Editorial
The theme for this issue is “IAOS – Past, Present, and Future”. This theme may sound familiar to those of you who attended the 2017 ISI World Statistics Congress (WSC) where immediate-past-IAOS-president Ola Awad organized and chaired a session with a similar focus. In this issue, we have summarized her statements about the period 2015–2017. Past-president Stephen Penneck gives the history of IAOS, and you will find a reflection on the future directions of the association in Katherine Condon’s interview with current president, Mario Palma.
We also had room to publish a conversation piece. Nancy Torrieri talks to Timothy Trainor about geography and its role as the framework for statistics, survey design, sample selection, data collection, tabulation, and dissemination of official statistics. Mr. Trainor held the position of Chief Geospatial Scientist for the US Census Bureau before his retirement in January of this year. He now pursues new interests in the discipline of geography.
As always, the views and opinions expressed in the interviews and conversations published in SJIAOS are those of the interviewee and do not necessarily reflect the policy or position of the Journal, IAOS nor IOS Press.
The 2017 WSC also gave us the opportunity to once again focus on the independence of statistical agencies, a topic of extreme importance to official statistics. An invited paper session looked at the question: Must the production and dissemination of official statistics be undertaken outside the Executive Branch of Government to ensure independence from political and stakeholder influences? We are very fortunate that all presenters from that session (Andreas Georgiou, Jean-Luc Tavernier, Dennis Trewin and Pali Lehohla) agreed to prepare manuscripts based on their presentations at the conference. Hallgrimur Snorrason, IAOS president 1993–1995, introduces the topic and the papers and Gerry O’Hanlon’s discussion summarizes and concludes the section. Together these individuals have accumulated a wealth of experiences through decades of professional involvement in the production and dissemination of official statistics in different countries (Greece, France, Australia, South Africa, Ireland and Iceland). They provide insightful observations and bring unique perspectives.
The question will be asked again in the fall at the upcoming IAOS-OECD 2018 Conference (www.oecd.org/iaos2018/). A special meeting will be convened to look at the threats and responses to the professional independence of NSOs. There will be an opportunity to discuss concrete cases, governance arrangements and the role of the statistical community. For more information, please contact Mario Palma at [email protected].
I would also like to draw your attention to the many other fine technical manuscripts in this issue. We have two papers from the Center for Administrative Records Research and Applications in the US Census Bureau.
The paper: “When Race and Hispanic Origin Reporting are Discrepant Across Administrative Records and Third-Party Sources: Exploring Methods to Assign Responses,” by Sharon Ennis, Sonya Porter, James Noon and Ellen Zapata explores different methods to assign a unique race and a unique Hispanic response when there are discrepancies in the data. The research also shows the characteristics of individuals with matching, non-matching and missing race by household and contextual variables.
“Assimilation and Coverage of the Foreign-Born Population in Administrative Records,” by Renuka Bhaskar, Leticia Fernandez and Sonya Porter looks at ways to incorporate administrative data in decennial censuses and survey operations. Critical to this work is an understanding of the coverage of the population by administrative records. The authors use federal and third party administrative data linked to the American Community Survey (ACS) to evaluate the extent to which administrative records provide data on foreign-born individuals in the ACS and employ multinomial logistic regression techniques to evaluate the characteristics of those who are in administrative records relative to those who are not.
The December 2017 issue of SJIAOS had several papers of relevance to monitoring and reporting on the sustainable development goals. “The Potential of Population and Housing Censuses for International Migrant Analysis” by Sabrina Juran and Rachel Snow in the Population and Development Branch at the United Nations Population Fund, Technical Division fits in this category. The authors report on the availability of migration data from all national population censuses by the countries that participated in the 2010 census-round and highlight the potential of these data to generate migration profiles and analysis of international migration, especially within the context of monitoring and reporting on the sustainable development goals.
Identification of indigenous populations and health measurement is a topic of a future special SJIAOS issue. Here, we publish a paper by Ching Choi and Len Smith at the University of New South Wales and the Australian National University. It is entitled “Record Linkage to Advance Indigenous Mortality Statistics in Australia – Sources of Error and Bias.” The paper describes efforts made in Australia in the use of data linkage to enhance mortality statistics for indigenous populations. The authors point to the inadequacies of statistics sourced from death registration and show improvements resulting from data linkage. They also discuss conceptual, methodological and data issues that may give rise to error and bias in such data linkages.
