Census Knowledge Base » Browse » EVALUATION OF CENSUS RESULTS

URUGUAY - INFORME DE LA COMISIÓN TÉCNICA HONORARIA PARA LA EVALUACION DEL CENSO URUGUAY 2011

Margaret Mbogoni — Fri, 25 Jan 2013 11:55:41 GMT

Evaluation of Uruguay Census 2011.
http://www.ine.gub.uy/censos2011/index.html

Uruguay - Metodología de estimación de la población total residente en el Censo de Población 2011

Margaret Mbogoni — Fri, 25 Jan 2013 11:55:06 GMT

Methodology for the estimation of the total resident population in Population Census 2011.
http://www.ine.gub.uy/censos2011/index.html

Ethiopia 2007 Population and Housing Census - Administrative Report

Margaret Mbogoni — Fri, 25 Jan 2013 11:54:16 GMT

The report gives an overview of the census experience, from planning to final dissemination and archiving.

Kosovo Population and Housing Census 2011- Final Results: Evaluation of Census Results with the Post Enumeration Survey

Margaret Mbogoni — Fri, 12 Oct 2012 12:18:12 GMT

This report defines the PES implemented and enumerates its objectives. In addition, the manual covers elements of: sample design; questionnaire design; planning and implementation of a PES; matching; field reconciliation; the Dual System of Estimation (DSE); tabulations; and as main PES outcome, the evaluation of coverage and content error. The conclusion highlights the usefulness of the PES and care that must be taken in its results’ interpretation.

Post Enumeration Surveys - Technical Report

Jan Beise — Wed, 26 May 2010 11:44:28 GMT

By United Nations Statistics Division, DESA, 2010.

The present manualwas developed to provide operational guidelines for the preparation andimplementation of a post enumeration survey (PES). It defines the PES andenumerates its objectives. In addition, the manual covers elements of: sampledesign; questionnaire design; planning and implementation of a PES; matching;field reconciliation; the Dual System of Estimation (DSE); tabulations; theevaluation of content error. The conclusion highlights the usefulness of a PESand care that must be taken in its implementation. It additionally, presentschallenges associated to a successful implementation of the PES and how they canbe mitigated. Finally, the Annex presents selected examples from countries thatconducted PES during the 2000 and 2010 round of censuses.

Post Enumeration Survey: 2002 Uganda Census

Jan Beise — Thu, 22 Apr 2010 06:11:56 GMT

By Uganda Bureau of Statistics, 2005.

Uganda conducted the Post Enumeration Survey (PES) in January 2003 to evaluate the
coverage and content errors of 2002 population and housing census. Two major domains
of study were selected namely; urban and rural. The rural domain was stratified into four
regions; Central, Eastern, Northern and Western. A total of 350 enumeration areas were
selected as primary sampling units (PSUs) using the probability proportional to size.
Highly experienced enumerators who worked during the census were retrained to collect
data on a few selected variables. For absolute independence, organizers ensured that the
enumerators worked in different areas from those covered during the main census.
A matching exercise was undertaken after data collection, which was basically aimed at
investigating whether the PES persons/households were enumerated during the census.
Unmatched records were then reconciled in the field with the main purpose of identifying
erroneous inclusions. The CSPRo software was used for data capture, verification and
tabulation.

Principles and Recommendations for Population and Housing Censuses, Rev. 2

Jan Beise — Wed, 06 Jan 2010 06:05:21 GMT

By United Nations Statistics Division, 2008.

Since its earliest years, the United Nations has issued a series of international principles and recommendations on population and housing censuses to assist national statistical offices and census officials, throughout the world, in planning and carrying out improved and cost-effective censuses.

The Principles and Recommendations for Population and Housing Censuses, Revision 2 is divided into three parts: Part One - Operational aspects of population and housing censuses – covers mainly issues of census planning and management; Part Two – Topics for population and housing censuses – includes topics as well as their definitions and classification for both population and housing; and Part Three – Census products and data utilizations – is aimed at enhancing the dissemination and utilization of census data. The publication also contains a set of recommended tabulations on population and housing that every country is should produce at least once during the 2010 census round. There are also additional tabulations that countries may produce depending on their needs.

Principles and Recommendations for Population and Housing Censuses, Revision 2 (United Nations publication, Sales No. E.07.XVII.8), 2008.

