TIME SERIES MODELLING OF RELATIVE HUMIDITY IN UYO METROPOLITAN CITY USING BOX AND JENKIN’S APPROACH

ABSTRACT The focus of the study was to model the amount of relative humidity of Uyo which were collected from the Department of Geography and regional planning, University of Uyo, Akwa Ibom State for a period of eleven (11) years (2013 to 2023). The time plot shows an annual recurrent of relative humidity. The Autocorrelation Function (ACF) of the original series shows significant spikes at seasonal lags while its partial autocorrelation function (PACF) shows a cutoff at lag 12, the series was transformed by differencing. The ACF of the first differenced series indicates a significant spikes at lag 1 and 12 with one spike at lag 24 and its PACF shows significant spike at lag 1 and a cutoff at lag 12 indicating the presence of seasonal autoregression integrated moving average (SARIMA) model. SARIMA (1,1,1) × (1,0,0)₁₂ and SARIMA (0,1,1) x (1,0,0)₁₂ were tentatively identified and fitted to the relative humidity data, but during seasonal differencing SARIMA (0,0,0) × (0,1,1)₁₂ model was found to be suitable to the series after series of diagnostic checks. The forecast generated from SARIMA (0,0,0) X (0,1,1)12 model indicate future increase in April and decrease in March for the first five month of relative humidity in Uyo.