Outlier Detection in Simultaneous Equations with Panel Data

Suci Ismadyaliana, Setiawan*, Jerry Dwi Trijoyo Purnomo

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

An outlier in a set of data is an observation (or subset of observation) that appears to be inconsistent with the remainder of that set of data. Outliers can have a marked effect on any type of empirical analysis. Therefore, outlier detection is very important in a statistical analysis. Outlier detection in regression model used residual to determine the anomaly score. This research used internally studentized residual (ISR) to detect outliers in panel data model and simultaneous equation with panel data. The application of data in this study is data for ten countries that are members of the ASEAN-China Free Trade Area (ACFTA) during the period 2007–2021. The result showed that outlier observations will vary depending on the type of modeling. Each model will obtain certain residuals, so that the observations detected as outliers will also be different. Outlier detection results in the simultaneous equations show that the outlier observations are a subset of the independent equation outliers that compose them.

Original languageEnglish
Title of host publicationLecture Notes on Data Engineering and Communications Technologies
PublisherSpringer Science and Business Media Deutschland GmbH
Pages415-427
Number of pages13
DOIs
Publication statusPublished - 2024

Publication series

NameLecture Notes on Data Engineering and Communications Technologies
Volume191
ISSN (Print)2367-4512
ISSN (Electronic)2367-4520

Keywords

  • ACFTA
  • Internally studentized residual
  • Outlier detection
  • Panel data
  • Simultaneous equation

Fingerprint

Dive into the research topics of 'Outlier Detection in Simultaneous Equations with Panel Data'. Together they form a unique fingerprint.

Cite this