There are more manuscripts addressing methodological issues, innovative solutions and best practices. Jacco Daalman (Statistics Netherlands) has written a paper on frequency tables produced from several sources and the risk of numerically inconsistent results. Statistics Netherlands developed a Repeated Weighing (RW) method for this purpose. The method was applied to the 2001 and 2011 Dutch censuses. The paper presents two new Divide-and-Conquer (D&C) methods, based on quadratic programming (QP) that avoid many of the problems experienced with RW.
Itsuo Sakuma, Masako Tsujimura and Kazusuke Tsujimura, from Faculties of Economics at Senshu, Rissho and Keio Universities and the Keio Economic Observatory in Tokyo discuss domestic investment, lowering interest rates, and inflation rates. They examine the theoretical meaning of the value added deflators using a highly simplified symmetric input output table and use SNA-IO, the input/output table published as a part of the Japanese SNA to experimentally estimate both value added and operating surplus deflators. Their paper is entitled: “The Value Added and Operating Surplus Deflators for Industries: The Right Price Indicators That Should be Used to Calculate the Real Interest Rates.”
A manuscript from Statistics Sweden co-authored by Yingfu Xie, Andreas Lennmalm, Daniel Lennartsson and Annica de Groote looks at “Uncertainty and Automatic Balancing of National Accounts (NA) with a Swedish Application.” The authors use a weighted least squares approach for automatically balancing a large-scale supply-use framework in the Swedish NA system. Efforts are made to estimate the uncertainties not only from sampling errors but also from non-sampling errors. The error estimates are used as weights in the balancing procedure. The approach is evaluated through a test run in parallel with a real compilation of the Swedish annual NA.
From Mexico, we have “An Exploratory Study of how Undergraduate Students use Official Statistics as a Source of Information for Their Academic Assignments” by José Luis Ángel Rodríguez Silva, Universidad Politécnica de Aguascalientes and Mario Sánchez Aguilar, Instituto Politécnico Nacional, CICATA Legaria, Programa de Matemática Educativa. It is the premise of the paper that many undergraduate students do not use official statistics as a source of information and that they have limited knowledge of accessing, analyzing and extrapolating such information to their benefit, both in academic and personal settings. The authors show the main obstacles encountered by students when they try to access and use official statistics and offer suggestions specific to the National Institute of Statistics and Geography (INEGI), but with a wider application. They suggest a closer working relationship between official statistics offices and academia through lectures on the use of official statistics, and by fostering MSc and PhD studies in statistics among the personnel of the NSO in well-recognized academic institutions.
As a follow up to that suggestion, I would like to remind you of the programs already established by IAOS to get young people interested in official statistics. The Young Statistician Prize (YSP) started in 2011. To be eligible, you must be aged 34 and younger and working for a statistical agency. In this issue, we are pleased to publish “Variance Reduction Using a Non-Informative Sampling Design” by Thomas Zimmermann from the Federal Statistical Office of Germany (Destatis). His paper was awarded the second prize in the 2016 competition. SJIAOS congratulates him on this achievement.
In addition to the YSP, IAOS has started a new award for graduate students, the Young Scholars for Better Statistics Award. This award targets students writing their Master’s thesis or PhD dissertation. The students are asked to write essays related to official statistics. “If they have a need for official statistics in their dissertations, if they can write a critique of what is available for their subjects and they can describe the state of official statistics in that particular subject, they can participate in the contest” (see the interview with Mario Palma in this issue).
All manuscripts in the June issue have open access. You will note from the table of contents how official statistics and challenges related to their production, presentation and dissemination transcend geographic borders and political domains. Where ever you may be located physically, I hope this issue brings you manuscripts that matches your interest,
either as a producer or a user of official statistics and gives you an idea of the work that is undertaken to have “Better Statistics for Better Lives” – the theme for the upcoming IAOS-OECD 2018 Conference (www.oecd.org/iaos2018).
Kirsten West
Editor-in-Chief
June 2018
Statistical Journal of the IAOS
E-mail: [email protected]
