Introducing Functional Data Analysis to Managerial Science

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In this article, we introduce functional data analysis (FDA), a set of statistical tools developed to study information on curves or functions. We review fundamentals of the methodology along with previous applications in other business disciplines to highlight the potential of FDA to managerial science. We provide details of the three most commonly used FDA techniques, including functional principal component analysis, functional regression, and functional clustering, and demonstrate each by investigating measures of firm financial performance from a panel data set of the 1,000 largest U.S. firms by revenues from 1992 to 2008. We compare results obtained from FDA with hierarchical linear modeling and conclude by outlining ideas for future micro- and macro-level organizational research incorporating this methodology.

Original languageEnglish (US)
Pages (from-to)693-721
Number of pages29
JournalOrganizational Research Methods
Volume15
Issue number4
DOIs
StatePublished - Dec 2012
Externally publishedYes

Fingerprint

Principal component analysis
Macros
Industry
Methodology
Hierarchical linear modeling
Financial performance
Clustering
Organizational research
Revenue
Panel data

Keywords

  • firm performance
  • functional clustering
  • functional data analysis
  • functional principal component analysis
  • functional regression

ASJC Scopus subject areas

  • Management of Technology and Innovation
  • Strategy and Management
  • Decision Sciences(all)

Cite this

Introducing Functional Data Analysis to Managerial Science. / Dass, Mayukh; Shropshire, Christine.

In: Organizational Research Methods, Vol. 15, No. 4, 12.2012, p. 693-721.

Research output: Contribution to journalArticle

@article{f1ecf70ccc934e72a5f23875df291826,
title = "Introducing Functional Data Analysis to Managerial Science",
abstract = "In this article, we introduce functional data analysis (FDA), a set of statistical tools developed to study information on curves or functions. We review fundamentals of the methodology along with previous applications in other business disciplines to highlight the potential of FDA to managerial science. We provide details of the three most commonly used FDA techniques, including functional principal component analysis, functional regression, and functional clustering, and demonstrate each by investigating measures of firm financial performance from a panel data set of the 1,000 largest U.S. firms by revenues from 1992 to 2008. We compare results obtained from FDA with hierarchical linear modeling and conclude by outlining ideas for future micro- and macro-level organizational research incorporating this methodology.",
keywords = "firm performance, functional clustering, functional data analysis, functional principal component analysis, functional regression",
author = "Mayukh Dass and Christine Shropshire",
year = "2012",
month = "12",
doi = "10.1177/1094428112457830",
language = "English (US)",
volume = "15",
pages = "693--721",
journal = "Organizational Research Methods",
issn = "1094-4281",
publisher = "SAGE Publications Inc.",
number = "4",

}

TY - JOUR

T1 - Introducing Functional Data Analysis to Managerial Science

AU - Dass, Mayukh

AU - Shropshire, Christine

PY - 2012/12

Y1 - 2012/12

N2 - In this article, we introduce functional data analysis (FDA), a set of statistical tools developed to study information on curves or functions. We review fundamentals of the methodology along with previous applications in other business disciplines to highlight the potential of FDA to managerial science. We provide details of the three most commonly used FDA techniques, including functional principal component analysis, functional regression, and functional clustering, and demonstrate each by investigating measures of firm financial performance from a panel data set of the 1,000 largest U.S. firms by revenues from 1992 to 2008. We compare results obtained from FDA with hierarchical linear modeling and conclude by outlining ideas for future micro- and macro-level organizational research incorporating this methodology.

AB - In this article, we introduce functional data analysis (FDA), a set of statistical tools developed to study information on curves or functions. We review fundamentals of the methodology along with previous applications in other business disciplines to highlight the potential of FDA to managerial science. We provide details of the three most commonly used FDA techniques, including functional principal component analysis, functional regression, and functional clustering, and demonstrate each by investigating measures of firm financial performance from a panel data set of the 1,000 largest U.S. firms by revenues from 1992 to 2008. We compare results obtained from FDA with hierarchical linear modeling and conclude by outlining ideas for future micro- and macro-level organizational research incorporating this methodology.

KW - firm performance

KW - functional clustering

KW - functional data analysis

KW - functional principal component analysis

KW - functional regression

UR - http://www.scopus.com/inward/record.url?scp=84873809207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873809207&partnerID=8YFLogxK

U2 - 10.1177/1094428112457830

DO - 10.1177/1094428112457830

M3 - Article

VL - 15

SP - 693

EP - 721

JO - Organizational Research Methods

JF - Organizational Research Methods

SN - 1094-4281

IS - 4

ER -