대한간호학회지 (Journal of Korean Academy of Nursing)

한국간호과학회 (Korean Society of Nursing Science)
권호 표지
DOI QR코드

DOI QR Code

간호연구에서의 형성적 측정 모형과 반영적 측정 모형: 횡단적 연구의 2차 자료 분석

Formative versus reflective measurement models in nursing research: a secondary data analysis of a cross-sectional study in Korea

  • Eun Seo Park (College of Police and Criminal Justice, Dongguk University) ;
  • Young Il Cho (College of Police and Criminal Justice, Dongguk University) ;
  • Hyo Jin Kim (College of Nursing, Seoul National University) ;
  • YeoJin Im (College of Nursing Science, Kyung Hee University) ;
  • Dong Hee Kim (College of Nursing, Sungshin Women's University)
  • 투고 : 2024.08.07
  • 심사 : 2025.01.03
  • 발행 : 2025.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Purpose: This study aimed to empirically verify the impact of measurement model selection on research outcomes and their interpretation through an analysis of children's emotional and social problems measured by the Pediatric Symptom Checklist (PSC) using both reflective and formative measurement models. These models were represented by covariance-based structural equation modeling (CB-SEM) and partial least squares SEM (PLS-SEM), respectively. Methods: This secondary data analysis evaluated children's emotional and social problems as both reflective and formative constructs. Reflective models were analyzed using CB-SEM, while formative models were assessed using PLS-SEM. Comparisons between these two approaches were based on model fit and parameter estimates. Results: In the CB-SEM analysis, which assumed a reflective measurement model, a model was not identified due to inadequate fit indices and a Heywood case, indicating improper model specification. In contrast, the PLS-SEM analysis, assuming a formative measurement model, demonstrated adequate reliability and validity with significant path coefficients, supporting the appropriateness of the formative model for the PSC. Conclusion: The findings indicate that the PSC is more appropriately analyzed as a formative measurement model using PLS-SEM, rather than as a reflective model using CB-SEM. This study highlights the necessity of selecting an appropriate measurement model based on the theoretical and empirical characteristics of constructs in nursing research. Future research should ensure that the nature of measurement variables is accurately reflected in the choice of statistical models to improve the validity of research outcomes.

키워드

과제정보

This work was supported by the Sungshin Women's University Research Grant of 2024 (No. H20240080).

