A new approach to analyse longitudinal epidemiological data with an excess of zeros

Table 3 Regression and model fit parameters for the three longitudinal models with a random intercept, evaluating the difference in development of the hypoglycaemic events over time

	Linear mixed model			Poisson mixed model			Two-part joint mixed model (binomial/Poisson)
	Coef.	Std. Err.	P > \|z\|	Coef.	Std. Err.	P > \|z\|	Coef.	Std. Err.	P > \|z\|
T1 (3 months)	−0.31	(0.26)	0.220	−0.11	(0.11)	0.333	−0.18	(0.12)	0.129
T2 (6 months)	−0.73	(0.24)	0.002	−0.26	(0.11)	0.015	−0.27	(0.10)	0.010
BIC	12395.09			7983.639			7013.644
Mean squared residual	13.61			9.02			6.56

Abbreviation: Regression coefficients (Coef.), Standard errors (Std. Err.), P-value (P > |z|), Bayesian information criterion (BIC).

ISSN: 1471-2288