50 views

Deciding the optimal ARMA model

The correlogram structure of the returns series I estimated (up to two lags) had an almost identical ACF and PACF structure. The signs were identical, and the magnitudes of the ACF and PACF up to 12 ...
1
vote
0answers
46 views

Interpretation of plots for outlier detection in healthcare

Christy et al. propose cluster-based approach to outlier detection as part of the preprocessing step. However, I don't think the plots are very interpretable. The authors use the R mclustbic function ...
0
votes
0answers
200 views

Comparing AIC and BIC of CFA and IRT

I was wondering does it make sense to compare AIC and BIC values of confirmatory factor analysis models and item response theory models? In many cases, goodness of fit indices for item response theory ...
2
votes
1answer
129 views

AIC/BIC for a segmented regression model?

Can AIC/BIC be calculated reliably for a segmented regression model? If so, can the results be compared against AIC/BIC calculations for non-segmented regression models on the same data?
1
vote
1answer
328 views

Are parsimonious models always better?

In my classes there is always some mention of AIC/BIC. Certainly model complexity is an important thing to penalize for in the sense that you don't want to include variables that are unnecessary. Is ...
4
votes
1answer
75 views

Residual Plots for Model Comparison

Other than using AIC and BIC, I'd like to compare two different models via graphical interpretation, therefore my question is, is it possible to compare two regression models with each one having the ...
0
votes
0answers
21 views

Compare two models with different priors

I want to compare two models' goodness-of-fit using BIC (and the same dataset), however, I know that one model is 100 times more probable a priori. Models have different number of parameters. Where ...
1
vote
0answers
38 views

BIC useless as it depends on units?

The Bayesian Information Criterion (BIC) is proportional to the log of the maximised likelihood. The likelihood is a density with units given by the inverse units of the parameters. We are free to ...
0
votes
0answers
16 views

Problems with repeated model selection from more than two models

In research on decision making the usual process to determine the strategies/models used by participants is to fit all possible models separately for each participant and then compare them for each ...
0
votes
0answers
43 views

Constructing a unified path analysis model from several datasets each with different combinations of variables

I have four observational experiments (data sets) that I wish to combine and summarize in a single path analysis model. Each experiment is 3-dimensional but the observables and therefore dimensions/...
7
votes
1answer
402 views

How can the AIC or BIC be used instead of the train/test split?

I've recently come across several "informal" sources that indicate that in some circumstances, if we use the AIC or BIC to train a time series model, we don't need to split the data into test and ...
0
votes
0answers
212 views

Differents values of number of clusters with the BIC criteria

I'm using a code to compute the BIC score (found in a topic of this communauty) to find the best number of cluster k for a clustering problem . But each run of this code conclude a different value of ...
2
votes
1answer
242 views

If the AIC and the BIC are asymptotically equivalent to cross validation, is it possible to dispense with a test set when using them?

Several sources I've come across state that the AIC and the BIC are asymptotically equivalent to cross-validation (see multiple answers here for example, and here), . When training a predictive ...
0
votes
1answer
32 views

AIC and BIC are so small while the loglikelihood is larger when comparing two different models

I am working with complex models. I fitted two different models to my data. Then, I calculate the logliklihood function and the AIC and BIC values. I found that the log likelihood of the first models ...
3
votes
1answer
559 views

Number of components for Gaussian mixture model?

I have a vector of numeric values. My hypothesis is that this vector is a mixture drawn from two Gaussian distributions (ie k = 2). However, it is possible that there is only one Gaussian underlying ...