Juana Sanchez

Central Limit Theorem: New SOCR Applet and Demonstration Activity.

Modern approaches for information technology based blended education utilize a variety of novel instructional, computational and network resources. Such attempts employ technology to deliver integrated, dynamically linked, interactive content and multi-faceted learning environments, which mayfacilitate student comprehension and information retention. In this manuscript, we describe one such innovative effort of using technological tools forimproving student motivation and learning of the theory, practice and usability of the Central Limit Theorem (CLT) in probability and statistics courses. Ourapproach is based on harnessing the computational libraries developed by the Statistics Online Computational Resource (SOCR) to design a new interactiveJava applet and a corresponding demonstration activity that illustrate the meaning and the power of the CLT. The CLT applet and activity have clear commongoals; to provide graphical representation of the CLT, to improve student intuition, and to empirically validate and establish the limits of the CLT. The SOCR CLT activity consists of four experiments that demonstrate the assumptions, meaning and implications of the CLT and ties these to specific hands-onsimulations. We include a number of examples illustrating the theory and applications of the CLT. Both the SOCR CLT applet and activity are freelyavailable online to the community to test, validate and extend (Applet: http://www.socr.ucla.edu/htmls/SOCR_Experiments.html and Activity: http://wiki.stat.ucla.edu/socr/index.php/SOCR_EduMaterials_Activities_GeneralCentralLimitTheorem).

R&D, Attrition and Multiple Imputation in BRDIS

Multiple imputation in business establishment surveys like BRDIS, an annual business survey in which some companies are sampled every year or multiple years, may enhance the estimates of total R&D in addition to helping researchers estimate models with subpopulations of small sample size. Considering a panel of BRDIS companies throughout the years 2008 to 2013 linked to LBD data, this paper uses the conclusions obtained with missing data visualization and other explorations to come up with a strategy to conduct multiple imputation appropriate to address the item nonresponse in R&D expenditures. Because survey design characteristics are behind much of the item and unit nonresponse, multiple imputation of missing data in BRDIS changes the estimates of total R&D significantly and alters the conclusions reached by models of the determinants of R&D investment obtained with complete case analysis.

INNOVATION OUTPUT CHOICES AND CHARACTERISTICS OF FIRMS IN THE U.S

This paper uses new business micro data from the Business Research and Development and Innovation Survey (BRDIS) for the years 2008-2011 to relate the discrete innovation choices made by U.S. companies to features of the company that have long been considered to be important correlates of innovation. We use multinomial logit to model those choices. Bloch and Lopez-Bassols (2009) used the Community Innovation Surveys (CIS) to classify companies according dual, technological or output-based innovation constructs. We found that for each of those constructs of innovation combinations considered, manufacturing and engaging in intellectual property transfer increase the odds of choosing innovation strategies that involve more than one type of categories (for example, both goods and services, or both tech and non-tech) and radical innovations, controlling form size, productivity, time and type of R&D. Company size and company productivity as well as time do not lean the choices in any particular direction. These associations are robust across the three multinomial choice models that we have considered. In contrast with other studies, we have been able to use companies that do and companies that do not innovate, and this has allowed to rule out to some extent selectivity bias.

International migration in Europe

This book is of high interest to demographers and applied statisticians. Its main purpose is to show that heterogeneous and incomplete international migration data can be harmonised across countries by statistical modelling of the flows of migration rather than conventional models of migration. The book is the first on international migration to include Bayesian methods. This encyclopaedic book is a collection of independent articles that discuss the following: the long and difficult history of the measurement of international migration flows in Europe, the sources of data and the lack of quality and comparability of the data (Part I); the potential of statistical models of the process of migration to solve the problems confronting harmonisation (Part II); the estimates and forecasts obtained with the statistical models (Parts III and IV). The main motivation of the book is to address the increased concern in Europe after acknowledging the need for common European Union (EU) policy and comparable EU-wide data to inspire it. The approval in 2005 of the use of statistical methods in policy-making in Europe encouraged wider involvement of statisticians to address that concern. Migration has a spatial and time dimension and is the result of an underlying random phenomenon that makes both frequentist and Bayesian methods suitable to address its estimation. Having data of different types from different sources makes it difficult to model the data. Thus the statistical models harmonise by estimating migration flows from incomplete data, something for which Bayesian models are particularly suitable. The statistical models surveyed in the book range from multivariate survival (time to event) to Markov models. Although specialised to the topic at hand, the models proposed suggest many interesting applications to other research areas, such as for example, Internet traffic, economic flows of investment, and animal migration, among others. Because the book is written in separate chapters by different authors, some topics receive more than a single treatment. The introductory Chapter 1 and the conclusion in Chapter 16 provide a good overview of the book. After that, the reader can proceed to individual chapters at leisure. The book is a must read for anybody interested in international migration and should be in every library.

Introduction to modern time series analysis

This book is an introduction to the literature of time series and econometrics since the late sixties. Written for economists and statisticians interested in applied time series, the book is a historical account of the three most lively decades in the history of time series econometrics. Those were the decades when econometricians embraced the Box–Jenkins approach to time series analysis and gave it a life of its own, resulting in the Nobel Prize. The combination of technical and historical narrative and the comprehensive commented bibliography makes this book stand out among the many other books covering the same standard topics, namely autoregressive moving average models, Granger causality, vector autoregression, unit roots, cointegration and autoregressive conditional heteroscedasticy. The authors demonstrate a deep knowledge of all the publications during the period studied. They start each chapter by putting the method in its historical context. Having motivated it that way, the method is then developed clearly and concisely with a mathematical level accessible to seniors in college. Pedagogy prevails. Before moving on to difficult technical discussions, the authors give very basic examples that illustrate why and how the next results are needed, thus teaching the reader econometric reasoning by simplifying published results. Concluding remarks in each chapter create anticipation for the next one. The bibliography at the end of each chapter is an integral part of the narrative. Organised in subsections with historical comments, such as ‘this method was first used by ...’ or ‘a survey of these methods was given by ...’, these bibliographies are a precious gift. The contents of chapters are connected smoothly because the authors go back and forth to make the historical connections among new and old methods more evident. Unfortunately, the book does not include any exercises. But all of the examples use economic data and the solutions are given with extreme detail, making these examples very useful illustrations of the application of the methods. No particular software is used to solve the examples. Although the book would not make a good textbook for a time-series course for non-economic majors, it is required reading for those interested in understanding why time-series econometrics is what it is today and for those wanting a guided tutorial of the extensive literature on this topic. The book should certainly occupy a prominent position in any econometrics library.