Factor Analysis Or Structural Equation Modeling? Theoretical And Measurement Implications Of Your Research Method When Studying Nursing Work Environments

2.50
Hdl Handle:
http://hdl.handle.net/10755/148177
Type:
Presentation
Title:
Factor Analysis Or Structural Equation Modeling? Theoretical And Measurement Implications Of Your Research Method When Studying Nursing Work Environments
Abstract:
Factor Analysis Or Structural Equation Modeling? Theoretical And Measurement Implications Of Your Research Method When Studying Nursing Work Environments
Conference Sponsor:Sigma Theta Tau International
Conference Year:2003
Author:Cummings, Greta G., RN, MEd
P.I. Institution Name:Cross Cancer Institute
Title:Senior Leader, Medical/Nursing Services
Co-Authors:Leslie Hayduk, PhD; Carole A. Estabrooks, RN, PhD
Objective: The study purpose was to test existing and new assertions about the measurement of the nursing practice environment. Design: We examined the models underlying three published perspectives on the nursing work index using structural equation modeling, and then developed and tested an alternative model based on theoretical assertions about the healthy nursing workplace, using structural equation modeling. Concepts: The Revised Nursing Work Index (NWI-R) is a survey scale used to measure the nursing work environment. Aiken and Patrician (2000) reported four conceptually derived subscales (autonomy, control over practice setting, nurse/physician relationships and organizational support). Lake (2002) reported five empirically derived subscales (nurse participation in hospital affairs, nursing foundations for quality of care, nurse manager ability, leadership and support, staffing and resource adequacy, and collegial nurse-physician relations) using a factor analytic method. Estabrooks (2002) reported a single factor solution representing the practice environment. Methods: The Aiken 4-factor, Lake 5-factor and Estabrooks 1-factor models were estimated using the Canadian Hospital Outcomes Survey database. A theoretical model was then developed based on assertions about healthy hospital nursing workplaces and tested as a structural equation model against the same data. This model was analyzed and compared to the three factor models, with emphasis on measurement and the integration of theory and statistical analysis. Findings: The published factor analytic models failed significantly. Although the structural equation model also failed, its diagnostics showed a much closer fit of its theoretical assertions to the data. Conclusions: The failure of the published models stands in stark contrast to the reported claims that these scales and subscales are adequate and appropriate measures of the nursing practice environment. Implications: The most useful advances in developing the concept of the practice environment will result from testing clearly specified causal relationships using powerful methods such as structural equation modeling.
Repository Posting Date:
26-Oct-2011
Date of Publication:
17-Oct-2011
Sponsors:
Sigma Theta Tau International

Full metadata record

DC FieldValue Language
dc.typePresentationen_GB
dc.titleFactor Analysis Or Structural Equation Modeling? Theoretical And Measurement Implications Of Your Research Method When Studying Nursing Work Environmentsen_GB
dc.identifier.urihttp://hdl.handle.net/10755/148177-
dc.description.abstract<table><tr><td colspan="2" class="item-title">Factor Analysis Or Structural Equation Modeling? Theoretical And Measurement Implications Of Your Research Method When Studying Nursing Work Environments</td></tr><tr class="item-sponsor"><td class="label">Conference Sponsor:</td><td class="value">Sigma Theta Tau International</td></tr><tr class="item-year"><td class="label">Conference Year:</td><td class="value">2003</td></tr><tr class="item-author"><td class="label">Author:</td><td class="value">Cummings, Greta G., RN, MEd</td></tr><tr class="item-institute"><td class="label">P.I. Institution Name:</td><td class="value">Cross Cancer Institute</td></tr><tr class="item-author-title"><td class="label">Title:</td><td class="value">Senior Leader, Medical/Nursing Services</td></tr><tr class="item-email"><td class="label">Email:</td><td class="value">gretac@ualberta.ca</td></tr><tr class="item-co-authors"><td class="label">Co-Authors:</td><td class="value">Leslie Hayduk, PhD; Carole A. Estabrooks, RN, PhD</td></tr><tr><td colspan="2" class="item-abstract">Objective: The study purpose was to test existing and new assertions about the measurement of the nursing practice environment. Design: We examined the models underlying three published perspectives on the nursing work index using structural equation modeling, and then developed and tested an alternative model based on theoretical assertions about the healthy nursing workplace, using structural equation modeling. Concepts: The Revised Nursing Work Index (NWI-R) is a survey scale used to measure the nursing work environment. Aiken and Patrician (2000) reported four conceptually derived subscales (autonomy, control over practice setting, nurse/physician relationships and organizational support). Lake (2002) reported five empirically derived subscales (nurse participation in hospital affairs, nursing foundations for quality of care, nurse manager ability, leadership and support, staffing and resource adequacy, and collegial nurse-physician relations) using a factor analytic method. Estabrooks (2002) reported a single factor solution representing the practice environment. Methods: The Aiken 4-factor, Lake 5-factor and Estabrooks 1-factor models were estimated using the Canadian Hospital Outcomes Survey database. A theoretical model was then developed based on assertions about healthy hospital nursing workplaces and tested as a structural equation model against the same data. This model was analyzed and compared to the three factor models, with emphasis on measurement and the integration of theory and statistical analysis. Findings: The published factor analytic models failed significantly. Although the structural equation model also failed, its diagnostics showed a much closer fit of its theoretical assertions to the data. Conclusions: The failure of the published models stands in stark contrast to the reported claims that these scales and subscales are adequate and appropriate measures of the nursing practice environment. Implications: The most useful advances in developing the concept of the practice environment will result from testing clearly specified causal relationships using powerful methods such as structural equation modeling.</td></tr></table>en_GB
dc.date.available2011-10-26T09:41:23Z-
dc.date.issued2011-10-17en_GB
dc.date.accessioned2011-10-26T09:41:23Z-
dc.description.sponsorshipSigma Theta Tau Internationalen_GB
All Items in this repository are protected by copyright, with all rights reserved, unless otherwise indicated.