Editorial
It is my pleasure to introduce the December issue. This issue came about as a result of a “Call for Papers” with the topic of administrative data. Nancy Torrieri prepared the announcement:
“Please consider submitting a paper for a special issue of the Statistical Journal of the International Association for Official Statistics (SJIAOS) on the topic of administrative data. Increasing use of administrative data worldwide is of interest to governments, academia, the private sector, and wherever official statistics are produced. While the advantages of improved use of administrative data sources are evident to many, there are clear challenges in the use of these sources in fields ranging from epidemiology to agriculture. Assuring the quality of data, planning for thorough program evaluation, controlling costs, integrating data sources effectively, and developing appropriate analysis frameworks and applications represent only a few of the many challenges in producing usable data from administrative records. For the special issue being planned, papers may focus on any aspect of administrative data research and applications. Preference will be given to papers that describe recent administrative data initiatives under development since 2010. Papers presenting methodologies and techniques for improving and broadening the use and integration of administrative data sets to benefit the production of official statistics are especially welcome.”
As you can tell from the contents, our solicitation resulted in many excellent manuscripts.
Nancy Torrieri is the guest editor for this special issue. She is also one of our associate editors. You know her work from the many interesting conversations she has brought us over the last few years with experts in Geography and Official Statistics. Nancy is herself an expert in the area. She has a Ph.D. in Geography from the University of Maryland, College Park. During her 28-year career at the U.S. Census Bureau, she managed statistical area programs in the Geography Division, and later worked as a program specialist in the American Community Survey Office. Her contributions include the development of a variety of program communication initiatives and public-facing documents, publications, and presentations that explain the Census Bureau’s goals, operations, and policies. She has received two Bronze Medals and numerous recognitions for her contributions to the U.S. Census Bureau.
Thank you, Nancy, for the tremendous job you did managing the review process and for introducing the manuscripts in the guest editorial.
The interview for this issue matches the focus on administrative data. Our interview is with Olav Ljones, IAOS president (2007–09). He has dealt with many issues associated with the use of administrative records. Mr. Ljones was instrumental in the research that allowed Statistics Norway to conduct its first 100 percent register-based census in 2011. Before his retirement in 2016, he served as the Deputy Director, International Relations at Statistic Norway.
The views and opinions expressed in the interviews and conversations are those of the interviewees and do not necessarily reflect the policy or position of the Journal, nor IAOS or IOS Press.
Four additional manuscripts appear in this issue. Tam and Kim contribute with a paper entitled “Big Data Ethics and Selection Bias: An Official Statistician’s Perspective.” The authors discuss how the use of Big Data raises a number of ethical and statistical challenges for official statistics. The authors find that National Statistical Offices are generally well equipped to address these challenges.
Haitham Zeidan reports on a Palestinian Central Bureau of Statistics (PCBS) experiment in administrative data records linkage in the paper “Matching Techniques and Administrative Data Records Linkage.” The focus is on matching different data sources from different ministries, municipalities and other partners with the PCBS Establishments Census 2012. Different matching algorithms and tools were used in the experiment.
Di Consiglio and Tuoto tell us about their experiences with linkage of different data sources in the paper “When Adjusting for the Bias due to Linkage Errors: A Sensitivity Analysis.” They assert that there are two types of errors to consider when dealing with data resulting from a record linkage process: false links and missed matches. If the linkage errors are not properly taken into account, i.e. standard statistical procedures are applied to the linked data, it may result in biased estimates and mis-relationships between variables recorded in different data sources. Their paper provides a sensitivity analysis of the effect of linkage errors on the estimation of linear and logistic regressions.
Finally, in the paper by Kissam, Queszade and Intili we hear about a novel approach used to improve the census address list in California. The strategy demon-
strates the efficacy of drawing on social, cultural, and civic capital in communities with limited financial resources to ameliorate the negative impact of budget constraints on central government funding on accurate census enumeration.
Kirsten West
Editor-in-Chief
December 2018
Statistical Journal of the IAOS
E-mail: [email protected]
