Mini/micro computer evaluation of system features: An empirical discriminant model of software and hardware expandability,compatibility, cost-efficiency,installation and delivery

The rapid advances in technology with declining costs of hardware is expected to widen the market for computers. One of the interesting balances for vendors to achieve is keeping users happy with increases in price performance, usually with lower unit costs. One way to achieve this objective is by satisfying users and meeting their needs. Users have many different needs, however, and it may be very difficult to prioritize them since many of the needs are partially mutually exclusive. For example, the promotion of one need, low response time, would be at the expense of another need, low cost. Therefore, mini/micro vendors and users could use a model that will prioritize needs and measure how satisfied users are with specific computer systems as compared to others. Similarly, the same information may be very useful to current and future computer users for system selection. Accordingly, the main purpose of the present study is to provide vendors and users of mini/micro computers with a discriminant model. This model classifies correctly 93% of the successful systems. Thus it can be used for system selection by users and for system design by vendors.     

Small sample performance of the Stein-Rule in non-orthogonal designs

The effects of multicollinearity upon the risk improvement provided by Stein-like estimators over the maximum likelihood estimator in the normal regression model are investigated via Monte Carlo methods. Risk gains are found to degenerate rapidly given moderate degrees of multicollinearity.     

Correcting the t statistic for measurement error

Studies in marketing often involve application of multi-item scales to measure latent constructs. Once the psychometric properties of a scale have been assessed, responses to individual scale items are often summed to form a composite score, which then is compared across groups by performing statistical tests such as a t test. In this note, we draw researchers?? attention to an often overlooked fact that the t test is attenuated by imperfect measures. As a solution, we propose the disattenuated t statistic and discuss how it would increase accuracy of estimates and affect decisions in the marketing discipline.