A Continuous Representation of the Family of Stable Law Distributions

Conventional parametric representations of stable law distributions do not allow all members of the family to be obtained as continuous limits of the parameters. Model building (or simulation) using such representations will be numerically unstable near such limits in consequence. Existing tables are not satisfactory near such limits as interpolation cannot be carried out. We show that these difficulties are overcome by using a new shifted Cartesian representation which characterizes the entire stable law family in a completely continuous way. Standardization is still possible with this representation so that tabulation, using just two bounded parameters, can be carried out. Its use is illustrated in a non-regular threshold estimation problem involving stable distributions which are discontinuous limits in conventional representations.     

Employment-based health benefits: analysis of the April 1993 Current Population Survey

The April 1993 CPS differs from the March 1993 CPS in a number of respects. The April 1993 CPS supplement surveys only workers, whereas the March CPS examines the noncash benefits received by all Americans. The April CPS asks workers about health coverage in the week in which the questions were fielded, whereas the March CPS asks about coverage in the preceding year. In April 1993, there were 112.5 million civilian American workers between the ages of 18 and 64 with jobs. Eighty-two million (73 percent) of them worked for an employer that sponsored a health insurance plan, and 65 million (58 percent of all workers) participated in their employer's health plan. About one-third of workers at firms with fewer than 10 employees had employers who offer health benefits; about one-quarter of all of the workers in these firms participated in their employer's plan. Conversely, 94 percent of workers at firms with more than 1,000 employees had an employer who sponsored health benefits, and over 77 percent of these workers participated in their employer's plan. There are 16.5 million American workers whose employers sponsored health benefits but who did not participate in these benefits. Over one-half of these workers (8.5 million) chose not to be covered. Another 36 percent of these workers (5.9 million) did not participate because they were ineligible or denied coverage. Over 66 percent of the ineligible workers did not participate because they were part-time, contract, or temporary workers. Another 26 percent had not yet completed a probationary period. Among the reasons that those who chose not to participate in their employer's coverage, the vast majority (75 percent) stated they were covered by another health care plan. Twenty-nine percent stated that they chose not to purchase coverage because it was too costly or that they did not need or want the coverage. In 1993, there were 16.7 million workers with no health insurance coverage. The vast majority of these workers (95 percent) were employed by private employers. Sixty-six percent of the workers with no health insurance coverage were self-employed or worked for firms with fewer than 100 employees.     

Ultrastructural elliptical models

Dolby's (1976) ultrastructural model with no replications is investigated within the class of the elliptical distributions. General asymptotic results are given for the sample covariance matrix S in the presence of incidental parameters. These results are used to study the asymptotic behaviour of some estimators of the slope parameter, unifying and extending existing results in the literature. In particular, under some regularity conditions they are shown to be consistent and asymptotically normal. For the special case of the structural model, some asymptotic relative efficiencies are also reported which show that generalized least squares and the method of moment estimators can be highly inefficient under nonnormality.     

Nonparametric regression estimation at design poles and zeros

ABSTRACT In most treatments of nonparametric regression, it is assumed that the marginal density of the explanatory variables is strictly bounded away from zero and infinity. This note investigates the pointwise asymptotics for nonparametric regression when this assumption fails, that is, the marginal density of the explanatory variable has either an isolated zero or a pole at the point of interest.     

Testing a theoretical model of adolescent sexual behavior among rural families in poverty

This was a study of 357 adolescents, aged 13 to 17 years, who resided in a family receiving AFDC in 10 rural counties in Arkansas. The study had a twofold purpose: 1) to examine what elements of social control, social learning, and strain theories predicted 3 measures of sexual behavior; and 2) to test an integrated theoretical model with 2-stage least squares regression to see if it fit the data on the 3 measures of sex. The measures of sexual behavior were frequency of sexual intercourse in the past year, number of sexual partners in the past year, and number of sexual partners in lifetime. Bivariate analyses revealed that the consistent predictors of the 3 measures of sex were age, gender, attachment to mother, beliefs, parental supervision and punishment, family and friend support, frustration, and use of rationalizations. The theoretical model that fit all measures of sex showed that bonding influences sexual behavior through frustration, and that age, gender and rationalizations directly impact behavior.     

Frank Parsons's Enablers: Pauline Agassiz Shaw,Meyer Bloomfield,and Ralph Albertson

Frank Parsons was not the 1st American to recognize or address the need for vocational guidance. Why he, rather than his predecessors, is credited with initiating the field can be attributed to the largely overlooked contributions of 3 other persons: Pauline Agassiz Shaw, Meyer Bloomfield, and Ralph Albertson. The author calls attention to the contributions of these 3 remarkable individuals, and several others who supported them, in enabling and perpetuating Parsons's work.