Washington Statistical Society
        Washington Statistical Society on Meetup

June 2014

Contents:



The Results Are In!

WSS 2014 Election Results

Once again this year the Washington Statistical Society was privileged to have an exceptional slate of candidates who volunteered their services and stood for election to the WSS Board. On behalf of the Nominations Committee I would like to thank each of the candidates for volunteering despite the many other responsibilities that they have. We would like to congratulate the members who were elected based on the votes of the membership in June.

Congratulations Newly-Elected Board Members!

President
Chris Moriarity, National Center for Health Statistics

Methodology Program Chair
Don Jang, Mathematica-MPR

Communications Officer
Tom Mule, US Census Bureau

Representatives-at-Large
Ken Copeland, National Opinion Research Center Tom Krenzke, Westat

Treasurer
Jill Dever, RTI International

Congratulations Newly-Elected Board Members!

President: Diane Herz

President-Elect: Chris Moriarity

Past-President: Nancy Bates

Methodology Section Chair: Mike Fleming

Communications Officer: Tom Mule

Secretary: Andy Keller

Treasurer: Jill Dever

Council of Chapters Representative: Eileen O'Brien

Representatives-At-Large: Ken Copeland, Tom Krenzke, Jaki McCarthy, Steve Paben

Contact information for Board members is provided at the end of the newsletter and at http://www.washstat.org/.

– Keith Rust
Past-President 2013-14, Chair of the 2014 Nominations Committee

Return to top

Special WSS Event!

You are cordially invited to the
Cox Award Presentation and Annual Dinner on behalf of the Washington Statistical Society

Tuesday, June 24, 2014

Presentation:
Sharing Confidential Data in an Era with No Privacy
Jerome Reiter
Speaker event commences at 4:00 pm RTI International
701 13th St NW Suite 705, Washington, DC

- and -

Annual Dinner:
Carmine's
Dinner commences at 6:00 pm
425 7th St NW, Washington, DC

The Gertrude M. Cox Award is co-sponsored by RTI International.

Registration

All are encouraged to attend both events regardless of WSS membership status.

Please register for the presentation and dinner separately.

Email your RSVP for the Cox Award Presentation to Frank Yoon (FYoon@Mathematica-MPR.com).

Online registration is available to attend the Annual Dinner at http://goo.gl/AMYIiP.

The registration fee is $45 for WSS Members and $50 for guests and nonmembers. Instructions for submitting credit card or check payments are provided in the online registration form. The receipt will be emailed to you.

Contact Frank Yoon at FYoon@Mathematica-MPR.com if you do not receive the receipt via email.

Return to top

WSS Conference on Administrative Records for Best Possible Estimates

  • Date/Time:September 18, 2014 1:00 pm -- 4:30 pm
  • Location: Bureau of Labor Statistics Conference Center
    To be placed on the seminar attendance list at the Bureau of Labor Statistics, you need to e-mail your name, affiliation, and seminar name to wss_seminar@bls.gov (underscore after 'wss') by noon at least 2 days in advance of the seminar, or call 202-691-7524 and leave a message. Bring a photo ID to the seminar. BLS is located at 2 Massachusetts Avenue, NE. Use the Red Line to Union Station.
  • WebEx event address for attendees: https://dol.webex.com/dol/j.php?MTID=m8fd58b3edba64f3bfaf63eeb8e63edfe
  • For audio:
    Call-in toll-free number (Verizon): 1-866-747-9048 (US)
    Call-in number (Verizon): 1-517-233-2139
    (US) Attendee access code: 938 454 2
  • Note: Particular computer configurations might not be compatible with WebEx.

