Explore the vast range of titles available.

Down syndrome (DS), or trisomy 21, is a common disorder associated with several complex clinical phenotypes. Although several hypotheses have been put forward, it is unclear as to whether particular gene loci on chromosome 21 (HSA21) are sufficient to cause DS and its associated features. Here we present a high-resolution genetic map of DS phenotypes based on an analysis of 30 subjects carrying rare segmental trisomies of various regions of HSA21. By using state-of-the-art genomics technologies we mapped segmental trisomies at exon-level resolution and identified discrete regions of 1.8-16.3 Mb likely to be involved in the development of 8 DS phenotypes, 4 of which are congenital malformations, including acute megakaryocytic leukemia, transient myeloproliferative disorder, Hirschsprung disease, duodenal stenosis, imperforate anus, severe mental retardation, DS-Alzheimer Disease, and DS-specific congenital heart disease (DSCHD). Our DS-phenotypic maps located DSCHD to a <2-Mb interval. Furthermore, the map enabled us to present evidence against the necessary involvement of other loci as well as specific hypotheses that have been put forward in relation to the etiology of DS--i.e., the presence of a single DS consensus region and the sufficiency of DSCR1 and DYRK1A, or APP, in causing several severe DS phenotypes. Our study demonstrates the value of combining advanced genomics with cohorts of rare patients for studying DS, a prototype for the role of copy-number variation in complex disease.

In 2012, the US Census Bureau posed a challenge under the America COMPETES Act, an act designed to improve the competitiveness of the United States by investing in innovation through research and development. The Census Bureau contracted Kaggle.com to host and manage a worldwide competition to develop the best statistical model to predict 2010 Census mail return rates. The Census Bureau provided competitors with a block group-level database consisting of housing, demographic, and socioeconomic variables derived from the 2010 Census, five-year American Community Survey estimates, and 2010 Census operational data. The Census Bureau then challenged teams to use these data (and other publicly available data) to construct the models. One goal of the challenge was to leverage winning models as inputs to a new model-based hard-to-count (HTC) score, a metric to stratify and target geographic areas according to propensity to self-respond in sample surveys and censuses. All contest winners employed data-mining and machine-learning techniques to predict mail-return rates. This made the models relatively hard to interpret (when compared with the Census Bureau's original HTC score) and impossible to directly translate to a new HTC score. Nonetheless, the winning models contained insights toward building a new model-based score using variables from the database. This paper describes the original algorithm-based HTC score, insights gained from the Census Return Rate Challenge, and the model underlying a new HTC score.

Barry and Hartigan (1993) presented a Bayesian approach to the normal errors change point problem, in which the observations xi are independent N(μ i, σ2) and the probability of a change point is p, independently at each point i. Their method was shown to accurately estimate change points when compared to several older methods. However, the method was not implemented in a way that allowed comparison with newer methods, nor for application to larger, newly available data, such as DNA copy number measurements. This dissertation address these and other shortcomings with the Bayesian change point extension to the R statistical programming environment. We solve a numerical problem related to the critical calculation of the probability of a change point in Barry and Hartigan (1993); this problem was prohibiting the use of the procedure with data sets larger than 250 in length. We also reduce the computational complexity from O( n2) in the original implementation to O( n), making practical application of the method feasible. We present a recursive algorithm which allows exploration of the joint marginal likelihood of the probability of a change point and the ratio of signal to noise variance. We propose alternative Bayes and empirical Bayes procedures based on estimates obtained from the joint marginal likelihood, and improve on the method of Barry and Hartigan (1993) in a number of cases. We conclude by considering new challenges in the application of change point methods to multiple samples.

We replicate the essentials of the Huettel et al. (2006) experiment on choice under uncertainty with 30 Yale undergraduates, where subjects make 200 pair-wise choices between risky and ambiguous lotteries. Inferences about the independence of economic preferences for risk and ambiguity are derived from estimation of a mixed logit model, where the choice probabilities are functions of two random effects: the proxies for risk-aversion and ambiguity-aversion. Our principal empirical finding is that we cannot reject the null hypothesis that risk and ambiguity are independent in economic choice under uncertainty. This finding is consistent with the hypothesized independence of the neural mechanisms governing economic choices under risk and ambiguity, suggested by the double dissociation-fMRI study reported in Huettel et al.

Economists typically estimate the average treatment effect on the treated (ATT) when evaluating government programs. The economic interpretation of the ATT can be ambiguous when program outcomes are measured in purely physical terms, as they often are in evaluations of environmental programs (e.g., avoided deforestation). This paper presents an approach for inferring economic impacts from physical outcomes when the ATT is estimated using propensity-score matching. For the case of forest protection, we show that a protection program’s ex post economic impact, as perceived by the government agency responsible for protection decisions, can be proxied by a weighted ATT, with the weights derived from the propensity of being treated (i.e., protected). We apply this new metric to mangrove protection in Thailand during 1987–2000. We find that the government’s protection program avoided the loss of 12.8% of the economic value associated with the protected mangrove area. This estimate is about a quarter smaller than the conventional ATT for avoided deforestation, 17.3 percentage points. The difference between the two measures indicates that the program tended to be less effective at reducing deforestation in locations where the government perceived the net benefits of protection as being greater, which is the opposite of the relationship that would characterize a maximally effective program.