Econometric Modelling for Missing Weather Variables Estimation: Shinyanga Region of Tanzania

Abstract

This study was conducted to develop econometric models for weather variables for Shinyanga region of Tanzania. The developed models used to predict missing weather variables such as sunshine, maximum, and minimum temperatures from 1981 to 1987. The authors used weather time series data including rainfall, sunshine, maximum, and minimum temperatures from 1981 to 2017 to establish statistical relationship among variables from Mbeya and Shinyanga regions. Various statistical methods used include Ordinary Least Square regression, Augmented Dickey-Fuller test for Unit root test of time series stationarity, Johansen Cointegration test and error correction to establish relationship among variables. We developed three econometric models for missing sunshine, maximum and minimum variables for Shinyanga region. Sunshine model shows that for each unit rainfall (mm) increase in Mbeya region increased the sunshine for Shinyanga by 3.8%, while for each increase in lmm rainfall in Shinyanga region the sunshine decreases by 1%. Maximum temperature model reveals that increase in rainfall in Mbeya by lmm decreases the maximum temperature by 0.5 % while for each increase by lmm rainfall in Shinyanga leads to a decrease of maximum temperature by 0.7%. For the minimum temperature model, 1 mm increase in both Mbeya and Shinyanga rainfall decreases the minimum temperature for Shinyanga by 0.4 % while increase in 1°C minimum temperature for Mbeya region increases Shinyanga minimum temperature by 43%. Accordingly, we estimated the missing variables by the use of the respective constructed models.