Schedule

Time Speaker Point of Contact
1:00 Mike Fleming, WSS charles.fleming@bhox.com
1:10 Connie Citro, CNSTAT CCitro@nas.edu
1:35 Phil Kott, RTI pkott@rti.org
2:00 Graton Gathright, Census graton.m.gathright@census.gov
2:25 Intermission  
2:45 Shelly Martinez, OMB rmartinez@omb.eop.gov
3:10 Shawn Bucholtz, HUD shawn.j.bucholtz@hud.gov
3:35 Amy O'Hara, Census amy.b.ohara@census.gov
4:00 Questions and Answers  

Abstracts

From Multiple Modes for Surveys to Multiple Data Sources for Estimates: The Role of Administrative Records in Federal Statistics

Users, funders, and providers of federal statistics want estimates that are wider, deeper, quicker, better, cheaper (channeling Tim Holt, former head of the UK Office for National Statistics), to which I would add more relevant and less burdensome. Each of these adjectives poses challenges and opportunities for those who produce statistics. Since World War II, we have relied heavily on the probability sample survey as the best we could do, and that best being very good, indeed, to meet these goals for estimates in many areas, including household income and unemployment, self-reported health status, time use, crime victimization, business activity, commodity flows, consumer and business expenditures, and so on. Faced with secularly declining unit and item response rates and evidence of reporting error, we have responded in many ways, including the use of multiple survey modes, more sophisticated weighting and imputation methods, adaptive design, cognitive testing of survey items, and other means to maintain data quality. For statistics on the business sector, in order to reduce burden and costs, we long ago moved away from relying solely on surveys to produce needed estimates and have made extensive use of administrative records, but, to date, we have not done that for household surveys. I argue that we can and must move from a paradigm of producing the best estimates possible from a survey to that of producing the best possible estimates to meet user needs from multiple data sources. Such sources include administrative records, as well as, increasingly, transaction and Internet-based data. I provide several examples, including household income and household plumbing facilities, to illustrate my thesis. I conclude by suggesting ways to inculcate a culture of federal statistics that focuses on the end result of relevant, timely, accurate, and cost-effective statistics and treats surveys, along with administrative records and other data sources, as means to that end.

– Constance F. Citro, Director Committee on National Statistics, The National Academies

A Different Paradigm Shift: Combining Administrative Data and Survey Samples for the Intelligent User

In her startling WSS President's Invited Lecture, Connie Citro called for the slow and careful implementation of a paradigm shift in the way government agencies produce federal statistics. She provided a number of reasons for a shift away from a primary reliance on the survey sampling, chief among them were unaddressed measurement error, decreasing response rates, and increasing cost, both financial and psychic (e.g., dealing with irate Congressmen complaining about the burden of government surveys on their constituents).

Measurement error often results from attempting to measure quantities on a survey that the sample respondents cannot adequately provide. This is not a new problem, but a growing one as the demands for more policy-relevant data increase. Still, surveys aimed at collecting specific information are often better suited for providing relevant data than external sources like administrative data.

Measuring and removing the potential biases from increasing nonresponse rates is a concern that, it seems to me, has been adequately addressed in the survey sampling literature, although theory is not always quickly translated into practice. That leaves the cost of sample surveys in an era of tight budgets and increasing demands for data products. By itself, the cost of providing defensible estimates at ever lower levels of aggregation provides reason enough to replace or at least modify the current paradigm. This talk will review recent literature on combining simple linear models and probability- sampling principles when combining administrative data with survey samples to produce useful estimates at levels of aggregation where using the latter alone would be inadequate. Multiple imputation fails as a method of variance estimation in this context. Jackknife variance estimation can be used in its place, but a jackknife requires the generation of multiple data set--much more that the standard five with multiple imputation.

Since the approach described above depends on a model, statistical tests will be proposed to assess the viability of the model and also to inform users of potential biases in the estimates. There are issues of Type 1 and Type 2 error which often separate survey sampling from the rest of statistics that need to be conveyed to the user as do all the other problems associated with the estimation process. Indeed, that is the paradigm shift I am proposing: government statistical agencies should stop treating most users like they are dumber than dirt and cater more to intelligent users of their statistics.

– Phillip S. Kott, RTI International

The Role of Linked Administrative Data in the Evaluation and Improvement of the Survey of Income and Program Participation

The Census Bureau uses Federal and State administrative data to evaluate and improve the quality of data from the Survey of Income and Program Participation (SIPP). This talk will describe how the SIPP program uses administrative data to investigate bias from unit and item nonresponse, to validate survey responses, to improve imputation of missing data, and to augment the SIPP data.

