Analysis of outlier data using parallel maximum likelihood estimator

Yekti Widyaningsih, Devvi Sarwinda, Anis Y. Yasinta

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we investigate about implementation of parallel maximum likelihood estimator (Parallel-MLE) in analysis of outlier data for multiple linear regression model. Parallel method is a method that divides data into clusters. In this study, K-Means Clustering is applied for clustering method. The data in this research was obtained from bankruptcy data (bank32nh). Bank32 is queues data at an XYZ bank, where it consist of 4500 observations, 1 dependent variable, and 31 independent variables. The experimental results show Parallel-MLE show better mean square error (MSE) and performance compare to MLE. Our proposed method achieved smaller MSE for more outlier observations (7-30 outliers) i.e. 0.000059.

Original languageEnglish
Title of host publicationProceedings of the 2019 2nd International Conference on Software Engineering and Information Management, ICSIM 2019 - Workshop 2019 2nd International Conference on Big Data and Smart Computing, ICBDSC 2019
PublisherAssociation for Computing Machinery
Pages166-170
Number of pages5
ISBN (Electronic)9781450366427
DOIs
Publication statusPublished - 10 Jan 2019
Event2nd International Conference on Software Engineering and Information Management, ICSIM 2019 - and its Workshop 2019 2nd International Conference on Big Data and Smart Computing, ICBDSC 2019 - Bali, Indonesia
Duration: 10 Jan 201913 Jan 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2nd International Conference on Software Engineering and Information Management, ICSIM 2019 - and its Workshop 2019 2nd International Conference on Big Data and Smart Computing, ICBDSC 2019
Country/TerritoryIndonesia
CityBali
Period10/01/1913/01/19

Keywords

  • K-means clustering
  • Multiple linear regression
  • Outlier data
  • Parallel maximum likelihood

Fingerprint

Dive into the research topics of 'Analysis of outlier data using parallel maximum likelihood estimator'. Together they form a unique fingerprint.

Cite this