[available in English, Arabic, Russian]

Botswana 2011 Population and Housing Census Project Document

Jan Beise — Wed, 06 Jan 2010 05:06:10 GMT

By Central Statistics Office, Botswana, 2009.

The CSO in collaboration and support from UNFPA embarked on the development
of a comprehensive Census Project Document that will also serve as source for
support and resource mobilization for all processes of the 2011 Census undertaking.
Botswana has a tradition of preparing project documents for the census. Census
project documents have been prepared for the 2001, 1991 and 1981 censuses. It is
hoped that the document will assist in resource mobilisation especially from
development partners to participate in this massive project during the current global
economic challenges.
This Document covers the evaluation of the 2001 census processes, the expected
structure of the 2011 National Census Secretariat, roles and responsibilities of
different census committees, the institutional capacity assessment of the CSO for a
successful conduct of the census in order to find response to needs’ requirements
and to proactively fill the gaps. The project document also provides different
strategies as census implementation guide and the needed Technical Assistance.
The Document provides recommendations to be implemented for the success of the
2011 Census.

Methodology of the Hong Kong 2006 Population By-census

Jan Beise — Mon, 14 Dec 2009 06:10:36 GMT

By Census and Statistics Department, Hong Kong, 2007.

The 2006 Population By-census wasconducted in July to August 2006. The By-censusprovides a wealth of data on the socio-economiccharacteristics of the population in Hong Kong, thusallowing studies to be undertaken on various facets ofthe community.

This report provides an overview on how the2006 Population By-census was conducted withdetailed descriptions on various aspects fromplanning, to data collection, processing anddissemination. It describes the design, data collection method,operation procedures and techniques of the By-census. It also includesan assessment of the data quality.

This document is Volume II of the two part "Main Report".Volume I presents detailed analysis and interpretation of the resultsof the 2006 Population By-census.

[In Chinese and English]

Quality Assessments of the 2001 census in Portugal

Jan Beise — Mon, 14 Dec 2009 06:01:46 GMT

By Instituto Nacional de Estatística, Portugal, 2003.

This document is a detailed description of the quality evaluation ofthe 14th Population and 9th Housing 2001 Census undertaken by thenational statistics office of Portugal.

[In Portuguese]

POST ENUMERATION SURVEY OF THE 2001 PORTUGUESE POPULATION AND HOUSING CENSUSES

Jan Beise — Mon, 14 Dec 2009 05:59:18 GMT

By P.S. Coelho (Universidade Nova de Lisboa) and F. Casimiro (Instituto Nactional de Estatística, Portugal), 2008.

Within the framework of the quality control and evaluation program forthe Portuguese 2001 Census, the Portuguese statistical office (INE)conducted a Post Enumeration Survey (PES) to measure quality. The mainaims of the PES were to evaluate coverage errors and content errors forthe target populations. The PES is a probabilistic sampling surveyrepresentative at NUTS II level. This paper describes the methodologyfor this survey. The paper includes a discussion of sample size andallocation resulting from the imposition of maximum coefficients ofvariation for a set of variables both at regional and national level.The methodology used to obtain predictions for resident populations anddwellings is also presented. These predictionsare used in the definition of inclusion probabilities for the primarysampling units. The sampling design is finally compared with twoalternative designs (with a smaller number of stages), concluding forthe advantage of the proposed design in regard to the survey goals.

Quality Assessments of the 2008 integrated census – Israel

Jan Beise — Mon, 28 Sep 2009 10:33:00 GMT

By the Central Bureau of Statistics, Israel, 2009.

Census operation and results were evaluated by several quality assessment dimensions. These included Coverage, Accuracy, Consistency, Completeness, Reliability and Validity. The United Nations Economic Commission for Europe publication "Conference of European Statisticians Recommendations for the 2010 Censuses of Population and Housing" lists some quality elements in the three stages of the census process; design, implementation and evaluation. The elements relate to: accuracy, timeliness, accessibility, interpretability and coherence. Israel conducted an integrated census in 2008 with no post enumeration phase since it was assumed that the integrated census with its two samples would provide the necessary information to evaluate the census operations. The evaluation process also took advantage of the fact that the census was an integrated one, which incorporates administrative sources and field operations. The census data collection operation was fully computerized with the use of laptops for data collection and daily data transmission to a central database of collected data. These features made it possible to monitor the field operation with specific tools which took advantage of the technology. To date, the full evaluation process has not yet been completed; it will be completed by the end of 2009. Nevertheless, most of the evaluation elements are completed.

