On the Run Length of a State-Space Control Chart for Multivariate Autocorrelated Data

The literature on statistical process control (SPC) describes the negative effects of autocorrelation in terms of the increase in false alarms. This has been treated by the individual modeling of each series or the application of VAR models. In the former case, the analysis of the cross correlation structure between the variables is altered. In the latter, if the cross correlation is not strong, the filtering process may modify the weakest relations. In order to improve these aspects, state-space models have been introduced in multivariate statistical process control (MSPC). This article presents a proposal for building a control chart for innovations, estimating its average run length to highlight its advantages over the VAR approach mentioned above.     

Detection of a change-point in student-t linear regression models

In this work the Schwarz Inforamtion Criterion (SIC) is used in order to locate a change-point in linear regression models with independent errors distributed according to the Student-t distribution. The methodology is applied to data sets from the financial area.     

Educating Administrators to Interact with Citizens: A Research Note

This article examines the place of citizen participation courses in American Masters of Public Administration programs. A survey of course syllabi shows that very few programs provide courses that focus on citizen participation. While the evidence on course content is more ambiguous, course goals tend to focus on imparting cognitive knowledge rather than developing skills or engendering psychological transformation—outcomes that may be key to having administrators who are comfortable working with citizens. An argument is made for a more visible place for citizen-participation courses to show that the ability to involve citizens is part of administrative competence.     

Modelling safety climate in the prediction of levels of safety activity

This study examined the architecture of the relationships between components of organizational safety climate, including employee attitudes to safety issues and perceptions of the work environment, and related this to self-reported levels of safety activity. Data were collected from a large multinational manufacturing organization by questionnaire. A total of 915 valid questionnaires were returned and formed the basis for structural equation modelling and subsequent analyses. These data showed that a common structure, or architecture, of attitudes to safety issues and perceptions of the work environment could be constructed that explained levels of safety activity. The strength of employees' attitudes with regard to safety management played a pivotal role in this model through both direct and indirect paths. This is consistent with earlier findings on the importance of management commitment in organizations with well developed safety cultures. An examination of the differences between plants/sites showed that employees differed in their attitudes to safety issues, such as the management of safety and communication, and in their perceptions of workplace hazards. It is intended that this model be further utilized within the organization under study as a basis for monitoring safety performance and planned improvements in safety.     

Influence diagnostics for the Grubbs's model

In this paper we consider applications of local influence (Cook, 1986) to evaluate small perturbations in the model or in data sets of several measuring devices, assuming Grubbs's model. Different perturbation schemes are investigated and an application is considered to two real data sets.     

Additive outliers in INAR(1) models

In this paper the integer-valued autoregressive model of order one, contaminated with additive outliers is studied in some detail. Moreover, parameter estimation is also addressed. Supposing that the timepoints of the outliers are known but their sizes are unknown, we prove that the conditional least squares (CLS) estimators of the offspring and innovation means are strongly consistent. In contrast, however, the CLS estimators of the outliers’ sizes are not strongly consistent, although they converge to a random limit with probability 1. We also prove that the joint CLS estimator of the offspring and innovation means is asymptotically normal. Conditionally on the values of the process at the timepoints neighboring to the outliers’ occurrences, the joint CLS estimator of the sizes of the outliers is also asymptotically normal.     

Characterizations of discrete distributions based on conditional expectations of record values

r -th record values subject to (r + 1)-th record values, record mean function, from a distribution of discrete type. We give some properties of the record mean function and an explicit expression for the distribution function based on its record mean function, which allows us to characterize particular discrete distributions using the record mean functions. Received: January 4, 1999; revised version: September 27, 1999     

Convergence Properties of the Likelihood of Computed Dynamic Models

This paper studies the econometrics of computed dynamic models. Since these models generally lack a closed‐form solution, their policy functions are approximated by numerical methods. Hence, the researcher can only evaluate an approximated likelihood associated with the approximated policy function rather than the exact likelihood implied by the exact policy function. What are the consequences for inference of the use of approximated likelihoods? First, we find conditions under which, as the approximated policy function converges to the exact policy, the approximated likelihood also converges to the exact likelihood. Second, we show that second order approximation errors in the policy function, which almost always are ignored by researchers, have first order effects on the likelihood function. Third, we discuss convergence of Bayesian and classical estimates. Finally, we propose to use a likelihood ratio test as a diagnostic device for problems derived from the use of approximated likelihoods.     

Reliability of translated measures assessing dating violence among Mexican adolescents

Research on the prevalence and correlates of dating violence in Mexican teens is challenged by the lack of culturally and linguistically appropriate assessment tools. This study modified, translated, and back-translated the Conflict in Adolescent Dating Relationships Inventory (CADRI; Wolfe et al., 2001) and the Attitudes Towards Dating Violence Scales (Price, Byers, & the Dating Violence Research Team, 1999) for Mexican adolescents. Analyses on 307 adolescents (15-18 years old) from Monterrey and Mexicali, Mexico, revealed that most of the translated CADRI subscales and Attitudes Towards Dating Violence Scales had acceptable internal consistency and test-retest reliability coefficients. The study offers some evidence that the measures may be useful in assessing dating violence in Mexican teens.     

Measures of non-exchangeability for bivariate random vectors

We introduce a set of axioms for measures of non-exchangeability for bivariate vectors of continuous and identically distributed random variables and give some examples together with possible applications in statistical models based on the copula function.