The occurrence of outliers in the explanatory variable considered in an errors-in-variables framework

Summary The problem of estimating the slope of a linear relationship between two jointly normally distributed random variables is considered when outliers may occur in the explanatory variable. It will be studied as a special case of an errors-in-variables problem where the explanatory variable is measured which a nonnormally distributed error. In this more general model and under certain conditions a consistent estimator can be given with a normal limiting distribution. Applications to cases of outliers in the explanatory variable will be presented.     

Anonymous voting and minimal manipulability

We compare the manipulability of different choice rules by considering the number of manipulable profiles. We establish the minimal number of such profiles for tops-only, anonymous, and surjective choice rules, and show that this number is attained by unanimity rules with status quo.     

Pricing default swaps: Empirical evidence

In this paper we compare market prices of credit default swaps with model prices. We show that a simple reduced form model outperforms directly comparing bonds' credit spreads to default swap premiums. We find that the model yields unbiased premium estimates for default swaps on investment grade issuers, but only if we use swap or repo rates as proxy for default-free interest rates. This indicates that the government curve is no longer seen as the reference default-free curve. We also show that the model is relatively insensitive to the value of the assumed recovery rate.     

Longitudinal measurement in organisational transformation: a case of a Dutch Flex Company

This paper will present the analysis of data over 3 years (1998, 1999, and 2000) on the satisfaction of flex workers in the context of a flex company’s service excellence programme, as an example of the use of measurements in relation to the change process. The important issues related to the specific data of the flex workers’ satisfaction surveys are: (a) the relationships between perceived satisfaction of flex workers and possible behavioural consequences, like making complaints and making use of other flex companies; (b) the stability of factor constructs over time that identify the major dimensions of satisfaction of flex workers; and (c) the satisfaction dynamics over time.     

An empirical study into the influence of customer satisfaction on customer revenues

It is broadly expected that customer satisfaction (CS) influences customer revenues (CR), but there is little evidence for the corresponding hypothesis. If CS influences CR, there must be a relation between CS at time t?=?0 and CR at time t?>?0. We developed a statistical model representing this relation, which we tested in a longitudinal study using person-level data (N?=?1682) from a Dutch retail bank. We found that CS had a positive effect on CR with 1-year and 2-year time lags. These results support the hypothesis that CS influences CR.