Original ResearchA latent class analysis of job satisfaction and turnover among practicing pharmacists
Section snippets
Background
Latent class analysis (LCA) is a statistical method for finding subtypes of related cases (latent classes) from multivariate categorical data.1 The most common use of LCA is to discover case subtypes (or confirm hypothesized subtypes) based on multivariate categorical data.1, 2, 3, 4 LCA is well suited to many health applications for which one wishes to identify disease subtypes or diagnostic subcategories.1, 2, 3, 4 LCA models do not rely on traditional modeling assumptions (normal
Objectives
Research using LCA, job satisfaction, and turnover has been conducted in other disciplines.13, 14 Using LCA, Shockey observed that 4 classes explained his job satisfaction data quite well.13 The conclusion was that the true prevalence of job satisfaction is constant over groups once response errors have been accounted for.
In reference to job satisfaction and turnover, researchers have found a causal link between satisfaction, organizational commitment, and turnover.14 For example, Currivan
Methods
The study's theoretical framework is based on the relationship between job satisfaction and organizational commitment in models of employee turnover.15 Furthermore, included in the model is the covariate “practice site.” Research shows a strong relationship between practice site and job satisfaction.16 Demonstrating the causal order between job satisfaction, practice site, and turnover requires specifying the individual characteristics and workplace structures as determinants of turnover.16 A
Results
The adjusted overall response rate was 23% (n = 533/2353). For the purpose of this study, which was focused on actively practicing pharmacists, a total of 429 surveys were usable and were included in the final data analysis. There were no significant differences between the characteristics of early and late respondents. The respondents' average age was approximately 45 years and more than half (55%) were female. The majority worked full time (89%), practiced in a retail setting (57%), and
Discussion
This study demonstrated the utility of LCA in the measurement of job satisfaction. This LCA arrived at a statistically sound and relatively straightforward interpretable number of classes. The basic idea underlying LCA is a very simple one: some of the parameters of a postulated statistical model differ across previously unrecognized subgroups.19 These subgroups form the categories of a categorical latent variable. Outside social sciences, latent class models are often referred to as finite
Conclusion
The LCA method was found to be effective for finding relevant subgroups with a heterogeneous at-risk population for turnover. The minimal cross-classification between classes may be the result of the small sample size. Furthermore, in reviewing the model fit indices, a 4-class solution was certainly possible, although not as strong as a 5-class solution. Hence, it is possible that the similarity in responses to specific items (ie, items 1 and 5) make it difficult for the model to perfectly
References (19)
- et al.
Improvements in social functioning reported by a birth cohort in mid-adult life: a person-centred analysis of GHQ-28 social dysfunction items using latent class analysis
Pers Individ Dif
(2007) The causal order of job satisfaction and organizational commitment in models of employee turnover
Hum Resour Manag Rev
(1999)LCA frequently asked questions (FAQ)
- et al.
Latent Structure Analysis
(1968) Latent Class Analysis
(1987)- et al.
Developmental typology of trajectories to nighttime bladder control: epidemiologic application of longitudinal latent class analysis
Am J Epidemiol
(2003) The Analysis of Contingency Tables
(1992)- et al.
Finite Mixture Distributions
(1991)
Cited by (0)
- 1
Tel.: +1 954 262 1332; fax: +1 954 262 2278.