Claim Missing Document
Check
Articles

Found 3 Documents
Search

TIME SERIES IMPUTATION USING VAR-IM (CASE STUDY: WEATHER DATA IN METEOROLOGICAL STATION OF CITEKO) Rizal, Muhammad Edy; Wigena, Aji H; Afendi, Farit M
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 16 No 4 (2022): BAREKENG: Journal of Mathematics and Its Applications
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (851.852 KB) | DOI: 10.30598/barekengvol16iss4pp1373-1384

Abstract

Univariate imputation methods are defined as imputation methods that only use the information of the target variable to estimate missing values. While univariate imputation methods are convenient and flexible since no other variable is required, multivariate imputation methods can potentially improve imputation accuracy given that the other variables are relevant to the target variable. Many multivariate imputation methods have been proposed, one of which is Vector Autoregression Imputation Method (VAR-IM). This study aims to compare imputation results of VAR-IM-based methods and univariate imputation methods on time series data, specifically on long lag seasonal data such as daily weather data. Three modified VAR-IM methods were studied using simulations with three steps: deletion, imputation, and evaluation. The deletion step was conducted using six different schemes with six missing proportions. The simulations were conducted on secondary daily weather data collected from meteorological station of Citeko from January 1, 1991, to June 22, 2013. Nine weather variables were examined, that is the minimum, maximum, and average temperatures, average humidity, rainfall rate, duration of solar radiation, maximum and average wind speed, as well as wind direction at maximum speed. The simulation results show that the three modified VAR-IM methods can improve the accuracies in around 75% of cases. The simulation results also show that imputation results of VAR-IM-based methods tend to be more stable in accuracy as the missing proportion increase compared to the imputation results of univariate imputation methods.
PEMODELAN CLUSTERWISE REGRESSION PADA STATISTICAL DOWNSCALING UNTUK PENDUGAAN CURAH HUJAN BULANAN Butar-butar, Victor Pandapotan; Soleh, Agus M; Wigena, Aji H
Indonesian Journal of Statistics and Applications Vol 3 No 3 (2019)
Publisher : Statistics and Data Science Program Study, SSMI, IPB University, in collaboration with the Forum Pendidikan Tinggi Statistika Indonesia (FORSTAT) and the Ikatan Statistisi Indonesia (ISI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/ijsa.v3i3.310

Abstract

Statistical downscaling (SDS) is one of the developing models for rainfall estimation. The SDS model is a regression model used to analyze the relation of global (GCM output) and local data (rainfall). Rainfall has large variance so that clustering is needed to minimize the variance. One of the analytical methods that can be used in clustering rainfall estimation is cluster wise regression. There are three Methods for Clusterwise regression namely Linear Regresion, Finite Mixture Method (FMM) and Cluster-Weighted Method (CWM). This study used GCM outputs data namely CFRSv2 as a covariate. The response variable is rainfall data in four stations such as Bandung, Bogor, Citeko and Jatiwangi from BMKG. The purpose of this study is to increase the accuracy of rainfall estimation using the three methods and compare the clusterwise regression with PCR and PLS models. Based on the value of RMSEP, the clusterwise regression with FMM was the best method to estimate rainfall in four stations.
PEMODELAN AUTOREGRESIF SPASIAL MENGGUNAKAN BAYESIAN MODEL AVERAGING UNTUK DATA PDRB JAWA Sarimah, Sarimah; Djuraidah, Anik; Wigena, Aji H
Indonesian Journal of Statistics and Applications Vol 3 No 3 (2019)
Publisher : Statistics and Data Science Program Study, SSMI, IPB University, in collaboration with the Forum Pendidikan Tinggi Statistika Indonesia (FORSTAT) and the Ikatan Statistisi Indonesia (ISI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/ijsa.v3i3.376

Abstract

Economic data always contains spatial effects. Gross Regional Domestic Product (GRDP) in Java is one of economic data that describes spatial dependence between adjacent districts/cities. The method that is suitable for modeling GDRP is spatial regression with spatial dependence on lags that is spatial autoregressive. GDRP prediction used the Bayesian Model Averaging (BMA) method. The ten autoregressive spatial model that have highest posterior probability was chosen to determined the BMA model by posterior probability. The explanatory variables used in this study were (1) mean years of schooling (2) life expectancy (3) income per capita (4) local revenue (5) number of workers (6) district minimum salary. The results showed that the number of workers was chosen as a predictor for the ten models. The model that have highest posterior probability probability is 0.54 which contains five explanatory variables that are mean years of schooling, income per capita, local revenue, number of workers and district minimum salary and the pseudo R2 of the model is 0.696.