Search

In this paper, the distributions of scan statistics of inhomogeneous Poisson processes are studied. First, the distribution of the continuous scan statistic of an inhomogeneous Poisson process is approximated by the distribution of the discrete scan statistic for a sequence of Bernoulli trials with unequal probabilities of success. Next, we introduce a weighted scan statistic to adjust the inhomogeneity and the weighted continuous scan statistic is also approximated by the weighted discrete scan statistic. The finite Markov chain imbedding technique is used to obtain the exact distributions of weighted discrete scan statistics. An example using the weighted scan statistic of an inhomogeneous Poisson process for detecting DNA copy number variation is given. Numerical results and simulations are also given to illustrate our theoretical results. [ABSTRACT FROM AUTHOR]

Since the early 2000s, theorizing on incremental institutional change has made inroads in comparative historical analysis. In particular, the ideas, concepts, and theory introduced by Kathleen Thelen and her collaborators have been widely adopted by scholars. These scholars are not, however, univocally positive about the theory. Three main critiques have been plaguing the theory since its early days: the concepts it builds on lack clarity, the model of agency it uses is too static, and the theory lacks analytical power overall. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis method, this article presents a meta-analysis of the peer-reviewed empirical literature from 2005 to 2015 that applies this theory. It seeks to better understand the reach of the critiques expressed, as this may provide a starting point for improvement. It finds considerable quantitative support for the critiques, and uncovers an additional problematic issue: the tendency for concept stretching and concept proliferation by scholars seeking to overcome the shortcomings of the theory. Paradoxically, concept stretching and proliferation only further reduce the analytical power of the theory. The article concludes with suggestions for improvement of the development and application of the theory. [ABSTRACT FROM AUTHOR]

This article is based on an invited speech given at Massey University in August 2016 where Tolich revealed the inspiration for his 25-year sociological analysis of research ethics committees and their codes. The title of the talk "sociologically, do we need ethics committees?" began exploring the stigma ethics committee applicants experience when their qualitative research design does not meet the ethics committee's biomedical expectations at issue. In 1992 this disjuncture provoked Tolich's sociological imagination to engage a literature where he found his private troubles were for other sociologists' public issues, as if these other qualitative researchers collectively experienced a similar stigma. The article reports on Tolich's attempts to resolve power imbalances between researchers and ethics committees by creating an experimental ethics committees and resources that support the ethics of social science researchers. The second half of the article critiques the codes ethics committees' use finding they contain little understanding of qualitative research with the potential to harm research participants. The article ends contrasting the impoverishment of New Zealand's ethics codes with those in Australia, and especially in Canada asking why doesn't New Zealand have an equivalent National Statement? [ABSTRACT FROM AUTHOR]

In an influential paper Pesaran ('A simple panel unit root test in presence of cross-section dependence', Journal of Applied Econometrics, Vol. 22, pp. 265-312, 2007) proposes two unit root tests for panels with a common factor structure. These are the CADF and CIPS test statistics, which are amongst the most popular test statistics in the literature. One feature of these statistics is that their limiting distributions are highly non-standard, making for relatively complicated implementation. In this paper, we take this feature as our starting point to develop modified CADF and CIPS test statistics that support standard chi-squared and normal inference. [ABSTRACT FROM AUTHOR]

Official statistics is dipping its toe in the ocean of big data, and leaders are emphasizing the need for a major paradigm change. One aspect is the increased volume of data that are not collected on probability samples of the target population. Making full use of these data requires a fundamental change, not only in data collection and dissemination, but also in the methods of statistical inference. The classical "design-based" approach to survey inference, developed from the seminal work of Neyman [41], is simply not applicable to these data. Rather, statistical models are needed that potentially reflect selection bias from the lack of random sampling. I suggest that "Calibrated Bayes" is the appropriate statistical paradigm for addressing the analysis. Under this paradigm, inferences for a particular data set are Bayesian, but models are sought that yield inferences with robust repeated sampling properties. Probability sampling remains a powerful tool under this paradigm, since by ensuring that the selection mechanism is ignorable it enhances robust modeling, but it is not essential for the inference. I outline two applications of Calibrated Bayes to data collected by the U.S. Census Bureau. [ABSTRACT FROM AUTHOR]

The Survey of Employment, Payrolls and Hours (SEPH) is a monthly business survey conducted by Statistics Canada that produces estimates of levels for variables such as employment, earnings and hours at detailed industrial levels for Canada, the provinces and territories. To improve the efficiency of collection activities for this survey, an electronic questionnaire (EQ) was introduced in the fall of 2012. Given the timeframe allowed for this transition and the production calendar of the survey, a conversion strategy of units from paper questionnaires to EQ was developed. The goal of the strategy was to ensure a good adaptation of the collection environment and also to allow the implementation of a plan of analysis that would evaluate the impact of this change on the results of the survey. This paper will give an overview of the conversion strategy implemented as well as the results of various evaluations that were conducted. For example, the impact of the integration of the EQ on the collection process, the response rate and the failed edit follow-up rate will be presented. In addition, the results of a randomized experiment that was conducted in order to determine the presence of a mode effect will be discussed. [ABSTRACT FROM AUTHOR]

The constant growth of the scope and depth of evidence-based decision making in government throughout the 19th and 20th centuries has led countries to develop the concept of statistical independence of political and other vested interests. This independence is the most important condition necessary for maintaining and increasing data quality, yet the institutional position of statistical offices as part of government makes this hard to achieve. The institutions and governance of statistics in many countries, including developed ones, still leave much to be desired. In spite of this, history of the last several decades suggests there is systematic improvement in the governance of statistics within countries, with legislation and e.g. the acceptance of codes of practice ensuring this independence, etc. Recent developments have, however, introduced a relatively new danger in the rapid development of automatisms, where evidence-based decision making is being replaced by automatic decisions that virtually, or even fully, leave the responsible human decision maker out of the process. This development, which seems to be a welcome gradation of evidence-based decision making, is in fact a grave danger for the independence and quality of statistics, because it re-orients the target of lobbying from the decision makers (who are no longer in the loop) to the data sources, thus putting the quality of official statistics under new powerful pressures. In this context it is more necessary now than ever before to protect the statistical systém from these influences by ensuring full independence in the governance of statistics. [ABSTRACT FROM AUTHOR]

The financial challenges of recent times places a premium on national statistical institutes (NSIs) to creatively examine how to 'do more with less'. Faced with significant staffing reductions and demands for quality improvements, CSO introduced the lean six sigma problem solving methodology. In this paper we explore: * Why CSO introduced lean and how we introduced it * Examples of successful lean projects: how we did it and the benefits achieved in terms of cost reduction and quantifiable quality improvement * Examples of where we had difficulties with lean projects - the learning lessons/implementation issues national statistical institutes should be aware of, including the importance of placing lean within a strategic context. [ABSTRACT FROM AUTHOR]

Learning about statistics is a lot like learning about science: the learning is more meaningful if you can actively explore. This tenth installment of Explorations in Statistics explores the analysis of a potential change in some physiological response. As researchers, we often express absolute change as percent change so we can account for different initial values of the response. But this creates a problem: percent change is really just a ratio, and a ratio is infamous for its ability to mislead. This means we may fail to find a group difference that does exist, or we may find a group difference that does not exist. What kind of an approach to science is that? In contrast, analysis of covariance is versatile: it can accommodate an analysis of the relationship between absolute change and initial value when percent change is useless. [ABSTRACT FROM AUTHOR]

The article presents the compilation of social statistics of the Arab society by the Statistics Division of the Economic and Social Commission for Western Asia region which focuses on the issue of population, education, and poverty.