Abstract

This study develops and compares three time series models, ARIMA, ARIMAX, and VAR(p) for short-term inflation forecasting in Sierra Leone to aid evidence-based monetary policy formulation. Using monthly data from January 2018 to June 2023 on the Consumer Price Index (CPI), exchange rate (EXR), and money supply (M2), the study first confirmed that all series are integrated of order one (I(1)) using Augmented Dickey-Fuller (ADF) and Phillips-Perron (PP) tests. The ARIMA and ARIMAX models were estimated using Box-Jenkins methodology, with the ARIMAX model incorporating the exchange rate as an exogenous variable. A VAR(p) model was also specified using differenced series after cointegration tests showed no long-run relationship. Model performance was evaluated over a 12-month out-of-sample period (July 2023–June 2024) using Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE). Results show that the ARIMAX model significantly outperformed ARIMA and VAR(p), achieving the lowest forecast errors (MAPE = 2.03%, RMSE = 4.76), reflecting a 71.8% and 83.3% improvement in MAPE over ARIMA and VAR(p), respectively. These findings confirm the exchange rate as a critical driver of short-term inflation in Sierra Leone. The superior performance of the ARIMAX model underscores the importance of including exogenous (exchange rate) information in inflation forecasting frameworks. Policymakers are advised to closely monitor exchange rate movements as a leading indicator of inflation, highlighting the centrality of exchange rate pass-through effects in inflation dynamics and to consider exogenous-variable-enriched models like ARIMAX for effective short-term inflation targeting.

Keywords

  • Inflation Forecasting
  • ARIMA
  • ARIMAX
  • VAR
  • Exchange Rate
  • Forecast Accuracy
  • Monetary

References

  1. Friedman M. The quantity theory of money – A restatement. In: Friedman M, editor. Studies in the Quantity Theory of Money. Chicago: University of Chicago Press; 1956. p. 3–21.
  2. Fisher I. The Purchasing Power of Money: Its Determination and Relation to Credit, Interest, and Crises. New York: Macmillan; 1911. https://www.econlib.org/library/YPDBooks/Fisher/fshPPM.html
  3. Keynes JM. The General Theory of Employment, Interest and Money. London: Macmillan; 1936.
  4. Phillips AW. The relationship between unemployment and the rate of change of money wage rates in the United Kingdom, 1861–1957. Economica. 1958;25(100):283–299.
  5. Friedman M. The role of monetary policy. Am Econ Rev. 1968;58(1):1–17.
  6. Alnaa SE, Ahiakpor F. ARIMA (autoregressive integrated moving average) approach to predicting inflation in Ghana. J Econ Int Finance. 2011;3(5):328–336.
  7. Doguwa SI, Alade SO. Short-term inflation forecasting models for Nigeria. CBN J Appl Stat. 2013;4(3):1–29.
  8. Iqbal M, Naveed A. Forecasting inflation: Autoregressive integrated moving average model. Euro-pean Scientific Journal 2016;12(1):83–92. https://eujournal.org/index.php/esj/article/view/6887
  9. Ekpenyong EJ, Udoudo UP. Short-term forecasting of Nigeria inflation rates using seasonal ARIMA model. Sci J Appl Math Stat. 2016;4(3):101–107.
  10. Okafor C, Shaibu I. Application of ARIMA models to Nigerian inflation dynamics. Res J Finance Account. 2013;4(3):138–150.
  11. Olajide JT, Ayansola OA, Odusina MT, Oyenuga IF. Forecasting the inflation rate in Nigeria: Box-Jenkins approach. IOSR J Math. 2012;3(5):15–19.
  12. Faisal F. Forecasting Bangladesh’s inflation using time series ARIMA models. World Rev Bus Res. 2012;2(3):100–117.
  13. Adjepong S, Oduro D. Comparison of the forecasting performance of Holt-Winters exponential smoothing and seasonal ARIMA model for Ghana. J Econ Sustain Dev. 2013;4(4):48–58.
  14. Jere S, Siyanga M. Forecasting inflation rate of Zambia using Holt’s exponential smoothing. Open J Stat. 2016;6(2):363–372. https://file.scirp.org/Html/14-1240584_65940.htm
  15. Abdus Salam M, Salam S, Feridun M. Modelling and forecasting Pakistan's inflation by using time series ARIMA models. Econ Anal Working Pap. 2007;2007(1). https://ideas.repec.org/a/eac/articl/01-06.html
  16. Meyler A, Kenny G, Quinn T. Forecasting Irish inflation using ARIMA models. MPRA Paper. 1998; No. 11359.
  17. Mansaray-Pearce EA, Liu P. The determinants of inflation in Sierra Leone: A cointegration analysis. J Econ Sustain Dev. 2015;6(6):121–131.
  18. Gottschalk J, Kalonji KD. Analysing determinants of inflation when there are data limitations: The case of Sierra Leone. [Working Paper].
  19. Kallon, K. M. (1994). An econometric analysis of inflation in Sierra Leone. Journal of African Economies, 3(2), 199–230.
  20. Kabundi A. Dynamics of inflation in Uganda. African Development Bank Group Working Paper. 2012;152.
  21. Kelikume I, Salami A. Time series modelling and forecasting inflation: Evidence from Nigeria. Int J Bus Finance Res. 2014;8(2):41–51.
  22. James LV, Mokoti TP, Molalapata I. Bank of Botswana’s short-term inflation forecasting models. Bank Botswana Res Bull. 2009;23(1):27–35.
  23. Pufnik A, Kunovac D. Short-term forecasting of inflation in Croatia with seasonal ARIMA process-es. Croatian National Bank Working Paper. 2006; No. 16.
  24. Valley AS. Inflation forecasts with ARIMA and vector autoregressive models in Guatemala. Banco De Guatemala Econ Res Dept Working Paper. 2002.
  25. Robinson W. Forecasting inflation using VAR analysis. In: Econometric Modelling of Issues in Car-ibbean Economics and Finance. Port of Spain: Central Bank of Trinidad and Tobago; 1998. p. 231–250.
  26. Box GEP, Jenkins GM. Time Series Analysis: Forecasting and Control. San Francisco: Holden-Day; 1976.
  27. Lütkepohl H. New Introduction to Multiple Time Series Analysis. Berlin: Springer-Verlag; 2005.
  28. Bernanke BS, Boivin J, Eliasz P. Measuring the effects of monetary policy: A factor-augmented vec-tor autoregressive (FAVAR) approach. Q J Econ. 2005;120(1):387–422.
  29. Johansen S. Estimation and hypothesis testing of cointegration vectors in Gaussian vector auto-regressive models. Econometrica. 1991;59(6):1551–1580.
  30. Engle RF, Granger CWJ. Co-integration and error correction: Representation, estimation, and testing. Econometrica. 1987;55(2):251–276.
  31. Bank of Sierra Leone. (1980–2023). Annual reports.
  32. Statistics Sierra Leone. (n.d.). Monthly CPI release. Retrieved from www.statistics.si
  33. World Economic Outlook. (1980–2023). Inflation figures for Sierra Leone.