Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Xplore: Journal of Statistics

Pemodelan Regresi Spasial Kekar: Studi Kasus Jumlah Kunjungan WIsatawan Mancanegara Asal Eurasia di Indonesia Tahun 2015 Resti Cahyati; Anik Djuraidah; Septian Rahardiantoro
Xplore: Journal of Statistics Vol. 2 No. 1 (2018): 30 Juni 2018
Publisher : Department of Statistics, IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (388.691 KB) | DOI: 10.29244/xplore.v2i1.85

Abstract

Spatial regression model is a model used to evaluate the relationship between one variable with some other variables considering the spatial effects in each region. One of the causes of imprecise spatial regression model in predicting is the presence of outlier or extreme value. The existence of outlier or extreme value could damage spatial regression parameter estimator. However, discarding the outlier or extreme value in spatial analysis, could change the composition of the spatial effect on the data. Visitor arrivals from Eurasia to Indonesia by nationality in 2015 great diversity caused by the outlier. So in this paper, we need a spatial regression parameter estimation method which is robust where the value of the estimation is not much affected by small changes in the data. The application of the S prediction principle is carried out in the estimation of the coefficient of spatial regression parameters which is robust to the observation of silane. The result of modeling by applying the principle of the S estimator method on the estimation of the stocky spatial regression parameter is able to accommodate the existence of pencilan observation on the spatial regression model quite effectively. This is indicated by a considerable change in the coefficient coefficient estimator parameters of spatial regression is able to decrease the value of MAPE and MAD produced by spatial regression regression modeling.
Pendugaan Produktivitas Bagan Perahu dengan Regresi Gulud, LASSO dan Elastic-net Resty Fanny; Anik Djuraidah; Aam Alamudi
Xplore: Journal of Statistics Vol. 2 No. 2 (2018): 31 Agustus 2018
Publisher : Department of Statistics, IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (332.547 KB) | DOI: 10.29244/xplore.v2i2.89

Abstract

Regression analysis is a statistical technique to examine and model the relationship between dependent variable and independent variable. Multiple linear regression includes more than one independent variable. Multicollinearity in multiple linear regression occurs when the independent variables has correlations. Multicolinearity causes the estimator by ordinary least square to be unstable and produce a large variety. Multicollinearity can be overcome by the addition of penalized regression coefficient. The purpose of this research is modeling ridge regression, LASSO, and elastic-net. Data which is data of fisherman catch at Carocok Beach of Tarusan Sumatera Barat as dependent variable and amount of labor, amount of fuel, volume of fishing/waring boat, number of catches, ship size, number of boat wattage, sea experience, education and age of fisher as independent variables. The best model provided by LASSO that has a RMSEP value of validated regression model is minimum than ridge regression and elastic-net. LASSO shrinked amount of labor, amount of fuel and number of wattage equal zero. There can be influence (productivity change) that is volume of fishing/waring boat and boat size that used by fisher.
Kajian Simulasi Perbandingan Interpolasi Tetangga Terdekat dan 2-Tetangga Terdekat pada Sebaran Titik Spasial Retno Ariyanti Pratiwi; Muhammad Nur Aidi; Anik Djuraidah
Xplore: Journal of Statistics Vol. 2 No. 2 (2018): 31 Agustus 2018
Publisher : Department of Statistics, IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (342.431 KB) | DOI: 10.29244/xplore.v2i2.106

Abstract

Spatial point distribution in an area has three types of pattern. They are random, regular, and cluster. A set of points in space is an information about the number of events in that particular space. Oftenly, the number of events in a space is difficult to obtain, thus number of events estimation is necessary in order to conduct analysis and generate the right conclusion. This research uses nearest neighbor and 2- nearest neighbors interpolation as an interpolation methods under the principle of the object location proximity. The accuracy measurements were used in both methods can be computed by the smallest MAE values. MAE is a measure to evaluate the level of accuracy by using the absolute mean of the observed and interpolation expected value difference. This research uses MAE to determine the best method. This research uses both simulated and real-life data regarding the number of Dengue Hemorrhagic Fever (DBD) patient in Central Java Province. Simulated data were generated from the Poisson, binomial, and negative binomial distribution which were set in the quadrant. The results show that the 2-nearest neighbors interpolation yield smaller MAE value than the nearest neighbor interpolation MAE either in the random, regular, or cluster spatial point distribution. The percentage of bias of the observation and estimation value of the two interpolation methods are relatively small or less than 20%. Meanwhile, in the real-life data, the 2-nearest neighbors interpolation also yield a smaller MAE value than the nearest neighbor interpolation.