Regression for Exploring Rainfall Pallem in Indramayu Regency

Abstract

Quantile regression is an imp:ll1ant tool for conditional quantiles estimation of a response Y for a given vt':Ct(X" of covariates X. It can be used to measure the effect of covariates not onJy in the center of a distribution, but also in the upper and lower tails. Regression coefficients roc each quantile can be estimated through an objective function which is weighted average absolute errors. Each quantile regression characterizes a particular aspect of a conditional distribution. Thus we can oombine different quantile regressions to describe more completely the underlying conditiona1 distribution. The analysis model of quantile regression would be specifically w:;eful when the conditional distribution is not a nonna1 shape, such as an asymmetric distribution or truncated distribution. In genera1, rainfall in Indramayu regency during 1972-2001 at 23 stations is highly variable in amount across time (month) and SJXlCe. So, the first objective of the rese2TCh is reducing the variability in space using classification of the rainfall stations. The second objective is modelling the variability in time using quantile regression for every cluster of rainfall stations. The result shows that there are tv.{) clusters of rainfall stations. The first cluster has higher amount of rainfall than the second cluster. The coefticient of quanti le regression for quantile 50 and 75 percent are similar, but for quantile 5 and 90 pcrccnt are very different. Exploring (Xlt1em of rainfallll':iing quantile regression can detect noonal or extreme rainfall that very useful in agricultural.