I will discuss the challenges that have been faced in accessing, linking, interpreting, and protecting the administrative data; what has been learned about SIPP data quality and what SIPP improvements have been achieved; and the potential new uses of administrative data for SIPP improvement that are currently being investigated.

–Graton Gathright, Social, Economic, and Housing Statistics Division; U.S. Census Bureau

One piece of the Multiple Data Sources Paradigm Shift: New Policy on Accessing and Use Administrative Data for Statistical Purposes

In her 2013 WSS President's Invited Lecture, Connie Citro called for implementation of a paradigm shift in the way government agencies produce federal statistics. She discussed a number of challenges to making this shift. This talk describes one set of challenges - those to accessing and successfully using government administrative data in statistical programs--and how 2014 guidance issued by OMB is designed to address those challenges. The talk will also discuss some agency implementation activities to date, and some early lessons learned from those efforts.

–Shelly Wilkie Martinez, Statistical and Science Policy, Office of Management and Budget

Integrating Administrative Records and Commercial Data Sources into HUD's Housing Surveys: Past, Present, and Future

HUD, in partnership with the Census Bureau, is redesigning the American Housing Survey and the Rental Housing Finance Survey for 2015. A major part of the redesign effort is to maximize the use of administrative records and commercial data. This talk will: (1) summarize how HUD and Census have used HUD administrative records in prior American Housing Surveys; (2) summarize our current research into administrative records and commercial data for sample frame improvement, imputation, response replacement, and question replacement; and (3) discuss challenges and unresolved issues in integrating administrative records and commercial data into our housing surveys.

–Shawn Bucholtz, Director, Housing and Demographic Analysis, Office of Policy

Development and Research, U.S. Department of Housing and Urban Development

Fully Leverage External Data Sources: A Census Bureau Change Principle The Census Bureau is investigating the strategic reuse of Administrative Records and Third Party Data to improve data quality, reduce costs and respondent burden, and develop new data products. This talk will describe how administrative records are featured in the Census Bureau's Strategic Plan, addressing Connie Citro's call for vision and long-term planning. Efforts to integrate administrative records into frame construction, contact approaches, adaptive design, and imputation are underway for the decennial census and multiple household surveys. This talk discusses progress on these uses, and highlights the need to understand data quality, design data systems to accommodate "big" data, and collaborate with program and statistical agencies.

–Amy O'Hara, Center for Administrative Records Research and Applications, U.S. Census Bureau

Return to top

Congratulations Award Winner!
Julia Lane to Receive 2014 Julius Shiskin Award

Return to top

Seeking Award Nominations
The Info-Metrics Annual Prize in Memory of Halbert L. White, Jr.

Julia Ingrid Lane, Senior Managing Economist and Institute Fellow at the American Institutes for Research (AIR), has been selected to receive the 2014 Julius Shiskin Memorial Award for Economic Statistics. The award recognizes unusually original and important contributions in the development of economic statistics or in the use of statistics in interpreting the economy. Dr. Lane is recognized for her contributions to the development of a new Census Bureau program that has significantly advanced research on employment dynamics. She initiated what is now known as the Longitudinal Employer Household Dynamics (LEHD) program, the first large-scale linked employer-employee dataset in the United States. This dataset filled a major data gap by providing researchers with matched employee-employer data containing information for most states on income and worker mobility and on the entry and exit of firms. She later developed one of the first remote access data enclaves with government micro data records at a private firm. Dr. Lane is the 42nd recipient of the Award; she will be honored at events hosted by the three sponsors of the award: the Washington Statistical Society, the National Association for Business Economics, and the Business and Economics Section of the American Statistical Association (ASA).

Dr. Lane joined the faculty of the economics department of the American University (AU) in 1990 and became a full professor in 1997. While at AU and serving as a consultant to the World Bank, she conducted research on job and worker flows that, in 1997, led to her selection as an ASA/National Science Foundation (NSF) Fellow at the Census Bureau with the task of demonstrating how her concept for a linked employer-employee dataset might be converted into an operational program. Her success in showing the feasibility of her proposal led to her being named a Senior Research Fellow at the Census Bureau to continue working on the LEHD - a position she held until 2004. Lane continued working on the LEHD after becoming Director of the Employment Dynamics program at the Urban Institute in 2000. After ending her direct involvement with the LEHD in 2004, Lane held senior positions at the National Opinion Research Center (NORC) and NSF before joining AIR. At NORC she developed a data enclave, one of the first to provide a confidential, protected environment for authorized researchers to access previously unavailable federal micro data records. It now hosts confidential data for four federal agencies and two private foundations.

