The initial purpose of this study was to establish the effect of childhood conditions on longevity from the Brabant data set. This data set combines information at ages 12, 43, 53 and mortality between 53 and 71 for a sample of some 3000 individuals born around 1940 in the Dutch province of...

The Brabant Data Set, now freely accessible, contains informationon a sample cohort of 3,000 individuals born around 1940 from surveysin 1952, 1983 and 1993, as well as on deaths between 1994 and 2009.In line with numerous epidemiological studies we find that among theearly variables recorded at...

A bank employs logistic regression with state-dependent sample selection to identify loans thatmay go wrong. Inspection shows that the logit model is inappropriate. A bounded logit model witha ceiling of (far) less than 1 fits the data much better.

The discrete outcome of a probability model is recordedas Y(i)=1 while otherwise Y(i)=0. y is the vector of observedoutcomes, p the corresponding probabilities, p^a consistent estimate of p, and residuals are defined ase = y - p^. Under quite general conditions, theasymptotic properties of p^...

In binary discrete regression models like logit or probit the omis- sion of a relevant regressor (even if it is orthogonal) depresses the re- maining <font face="Symbol">b</font> coefficients towards zero. For the probit model, Wooldridge (2002) has shown that this bias does not carry over to the effect of the regressor...

In a discrete model, the predicted probabilities of a particular event can be matched to the observed (0, I) outcomes and this will give rise to a measure of fit for that event. Previous results for the binomial model are applied to multinomial models. In these models the measure of fit will...

The discrete outcome of a probability model is recorded as Y(i)=1 while otherwise Y(i)=0. y is the vector of observed outcomes, p the corresponding probabilities, p^ a consistent estimate of p, and residuals are defined as e = y - p^. Under quite general conditions, the asymptotic properties of...

In a binary logit analysis with unequal sample frequencies of the two outcomes the less frequent outcome always has lower estimated prediction probabilities than the other one. This effect is unavoidable, and its extent varies inversely with the fit of the model, as given by a new measure that...

A bank employs logistic regression with state-dependent sample selection to identify loans that may go wrong. Inspection shows that the logit model is inappropriate. A bounded logit model with a ceiling of (far) less than 1 fits the data much better.

This paper describes the origins of the logistic function, its adoption in bio-assay, and its wider acceptance in statistics. Its roots spread far back to the early 19th century; the survival of the term logistic and the wide application of the device have been determined decisively by the...