TEACHING EFFECTIVENESS IN THE DECISION SCIENCES: THE USE OF STUDENT EVALUATIONS

This article presents the results of an AIDS-sponsored investigation of teaching effectiveness in the decision sciences. Two national samples were employed in the study: a sample of 247 business school deans and a sample of 3,292 students from 32 different business schools. Included among the findings are that 87 percent of the deans responding indicate they require some sort of faculty teaching effectiveness evaluation, and that great care must be exercised when interpreting student ratings of an individual instructor's teaching effectiveness.     

MULTIPLE REGRESSION ANALYSIS APPLIED TO RESIDENTIAL PROPERTIES

An interesting and promising innovation in the assessment of property for tax purposes is the application of multiple regression analysis. Sales prices are regressed on various housing characteristics, and models developed from sold properties are used to generate value estimates for unsold properties. Two important issues relating to the development of such models are (1) the extent to which real estate markets are stable in terms of structural relationships over time, and (2) the extent to which sales prices reflect actual market values. The first issue is important because it affects how current sales must be before they can be used in model development, as well as the amount of information the assessor must collect and maintain on properties. The second issue is important because it concerns the amount of measurement error in the models and the extent to which the assessor/analyst can unambiguously interpret residual variance. These issues are investigated by comparing regression models developed from a sample of properties in Eugene, Oregon, which sold in each of two well separated time periods.     

SENSITIVITY ANALYSIS WITH INTERACTION EFFECTS

The purpose of this paper is to extend the sensitivity analysis methodology as it applies to linear programming. The methodology developed herein is concerned with those changes in a technological coefficient that cause simultaneous changes in the relevant cost coefficients of the objective function. By proceeding from the definitions of feasibility and optimality, the authors develop formulas for determining bounds on the extent to which a technological coefficient, which has a predetermined effect on the corresponding cost coefficient, can vary without changing the optimal set of activities. After the formulas are developed, their use is demonstrated on a product-mix problem. This technique is of interest because changes in the rate at which an input is utilized can be expected to change the cost per unit of a resulting product. This interdependence should be recognized whenever a sensitivity analysis is performed on a technological coefficient of either a cost minimization or a contribution margin maximization problem.     

Digit ratios (2D:4D) as predictors of risky decision making for both sexes

Many important decisions involve financial risk, and substantial evidence suggests that women tend to be more risk averse than men. We explore a potential biological basis of risk-taking variation within and between the sexes by studying how the ratio between the length of the second and fourth fingers (2D:4D) predicts risk-taking. A smaller 2D:4D ratio has been linked to higher exposure to prenatal testosterone relative to estradiol, with men having lower ratios than women. In financially motivated decision-making tasks, we find that men and women with smaller 2D:4D ratios chose significantly riskier options. We further find that the ratio partially explains the variation in risk-taking between the sexes. Moreover, for men and women at the extremes of the digit-ratio distribution the difference in risk-taking disappears. Thus, the 2D:4D ratio partially explains variation in financial risk-taking behavior within and between sexes and offers evidence of a biological basis for risk-taking behavior.     

Assessing the Concept of the ‘Insecure‐Other’ Category in the Cassidy–Marvin Scheme: Changes Between 4 and 6 Years in the English and Romanian Adoptee Study

We set out to explore the meaning of the attachment categories in the Cassidy/Marvin strange situation procedure, as employed in the home, using data from a longitudinal study of children adopted into UK families up to the age of 42 months from Romanian institutions, and of adopted children without the experience of institutional care––both groups being assessed at 4 and 6 years of age. Inter‐rater reliability was found to be good. Security (meaning the use of the parent as a secure base and no negative behavior on reunion) was the modal categorical rating in both the institution‐reared and comparison groups, but the category of anomalous non‐normative behavior (meaning a lack of any ordered attachment behavior as covered by the standard ratings), previously labeled ‘insecure‐other’, was more common in the institution‐reared children. Because this was unassociated with the usual manifestations of insecurity (such as avoidance or resistance) and because it was largely evident in interactions with the stranger, it is concluded that the adjective ‘insecure’ was not appropriate. Although this ‘insecure‐other’ category was associated with disinhibited attachment as reported by parents (meaning a lack of differentiation among adults, a willingness to go off with strangers and a lack of checking back with parents in anxiety‐provoking situations), it did not prove to be a good index of disinhibited attachment because changes over time in the ‘insecure‐other’ category were not associated with changes in the rate of disinhibited attachment. Also, whereas the rate of ‘insecure‐other’ fell markedly in the institution‐reared group between 4 and 6 years of age, it rose in the comparison group, raising queries over its meaning.     

Quantifying the Distribution of Inhalation Exposure in Human Populations: 2. Distributions of Time Spent by Adults, Adolescents, and Children at Home, at Work, and at School

Using distributions of time spent at various ventilation levels, ranges of inhalation exposure in the population can be established. Distributions of exposure time were determined using results of a study by the California Air Resources Board (CARB) which focused on time spent by humans participating in various activities and the locations where the activities occurred. The daily at-home activities from the CARB study were assigned to one of three ventilation levels, generating aggregate time periods. Distinct age and gender populations were identified, and distributions for aggregate time were established for these populations at each of the ventilation levels. In addition to aggregate time spent at home, distributions for various ages and genders were established for aggregate time spent at school and work. By combining distributions of aggregate time with corresponding ventilation rates, the distribution of inhalation rates can be established for at home, at work, and at school exposures.     

Identifiable finite mixtures of location models for clustering mixed-mode data

For clustering mixed categorical and continuous data, Lawrence and Krzanowski (1996) proposed a finite mixture model in which component densities conform to the location model. In the graphical models literature the location model is known as the homogeneous Conditional Gaussian model. In this paper it is shown that their model is not identifiable without imposing additional restrictions. Specifically, for g groups and m locations, (g!)m–1 distinct sets of parameter values (not including permutations of the group mixing parameters) produce the same likelihood function. Excessive shrinkage of parameter estimates in a simulation experiment reported by Lawrence and Krzanowski (1996) is shown to be an artifact of the model's non-identifiability. Identifiable finite mixture models can be obtained by imposing restrictions on the conditional means of the continuous variables. These new identified models are assessed in simulation experiments. The conditional mean structure of the continuous variables in the restricted location mixture models is similar to that in the underlying variable mixture models proposed by Everitt (1988), but the restricted location mixture models are more computationally tractable.     

On perfect simulation for some mixtures of distributions

This paper studies the implementation of the coupling from the past (CFTP) method of Propp and Wilson (1996) in the set-up of two and three component mixtures with known components and unknown weights. We show that monotonicity structures can be exhibited in both cases, but that CFTP can still be costly for three component mixtures. We conclude with a simulation experiment exhibiting an almost perfect sampling scheme where we only consider a subset of the exhaustive set of starting values.     

DENSITY ESTIMATION FOR CLUSTERED DATA

The commonly used survey technique of clustering introduces dependence into sample data. Such data is frequently used in economic analysis, though the dependence induced by the sample structure of the data is often ignored. In this paper, the effect of clustering on the non-parametric, kernel estimate of the density, f(x), is examined. The window width commonly used for density estimation for the case of i.i.d. data is shown to no longer be optimal. A new optimal bandwidth using a higher-order kernel is proposed and is shown to give a smaller integrated mean squared error than two window widths which are widely used for the case of i.i.d. data. Several illustrations from simulation are provided.