Multiple event times in the presence of informative censoring: modeling and analysis by copulas

Motivated by a breast cancer research program, this paper is concerned with the joint survivor function of multiple event times when their observations are subject to informative censoring caused by a terminating event. We formulate the correlation of the multiple event times together with the time to the terminating event by an Archimedean copula to account for the informative censoring. Adapting the widely used two-stage procedure under a copula model, we propose an easy-to-implement pseudo-likelihood based procedure for estimating the model parameters. The approach yields a new estimator for the marginal distribution of a single event time with semicompeting-risks data. We conduct both asymptotics and simulation studies to examine the proposed approach in consistency, efficiency, and robustness. Data from the breast cancer program are employed to illustrate this research.

     

The Pointing–Vocal Coupling Progression in the First Half of the Second Year of Life

This study investigated the development of the pointing–vocal coupling system. We were interested in the infants’ behavior to attune prosody with pointing intentions. Twenty‐five children were involved at 12, 15, and 18 months of age in an experimental procedure devised to elicit imperative and declarative pointing. Pointing, vocality associated with pointing, and the prosody of that vocality were analyzed. A significant increase in the coupling of pointing and vocality was observed from 12 to 15 months, and in the ability to differentiate prosody with respect to the intention of the gesture from 15 to 18 months. Also, the infants who pointed declaratively at 12 months were likely to couple declarative pointing with vocality at 15 months, and the infants who coupled at 15 months were likely to differentiate prosody by the pointing intention at 18 months. Results suggest that the match between prosody and pointing intentions emerges gradually during the first half of the second year of life. They also show a relationship between earlier and later pointing–vocal coupling, and a role for declarative communication in promoting that progression. Overall, our study supports the view of intentional communication as a time‐based and context‐based developmental process.     

The Regulation of Infant Negative Emotions: The Role of Maternal Sensitivity and Infant‐Directed Speech Prosody

This study explored the role of maternal sensitivity and infant‐directed speech (IDS) prosody in infants’ expression and regulation of negative emotion. Seventy mothers and their 3‐month‐old infants were observed during the Still‐Face Paradigm (SFP). Maternal sensitivity and IDS prosody were assessed at baseline and infant negative affect in the baseline, still‐face, and reunion episodes. Results showed that prototypical IDS prosody characterized by wider fundamental frequency (F0) variability was related to decreases in infant's negative affect, but only if accompanied by maternal sensitivity. Infants of sensitive mothers who spoke with more prototypical IDS prosody showed better abilities to regulate negative affect during the SFP. When prototypical IDS prosody was accompanied by low maternal sensitivity, infants showed lower regulation of negative emotions. In conclusion, infant negative affect regulation in a dyadic setting is facilitated by an optimal combination of both more prototypical maternal IDS prosody and maternal sensitive responsiveness. Implications for the study of mother–infant interaction are discussed.     

Cramér‐von Mises statistics for discrete distributions with unknown parameters

Choulakian, Lockhart & Stephens (1994) proposed Cramér‐von Mises statistics for testing fit to a fully specified discrete distribution. The authors give slightly modified definitions for these statistics and determine their asymptotic behaviour in the case when unknown parameters in the distribution must be estimated from the sample data. They also present two examples of applications.     

An Empirical Evaluation of Conflict in the Franchise System

This paper articulates the theoretical rationale for conflict in franchising, operationalizes conflict through the measurement of franchisee satisfaction and labels empirically supported stratified satisfaction levels. Two propositions are advanced in relation to the drivers of conflict in franchise systems. The first proposition is underpinned by relational exchange theory, which postulates that franchisee–franchisor goal congruence is important to the fulfilment of the alliance efficiencies which motivate inter-organizational forms. Cooperation, communication, coordination and commitment, as perceived by the franchisees, are used in the context of a survey instrument to operationalize goal congruence.
The second proposition involves franchisor-provided services. Transaction-cost analysis suggests that long-term contractual relationships must be flexibly interpreted and governed if the relationship is to be maintained over a series of transactions. We propose that the transactional intersection of the franchise system is in franchisor-provided services. The perceived importance and subsequent adequacy of delivery of these services established a tolerance zone within which transactions support and/or enhance the relationship between the franchisor and the franchisee.
The empirical objectives of the study are accomplished utilizing a questionnaire sent to nine franchise systems, to which 621 franchisees responded. Three clear clusters of franchisee conflict emerged in near equal proportions. The propositions are supported and illustrated empirically and in CHAID tree diagram form.     

Protectionism and real wage rigidity: A discussion of the macroeconomic literature

The paper discusses the macroeconomic literature on the relationship between real wage rigidity and the case for protectionism. First, it gives an account of the analytical arguments that lie behind the protectionist position of the Cambridge Economic Policy Group (CEPG). Then, it provides a critical appraisal of the model of the CEPG; the discussion is focused on its supply side, on the role it assigns to financial markets as well as on the issue of retaliation. Finally, the paper considers and evaluates the subsequent work by Eichengreen, which incorporates aggregate supply and wealth effects into the CEPG analysis.     

The Effect of Changing Sexual, Marital and Contraceptive Behaviour on Conceptions, Abortions, and Births

A model is proposed to estimate the number of conceptions during a single year using scarce survey data, official data on births and abortions for the two years following the survey, and some parameters on contraception failure. The model is fitted for 1979, 1989, 1994 to Puglia, a Southern Italian region with a population of 4 millions. Simulations are also produced.The decrease in births is caused mainly by the decline in wanted births, whereas the decline in abortions is caused by diffusion of the pill, IUD, and condom. The rapid increase in the proportion of never-married women explains the slow decrease in unwanted births and conceptions, compared to the fast decline in wanted ones. This situation is different compared to other Western countries (e.g. France, UK, and USA) where the decline in TFR during the 1960s and 1970s was largely caused by the decline in unwanted fertility, thanks to improved modern contraception and sterilisation.     

Testing fit for the grouped exponential distribution

Grouped data can often arise due to the lack of resolution of the measurement instruments; they also arise when data are deliberately rounded to a certain accuracy and are presented, say, in the form of a histogram. The author uses statistics of the Cramér‐von Mises type to test for the exponential distribution when data are grouped.     

Analysis of recurrent events with non-negligible event duration,with application to assessing hospital utilization

In an attempt to provide tools for assessing hospital utilization, this paper extends well-known models for recurrent events to address non-negligible event duration and presents a procedure for estimating the model parameters. The model extension is natural and easy to understand. Asymptotic properties of the associated inferences are derived adapting the well-developed methods based on the counting process formulation. Several specifications of the proposed modeling are illustrated with the hospitalization records of childhood cancer survivors from a health care insurance system that motivated this research. The usefulness and robustness of the proposed approach is demonstrated numerically via simulation.     

Cramér-von Mises tests of fit for the Poisson distribution

Goodness-of-fit tests based on the Cramér-von Mises statistics are given for the Poisson distribution. Power comparisons show that these statistics, particularly A², give good overall tests of fit. The statistic A² will be particularly useful for detecting distributions where the variance is close to the mean, but which are not Poisson.