Webpage last modified: 2008-Sep-15
Harmonization in cross-national and cross-cultural contexts occurs when producers of survey or statistical data create common measures of key economic, political, social, and health indicators. The goal is to present data that permit a degree of comparability over time or space.
When collecting data on the core characteristics of their populations, national statistical agencies strive in their harmonization efforts to create measures of such important concepts as income, poverty levels, gross domestic product (GDP), etc., which are intended to have the same basic conceptual meaning no matter when or how they were collected. Producers of longitudinal survey data often ask respondents the same question over multiple waves of a single data collection and/or plan the entire survey collection process so that concepts are closely comparable between waves.
Even those who conduct cross-sectional surveys may consider harmonization after the fact (ex-post) if they decide the subject matter is important enough that users interested in a given topic would benefit from comparing concepts and responses over multiple surveys. Secondary users (for example, individual researchers not directly connected to the original data collection effort, or social science data archives) may undertake harmonization projects of their own to create new data resources.
Various harmonization strategies exist, both ex-ante/input oriented and ex-post/output oriented. Each has advantages and disadvantages.
Goal: To ensure that survey and statistical research teams follow accepted standards when creating harmonized data and documentation files, and use a harmonization strategy that best fits their basic source materials and the objectives they wish to achieve.
'Input' harmonization, usually applied in a multi-national context, seeks to impose strict guidelines by which each country follows both the same survey procedures and a common questionnaire. The strategy permits a high degree of comparability, which allows analysts maximum flexibility in studying the information collected from diverse populations. Effective input implementation of common standards across countries increases the chances of collecting high-quality data in the field. However, this does come with significant cost implications, since it requires a high degree of planning at the very outset of the project, as well as continuous monitoring throughout the process.
This type of harmonization is implemented through two main strategies, one "ex-ante" and the other "ex-post." When harmonization has already been considered during survey planning with regard to the development of common goals, measurements and understanding of concepts, the ex-ante strategy ensures that specific targets are established for the collection of data on key variables. However, the questions used to collect these data may vary from country to country.
The second variant is an ex-post strategy, by which statistical or survey data are made comparable through a conversion procedure after completion of the data collection process. Ex-post strategies can be used in situations where intensive early planning is not possible because of financial or policy constraints. The goal of the harmonization procedures could, for example, be to present in a comparative fashion data on a given topic that has been collected in separate, cross-sectional surveys.
Following a systematic approach from the beginning of the harmonization process allows data producers to document all of their decisions at the time they are made. When documentation is produced at the end of the process, it is often incomplete because producers might not remember the rationale for some of the decisions they made.
Harmonization efforts usually concentrate on comparing and integrating information involving specific variables across data files. However, it is equally important to consider the overall characteristics of the surveys that make them good candidates for harmonization, and to report the decisions involving this process to end users.
Researchers may analyze harmonized files in new and unexpected ways. It is crucial to provide them sufficient information about the concepts and definitions presented, and the assumptions underlying the decisions made in their construction.
Strictly speaking, these traits apply to statistical data. However, many of them would apply equally to survey data, particularly those regarding the comparability of social, economic, and demographic concepts cross-nationally or cross-culturally.
Regardless of whether researchers adopt input or output harmonization as a strategy, all aspects of the survey planning, collection, and dissemination process should be considered when producing harmonized data files or creating accompanying documentation. Users should have access not only to the harmonized end result, but also to detailed information about all steps taken by the producers, in order for them to fully understand what decisions were made during the entire process.
This list is based on documentation provided in the Integrated Health Interview Series (IHIS). The IHIS is an effort to provide an assortment of variables from the core household and person level files from the National Center for Health Statistics' seminal data collection effort on the health conditions for the US population from 1969 to the present. It provides extensive user notes and FAQ pages to describe how their harmonization project coped with several of these components [8].
