And last but not least, modelling employment protection itself is quite a complicated issue and it probably deserves a more sophisticated modelling than simply implementing firing costs, the approach we followed in the model at hand.
This would challenge the proportional hazards assumption of a standard Cox regression, and it suggests we should model employment status as a time-dependent quantity.
Often described as a model for chief executives, John F. Welch Jr. appears to have also created the model employment contract.
In Chapter 5, Rolf Färe, Shawna Grosskopf, Carl Pasurka, and Ronald Shadbegian model employment impacts under different regulatory approaches, comparing more rigid, traditional regulation with more flexible, market-based instruments.
Six criteria were used with this model: employment density, population density, feeder bus service, location on the alignment, location at a street intersection, and a minimum of ½ mile distance from the next station.
In Keynes's model, employment and output are driven by aggregate demand, the sum of consumption and investment.
In the fully adjusted model, employment status, urban/rural dwelling, household income (and, for men only, education) remained significant determinants of supplementary insurance.
In a crude unadjusted model employment was associated with over a twofold increased odds (OR=2.36, 95% CI 2.08 to 2.67) of being persistently active, although was attenuated to the null in the final adjusted model.
Therefore, we only included the following three demographic variables in our logistic regression models: employment status (employed vs. unemployed), ethnicity (urban origin vs. Bedouin origin), and age as continuous variable.
