|Generate QR code
Open Access
Subscription Access
Seasonal Adjustment of Weekly Consumer Price Index Estimates
https://doi.org/10.34023/2313-6383-2025-32-3-51-61
Abstract
The article covers methods for removing seasonality from weekly consumer price index (CPI) figures, published by Rosstat. The impact of the seasonal factor on weekly CPI estimates and its components complicates the analysis of their dynamics. The paper, therefore, substantiates the need for seasonal adjustment of the index. In the Russian economic literature, the issue of removing a seasonal component from the CPI weekly frequency has never been examined before.
The study aims to determine the best methods for seasonal adjustment of weekly CPI estimates based on a comparative analysis of models applied universally using direct (adjustment of the entire index) and indirect (adjustment of constituent parts) approaches. Study objectives include considering application of the MoveReg, Prophet, and STL (Seasonal-Trend decomposition using Locally estimated scatterplot smoothing) models to eliminate seasonality influence on the weekly CPI and its components dynamics; testing the models effectives using autocorrelation functions, as well as the Ljung-Box statistical test and its modified version (QS test) and choosing the most preferable one. Experimental model testing was carried out on Rosstat data, including information on prices for individual goods and services as part of the weekly CPI from July 2017 to December 2024.
The study determined that to eliminate the influence of seasonality on weekly CPI estimates, it is appropriate to use the direct approach, applied to the entire index rather than to each of its constituent parts separately. Based on the study’s findings, the STL model was found to be the most preferable one, as it is less likely to «overfit» compared to the other two models. This reduces the risk of excessive seasonality reduction.
About the Author
R. R. Latypov
Lomonosov Moscow State University
Russian Federation
Russian Federation
Rodion R. Latypov – Third-Year Postgraduate Student, Department of Mathematical Methods for Economic Analysis, Faculty of Economics
1-46, Leninskiye Gory, GSP-1, Moscow, 11999
References
1. Sapova A.K. et al. Peculiarities of the Consumer Price Index Seasonal Adjustment. Voprosy Statistiki. 2018; 25(5):42–54. (In Russ.)
2. Mollins J., Lumb R. Seasonal Adjustment of Weekly Data. Bank of Canada Staff Discussion Paper, No. 2024-17. Ottawa: Bank of Canada; 2024. Available from: https://doi.org/10.34989/sdp-2024-17.
3. Evans T.D., Monsell B.C., Sverchkov M. Review of Available Programs for Seasonal Adjustment of Weekly Data. In: 2021 Joint Statistical Meetings, August 8–12, 2021, virtual. Available from: https://www.bls.gov/osmr/research-papers/2021/pdf/st210020.pdf.
4. Harvey A., Koopman S.J., Riani M. The Modeling and Seasonal Adjustment of Weekly Observations. Journal of Business & Economic Statistics. 1997;15(3):354–368. Available from: https://doi.org/10.2307/1392339.
5. Cleveland W., Evans T., Scott S. Weekly Seasonal Adjustment – A Locally-Weighted Regression Approach. Economic Working Papers 473, Bureau of Labor Statistics. Available from: https://www.bls.gov/osmr/research-papers/2014/pdf/ec140040.pdf.
6. Taylor S., Letham B. Forecasting at Scale. The American Statistician. 2018;72(1):37–45. Available from: https://doi.org/10.1080/00031305.2017.1380080.
7. Cleveland R.B. et al. STL: A Seasonal-Trend Decomposition Procedure Based on Loess. Journal of Official Statistics. 1990;6(1):3–73.
8. Cleveland W.S., Devlin S.J. Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting. Journal of the American Statistical Association. 1988;83(403):596–610. Available from: https://doi.org/10.1080/01621459.1988.10478639.
9. Savitzky A., Golay M.J.E. Smoothing and Differentiation of Data by Simplified Least Squares Procedures. Analytical Chemistry. 1964;36(8):1627–1639. Available from: https://doi.org/10.1021/ac60214a047.
10. Bandara K., Hyndman R.J., Bergmeir C. MSTL: A Seasonal-Trend Decomposition Algorithm for Time Series with Multiple Seasonal Patterns. arXiv preprint arXiv:2107.13462. Available from: https://arxiv.org/abs/2107.13462.
11. Ljung G.M., Box G.E.P. On a Measure of a Lack of Fit in Time Series Models. Biometrika. 1978;65(2):297–303. Available from: https://doi.org/10.1093/biomet/65.2.297.
12. Ollech D. Seasonal Adjustment of Daily Time Series. Deutsche Bundesbank. Discussion Paper No 41/2018. Available from: https://www.bundesbank.de/resource/blob/763892/f5cd282cc57e55aca1eb0d521d3aa0da/mL/2018-10-17-dkp-41-data.pdf.
Review
For citations:
Latypov R.R. Seasonal Adjustment of Weekly Consumer Price Index Estimates. Voprosy statistiki. 2025;32(3):51-61. (In Russ.) https://doi.org/10.34023/2313-6383-2025-32-3-51-61
Views:
279
Email this article 