An Initial Study on the Forecast Model for Unemployment Rate Mohd Nadzri Mohd Nasir, Kon Mee Hwa and Huzaifah Mohammad1
Abstract The purpose of the article is to determine the most suitable technique to generate the forecast of unemployment rate using data from the series of Labour Force Surveys. The models understudied are based on Univariate Modelling Techniques i.e. Naïve with Trend Model, Average Change Model, Double Exponential Smoothing and Holt’s Method Model. These models are normally used to determine the short-term forecasts (one quarter ahead) by analyzing the pattern such as quarterly unemployment rates. The performances of the models are validated by retaining a portion of the quarterly observations as holdout samples. In addition, comparisons are made to see how well the historical and forecasted data matched and correlated. The selection of the most suitable model was indicated by the smallest value of mean square error (MSE). Based on the analysis, Holt’s Method Model is the most suitable model for forecasting quarterly unemployment rates. Keywords: Univariate Modelling Techniques; Forecast Model; Mean Square Error.
Introduction Forecasting is defined as the prediction of future events based on known past values of relevant variables (Makridakis, S., Wheelright, S. C. & Hyndman, R. J., 1998). Forecasting unemployment rate accurately is important because it helps economists to have a better idea of what the future economy holds (Lewis, R., & Brown, C., 2001). Besides, it is also important for the government in terms of decision and policy making. With the support of stable economic growth, Malaysia experienced low unemployment rates in the 1990s with the lowest recorded in 1997 at 2.4 per cent. From 1999 onwards, the unemployment rate has increased as a result of the financial crisis and subsequent economic downturn. Univariate Modelling Techniques are methods for analyzing data on a single variable at a time. Examples of Univariate Modelling Techniques are the Naive Models, Methods of Average, the Exponential Smoothing Techniques and the
Mohd Nadzri Mohd Nasir is currently the Director of Department of Statistics, Pahang, Kon Mee Hwa is Assistant Director of Services Statistics Division and Huzaifah Mohammad is Assistant Statistical Officer of Price, Income and Expenditure Statistics Division.
Mohd Nadzri Mohd Nasir, Kon Mee Hwa And Huzaifah Mohammad
Box-Jenkins Methodology. Both Double Exponential Smoothing and Holt’s Method illustrated in this study are classified in the Exponential Smoothing Techniques. Other models available in this same category are Single Exponential Smoothing, Adaptive Response Rate Exponential Smoothing (ARRES), Holt’s Method and Holt-Winters’ Trend & Seasonality. This paper is divided into several sections. Following the introduction, the second section describes the definitions, objectives and literature review of the study, the third section focuses on the methodology and some of the attempts made to move beyond the models. In this section, a same set of unemployment data were tested using four different univariate forecasting models to obtain MSE value. The fourth section goes beyond the discussion of analysis and results while the fifth section explores selection of models. This is followed by a normality test, paired samples t-test and a correlation test on the chosen model. The final section presents an evaluation of Holt’s Method and a brief conclusion.
Definition of unemployment International Labour Organization (ILO) defines “Unemployed” as all individuals above a specified age who satisfies simultaneously the following criteria: a) b) c) without work (not in paid or self employment); currently available for paid employment or self-employment; and actively seeking work.
The “unemployment rate” is defined as the share of people not working, available and actively seeking for work out of the working age population (ILO Geneva, 1990). Basic economic...
Please join StudyMode to read the full document