At the Census Bureau, Lane jointly directed the development of the LEHD into a permanent Census Bureau program. Her concept was to create a linked employee-employer file for the United States based on information from state unemployment insurance (UI) records. Her concept was the result of many years of research on employment dynamics, which included collaborations with other researchers. In 1996, Lane with Simon Burgess and David Stevens, coauthored "Worker and Job Flows," which appeared in Economic Letters, and "Job Flows, Worker Flows, and Churning," which appeared in the July 2000 issue of the Journal of Labor Economics. Lane's research and work related to the LEHD is well documented in the four books she has co-authored or co-edited and the more than 50 peer- reviewed articles in scientific journals.

Lane initiated the LEHD to fill a major gap in the information on employment dynamics. Although researchers had information on how much employment had changed in a given time period, they could not determine how many new jobs had been created (job creations) or how many jobs had been lost (job destructions). Similarly, they did not know the number of employees who left their jobs between one period and the next (separations), or the number who acquired new jobs in that period (hires). The Census Bureau had tried to provide information on the gross flows by integrating its business and household data, but had made only limited progress - and collecting the information by a survey would have been too costly.

Her proposal was to create a linked employer-employee dataset for the United States by obtaining access from states to their UI wage records because they include both the firm's identification number and the employee's Social Security number and cover the almost all employees. This information would be used link these records to each other and then to Census Bureau records. Lane's linked dataset would provide information about jobs at minimal cost and with no increase in respondent burden. For the first time, information would be available for detailed industries and small geographic areas and provide policy makers at all levels of government, businesses, and researchers, with information on how the economy is functioning. In fact, these groups have extensively used the LEHD to study the underlying employment dynamics of the U.S. economy and other topics.

Converting the proposal into a permanent Census Bureau program would not be easy. Lane's first had to demonstrate the need for a linked dataset. She raised the funds for, and organized, a two-day International Symposium on Linked Employer-Employee Data, that was held in May 1998. More than 200 researchers from 20 different countries participated and the presentations convinced the senior staff of the Census Bureau that they should continue supporting Lane's concept and in 1999 named her a Senior Research Fellow. Working with John Abowd of Cornell University and John Haltiwanger, Lane sought outside funding to supplement the resources available from the Census Bureau and the Bureau of Labor Statistics. She was successful in obtaining grants and contracts from the National Institute on Aging, NSF, the Alfred P. Sloan Foundation, the Department of Health and Human Services, the Russell Sage Foundation, and Eurostat. Of particular importance was that the Census Bureau also provided funds to allow John Abowd to join the project to deal with the difficult technical issues related to the LEHD.

Next, she had to persuade states to provide the Census Bureau with their UI records. Lane personally met with the state Labor Market Information agencies, governors' offices, and the state workforce investment boards to convince them to be partners in the project, explaining how their state would gain as a partner with the Census Bureau. She worked with the states to resolve the legal obstacles they encountered when seeking permission to provide their UI wage records to the Census Bureau. By 2004, Lane had convinced more than 25 states to partner with the Census Bureau.

Once these data became available to the Census Bureau, it was necessary to develop methodologies to validate the linking of the employee and employer state UI records and then to link those records to Census Bureau business records. Abowd, working with Lane and a team of LEHD researchers, provided the specifications for editing, linking, and imputing missing items in the UI records, and Haltiwanger assisted in the linking to the Census Bureau's records. Abowd's work also included the development of statistical matching techniques to associate employees with their place of work and to make identifiers longitudinally consistent. He also developed disclosure avoidance techniques that would allow the Census Bureau to release the detailed data in the LEHD without compromising the confidentiality of individuals and firms. His proposal, developed with assistance of the LEHD team, would use the idea of "adding noise" to protect the confidentiality of the records a technique that had been proposed some years earlier.

