@techreport {handle:1813:52650, title = {Effects of a Government-Academic Partnership: Has the NSF-Census Bureau Research Network Helped Secure the Future of the Federal Statistical System?}, number = {1813:52650}, year = {2017}, institution = {NCRN Coordinating Office}, type = {Preprint}, abstract = {

Effects of a Government-Academic Partnership: Has the NSF-Census Bureau Research Network Helped Secure the Future of the Federal Statistical System? Weinberg, Daniel; Abowd, John M.; Belli, Robert F.; Cressie, Noel; Folch, David C.; Holan, Scott H.; Levenstein, Margaret C.; Olson, Kristen M.; Reiter, Jerome P.; Shapiro, Matthew D.; Smyth, Jolene; Soh, Leen-Kiat; Spencer, Bruce; Spielman, Seth E.; Vilhuber, Lars; Wikle, Christopher The National Science Foundation-Census Bureau Research Network (NCRN) was established in 2011 to create interdisciplinary research nodes on methodological questions of interest and significance to the broader research community and to the Federal Statistical System (FSS), particularly the Census Bureau. The activities to date have covered both fundamental and applied statistical research and have focused at least in part on the training of current and future generations of researchers in skills of relevance to surveys and alternative measurement of economic units, households, and persons. This paper discusses some of the key research findings of the eight nodes, organized into six topics: (1) Improving census and survey data collection methods; (2) Using alternative sources of data; (3) Protecting privacy and confidentiality by improving disclosure avoidance; (4) Using spatial and spatio-temporal statistical modeling to improve estimates; (5) Assessing data cost and quality tradeoffs; and (6) Combining information from multiple sources. It also reports on collaborations across nodes and with federal agencies, new software developed, and educational activities and outcomes. The paper concludes with an evaluation of the ability of the FSS to apply the NCRN{\textquoteright}s research outcomes and suggests some next steps, as well as the implications of this research-network model for future federal government renewal initiatives. This paper began as a May 8, 2015 presentation to the National Academies of Science{\textquoteright}s Committee on National Statistics by two of the principal investigators of the National Science Foundation-Census Bureau Research Network (NCRN) {\textendash} John Abowd and the late Steve Fienberg (Carnegie Mellon University). The authors acknowledge the contributions of the other principal investigators of the NCRN who are not co-authors of the paper (William Block, William Eddy, Alan Karr, Charles Manski, Nicholas Nagle, and Rebecca Nugent), the co- principal investigators, and the comments of Patrick Cantwell, Constance Citro, Adam Eck, Brian Harris-Kojetin, and Eloise Parker. We note with sorrow the deaths of Stephen Fienberg and Allan McCutcheon, two of the original NCRN principal investigators. The principal investigators also wish to acknowledge Cheryl Eavey{\textquoteright}s sterling grant administration on behalf of the NSF. The conclusions reached in this paper are not the responsibility of the National Science Foundation (NSF), the Census Bureau, or any of the institutions to which the authors belong

}, url = {http://hdl.handle.net/1813/52650}, author = {Weinberg, Daniel and Abowd, John M. and Belli, Robert F. and Cressie, Noel and Folch, David C. and Holan, Scott H. and Levenstein, Margaret C. and Olson, Kristen M. and Reiter, Jerome P. and Shapiro, Matthew D. and Smyth, Jolene and Soh, Leen-Kiat and Spencer, Bruce and Spielman, Seth E. and Vilhuber, Lars and Wikle, Christopher} } @article {2221, title = {Bayesian Lattice Filters for Time-Varying Autoregression and Time{\textendash}Frequency Analysis}, journal = {Project Euclid}, year = {2015}, month = {10/2015}, pages = {27}, abstract = {Modeling nonstationary processes is of paramount importance to many scientific disciplines including environmental science, ecology, and finance, among others. Consequently, flexible methodology that provides accurate estimation across a wide range of processes is a subject of ongoing interest. We propose a novel approach to model-based time{\textendash}frequency estimation using time-varying autoregressive models. In this context, we take a fully Bayesian approach and allow both the autoregressive coefficients and innovation variance to vary over time. Importantly, our estimation method uses the lattice filter and is cast within the partial autocorrelation domain. The marginal posterior distributions are of standard form and, as a convenient by-product of our estimation method, our approach avoids undesirable matrix inversions. As such, estimation is extremely computationally efficient and stable. To illustrate the effectiveness of our approach, we conduct a comprehensive simulation study that compares our method with other competing methods and find that, in most cases, our approach performs superior in terms of average squared error between the estimated and true time-varying spectral density. Lastly, we demonstrate our methodology through three modeling applications; namely, insect communication signals, environmental data (wind components), and macroeconomic data (US gross domestic product (GDP) and consumption).}, keywords = {locally stationary, model selection, nonstationary partial autocorrelation, piecewise stationary, sequential estimation, time-varying spectral density}, doi = {10.1214/15-BA978}, url = {http://projecteuclid.org/euclid.ba/1445263834}, author = {Yang, W.