A time series approach on the effect of climate variability on Davao's coconut production

• Main Authors: Fuentes, Justin Lorenzo R., Ling, Celene Maryse C.
• Format: text
• Language: English
• Published: Animo Repository 2009
• Subjects: Coconut > Climatic factors > Philippines; Time-series analysis; Statistics and Probability
• Online Access: https://animorepository.dlsu.edu.ph/etd_bachelors/5216
• Institution: De La Salle University

Coconut is one of Philippines' major exports and is a major source of income and livelihood for many Filipinos. However, studies on the effect of climate changes on coconut production in the Philippines are limited. The researchers used time series analysis to study the effect of climate variations, specifically of temperature and rainfall on coconut production in Davao Region from 1994-2008. A univariate AR(3) model for quarterly coconut production was obtained and compared with transfer function models that relate coconut production with rainfall, maximum temperature and minimum temperature. For each climate variable, an ARIMA model was fitted that served as pre-whitening filters in identifying transfer function models. The univariate AR(3) model and the transfer functions were compared in terms of the accuracy of their predicted values. The univariate AR(3) model and the transfer function using rainfall as an input series were the best models in terms of predicting coconut production. Using the best models, coconut production was forecasted for the next six years.