참고문헌

  1. Bollen KA. Interpretational confounding is due to misspecification, not to type of indicator: comment on Howell, Breivik, and Wilcox (2007). Psychol Methods. 2007;12(2):219-228. https://doi.org/10.1037/1082-989X.12.2.219
  2. Bollen KA. A new incremental fit index for general structural equation models. Sociol Methods Res. 1989;17(3):303-316. https://doi.org/10.1177/0049124189017003004
  3. Fornell C, Bookstein FL. Two structural equation models: LISREL and PLS applied to consumer exit-voice theory. J Mark Res. 1982;19(4):440-452. https://doi.org/10.1177/002224378201900406
  4. Kline TJ. Psychological testing: a practical approach to design and evaluation. Sage Publications; 2005. p. 1-356. https://doi.org/10.4135/9781483385693
  5. Baker EH. Socioeconomic status, definition. In: Cockerham WC, Dingwall R, Quah S, editors. The Wiley Blackwell Encyclopedia of health, illness, behavior, and society. John Wiley & Sons; 2014. p. 2010-2214. https://doi.org/10.1002/9781118410868.wbehibs395
  6. Bagozzi RP, Fornell C. Theoretical concepts, measurements, and meaning. In: Fornell C, editor. A second generation of multivariate analysis. Praeger; 1982. p. 5-23.
  7. Edwards JR, Bagozzi RP. On the nature and direction of relationships between constructs and measures. Psychol Methods. 2000;5(2):155-174. https://doi.org/10.1037/1082-989x.5.2.155
  8. Jöreskog KG. Analysis of covariance structures. In: Nesselroade JR, Cattell RB, editors. Handbook of multivariate experimental psychology. Springer; 1988. p. 207-230. https://doi.org/10.1007/978-1-4613-0893-5_5
  9. Wold H, Bertholet JL. The PLS (Partial Least Squares) approach to multidimensional contingency tables. Metron [Internet]. 1982 [cited 2024 May 27];40(1-2):303-326. Available from: https://archive-ouverte.unige.ch/unige:114517
  10. Hair JF, Sarstedt M, Pieper TM, Ringle CM. The use of partial least squares structural equation modeling in strategic management research: a review of past practices and recommendations for future applications. Long Range Plan. 2012;45(5-6):320-340. https://doi.org/10.1016/j.lrp.2012.09.008
  11. Bollen KA, Diamantopoulos A. In defense of causal-formative indicators: a minority report. Psychol Methods. 2017;22(3):581-596. https://doi.org/10.1037/met0000056
  12. Bollen K, Lennox R. Conventional wisdom on measurement: a structural equation perspective. Psychol Bull. 1991;110(2):305-314. https://doi.org/10.1037/0033-2909.110.2.305
  13. Diamantopoulos A, Winklhofer HM. Index construction with formative indicators: an alternative to scale development. J Mark Res. 2001;38(2):269-277. https://doi.org/10.1509/jmkr.38.2.269.18845
  14. Jarvis CB, MacKenzie SB, Podsakoff PM. A critical review of construct indicators and measurement model misspecification in marketing and consumer research. J Consum Res. 2003;30(2):199-218. https://doi.org/10.1086/376806
  15. MacKenzie SB, Podsakoff PM, Jarvis CB. The problem of measurement model misspecification in behavioral and organizational research and some recommended solutions. J Appl Psychol. 2005;90(4):710-730. https://doi.org/10.1037/0021-9010.90.4.710
  16. Petter S, Straub D, Rai A. Specifying formative constructs in information systems research. MIS Q. 2007;31(4):623-656. https://doi.org/10.2307/25148814
  17. Jellinek MS, Murphy JM, Robinson J, Feins A, Lamb S, Fenton T. Pediatric Symptom Checklist: screening school-age children for psychosocial dysfunction. J Pediatr. 1988;112(2):201-209. https://doi.org/10.1016/s0022-3476(88)80056-8
  18. Im Y, Kim DH. Family management style and psychosocial health of children with chronic conditions. J Child Fam Stud. 2021;30:483-492. https://doi.org/10.1007/s10826-020-01870-7
  19. Liu J, Guo S, Gao R, DiStefano C. Investigating school children's behavioral and emotional problems using pediatric symptoms checklist-17 in a structural equation modeling framework. Sch Psychol Int. 2020;41(3):257-275. https://doi.org/10.1177/0143034320912301
  20. Widaman KF. Common factor analysis versus principal component analysis: differential bias in representing model parameters? Multivariate Behav Res. 1993;28(3):263-311. https://doi.org/10.1207/s15327906mbr2803_1
  21. Park ES, Cho YI. New suggestions on the measurement model of juvenile delinquency: focusing on composite variable, reflective measurement, and formative measurement. Korean Assoc Police Sci Rev [Internet]. 2023 [cited 2024 May 27];25(5):91-114. Available from: https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART003013086 https://doi.org/10.24055/kaps.25.5.4
  22. Lee SM. Basics of factor analysis (research methods 14) [Internet]. Kyoyookbook; 2006 [cited 2024 May 27]. Available from: https://search.worldcat.org/ko/title/1082725819
  23. Kim C. Misuse of exploratory factor analysis and its remedies. Surv Res. 2016;17(1):1-29. https://doi.org/10.20997/SR.17.1.1
  24. Pearson K. LIII. On lines and planes of closest fit to systems of points in space. Lond Edinb Dublin Philos Mag J Sci. 1901;2(11):559-572. https://doi.org/10.1080/14786440109462720
  25. Hotelling H. Analysis of a complex of statistical variables into principal components. J Educ Psychol. 1933;24(6):417-441. https://doi.org/10.1037/h0071325
  26. Diamantopoulos A. The C-OAR-SE procedure for scale development in marketing: a comment. Int J Res Mark. 2005;22(1):1-9. https://doi.org/10.1016/j.ijresmar.2003.08.002
  27. Finn A, Kayande U. How fine is C-OAR-SE?: a generalizability theory perspective on Rossiter's procedure. Int J Res Mark. 2005;22(1):11-21. https://doi.org/10.1016/j.ijresmar.2004.03.001
  28. Coltman T, Devinney TM, Midgley DF, Venaik S. Formative versus reflective measurement models: two applications of formative measurement. J Bus Res. 2008;61(12):1250-1262. https://doi.org/10.1016/j.jbusres.2008.01.013
