Transition Models,
Probits, and Selection-Corrected Regressions
After applying statistical method of
probits to the experimental data, H.
Carrasco (2001) estudia el efecto de los hijos sobre la participacion de las mujeres en el mercado laboral mediante la estimacion de modelos
probits alternantes para datos de panel.
The main weakness of the analysis is that some of the techniques, such as the bivariate
probits, 2SLS, and fixed effects models, produced imprecisely measured estimates.
Indeed the values of [[PSI].sub.b(50)] derived from the relationship between the
probits of the accumulated daily germination percentages of Hylocereus setaceus and [PSI] - [[[theta].sub.H]/[t.sub.g]] shift to zero with increasing temperatures, although the median [[PSI].sub.b] values did not differ significantly to each other within the respective temperature range (if infra or supra-optimum), probably due to relatively high variance of the data.
To investigate whether families increase hours enough to qualify for this In-Work payment, we ran selection-corrected
probits for the probability of meeting the hours threshold separately for partnered and unpartnered women.
We obtain similar conclusions using different empirical definitions for overemployment and also when estimating alternative models, such as bivariate
probits, taking into account the possibility of no participation in the labour market.
One should note that while we think this method of estimating child care costs has substantial benefits over alternatives such as average child care costs in the location of residence (which is not available with SIPP data), because of its acknowledgment of differences in the probability of paying for care, the disadvantage is that bivariate
probits are in general quite sensitive to sample size.
An appendix compares bivariate
probits and two state least squares statistical approaches.
For example, at 40 [degrees] C and 140 g [kg.sup.-1] moisture content, Lot 6 had a rate of 0.3731
probits [d.sup.-1] but the rate for Lot 11 was only 0.1403
probits [d.sup.-1].
Using the explanatory variables discussed in Section 5,
probits are run to determine the variables that are associated with sharing responsibility internally (INTSHARE) and externally (EXTSHARE).
Initially, the military and work force
probits are estimated separately by Maximum Likelihood.