Abstract
This study quantifies the Gregorian seasonality of monthly retail trade turnover in Uzbekistan and the effects of moving holidays tied to the Islamic (Hijri) calendar—the month of Ramadan, Eid al-Fitr and Eid al-Adha—and identifies a reliable forecasting model. Using official data of the National Statistics Committee for January 2020 – September 2026 (81 observations), regARIMA (SARIMA “airline”) models augmented with calendar regressors, automatically detected outliers and a level shift are estimated alongside regression models with deterministic seasonality. Seven competing models are compared in a rolling-origin forecasting exercise covering 2023–2026. The Gregorian component dominates the seasonal pattern: turnover in December is 128% higher than in January and accounts for 13–18% of annual turnover. Ramadan lowers monthly turnover by 13.5% on average, whereas the days preceding Eid raise it by 3.1%. These effects, however, are not statistically significant (joint Wald test, p = 0.55) and mainly reflect a reallocation of purchases across months. Calendar regressors nevertheless reduce the forecast error (RMSE) by about 10% in months affected by Ramadan. An equal-weight combination of two models yields the most accurate forecasts at the three-month horizon (MAPE of 9.9%). Turnover is projected to reach 649 trillion soums in 2026 and 770 trillion soums in 2027.
References
[1] National Statistics Committee of the Republic of Uzbekistan. (2026). Retail trade turnover, January 2020 – September 2026 [Data set: SIAT indicators 1.07.02.0003 and 1.07.02.0006; analytical report for January–December 2025; domestic trade press releases for 2026]. https://api.siat.stat.uz/media/uploads/sdmx/sdmx_data_2821.pdf
[2] Bell, W. R., & Hillmer, S. C. (1983). Modeling time series with calendar variation. Journal of the American Statistical Association, 78(383), 526–534. https://doi.org/10.1080/01621459.1983.10478005
[3] Findley, D. F., Monsell, B. C., Bell, W. R., Otto, M. C., & Chen, B.-C. (1998). New capabilities and methods of the X-12-ARIMA seasonal-adjustment program. Journal of Business & Economic Statistics, 16(2), 127–152. https://doi.org/10.1080/07350015.1998.10524743
[4] Riazuddin, R., & Khan, M. H. (2005). Detection and forecasting of Islamic calendar effects in time series data. SBP Research Bulletin, 1(1), 25–34.
[5] Campante, F., & Yanagizawa-Drott, D. (2015). Does religion affect economic growth and happiness? Evidence from Ramadan. The Quarterly Journal of Economics, 130(2), 615–658. https://doi.org/10.1093/qje/qjv002
[6] Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). Wiley.
[7] Hyndman, R. J., Koehler, A. B., Snyder, R. D., & Grose, S. (2002). A state space framework for automatic forecasting using exponential smoothing methods. International Journal of Forecasting, 18(3), 439–454. https://doi.org/10.1016/S0169-2070(01)00110-8
[8] Chen, C., & Liu, L.-M. (1993). Joint estimation of model parameters and outlier effects in time series. Journal of the American Statistical Association, 88(421), 284–297. https://doi.org/10.1080/01621459.1993.10594321
[9] Bates, J. M., & Granger, C. W. J. (1969). The combination of forecasts. Operational Research Quarterly, 20(4), 451–468. https://doi.org/10.1057/jors.1969.103
[10] Wang, X., Hyndman, R. J., Li, F., & Kang, Y. (2023). Forecast combinations: An over 50-year review. International Journal of Forecasting, 39(4), 1518–1547. https://doi.org/10.1016/j.ijforecast.2022.11.005
[11] Diebold, F. X., & Mariano, R. S. (1995). Comparing predictive accuracy. Journal of Business & Economic Statistics, 13(3), 253–263. https://doi.org/10.1080/07350015.1995.10524599
[12] Harvey, D., Leybourne, S., & Newbold, P. (1997). Testing the equality of prediction mean squared errors. International Journal of Forecasting, 13(2), 281–291. https://doi.org/10.1016/S0169-2070(96)00719-4

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.