Paper presented at the joint UNECE/Eurostat meeting on Population and Housing Censuses, Geneva, 28-30 October 2009.

The Slovene example how to improve the census count in a register-based census

Jan Beise — Mon, 28 Sep 2009 10:32:00 GMT

By the Statistical Office of the Republic of Slovenia, 2009.

The paper focuses on the two main activities which took place in 2007 and 2008 at the Statistical Office of the Republic of Slovenia in order to improve the census count in the register based Census of Population and Housing in Slovenia in 2011. The first activity was focused on the identification of potential so-called ˝administrative survivors˝ in the Central Population Register (hereinafter CPR) among population aged 80 years or over. The second activity was the introduction of the census usual residence concept in the quarterly population statistics.

Due to the ageing of populations in the developed countries and the increase in the number of the persons aged 80 or over there is a tendency among national statistical institutes to disseminate also the population by the oldest age-groups (90 or more, 100 or more) and even more, to cross-tabulate these age groups with socio-economic topics. It is well known that the uncertainty and unreliability of the population estimates and population counts are higher for the oldest age-groups. Therefore at Slovene national statistical institute the analysis of potential ˝administrative survivors˝ in the age group 80 or over was done in order to improve the quality of the census count at the 2011 register-based census. On the basis of several analyses estimations were made that the centenarians in the quarterly population statistics are overestimated by about 15-20 per cent and the nonagenarians by about 2-3 per cent.

Paper presented at the joint UNECE/Eurostat meeting on Population and Housing Censuses, Geneva, 28-30 October 2009.

Accuracy evaluation of Nuts level 2 hypercubes with the adoption of a sampling strategy in the 2011 Italian Population Census

Jan Beise — Mon, 28 Sep 2009 10:31:00 GMT

By the National Institute of Statistics, Italy, 2009.

Italian National Institute of Statistics (Istat) is considering using sampling techniques in order to adopt a short/long form strategy for the 2011 Italian Population Census. The choice is based on a simple random design for the selection of private household samples from population registers and the calibrated estimators. Because the adoption of a sampling strategy causes the introduction of sampling errors, tests and studies have been conducted in order to evaluate the efficiency of sampling estimates and the accuracy of dissemination hypercubes.

The planning of the 2011 Italian Population Census has taken in account both the critical points of the last census and the possibility to introduce methodological innovations according to the international recommendations. In order to improve the efficiency of the survey operations, to reduce the workload of the municipalities and to minimize the statistical burden for the people involved in the enumeration, many solutions have been taken into consideration. The most important are related to the use of population registers, to a mailing for the census forms and to a mixed mode of data collection mainly based on mail and web.

Introducing sampling strategy in the next Census round implies not only savings and a smaller amount of data to be managed also provides an opportunity to improve the overall quality of data. It will be possible to set up and execute more checks on census forms and follows up in the field to reduce the non-sampling errors. Another advantage of the sampling strategy is improvements to the Census timeliness, which is a constraint since 2011 Census data have to be provided to Eurostat on 1 April 2014.

Paper presented at the joint UNECE/Eurostat meeting on Population and Housing Censuses, Geneva, 28-30 October 2009.

A quantitative approach to the European census quality reporting

Jan Beise — Mon, 28 Sep 2009 10:30:00 GMT

By the Statistical Office of the European Communities, 2009.

The Council of the European Union and the European Parliament adopted in 2008 a regulation on population and housing censuses. For the first time, a European Union (EU) regulation defines the concepts to be used in the census exercises, the topics to be covered and the data sources, and fixes the reference year for the first round on 2011. Further legislative measures – currently under preparation – are foreseen to define the technical specifications and breakdowns of the topics, the programme of statistical data and metadata, the technical format for data transmission, the modalities and structure of the quality reports. The methodological elements of this Regulation acknowledge the Conference of European Statistician (CES)Recommendations for 2010 Round of Population and Housing Censuses.

The Regulation (EC) No 763/2008 attributes great importance to quality issues. Inparticular, it devotes one entire article to the quality assessment, defining its dimensions,prescribing the submission of quality reports from the Member States to Eurostat and stating that"The Commission (Eurostat) shall assess the quality of the data transmitted.” Hence, for the firsttime, the population and housing censuses in the EU will have a formal, structured andcomparable quality reporting. Further, quality shall be assessed and this is a significant stepforward in comparison to simple reporting.

