Understanding Counseling Attrition: Insights from Logistic Regression

Brendon Lee Gore; Hu Yue

doi:10.63313/IJSSEH.2001

Authors

Brendon Lee Gore School of Science, Zhejiang University of Science and Technology, Hangzhou, China Author
Hu Yue School of Science, Zhejiang University of Science and Technology, Hangzhou, China Author

DOI:

https://doi.org/10.63313/IJSSEH.2001

Keywords:

Early Termination, Symptom Severity, odds ratio, Avoidance of Disclosure, The Hosmer & Lemeshow

Abstract

This study investigates the predictors of early termination among clients receiving counseling services at a community mental health centre. Early termi-nation, or dropout, poses significant challenges to the efficacy of therapeutic interventions, often leading to incomplete treatment and unaddressed mental health needs. Understanding the factors that contribute to this phenomenon is crucial for improving client retention and optimizing therapeutic outcomes. To explore these factors, a sample of clients who had engaged in counseling at the mental health centre was selected for the study. Each participant was inter-viewed, and their responses were meticulously recorded to ensure the accuracy and integrity of the data. The interview process was designed to encourage hon-est disclosure, enabling the collection of reliable information regarding their experiences and reasons for either continuing or discontinuing therapy. The study employed a binary logistic regression model to analyse the likelihood of early termination among these clients. The dependent variable in the model was the occurrence of early termination, operationalized as a binary outcome where '1' indicated early termination and '0' signified continuation of counseling until the intended completion. The group that did not terminate early was used as the reference category, while those who terminated early represented the target group for analysis. Two independent variables were identified as potential pre-dictors of early termination: symptom severity and avoidance of disclosure. Symptom severity ('sympsev') refers to the intensity of the clients' psychologi-cal symptoms, which was hypothesized to influence their likelihood of remain-ing in therapy. Avoidance of disclosure ('avdiscl') measures the extent to which clients were reluctant to share personal information during counseling sessions, which could hinder the therapeutic process and contribute to premature drop-out. Both predictors were treated as continuous variables within the model. The logistic regression analysis aimed to determine the relative contribution of these predictors to the likelihood of early termination. By calculating the odds ratios for each predictor, the study assessed how variations in symptom severity and avoidance of disclosure influenced the probability of a client terminating therapy prematurely. The results of this analysis provide valuable insights into the dynamics of client retention in counseling settings

References

[1] Hosmer Jr, D. W., Lemeshow, S., & Sturdivant, R. X. (2013). Applied logistic regression. John Wiley & Sons.

[2] Allison, P. D. (2012). Logistic regression using SAS: theory and application. SAS Institute.

[3] Menard, S. (2002). Applied logistic regression analysis (Vol. 106). Sage.

[4] Pituch, K.A., & Stevens, J.A. (2016). Applied multivariate statistics for the social sciences (6th ed). New York: Routledge.

[5] Hosmer, D.W., Hosmer, T. and Lemeshow, S. (1980) A Goodness-of-Fit Tests for the Mul-ti-ple Logistic Regression Model. Communications in Statistics, 10, 1043-1069.

https://doi.org/10.1080/03610928008827941

[6] Nagelkerke, N.J.D. (1991) A Note on a General Definition of the Coefficient of Determina-tion. Biometrika, 78, 691-692.

https://doi.org/10.1093/biomet/78.3.691

[7] Cox, D. R., & Snell, E. J. (1989). Analysis of binary data (2nd ed.). Chapman and Hall.

[8] McFadden, D. (1974) Conditional Logit Analysis of Qualitative Choice Behavior. In: Za-rembka, P., Ed., Economic Theory and Mathematical Economics, Academic Press, New York, NY, 105-142.

[9] Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861-874. https://doi.org/10.1016/j.patrec.2005.10.010

[10] Hair Jr, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2014). Multivariate data analysis (7th ed.). Pearson Education Limited.

[11] Peduzzi, P., Concato, J., Kemper, E., Holford, T. R., & Feinstein, A. R. (1996). A simulation study of the number of events per variable in logistic regression analysis. Journal of clinical epidemiology, 49(12), 1373–1379. https://doi.org/10.1016/s0895-4356(96)00236-3

[12] Field, A. (2018). Discovering statistics using IBM SPSS statistics (5th ed). Los Angeles: Sage.