An advantage of this applied model is that it allows the estimation of consistent and efficient estimates for unbalanced data structures by using maximum likelihood estimation [ 30].
Random intercept models, which utilise maximum-likelihood estimation, provide more efficient estimates of effects with unbalanced data than the traditional repeated measures approach [ 81].
Our approach yields more efficient estimates compared to the maximum likelihood estimator, the least squares estimator and the weighted least squares estimator, which do not utilize the conditional moment restrictions.
FIML estimation yields consistent and efficient estimates when data are missing at random [ 28].
Correction of that issue in the present work ensured that, at any positive correlation level, all the estimators tested here gave more efficient estimates than those obtained using simple random sampling.
To test which of the decision processes best describes the decision to undertake a level of activity that is sufficient to meet the recommended level, the Hausman specification test was used to check which estimator produced better consistent and efficient estimates.
This approach yields more efficient estimates under certain conditions.
However, this proposed method leads to consistent but not necessarily efficient estimates, because: 1.
Thus, under the assumptions of the model, the maximisation of (5) yields consistent and efficient estimates.
Thus, the Heckman probit (heckprob) provides consistent and asymptotically efficient estimates for all parameters in such model.
However, a parametric model may lead to more efficient estimates than the Cox model under certain conditions.