The linked LEHD dataset designed by Lane also was to be used as the basis for producing two other reports. The Quarterly Workforce Indicators (QWI) reports, released in 2003, include data on firms' total employment and change in employment, average monthly earnings, average monthly earnings for new hires, and characteristics of firms and their employees. The OnTheMap program, released in 2006, is an online mapping and reporting application that shows where people work and where workers live based on annual worker origin and destination data and QWI data files. The majority of LEHD data starts in the 1990s and continues to this day. Because the underlying files contain confidential worker and firm data, they are available only at Census Bureau Research Data Centers for use only by researchers with sworn status.

The development of the LEHD based on Lane's concepts was a collaborative effort of Lane and a small group of experts, most notably John Abowd of Cornell University and John Haltiwanger, the Census Bureau's Chief Economist. Other key contributors included the Census Bureau's LEHD staff, and Nancy Gordon and Frederick Knickerbocker, of the Census Bureau's executive staff.

Lane became a Senior Managing Economist and Institute Fellow at AIR in 2010. She holds honorary positions as the Gutenberg Chair and Professor cnv., BETA University of Strasbourg CNRS and Professor, Melbourne Institute of Applied Economics and Social Research at the University of Melbourne. Lane received the Vladimir Chavrid Award of the National Association of State Workforce Agencies in 2004 and was named a fellow of the American Statistical Association in 2009.

Prepared by Robert P. Parker Chair, Julius Shiskin Award Selection Committee.

Return to top
Art Hughes

WSS Member In The Spotlight
Meet WSS Member Art Hughes

1. Where do you work and what do you do?
I am currently on detail as the Acting Chief of the Populations Survey Branch (PSB) in the Center for Behavioral, Health Statistics and Quality, Substance Abuse and Mental Health Services Administration located in Rockville MD. My work involves managing a group of talented statisticians and survey methodologists working on the National Survey on Drug Use and Health which is a large household survey on substance abuse and mental health problems.

2. What attracted you to your current position?
I became Acting Chief when the permanent Branch Chief retired in January 2014. Prior to that, I worked in the branch as a mathematical statistician overseeing contractor work on sampling, weighting, statistical inference, and state and substate reports based on small area estimation procedures. I was also involved in methodological studies covering topics such as address-based sampling, validity of self-reported drug use, and comparison of state-level mental health measures across different surveys.

3. Finish this sentence: "I joined WSS to..."
... keep abreast of what's going on in other federal statistical agencies and topics related to my work. Joining WSS is a great way to further professional development and connect with former colleagues and persons with similar interests.

4. What was your first job?
My first job was working in a furniture store as a teenager in Baltimore City where I grew up. My duties included unloading trucks; delivering new furniture; and delivery, setup, and pickup of rental furniture. It was hard work, but a lot of fun on days when riding in the truck on a long distance delivery! While this job had nothing to do with statistics, lessons learned on how to organize warehouse stock, plan delivery schedules, and interact with the public were invaluable.

5. Describe yourself in 3 words.
Committed, detailed oriented, and personable.

6. Why did you join the statistics profession?
After a year in graduate school majoring in mathematics, I became interested in taking courses that were less theoretical. As a result, I took a two semester course in probability and statistics and found it to be quite enjoyable. While there was still theory to learn, there were plenty of practical data problems to solve as well. In addition, I was offered a fellowship to work on a NASA grant analyzing oceanic rainfall data using nonparametric methods. The combination of statistics courses and involvement on the NASA grant convinced me to join the statistics profession.

7. What skills are most important for the next generation of statistics professionals?
I think one of the most important skills for the next generation of statistics professionals is to be proficient in both statistical and graphical software packages that produce results that can be presented to a more culturally diverse audience. These skills are critical in a world where many data users are connected to social media where findings need to be presented in a format that can be quickly translated and absorbed.

8. How do you like to spend your time away from work?
I like to spend my free time with family, going to concerts, listening to a variety of music, and working on home projects. As far as concerts go, I particularly enjoy those that feature artists/groups that I listened to in the 1970's.

