Count data models for outpatient health services utilisation

Table 3 Comparisons across all models using LL, AIC and BIC.

Notes : Abbreviation: LL = log likelihood; AIC = Akaike’s information criterion; BIC = Bayesian information criterion; RMSE = root mean square error, R2 = r-square
^a Lower LL, AIC, and BIC were preferred. Lower RMSE and higher R2 values indicate lesser prediction errors
^b Positive Vuong statistics value indicates zero-inflated model is more appropriate than conventional
^c Statistical significance at p < 0.001
* indicates preferred model

ISSN: 1471-2288