~H. and Holan, Scott H. and Wikle, Christopher K.} } @article {2039, title = {Bayesian Marked Point Process Modeling for Generating Fully Synthetic Public Use Data with Point-Referenced Geography}, journal = {Spatial Statistics}, volume = {14}, year = {2015}, month = {08/2015}, pages = {439--451}, doi = {10.1016/j.spasta.2015.07.008}, url = {http://www.sciencedirect.com/science/article/pii/S2211675315000718}, author = {Quick, Harrison and Holan, Scott H. and Wikle, Christopher K. and Reiter, Jerome P.} } @article {2219, title = {Bayesian Spatial Change of Support for Count-Valued Survey Data with Application to the American Community Survey}, journal = {Journal of the American Statistical Association}, year = {2015}, month = {12/2015}, abstract = {We introduce Bayesian spatial change of support methodology for count-valued survey data with known survey variances. Our proposed methodology is motivated by the American Community Survey (ACS), an ongoing survey administered by the U.S. Census Bureau that provides timely information on several key demographic variables. Specifically, the ACS produces 1-year, 3-year, and 5-year {\textquotedblleft}period-estimates,{\textquotedblright} and corresponding margins of errors, for published demographic and socio-economic variables recorded over predefined geographies within the United States. Despite the availability of these predefined geographies it is often of interest to data-users to specify customized user-defined spatial supports. In particular, it is useful to estimate demographic variables defined on {\textquotedblleft}new{\textquotedblright} spatial supports in {\textquotedblleft}real-time.{\textquotedblright} This problem is known as spatial change of support (COS), which is typically performed under the assumption that the data follows a Gaussian distribution. However, count-valued survey data is naturally non-Gaussian and, hence, we consider modeling these data using a Poisson distribution. Additionally, survey-data are often accompanied by estimates of error, which we incorporate into our analysis. We interpret Poisson count-valued data in small areas as an aggregation of events from a spatial point process. This approach provides us with the flexibility necessary to allow ACS users to consider a variety of spatial supports in {\textquotedblleft}real-time.{\textquotedblright} We show the effectiveness of our approach through a simulated example as well as through an analysis using public-use ACS data.}, keywords = {Aggregation, American Community Survey, Bayesian hierarchical model, Givens angle prior, Markov chain Monte Carlo, Multiscale model, Non-Gaussian.}, doi = {10.1080/01621459.2015.1117471}, url = {http://www.tandfonline.com/doi/abs/10.1080/01621459.2015.1117471}, author = {Bradley, Jonathan R. and Wikle, Christopher K. and Holan, Scott H.} } @techreport {handle:1813:40179, title = {NCRN Meeting Spring 2015: Training Undergraduates, Graduate Students, Postdocs, and Federal Agencies: Methodology, Data, and Science for Federal Statistics}, number = {1813:40179}, year = {2015}, institution = {NCRN Coordinating Office}, type = {Preprint}, abstract = {NCRN Meeting Spring 2015: Training Undergraduates, Graduate Students, Postdocs, and Federal Agencies: Methodology, Data, and Science for Federal Statistics Cressie, Noel; Holan, Scott H.; Wikle, Christopher K. Presentation at the NCRN Spring 2015 Meeting}, url = {http://hdl.handle.net/1813/40179}, author = {Cressie, Noel and Holan, Scott H. and Wikle, Christopher K.} } @article {STA4:STA494, title = {Spatio-temporal change of support with application to American Community Survey multi-year period estimates}, journal = {Stat}, volume = {4}, year = {2015}, month = {10/2015}, pages = {255{\textendash}270}, abstract = {We present hierarchical Bayesian methodology to perform spatio-temporal change of support (COS) for survey data with Gaussian sampling errors. This methodology is motivated by the American Community Survey (ACS), which is an ongoing survey administered by the US Census Bureau that provides timely information on several key demographic variables. The ACS has published 1-year, 3-year, and 5-year period estimates, and margins of errors, for demographic and socio-economic variables recorded over predefined geographies. The spatio-temporal COS methodology considered here provides data users with a way to estimate ACS variables on customized geographies and time periods while accounting for sampling errors. Additionally, 3-year ACS period estimates are to be discontinued, and this methodology can provide predictions of ACS variables for 3-year periods given the available period estimates. The methodology is based on a spatio-temporal mixed-effects model with a low-dimensional spatio-temporal basis function representation, which provides multi-resolution estimates through basis function aggregation in space and time. This methodology includes a novel parameterization that uses a target dynamical process and recently proposed parsimonious Moran{\textquoteright}s I propagator structures. Our approach is demonstrated through two applications using public-use ACS estimates and is shown to produce good predictions on a hold-out set of 3-year period estimates. Copyright {\textcopyright} 2015 John Wiley \& Sons, Ltd.}, keywords = {Bayesian, change-of-support, dynamical, hierarchical models, mixed-effects model, Moran{\textquoteright}s I, multi-year period estimate}, issn = {2049-1573}, doi = {10.1002/sta4.94}, url = {http://dx.doi.org/10.1002/sta4.94}, author = {Bradley, Jonathan R. and Wikle, Christopher K. and Holan, Scott H.} }