[1] Collaborative Psychiatric Epidemiology Surveys (CPES). Retrieved Sept. 15, 2008 from http://www.icpsr.umich.edu/CPES
[2] Eurobarometer Survey Series. Retrieved Sept. 15, 2008 from http://www.gesis.org/en/data_service/eurobarometer
[3] European Social Survey. Retrieved Sept. 15, 2008 from http://europeansocialsurvey.org/
[4] European Values Study. Retrieved Sept. 15, 2008 from http://www.europeanvalues.nl/
[5] German Social Science Infrastructure Services (GESIS). ISSP DataWizard. Retrieved Sept. 15, 2008 from http://www.gesis.org/en/research/information_technology/ISSPWizard.htm
[6] Gunther, R. (2003). Working Paper #19, Report on compiled information of the change from input harmonization to ex-post harmonization in national samples of the European Community Household Panel — Implications on data quality (CHINTEX). Retrieved May 23, 2008 from http://www.destatis.de/jetspeed/portal/cms/ Sites/destatis/Internet/DE/Content/Wissenschaftsforum/Chintex/ Projekt/Downloads/WorkingPaper1__092003,property=file.pdf
[7] Heeringa, S., & Berglund, P. National Institutes of Mental Health (NIMH), Collaborative Psychiatric Epidemiology Survey Program (CPES) Data Set: Integrated Weights and Sampling Error Codes for Design-based Analysis. Retrieved Sept. 15, 2008 from http://www.icpsr.umich.edu/cocoon/cpes/ using.xml?section=Weighting#I.++Introduction
[8] Integrated Health Interview Series (IHIS). Retrieved Sept. 15, 2008 from http://www.ihis.us/ihis/
[9] Minkel, H. (2004). Working Paper #20, Report on data conversion methodology of the change from input harmonization to ex-post harmonization in national samples of the European Community Household Panel — Implications on data quality (CHINTEX). Retrieved May 23, 2008, from http://www.destatis.de/jetspeed/portal/cms/ Sites/destatis/Internet/DE/Content/Wissenschaftsforum/ Chintex/Projekt/Downloads/WorkingPaper2__012004,property=file.pdf
[10] United Nations Economic and Social Council. Environmental-economic accounting. E/CN.3/2005/15. Retrieved December 20, 2005, from http://unstats.un.org/unsd/statcom/doc05/2005-15e.pdf
Bauer, G., Jungblut, J., Muller, W., Pollak, R., Weiss, F., & Wirth, H. (2006). Issues in the comparative measurement of the supervisory function. Unpublished manuscript. Retrieved May 23, 2008, from http://www.mzes.uni-mannheim.de/publications/papers/Supervisor_Function.pdf
Bilgen, I., & Scholz, E. (2007). Cross-national harmonisation of socio-demographic variables in the International Social Survey Programme (ISSP). Anaheim, CA: American Association of Public Opinion Research.
Burkhauser, R. V., & Lillard, D. R. (2005). The contribution and potential of data harmonization for cross-national comparative research. Journal of Comparative Policy Analysis, 7(4), 313-330.
Carlson, R. O. (1958). To talk with kings. Public Opinion Quarterly, 22(3), 224.
Desrosieres, A. (2000). Measurement and its uses: Harmonization and quality in social statistics. International Statistical Review/Revue Internationale de Statistique, 68(2), 173-187.
Ehling, M. Harmonising data in official statistics.(2003). In J. H. P. Hoffmeyer-Zlotnik & C. Wolf, Advances in cross-national comparison: A European working book for demographic and socio-economic variables (pp. 17-31). New York: Kluwer Academic / Plenum Publishers.
Esteve, A., & Sobek, M. (2003). Historical methods; challenges and methods of international census harmonization. Historical Methods, 36(2), 66-79.
Gandek, B., Alacoque, J., V, U., Andrew-Hobbs, M., & Davis, K. (2003). Translating the short-form headache impact test (HIT-6) in 27 countries: Methodological and conceptual issues. Quality of Life Research, 12, 975-979.
Gil Alonso, F. (2006). Toward a European statistics system: Sources of harmonized data for population and households in Europe. Paper presented at the International Data Session of the EAPS European Population Conference.
Hantrais, L., & Mangen, S. (1996). Cross-national research methods in the social sciences. New York: Pinter.
Hoffmeyer-Zlotnik, J. H. P. (2004). Data harmonisation. Roundtable at a conference for the Network of Economic and Social Infrastructures, Luxembourg.
Kennett, P. A. (2001). Comparative social policy: Theory and research. Buckingham: Open University Press.
Korner, T., & Meyer, I. (2005). Harmonising socio-demographic information in household surveys of official statistics: Experiences from the Federal Statistical Office Germany. In J. H.P. Hoffmeyer-Zlotnik,& J. A. Harkness (Eds.), Methodological aspects in cross-national research (pp. 149-162). Mannheim: ZUMA Nachrichten Spezial, Band 11.
Niero, M., Martin, M., Finger, T., Lucas, R., Mear, I., Wild, D., et al. (2002). A new approach to multicultural item generation in the development of two obesity-specific measures: The obesity and weight loss quality of life (OWLQOL) questionnaire and the weight related sympton measure (WRSM). Clinical Therapeutics, 24(4), 690-700.
Olenski, J. (2003). SSDIS: Global standard for harmonization of Social statistics. Unpublished manuscript. Retrieved May 23, 2008, from http://unstats.un.org/UNSD/demographic/meetings/egm/Socialstat_0503/docs/no_10.pdf
Pennell, B. E. (2006). Survey design and management. From a course at the Summer Institute, Survey Research Center, University of Michigan.
U.K. Office for National Statistics. National statistics harmonization. Retrieved May 23, 2008, from http://www.statistics.gov.uk/about/data/harmonisation/default.asp
Previous chapter | Next chapter | Home
© 2008 The authors of the Guidelines hold the copyright. Please contact us if you wish to\n publish any of this material in any form.