On the Application of Conditional Independence to Ordinal Data

A special log linear parameterization is described for contingency tables which exploits prior knowledge that an ordinal scale of the variables is involved. It is helpful, in particular, in guiding the possible merging of adjacent levels of variables and may simplify interpretation if higher-order interactions are present. Several sets of data are discussed to illustrate the types of interpretation that can be achieved. The simple structure of the maximum likelihood estimates is derived by use of Lagrange multipliers.     

Competition for versus on the Rails: A Laboratory Experiment*

European countries and Japan are contemplating more competition in passenger rail service. In the Netherlands, the Ministry of Transport was assigned responsibility for making a recommendation to Parliament for choosing between competition for the rails and competition on the rails. The Ministry commissioned the experiments reported here to acquire better understanding of the properties of the alternative policies. Competition on the rails involves allocation of rights to use station and time‐slot routes by price bids in a combinatorial auction. Competition for the rails involves allocation of rights to regional monopolies by fare‐structure bids for supplying a prespecified minimum schedule.     

A continuous-time portfolio turnpike theorem

We prove a continuous-time portfolio turnpike theorem. The proof uses the theory of martin-gales and is more intuitively appealing than the usual discrete-time mode of proof using dynamic programming. When the interest rate is strictly positive, the present value of any contingent claim having payoffs bounded from above can be made arbitrarily small when the investment horizon increases. Thus an investor concentrates his wealth in buying contingent claims that have payoffs unbounded from above at the very beginning of his horizon. As a consequence, it is the asymptotic property of his utility function as wealth goes to infinity that determines his optimal investment strategy at the very beginning of his horizon.     

Reflections on Fourteen Cryptic Issues Concerning the Nature of Statistical Inference*

The present paper provides the original formulation and a joint response of a group of statistically trained scientists to fourteen cryptic issues for discussion, which were handed out to the public by Professor Dr. D.R. Cox after his Bernoulli Lecture 1997 at Groningen University.     

The appliance of science? New public management and strategic change

Changes in the nature of science as a social practice were fundamentally organic and endogenous in nature prior to the 1970s. Since then changes in UK public science has been policy-led and the imperatives exogenous. This shift was the result of attempts to achieve strategic managed change in the sector using new public management (NPM) techniques. This paper explores the discourses that promoted the change effort and the NPM techniques and processes deployed to this end. It seeks to identify the aims and objectives of the intended strategic change and evaluates the extent to which they have been achieved. Our conclusion is that rather than a planned, strategic change process directed at improved economy, efficiency and effectiveness, what occurred was a poorly processed ideologically driven attempt to achieve political aims.     

Mortality Regimes and Pricing

Abstract

Mortality dynamics are characterized by changes in mortality regimes. This paper describes a Markov regime-switching model that incorporates mortality state switches into mortality dynamics. Using the 1901-2005 U.S. population mortality data, we illustrate that regime-switching models can perform better than well-known models in the literature. Furthermore, we extend the 1992 Lee-Carter model in such a way that the time-series common risk factor to all cohorts has distinct mortality regimes with different means and volatilities. Finally, we show how to price mortality securities with this model.