A comparison of some robust,adaptive, and partially adaptive estimators of regression models

Numerous estimation techniques for regression models have been proposed. These procedures differ in how sample information is used in the estimation procedure. The efficiency of least squares (OLS) estimators implicity assumes normally distributed residuals and is very sensitive to departures from normality, particularly to "outliers" and thick-tailed distributions. Lead absolute deviation (LAD) estimators are less sensitive to outliers and are optimal for laplace random disturbances, but not for normal errors. This paper reports monte carlo comparisons of OLS,LAD, two robust estimators discussed by huber, three partially adaptiveestimators, newey's generalized method of moments estimator, and an adaptive maximum likelihood estimator based on a normal kernal studied by manski. This paper is the first to compare the relative performance of some adaptive robust estimators (partially adaptive and adaptive procedures) with some common nonadaptive robust estimators. The partially adaptive estimators are based on three flxible parametric distributions for the errors. These include the power exponential (Box-Tiao) and generalized t distributions, as well as a distribution for the errors, which is not necessarily symmetric. The adaptive procedures are "fully iterative" rather than one step estimators. The adaptive estimators have desirable large sample properties, but these properties do not necessarily carry over to the small sample case.

The monte carlo comparisons of the alternative estimators are based on four different specifications for the error distribution: a normal, a mixture of normals (or variance-contaminated normal), a bimodal mixture of normals, and a lognormal. Five hundred samples of 50 are used. The adaptive and partially adaptive estimators perform very well relative to the other estimation procedures considered, and preliminary results suggest that in some important cases they can perform much better than OLS with 50 to 80% reductions in standard errors.

     

A framework for evaluating eHealth research

Health care is in the midst of a consumer-oriented technology explosion. Individuals of all ages and backgrounds have discovered eHealth. But the challenges of implementing and evaluating eHealth are just beginning to surface, and, as technology changes, new challenges emerge. Evaluation is critical to the future of eHealth. This article addresses four dimensions of eHealth evaluation: (1) design and methodology issues; (2) challenges related to the technology itself; (3) environmental issues that are not specific to eHealth but pose special problems for eHealth researchers; and (4) logistic or administrative concerns of the evaluation methodology selected. We suggest that these four dimensions must be integrated to provide a holistic framework for designing and implementing eHealth research projects, as well as for understanding the totality of the eHealth intervention. The framework must be flexible enough to adapt to a variety of end users, regardless of whether the end user is a healthcare organization, a for-profit business, a community organization, or an individual. The framework is depicted as a puzzle with four interlocking pieces.     

历史解释中的形式主义与情境主义策略

历史解释中形式主义与情境主义策略之间的冲突自古就有.情境主义的隐含之义是"历史的".人们对历史对象和它们的情境进行的所有描述具有必然的比喻性质.情境主义解释策略在历史编纂中以对现象领域的描述为特色.对于情境及存在于情境中的实体的描述都是比喻性的,它们之间的关系可以用比喻本身的不同形态说明.新历史主义文学史研究有意无意地与文学和历史学领域中占优势的正统学说发生了冲突,它试图以情境主义来弥补当前盛行的形式主义,但它仍然包含有形式主义.在研究中,新历史主义提出了文化诗学的观点,并已经拓展到历史诗学.     

A Reality Check for Data Snooping

Data snooping occurs when a given set of data is used more than once for purposes of inference or model selection. When such data reuse occurs, there is always the possibility that any satisfactory results obtained may simply be due to chance rather than to any merit inherent in the method yielding the results. This problem is practically unavoidable in the analysis of time‐series data, as typically only a single history measuring a given phenomenon of interest is available for analysis. It is widely acknowledged by empirical researchers that data snooping is a dangerous practice to be avoided, but in fact it is endemic. The main problem has been a lack of sufficiently simple practical methods capable of assessing the potential dangers of data snooping in a given situation. Our purpose here is to provide such methods by specifying a straightforward procedure for testing the null hypothesis that the best model encountered in a specification search has no predictive superiority over a given benchmark model. This permits data snooping to be undertaken with some degree of confidence that one will not mistake results that could have been generated by chance for genuinely good results.     

