On the Applicability of Latent Variable Modeling to Research System Data

Ella Bingham; Heikki Mannila

doi:10.1016/B978-0-12-802806-3.00013-0

On the Applicability of Latent Variable Modeling to Research System Data

Ella Bingham, Heikki Mannila

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Scientific

Abstract

In this note, we discuss the applicability of latent variable models as a tool in analyzing the structure of a research system. We consider whether tensor methods, especially Parallel Factor Analysis, are appropriate for the description of the personnel structure and publication results of different scientific disciplines in different universities. As the measured variables (personnel structure and publications) interact with both the universities and the disciplines, it is useful to view the data as a tensor. Our preliminary results suggest that tensor methods are indeed able to find meaningful structure in such data.

Original language	English
Title of host publication	Advances in Independent Component Analysis and Learning Machines
Editors	Ella Bingham, Samuel Kaski, Jorma Laaksonen, Jouko Lampinen
Place of Publication	Academic Press
Publisher	Elsevier
Chapter	13
Pages	279-288
ISBN (Print)	978-0-12-802806-3
DOIs	https://doi.org/10.1016/B978-0-12-802806-3.00013-0
Publication status	Published - 2015
MoE publication type	B2 Book section

Access to Document

10.1016/B978-0-12-802806-3.00013-0

Cite this

@inbook{7124ebbf7f1d4bdeaefd5c6c43ba7093,

title = "On the Applicability of Latent Variable Modeling to Research System Data",

abstract = "In this note, we discuss the applicability of latent variable models as a tool in analyzing the structure of a research system. We consider whether tensor methods, especially Parallel Factor Analysis, are appropriate for the description of the personnel structure and publication results of different scientific disciplines in different universities. As the measured variables (personnel structure and publications) interact with both the universities and the disciplines, it is useful to view the data as a tensor. Our preliminary results suggest that tensor methods are indeed able to find meaningful structure in such data.",

author = "Ella Bingham and Heikki Mannila",

note = "VK: Mannila, H.; HIIT",

year = "2015",

doi = "10.1016/B978-0-12-802806-3.00013-0",

language = "English",

isbn = "978-0-12-802806-3",

pages = "279--288",

editor = "Ella Bingham and Samuel Kaski and Jorma Laaksonen and Jouko Lampinen",

booktitle = "Advances in Independent Component Analysis and Learning Machines",

publisher = "Elsevier",

address = "Netherlands",

}

On the Applicability of Latent Variable Modeling to Research System Data. / Bingham, Ella ; Mannila, Heikki.
Advances in Independent Component Analysis and Learning Machines. ed. / Ella Bingham; Samuel Kaski; Jorma Laaksonen; Jouko Lampinen. Academic Press: Elsevier, 2015. p. 279-288.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Scientific

TY - CHAP

T1 - On the Applicability of Latent Variable Modeling to Research System Data

AU - Bingham, Ella

AU - Mannila, Heikki

N1 - VK: Mannila, H.; HIIT

PY - 2015

Y1 - 2015

N2 - In this note, we discuss the applicability of latent variable models as a tool in analyzing the structure of a research system. We consider whether tensor methods, especially Parallel Factor Analysis, are appropriate for the description of the personnel structure and publication results of different scientific disciplines in different universities. As the measured variables (personnel structure and publications) interact with both the universities and the disciplines, it is useful to view the data as a tensor. Our preliminary results suggest that tensor methods are indeed able to find meaningful structure in such data.

AB - In this note, we discuss the applicability of latent variable models as a tool in analyzing the structure of a research system. We consider whether tensor methods, especially Parallel Factor Analysis, are appropriate for the description of the personnel structure and publication results of different scientific disciplines in different universities. As the measured variables (personnel structure and publications) interact with both the universities and the disciplines, it is useful to view the data as a tensor. Our preliminary results suggest that tensor methods are indeed able to find meaningful structure in such data.

UR - http://store.elsevier.com/Advances-in-Independent-Component-Analysis-and-Learning-Machines/isbn-9780128028063/

UR - https://www.sciencedirect.com/science/article/abs/pii/B9780128028063000130

U2 - 10.1016/B978-0-12-802806-3.00013-0

DO - 10.1016/B978-0-12-802806-3.00013-0

M3 - Chapter

SN - 978-0-12-802806-3

SP - 279

EP - 288

BT - Advances in Independent Component Analysis and Learning Machines

A2 - Bingham, Ella

A2 - Kaski, Samuel

A2 - Laaksonen, Jorma

A2 - Lampinen, Jouko

PB - Elsevier

CY - Academic Press

ER -

On the Applicability of Latent Variable Modeling to Research System Data

Abstract

Access to Document

Other files and links

Fingerprint

Cite this