Modeling Consumer Price Index of Thailand

The CPI attempts to quantify the overall price levels of goods and services in an economy and to measure the purchasing power of a respective country's currency unit. The CPI is used in the calculation of many key economic indicators that require a country's unit of currency measures, including estimates of income, earnings, productivity, output, and poverty. Thailand's CPI shows an upward trend. This study is designed to forecasts the CPI of Thailand. Monthly CPI data of Thailand for the period of May 2012 to October 2021 were obtained from the International Monitory Fund (IMF) database. Auto-Regressive Distributed Lag Model (ARDLM), Double Exponential Smoothing (DES), and Autoregressive Integrated Moving Average (ARIMA) models were tested to forecast the CPI of Thailand. Auto Correlation Function (ACF), Anderson Darling test and Ljung-Box Q (LBQ) test were applied to test the model assumptions. The relative and absolute measurements of errors were applied to assess the forecasting ability of the model. Results of the study revealed that the ARDLM with lags 1 and 2 is the most suitable model to forecast the CPI of Thailand. The future values of the CPI can be forecasted by the value of the last month and the month before. It is strongly recommended to design more studies on modeling the CPI for other countries furthermore