Comparison of Model Selection Criteria for Models Including Trend and Seasonal Components in Econometric Time Series

The paper aims to compare commonly used model selection criteria in time series modeling, such as Adjusted R2, log-likelihood, Akaike Information Criterion (AIC), Schwarz Information Criterion (SIC), Hannan-Quinn (HQ) Information Criterion, and Mean Squared Error (MSE). In this context, for an additive time series, data was produced in different sample sizes from n=60 to n=500 from (17) different stationary stochastic processes, including constant, trend, seasonal and irregular components. Each production was repeated 10000 times and the criteria were calculated. For very large sample sizes, the HQ information criterion provides the best results for all types of time series models. It was observed that log-likelihood performed poorly in almost all models. It has been found that "Adjusted R2" is the best option for models with sample sizes less than 120, and "AIC" criterion is the best option for choosing the right model as the sample size increased.

• Publication year

  2025

• Venue

  Ege Academic Review

• Publication date

  2025-12-24

• Fields of study

  Not labeled

• Identifiers
  DOI 10.21121/eab.20260205
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Focused information criteria for model selection – a Bayesian perspective

  2025cited by this paper
• Deviance Information Criterion for Bayesian model selection: Theoretical justification and applications

  2025cited by this paper
• Relative Performance of Model Selection Criteria for Cox Proportional Hazards Regression Based on Kullback’s Symmetric Divergence

  2025cited by this paper
• Information criteria for model selection

  2023cited by this paper
• Model Performans Kriterlerinin Kronolojisine ve Metodolojik Yönlerine Genel Bir Bakış: Bir Gözden Geçirme

  2020cited by this paper
• Performance comparison of model selection criteria by generated experimental data

  2018cited by this paper
• Computational Method for Extracting and Modeling Periodicities in Time Series

  2015cited by this paper
• Testing for deterministic and stochastic cycles in macroeconomic time series

  2007cited by this paper
• Methods and Criteria for Model Selection

  2004cited by this paper
• AIC and BIC

  2004cited by this paper
• Bayesian Model Selection and Model Averaging.

  2000cited by this paper
• Regression and Time Series Model Selection

  1998cited by this paper
• A comparison of model selection criteria

  1992cited by this paper
• Estimation Procedures for Structural Time Series Models

  1990cited by this paper
• Regression and time series model selection in small samples

  1989cited by this paper
• Likelihood of a model and information criteria

  1981cited by this paper
• The determination of the order of an autoregression

  1979cited by this paper
• Estimating the Dimension of a Model

  1978cited by this paper
• Fourier analysis of time series

  1976cited by this paper
• On the Probability of Correct Model Selection Using the Maximum R2 Choice Criterion

  1975cited by this paper

• No citing papers are available for this paper.