Intermediate Performance Impacts of Advanced Manufacturing Technology Systems: An Empirical Investigation*

A large-scale random sample is used to empirically examine the relationships between implementation of Advanced Manufacturing Technology (AMT) and three organization-level measures that have historically been attributed to AMT, but not fully tested along the AMT spectrum: market-oriented flexibility of the production process, organizational integration of production processes, and administrative intensity of the organization. Results indicate that as an organization moves along the technology scale from stand-alone AMT (e.g., CNC machines) through functionally oriented AMT (FMS and CAM) toward CIM, not only do its production processes become more integrated with each other, but those processes become more integrated with other functional systems of the organization, and the quality and timeliness of production information increase. Furthermore, this relationship becomes stronger as companies increase their level of implementation for the latter two technologies. Conversely, market-oriented flexibility decreases and administrative intensity is not observed to change as companies move along the technology spectrum. Future research should examine how organizational redesign and implementation strategies that accompany AMT implementation can concomitantly enhance organizational integration of the production process and market-oriented flexibility.     

Child protection pathways for newborn infants: A multi-disciplinary retrospective chart review of an Irish maternity hospital’s records

In Ireland, little is known about mothers and infants where child welfare and protection concerns arise during the perinatal period. This study explores, for the first time, perinatal child protection. A retrospective audit was carried out of a large maternity hospital's medical social work, neonatal and psychiatric files for a five-year period from 2016 to 2020. The study identified 99 children, born to 86 mothers, who were either subject to a child protection conference; placed for adoption; discharged to someone other than the mother; or discharged home under supervision. The study found that two-thirds of the children were discharged to their mother's care. When compared to national data, the health indicators for this cohort of mothers and children painted a grim picture. The maternal profiles identified high prevalence of mental health and addiction difficulties and domestic violence. The study found evidence of supports provided to the mothers to enable them to care for their infants while they remained in the hospital and during an initial discharge from hospital. However, a significant number of the mothers were not caring for their children when viewed across a longer time frame. Dedicated multi-disciplinary clinics and improved data systems were identified as of importance.     

Asymptotic Distribution Theory for Nonparametric Entropy Measures of Serial Dependence

Entropy is a classical statistical concept with appealing properties. Establishing asymptotic distribution theory for smoothed nonparametric entropy measures of dependence has so far proved challenging. In this paper, we develop an asymptotic theory for a class of kernel‐based smoothed nonparametric entropy measures of serial dependence in a time‐series context. We use this theory to derive the limiting distribution of Granger and Lin's (1994) normalized entropy measure of serial dependence, which was previously not available in the literature. We also apply our theory to construct a new entropy‐based test for serial dependence, providing an alternative to Robinson's (1991) approach. To obtain accurate inferences, we propose and justify a consistent smoothed bootstrap procedure. The naive bootstrap is not consistent for our test. Our test is useful in, for example, testing the random walk hypothesis, evaluating density forecasts, and identifying important lags of a time series. It is asymptotically locally more powerful than Robinson's (1991) test, as is confirmed in our simulation. An application to the daily S&P 500 stock price index illustrates our approach.     

Unemployment Propensity and Unemployment Duration

ABSTRACT: This paper analyses the factors affecting the duration of an unemployment spell. The results indicate the absence of statistically significant ‘‘duration dependence‘‘ effects for men. Person-specific unemployment propensity is found to have a significant effect on re-employment probabilities. The latter implies an unequal distribution of unemployment burden among the population.     

Seeds of Corruption? The Contingent Role of Ties to Politicians and Foreign Subsidiary Relations with Government-Sponsored Financial Institutions

In drawing from transaction cost economics and social network theories, this study examines the influence of corruption as a determinant of foreign subsidiary formal contracting practices with government-sponsored financial institutions. We hypothesize that lower corruption distance (between parent home and host countries) and higher perceived corruption (in host country) are positively related, and mutually reinforcing, when considering a foreign subsidiary's propensity to formally contract with government-sponsored financial institutions. We also suggest that these relationships strengthen with the intensification of political ties to government officials who can offer preferential political services via contractual agreements, changing the nature of market transactions in favour of a foreign subsidiary. We found support for our hypotheses using data from a sample of over 350 subsidiaries located in the Philippines and Thailand.