Exploratory data structure comparisons: three new visual tools based on principal component analysis*

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Exploratory data structure comparisons : three new visual tools based on principal component analysis*. / Petersen, Anne Helby; Markussen, Bo; Christensen, Karl Bang.

I: Journal of Applied Statistics, Bind 48, Nr. 9, 2021, s. 1675-1695.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Petersen, AH, Markussen, B & Christensen, KB 2021, 'Exploratory data structure comparisons: three new visual tools based on principal component analysis*', Journal of Applied Statistics, bind 48, nr. 9, s. 1675-1695. https://doi.org/10.1080/02664763.2020.1773772

APA

Petersen, A. H., Markussen, B., & Christensen, K. B. (2021). Exploratory data structure comparisons: three new visual tools based on principal component analysis*. Journal of Applied Statistics, 48(9), 1675-1695. https://doi.org/10.1080/02664763.2020.1773772

Vancouver

Petersen AH, Markussen B, Christensen KB. Exploratory data structure comparisons: three new visual tools based on principal component analysis*. Journal of Applied Statistics. 2021;48(9):1675-1695. https://doi.org/10.1080/02664763.2020.1773772

Author

Petersen, Anne Helby ; Markussen, Bo ; Christensen, Karl Bang. / Exploratory data structure comparisons : three new visual tools based on principal component analysis*. I: Journal of Applied Statistics. 2021 ; Bind 48, Nr. 9. s. 1675-1695.

Bibtex

@article{d6ce37eebc9d4c809dde1c538cfdaf72,
title = "Exploratory data structure comparisons: three new visual tools based on principal component analysis*",
abstract = "Datasets are sometimes divided into distinct subsets, e.g. due to multi-center sampling, or to variations in instruments, questionnaire item ordering or mode of administration, and the data analyst then needs to assess whether a joint analysis is meaningful. The Principal Component Analysis-based Data Structure Comparisons (PCADSC) tools are three new non-parametric, visual diagnostic tools for investigating differences in structure for two subsets of a dataset through covariance matrix comparisons by use of principal component analysis. The PCADCS tools are demonstrated in a data example using European Social Survey data on psychological well-being in three countries, Denmark, Sweden, and Bulgaria. The data structures are found to be different in Denmark and Bulgaria, and thus a comparison of for example mean psychological well-being scores is not meaningful. However, when comparing Denmark and Sweden, very similar data structures, and thus comparable concepts of well-being, are found. Therefore, inter-country comparisons are warranted for these countries.",
keywords = "covariance matrix, data structure, exploratory data analysis, Principal component analysis",
author = "Petersen, {Anne Helby} and Bo Markussen and Christensen, {Karl Bang}",
year = "2021",
doi = "10.1080/02664763.2020.1773772",
language = "English",
volume = "48",
pages = "1675--1695",
journal = "Journal of Applied Statistics",
issn = "0266-4763",
publisher = "Routledge",
number = "9",

}

RIS

TY - JOUR

T1 - Exploratory data structure comparisons

T2 - three new visual tools based on principal component analysis*

AU - Petersen, Anne Helby

AU - Markussen, Bo

AU - Christensen, Karl Bang

PY - 2021

Y1 - 2021

N2 - Datasets are sometimes divided into distinct subsets, e.g. due to multi-center sampling, or to variations in instruments, questionnaire item ordering or mode of administration, and the data analyst then needs to assess whether a joint analysis is meaningful. The Principal Component Analysis-based Data Structure Comparisons (PCADSC) tools are three new non-parametric, visual diagnostic tools for investigating differences in structure for two subsets of a dataset through covariance matrix comparisons by use of principal component analysis. The PCADCS tools are demonstrated in a data example using European Social Survey data on psychological well-being in three countries, Denmark, Sweden, and Bulgaria. The data structures are found to be different in Denmark and Bulgaria, and thus a comparison of for example mean psychological well-being scores is not meaningful. However, when comparing Denmark and Sweden, very similar data structures, and thus comparable concepts of well-being, are found. Therefore, inter-country comparisons are warranted for these countries.

AB - Datasets are sometimes divided into distinct subsets, e.g. due to multi-center sampling, or to variations in instruments, questionnaire item ordering or mode of administration, and the data analyst then needs to assess whether a joint analysis is meaningful. The Principal Component Analysis-based Data Structure Comparisons (PCADSC) tools are three new non-parametric, visual diagnostic tools for investigating differences in structure for two subsets of a dataset through covariance matrix comparisons by use of principal component analysis. The PCADCS tools are demonstrated in a data example using European Social Survey data on psychological well-being in three countries, Denmark, Sweden, and Bulgaria. The data structures are found to be different in Denmark and Bulgaria, and thus a comparison of for example mean psychological well-being scores is not meaningful. However, when comparing Denmark and Sweden, very similar data structures, and thus comparable concepts of well-being, are found. Therefore, inter-country comparisons are warranted for these countries.

KW - covariance matrix

KW - data structure

KW - exploratory data analysis

KW - Principal component analysis

U2 - 10.1080/02664763.2020.1773772

DO - 10.1080/02664763.2020.1773772

M3 - Journal article

C2 - 35706572

AN - SCOPUS:85086333334

VL - 48

SP - 1675

EP - 1695

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

SN - 0266-4763

IS - 9

ER -

ID: 244320649