  29. Borsboom D, Mellenbergh GJ, van Heerden J. The theoretical status of latent variables. Psychol Rev. 2003;110(2):203-219. https://doi.org/10.1037/0033-295X.110.2.203
  30. Churchill GA Jr. A paradigm for developing better measures of marketing constructs. J Mark Res. 1979;16(1):64-73. https://doi.org/10.1177/002224377901600110
  31. Nunnally JC, Bernstein IH. The assessment of reliability. In: Nunnally JC, Bernstein IH, editors. Psychometric theory. 3rd ed. McGraw Hill; 1994. p. 248-292.
  32. Trochim WM. Research methods knowledge base [Internet]. Conjointly; c2024 [cited 2024 May 27]. Available from: http://www.socialresearchmethods.net/kb/index.php
  33. Kline RB. Principles and practice of structural equation modeling. 15th ed. Guilford Publications; 2023.
  34. Cassel C, Hackl P, Westlund AH. Robustness of partial leastsquares method for estimating latent variable quality structures. J Appl Stat. 1999;26(4):435-446. https://doi.org/10.1080/02664769922322
  35. Hair JF, Sarstedt M, Ringle CM. Rethinking some of the rethinking of partial least squares. Eur J Mark. 2019;53(4):566-584. https://doi.org/10.1108/EJM-10-2018-0665
  36. Tucker LR, Lewis C. A reliability coefficient for maximum likelihood factor analysis. Psychometrika. 1973;38(1):1-10. https://doi.org/10.1007/BF02291170
  37. Bentler PM. Comparative fit indexes in structural models. Psychol Bull. 1990;107(2):238-246. https://doi.org/10.1037/0033-2909.107.2.238
  38. Browne MW, Cudeck R. Alternative ways of assessing model fit. Sociol Methods Res. 1992;21(2):230-258. https://doi.org/10.1177/0049124192021002005
  39. Hu LT, Bentler PM. Cutoff criteria for fit indexes in covariance structure analysis: conventional criteria versus new alternatives. Struct Equ Modeling. 1999;6(1):1-55. https://doi.org/10.1080/10705519909540118
  40. Hair J, Alamer A. Partial least squares structural equation modeling (PLS-SEM) in second language and education research: guidelines using an applied example. Res Methods Appl Linguist. 2022;1(3):100027. https://doi.org/10.1016/j.rmal.2022.100027
  41. Chin WW. The partial least squares approach for structural equation modeling. In: Marcoulides GA, editor. Modern methods for business research [Internet]. Lawrence Erlbaum Associates Publishers; 1998 [cited 2024 May 27]. p. 295-336. Available from: https://psycnet.apa.org/record/1998-07269-010
  42. Gefen D, Straub D. A practical guide to factorial validity using PLS-Graph: tutorial and annotated example. Commun Assoc Inf Syst. 2005;16(1):91-109. https://doi.org/10.17705/1CAIS.01605
  43. Bagozzi RP, Yi Y. On the evaluation of structural equation models. J Acad Mark Sci. 1988;16:74-94. https://doi.org/10.1007/BF02723327
  44. Fornell C, Larcker DF. Evaluating structural equation models with unobservable variables and measurement error. J Mark Res. 1981;18(1):39-50. https://doi.org/10.1177/002224378101800104
  45. Hair JF Jr, Hult GT, Ringle CM, Sarstedt M, Danks NP, Ray S. Partial least squares structural equation modeling (PLS-SEM) using R: a workbook. Springer Nature; 2021. p. 1-197. https://doi.org/10.1007/978-3-030-80519-7
  46. Henseler J, Ringle CM, Sarstedt M. A new criterion for assessing discriminant validity in variance-based structural equation modeling. J Acad Mark Sci. 2015;43:115-135. https://doi.org/10.1007/s11747-014-0403-8
  47. Hair JF, Sarstedt M. Explanation plus prediction: the logical focus of project management research. Proj Manag J. 2021;52(4):319-322. https://doi.org/10.1177/8756972821999945
  48. Hair JF, Hult GT, Ringle CM, Sarstedt M, Thiele KO. Mirror, mirror on the wall: a comparative evaluation of composite-based structural equation modeling methods. J Acad Mark Sci. 2017;45:616-632. https://doi.org/10.1007/s11747-017-0517-x
  49. Hair J, Hollingsworth CL, Randolph AB, Chong AY. An updated and expanded assessment of PLS-SEM in information systems research. Ind Manag Data Syst. 2017;117(3):442-458. https://doi.org/10.1108/IMDS-04-2016-0130
  50. Moshagen M, Bader M. semPower: general power analysis for structural equation models. Behav Res Methods. 2024;56(4):2901-2922. https://doi.org/10.3758/s13428-023-02254-7
  51. Kim HH. Psychosocial screening in childhood asthma [master's thesis]. Seoul: Ewha Womans University; 1989.
  52. Abidin RR. Parenting Stress Index-Short Form. Pediatric Psychology Press; 1990.
  53. Seo HY, Lee SH. A study on the adaptation and social support of mothers with disabled children. J Fam Res [Internet]. 1994 [cited 2024 May 27];6:37-68. Available from: https://api.semanticscholar.org/CorpusID:180943370
  54. Knafl K, Deatrick JA, Gallo AM. The interplay of concepts, data, and methods in the development of the Family Management Style Framework. J Fam Nurs. 2008;14(4):412-428. https://doi.org/10.1177/1074840708327138
  55. Rosseel Y. lavaan: an R package for structural equation modeling. J Stat Softw. 2012;48(2):1-36. https://doi.org/10.18637/jss.v048.i02
  56. Hair JF, Hult GT, Ringle CM, Sarstedt M, Danks NP, Ray S. The SEMinR package. In: Hair JF, Hult GT, Ringle CM, Sarstedt M, Danks NP, Ray S, editors. Partial least squares structural equation modeling (PLS-SEM) using R. Springer; 2021. p. 49-74.
  57. Dillon WR, Kumar A, Mulani N. Offending estimates in covariance structure analysis: comments on the causes of and solutions to Heywood cases. Psychol Bull. 1987;101(1):126-135. https://doi.org/10.1037/0033-2909.101.1.126
  58. Van Driel OP. On various causes of improper solutions in maximum likelihood factor analysis. Psychometrika. 1978;43(2):225-243. https://doi.org/10.1007/BF02293865
  59. Yi HS, Na W. Development and validation of teacher job stress inventory based on formative measurement structure: application of CB-SEM and PLS-SEM approach. J Educ Eval. 2018;31(4):885-911. https://doi.org/10.31158/JEEV.2018.31.4.885