Search

To improve the measurement precision of the shield΄s pose, the factors which influence the measurement results are studied in this paper. Coordinate transformation formula is applied to calculate the shield΄s pose by transforming the relative coordinate of the shield΄s cutter head center in the laser target coordinate system to the world coordinate. The relative coordinate of the cutter head center is calibrated by transforming the formula inversely. The calibration error of the relative coordinate caused by the measurement error of the attitude angle is analyzed detailedly. The position measurement error of the cutter head center is deduced based on the principle of error transfer. Finally, the impact of each attitude angle΄s measurement error on the cutter head center is obtained by traversal algorithm in the variation range of attitude angle. According to the different influence degree, the measurement error of each attitude angle is proportionally allocated. [ABSTRACT FROM AUTHOR]

The statistical properties of the two most widely used methods for setting environmental exposure standards are explored. The traditional NOAEL approach handles uncertainty in disagreement with the precautionary principle: a smaller and less sensitive study will tend to yield higher exposure limits. As an attractive alternative, the Benchmark dose approach estimates the exposure associated with a predefined risk increase above the background. Although advantageous in several respects, this method is sensitive to sources of uncertainty arising from measurement error and data dependent selection of the dose–response model as well the choice of critical endpoint. An improved Benchmark analysis can be conducted using structural equation models and Bayesian model averaging. [ABSTRACT FROM AUTHOR]

INTRODUCTION The National Crime Survey (NCS, now the National Crime Victimization Survey, or NCVS) was originally designed to provide a check against the crime statistics voluntarily provided to the FBI's Uniform Crime Reporting (UCR) Program by police departments (President's Commission, 1967, p. 21). Pilot surveys (Biderman et al., 1967; Ennis, 1967) had confirmed the widespread belief that many crimes are not reported to the police, the so-called “dark figure” of crime, so a survey would provide information about the nature and extent of unreported crime. Because the survey – which gathers data directly from household residents concerning victimizations they may have experienced over the past six months – provides a more direct check on the true amount of crime, it is considered superior to the UCR for this purpose. There are also reasons that the UCR may be considered superior to the NCVS. After all, the UCR is a complete count of crimes reported to the police, whereas the NCVS is based on a sample of crimes recalled by citizens aged 12 years and older, in 45,000 randomly selected households, which occurred within the past 6 months. A complete count has no sampling error, whereas the sampling error for the NCVS exists – and is growing as financial considerations dictate reductions in sample size. Moreover, the detailed nature of UCR reporting makes it possible to look at specific time patterns (hour of day, day of week or month) and places where crime is occurring, a specificity that is not available using the NCVS. [ABSTRACT FROM AUTHOR]

Trends in aggravated assaults recorded by the police and those reported in victim surveys diverge over time in the United States. Police-recorded assaults trend upward during the 1980s and flatten in the 1990s, whereas survey-estimated assaults are flat during the 1980s and decline during the 1990s. Previous research has attributed the divergence between the police and survey trends to changes in police recording practices, independent of the underlying rate of victimization (Blumstein, 1998; O'Brien, 1996). This study adds to that research by comparing police and survey trends in firearm and nonfirearm aggravated assaults, on the assumption that police recording practices are more likely to affect the latter than the former. Consistent with this assumption, the results show much less divergence in gun than nongun assault time trends. Together with previous research, this study offers strong, albeit circumstantial, evidence that changes in police recording of assaults explain much of the divergence in aggravated assault trends derived from police records and victim surveys. It also appears that the NCVS redesign has helped to reduce the divergence between UCR and NCVS aggravated assault trends in recent years. BACKGROUND AND SIGNIFICANCE Although the United States' two major crime indicators, the FBI's Uniform Crime Reports (UCR) and the Bureau of Justice Statistics' National Crime Victimization Survey (NCVS), are based on distinct methods of obtaining information about the number and nature of criminal events, they should tell essentially the same story about changes in crime rates over time. [ABSTRACT FROM AUTHOR]

Divergence between annual estimates of crime produced by the Uniform Crime Reports (UCR) and National Crime Victimization Survey (NCVS) may be explained, in part, by the way criminal events are classified and counted. One important type of criminal phenomenon, the repeat victim, poses a particularly challenging problem for victimization surveys. Although the definition has been operationalized in a variety of ways, the common denominator in these various definitions is one common factor: a person experiences more than one victimization in a given time period (Farrell, 1995; Pease, 1998). This is important because, unlike official police records that are often produced immediately after or within a few days of a criminal offense, the NCVS “survey method is heavily dependent upon the ability and motivation of the respondent to remember events and report them in the interview situation” (Biderman et al., 1967). Although recall accuracy is a cognitive task for all victims to some degree, it is especially difficult for the repeat victim. They must not only remember and report details of numerous crime events, but they also must not confuse aspects of different events and even treat continuous events as if they were discrete. This is a considerable burden. To accommodate the high-volume or chronic victim who could report dozens if not hundreds of victimizations, the NCVS developed a process that classifies six or more “similar” victimizations as a series incident (see Chapter 2, this volume). [ABSTRACT FROM AUTHOR]

Most of the literature on cost–effectiveness, cost–benefit, and program evaluation has focused either on what should in principle be included in costs, benefits, and effects of programs or on the empirical implementation for specific treatments and programs. The rest of this book discusses many of those issues. In Chapter 2, Allan Detsky examined issues related to the evidence of effectiveness for a treatment based on the nature of a study's design. Among other issues, he discussed the relative merits of randomized controlled trials (RCTs) and various observational study designs. In Chapter 4, David Dranove examined issues of measuring economic or opportunity costs in cost–effectiveness studies. In this chapter, we will concentrate on a number of statistical issues that arise in comparing alternative treatments. Part of our discussion provides the rationale for a preference for randomized over observational studies. The majority of our discussion, however, applies in differing degrees to RCTs and observational studies. Our basic concern is that the statistical modeling or analysis must mirror an understanding about how the behavior came about and what process generated the data, whether the data are observational or experimental. Observational behavior and data, especially in clinical or claims databases, did not come about at random. One has to understand the process that generated the treatment choices by physicians, the care seeking and compliance of patients, and the data reported to adequately understand whether the observed associations among the treatment, costs, and outcomes are really causal or merely an artifact of the correlation between the treatment and some other latent or unobservable causal factor. [ABSTRACT FROM AUTHOR]