Conditioning as disintegration

Conditional probability distributions seem to have a bad reputation when it comes to rigorous treatment of conditioning. Technical arguments are published as manipulations of Radon–Nikodym derivatives, although we all secretly perform heuristic calculations using elementary definitions of conditional probabilities. In print, measurability and averaging properties substitute for intuitive ideas about random variables behaving like constants given particular conditioning information.
One way to engage in rigorous, guilt-free manipulation of conditional distributions is to treat them as disintegrating measures—families of probability measures concentrating on the level sets of a conditioning statistic. In this paper we present a little theory and a range of examples—from EM algorithms and the Neyman factorization, through Bayes theory and marginalization paradoxes—to suggest that disintegrations have both intuitive appeal and the rigor needed for many problems in mathematical statistics.     

Eliminating the Barriers to Employment Equity in the Canadian Workplace

Have employment equity programs achieved the goal of equity for women in the workplace? We argue that they have not because gender stereotypes still persist. In fact, they may have created resentment and antagonism towards successful women and employment equity initiatives. Arguments are developed for the Canadian government to create a self-regulating system, in which the government plays a role of educator as opposed to monitor.     

Price rigidities and institutional variations in markets with posted prices

Summary Standard laboratory posted-offer markets respond slowly and incompletely to demand shocks. In these one-sided markets, where sellers control the setting of prices, very little information is transmitted via the process of exchange. For this reason, traders have trouble distinguishing randomness in their own experience from changes in market fundamentals. This paper reports the results of twelve laboratory markets conducted to assess whether some common variants to standard posted-offer rules can correct the adjustment deficiences. Although discounting, multiple postings and excess demand information all improve performance, we find that response remains poor, and efficiencies low.Support for this research was provided by the National Science Foundation (SBR 9319842 and SBR 9320044), and the University of Virginia Bankard Fund. Data are archived at FTP address: fido.econlab.arizona.edu. We wish to thank Charles Plott and Shyam Sunder for useful comments on an earlier draft of this paper. The usual disclaimer applies.     

Coordinated strategies for economic cooperation between Europe and the United States

Zusammenfassung Koordinierte Strategien für wirtschaftliche Zusammenarbeit zwischen Europa und den Vereinigten Staaten. - In diesem Aufsatz wird die dynamische Spieltheorie auf die Koordinierung der Politik zwischen den Vereinigten Staaten und der EWG in einem stark aggregierten Modell angewandt und folgendes gezeigt: (i) Eine Politik, die den Einflu\ von Ma\nahmen anderer L?nder vernachl?ssigt, führt in den USA zu Fiskalischen Einschr?nkungen und einer Verminderung der staatlichen Interventionen, in Europa dagegen zu einer Nachfragestimulierung, verbunden mit einer kontinuierlichen Herabsetzung des Diskontsatzes. Die EWG-L?nder sind, da sie ihre Politik nicht koordinieren, nach einigen Jahren wegen Zahlungsbilanzschwierigkeiten zu einer kontraktiven Nachfragepolitik gezwungen. (ii) Koordinierte Strategien best?tigen, da\ nicht-synchronisierte Politiken die Weltwirtschaft stabilisieren k?nnen. (in) Kooperation verbessert die wirtschaftlichen Leistungen, ausgedrückt in den Wachstumsraten und den Zahlungsbilanzen. Allerdings erbringt die ausdrückliche Zusammenarbeit kaum noch zus?tzliche Vorteile zu denen, die bereits im Rahmen der vollen Koordinierung erreicht werden k?nnen.

---

Resumen Estrategias coordinadas de cooperación económica entre Europa y los EEUU.- La aplicación de un modelo dinámico de teoría de juegos a la coordinatión de política económica entre los EEUU y la CEE, como parte de un modelo altamente agregado de la economía mundial, permite concluír en este trabajo que (i) políticas que ignoran la influencia de medidas tomadas en otros países dan lugar a una contractión fiscal y a una menor interventión del Gobierno en los EEUU, pero a una estimulación de la demanda combinada con reducciones continuas de la tasa de descuento en Europa; al seguir políticas descoordinadas los países de la CEE están obligados a contraer la demanda agregada al cabo de unos a?os, debido a los problemas de balance de pagos, (ii) estrategias coordinadas confirman que políticas no sincronizadas pueden estabilizar la economía mundial; (iii) la cooperación favorece a la economía en términos de tasas de crecimiento y balance de pagos. Sin embargo, los beneficios adicionales de una cooperatión explícita resultan marginales en comparación con los beneficios ya alcanzados por la solución con coordinación total.

---

Résumé Stratégies coordonnées pour la coopération entre l’Europe et les E.U. - En appliquant la théorie dynamique de jeu à la coordination de politique entre les E.U. et la CEE dans un modèle fortement agrégé de l’économie mondiale, cet article arrive aux conclusions suivants: (i) La politique qui ignore l’influence des actions suivies dans d’autres économies mène à la réduction fiscale et à moins interventions gouvernementales dans les E.U., mais à une stimulation de la demande avec des réductions continuelles du taux d’escompte en Europe. En cas d’une politique pas coordonnée les pays CEE sont forcés à prendre des mesures pour freiner la demande agrégée après quelques années à cause des problèmes de la balance des paiements. (ii) La stratégie coordonnée confirme que des politiques pas synchronisées pourraient stabiliser l’économie mondiale. (iii) La coopération peut élever le taux de croissance et améliorer la balance des paiements. Cependant, les gains additionnels d’une coopération explicite sont petits en comparaison avec les bénéfices déjà gagnés à l’aide d’une solution complètement coordonne’e.

     

Recall and recognition effects of brand name imagery

The strategic marketing decision regarding the selection of a brand name has long been an area neglected by academic researchers. This study attempts to apply psychological theory to this important strategic decision area. Specifically, the applicability of a dual-coding theory of memory to brand name recall/recognition is tested in an experimental setting. Results indicate, on average, a significant one hour and two day recall/recognition advantage of high imagery over low imagery brand names across a variety of product categories.     

The Impact of Option Introduction on Stock Return Variances: The Role of Bid-Ask Spreads, Return Autocorrelations, and Intrinsic Variances

The purpose of this paper is to examine changes in stock return variances following option introduction. The sample consists of National Market System stocks and employs both transaction returns and returns based on bid and ask quotes. Variances are decomposed into portions attributable to bid-ask spreads, return autocorrelations, and intrinsic variances. Spreads play a negligible role in explaining variance changes. A generally positive component to short-term autocorrelations falls following option introduction, increasing variances over short holding periods. Intrinsic variances fall prior to the October 1987 crash, but do not change after the crash with option introduction.     

Application of replacement theory in dairy cows and its use in disease treatment

A model to simulate the costs and returns of an individual dairy cow over 14 years under various assumptions of genetic potential, health status and management was developed especially to evaluate the effects of diseases that reduce production and reproduction efficiency and to evaluate alternative management interventions. Data were collected from the Food Animal Health Resource Management System (FAHRMX), Today's Electronic Planning (TELPLAN), Today's Electric Farm Accounting (TELFARM) databases and secondary sources at Michigan State University. A case study of cystic ovaries was analysed using the model. The results showed that it is more economical to treat cystic ovaries than not to treat, and treatment with Gonadotropin Releasing Hormone (GNRH) was superior to Human Chrionic Gonadotropin (HCG). Four to five lactations were the optimum for keeping a dairy cow to replacement and it was estimated that there is a loss of US$0.45 per day of extended calving interval (days open beyond the optimal 70 days).