Forecasting Monthly Maximum Temperature of Karachi City using Time Series Analysis

Abstract

The maximum temperature has led to several complications in our day to day life in the city of Karachi. Rising temperature has affected human health and in some cases has led to the deaths of civilians. In this study, the temperature data of Karachi city in Pakistan over period from January 2005 to December 2015 is assessed. A preliminary graphical method added with the analysis of Autocorrelation and Partial Autocorrelation Function indicated that the data is not stationary and has seasonal factor. SARIMA model of order (0, 0, 2) with seasonal order (2, 1, 1) and period 12 is used to forecast the maximum temperature of the Karachi city over a period of 12 months. We use R software to complete this study. This study will help the policy makers and the insurers to better plan for the future.