9. What is your favorite meal or local restaurant?
One of my favorite local restaurants is Far East Restaurant in Rockville. Their chicken and cashews dish has been deliciously prepared the same way since I started eating there over twenty years ago!!

10. Have you had any great mentors? If so, what made them great?
One of my most influential mentors was my graduate school mathematics advisor. He would take time to talk about anything on your mind while instilling a strong work ethic in his mentoring and as a teacher and researcher. It was his belief that you should do all of the exercises in the textbook, not just the ones assigned to you for homework, if you wanted to do your best on an exam.

Return to top

Spotlight A WSS Member!
Washington Statistical Society's Spotlight on Members Program

The WSS Board of Directors has established a program to highlight members who have made or are making notable contributions to the work of their organization or their professional field of expertise. We know that WSS members are doing interesting work in the fields of statistics, survey methodology, and the social sciences. Through this program, we hope to spotlight the accomplishments of our fellow WSS members.

This is our first request for nominations, to be featured in an upcoming issue of WSS News. We are interested in featuring members at all levels of the employment spectrum including recent graduates, mid-career employees, and those seasoned veterans.

Please feel free to nominate more than one person or a team working together. You may also nominate yourself as well. The nominees must be members of the WSS and not currently affiliated with the Board.

Please provide us with the following information about your nominee or nominees.

  1. Your name, email address, and telephone number
  2. Name or names of nominee(s)
  3. Organizational affiliation
  4. Job title
  5. Their contact information including email address and telephone number
  6. A brief narrative describing the reasons for your nomination
  7. A photo of the nominee, although not required, would be great be greatly appreciated

Please submit your nominations or direct any questions to, John Finamore (jfinamore@nsf.gov), member of the WSS Board. We look forward to hearing from you.

Return to top

Student Column

About a year ago, the director of the UDC MS in Applied Statistics program, Dr. Valbona Bejleri, asked me if I would like to be the Washington Statistical Society's Student Representative for a year. I did not know what I was getting into, but I accepted. If you get offered this position, I'd advise you to take it! It has been a fun and educational year.

In Fall and Spring WSS meet ups at local university Statistics programs, I've had the opportunity to meet many of my fellow DC-area Statistics students. You are a smart bunch! Although I did meet a few mid-career (i.e. dinosaur) students like myself, most of you are at the beginning of your careers. Seeing your enthusiasm and idealism helped me feel that way, too. My sincere thanks to the program directors with whom I worked to set up these meetings, especially Dr. Mary Gray of American, Dr. Zhaohai Li of GWU, Caroline Wu of Georgetown, and of course Dr. Valbona Bejleri of my alma mater, UDC.

Through monthly board meetings, I got to see the inner processes of the Society itself, and worked with the members of the WSS board--also a very smart bunch! And much more civil than you might expect! A lot goes into making an organization of our size work. The board has been supportive in defending Statistical education in the DC area; I believe this is potentially one of WSS's primary strengths. Thanks to the entire board, especially Nancy Bates, Keith Rust, and Phil Kalina who helped me find my feet.

Writing this column has been quite an experience as well. It was a bit nerve-racking to put statistics puzzles up for really real professional statisticians to try to work! But everyone was nice about it, and it made me have to think about what I would post all month. Thanks to the WSS Editor, Colleen Choi, for her patience as I asked for multiple deadline extensions!

Though my time as the Student Rep is ending, I look forward to running into you all at WSS events in the future. My email is timothychenallen@gmail.com. Thanks for a great year.

– Tim Allen, WSS Student Representative (timothychenallen@gmail.com)

Note: Please see page 23 of this month's newsletter for the answers to last month's Probs & Stats Brain Teaser crossword puzzle.

Return to top

Note From The WSS NEWS Editor

Items for publication in the July, 2014 issue of the WSS NEWS will be accepted until the 20th day of the preceding month.

Email items to wss.editor@gmail.com.

Please submit all materials in MS WORD or plain text.

Please do not submit your items in pdf or include them in the body of an email.

Return to top

Click here to see the WSS Board Listing (pdf)
Return to top