Modelling and forecasting volatility in apparel exports in Sri Lanka with a special reference to COVID 19 pandemic

Abstract

The apparel industry in Sri Lanka contributes predominantly to the country’s economy. Therefore, it is crucial for policymakers and other stakeholders to know about the behavior of apparel and textile exports in order to make informed decisions. Thus, the primary objective of this study is to model Sri Lankan apparel and textile exports for the period of January 2007 to December 2022 and provide accurate forecasts. The ARIMA model was employed to do the univariate time series analysis with modeling and forecasting. Accordingly, ARIMA(0,1,2)(2,0,0)[12] was found to be the bestfitted model. However, after fitting ARIMA model, heteroscedasticity was found in the residuals of the fitted model. Therefore, in order to capture the volatility behavior, a hybrid ARMA-GARCH model was fitted, and the best-fitted model was ARMA(0,2)- GARCH(1,1). Forecasts were generated for the two years ahead. When selecting the most appropriate model from the other candidate models, information criteria such as AIC, AICc, and BIC values were considered, and forecast accuracy was checked with metrics such as MAPE, RMSE, and MAE. The best-fitted model for generating forecasts had a MAPE of 7.26%, which implied a good forecast for the period considered. Apart from the numerical forecasts found for the two-year period, the fluctuations over the study period were also examined using a seasonal plot and a subseries plot. In addition to the seasonal fluctuations due to seasonal variations in the countries of major markets for Sri Lankan apparel and textile exports, a significant drop in export earnings was identified in March 2020 because of the COVID-19 pandemic. However, when scrutinizing the COVID-19 caused fluctuations, it was found that the industry was resilient and could quickly adapt and bounce back within a short period. The findings of this study will provide valuable insights for the government and stakeholders in making informed decisions to improve industry dynamics, considering the impact of the apparel industry on the national economy.