Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Enthusiastic : International Journal of Applied Statistics and Data Science

Mardia’s Skewness and Kurtosis for Assessing Normality Assumption in Multivariate Regression Wulandari, Dewi; Sutrisno, Sutrisno; Nirwana, Muhammad Bayu
Enthusiastic : International Journal of Applied Statistics and Data Science Volume 1 Issue 1, April 2021
Publisher : Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (252.901 KB) | DOI: 10.20885/enthusiastic.vol1.iss1.art1

Abstract

In Multivariate regression, we need to assess normality assumption simultaneously, not univariately. Univariate normal distribution does not guarantee the occurrence of multivariate normal distribution [1]. So we need to extend the assessment of univariate normal distribution into multivariate methods. One extended method is skewness and kurtosis as proposed by Mardia [2]. In this paper, we introduce the method, present the procedure of this method, and show how to examine normality assumption in multivariate regression study case using this method and expose the use of statistics software to help us in numerical calculation. Received February 20, 2021Revised March 8, 2021Accepted March 10, 2021
Comparison of Simple and Segmented Linear Regression Models on the Effect of Sea Depth toward the Sea Temperature Nirwana, Muhammad Bayu; Wulandari, Dewi
Enthusiastic : International Journal of Applied Statistics and Data Science Volume 1 Issue 2, October 2021
Publisher : Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (363.417 KB) | DOI: 10.20885/enthusiastic.vol1.iss2.art3

Abstract

The linear regression model is employed when it is identified a linear relationship between the dependent and independent variables. In some cases, the relationship between the two variables does not generate a linear line, that is, there is a change point at a certain point. Therefore, themaximum likelihood estimator for the linear regression does not produce an accurate model. The objective of this study is to presents the performance of simple linear and segmented linear regression models in which there are breakpoints in the data. The modeling is performed onthe data of depth and sea temperature. The model results display that the segmented linear regression is better in modeling data which contain changing points than the classical one.Received September 1, 2021Revised November 2, 2021Accepted November 11, 2021