Paper presented at the joint UNECE/Eurostat meeting on Population and Housing Censuses, Geneva, 28-30 October 2009.

The Census Coverage Survey in the UK – the key element of a One Number Census

Jan Beise — Fri, 25 Sep 2009 05:22:00 GMT

By the Office of National Statistics, UK.

The key measure of census quality is the level of response achieved. In recent censuses worldwide this level has been in the high nineties per cent. This was also true of censuses in Britain in 1991 (98 per cent). However, what was particularly noticeable about the census in Britain in 1991 was the differential response rate and the difficulty in effectively measuring this. The One Number Census programme was set up in the UK to research and develop a more effective methodology to measure and account for underenumeration in the 2001 Census. The key element in this process is the Census Coverage Survey – a significantly larger and redesigned post-enumeration survey. This article describes the planning and design of the survey with particular emphasis on the implementation of the proposed field methodology in practice. It also provides a highlevel overview of the success of the survey.

An Estimating Equation Approach to Census Coverage Adjustment

Jan Beise — Tue, 28 Jul 2009 10:26:00 GMT

By Australian Bureau of Statistics, 2007.

A Census Post-Enumeration Survey (PES) is conducted after each Australian Population Census. The PES provides a measure of the net under-count of the Census, and is a key input into the production of the official Estimated Resident Population counts.

This paper describes estimation of net under-count in the context of the 2006 Census and PES. It introduces a new estimator, the prediction regression (PREG) estimator, as an extension of the dual system estimator (DSE) standardly used in estimating Census under-count. In contrast to the DSE, the PREG estimator can use a variety of benchmark variables without the need to form non-overlapping post-strata. It can also adjust appropriately for persons that report different categories in the PES than were recorded in the Census.

Experimentation and Evaluation Plans for the 2010 US Census: Interim Report

Jan Beise — Wed, 15 Apr 2009 11:38:00 GMT

By National Research Council, USA, 2008.

In connection with every recent decennial census, the U.S. Census Bureau has carried out experiments and evaluations. A census “experiment” usually involves field data collection during the census in which alternatives to current census processes are assessed for a subset of the population. An “evaluation” is usually a post hoc analysis of data collected as part of the decennial census processing to determine whether individual steps in the census operated as expected. The Census Bureau program for evaluations and experiments for the 2010 decennial census is referred to as the 2010 CPEX Program.

CPEX, like its predecessor programs, has enormous potential to help improve the next census, which is the federal government’s single most important, and most costly, data collection activity. A well-planned and well-executed CPEX is a sound investment to ensure that the 2020 census is as cost-effective as possible.

The primary purpose of this interim report is to help reduce the possible subjects for census experimentation from an initial list of 52 research topics compiled by the Census Bureau to perhaps 6, which is consistent with the size of the experimentation program in 2000. This interim report also offers broad advice on plans for evaluations of the 2010 census. The panel expects to provide fuller details of individual experiments and evaluations in its subsequentreports.

The Role of Population Estimates and Projections in the Evaluation of Censuses

Jan Beise — Thu, 07 Aug 2008 10:24:00 GMT

By U.S. Census Bureau, 2003

When the results of a new census become available, there may be a tendency to immediately move to the analysis and then use the results as the basis for new yearly estimates as well as longer-term projections of the population. This paper will discuss several reasons why it is a good idea to pause and reflect before abandoning estimates and projections based on an earlier census to be sure that all the lessons learned from the comparison to the new census can be appreciated. We will explore several processes where the comparison of census and population estimates or projections can be useful and also will look at examples of these processes and pose some questions about further research. Our goal is to increase discussion of lessons learned by comparing census results to population estimates and projections.

Paper presented at the 21th Population Census Conference, Analysis of the 2000 Round of Censuses, Kyoto, Japan, 19 - 21 November 2003.

Evaluation of Accuracy of the 2000 Population Census of Japan

Jan Beise — Thu, 07 Aug 2008 09:47:00 GMT

By Statistics Bureau of Japan, 2003

To evaluate the accuracy of the Population Census, the Statistics Bureau of Japan conducts a Post-Enumeration Survey and examines omissions and duplications. It is an attempt to measure indirectly the effectiveness of the various countermeasures adopted for the 2000 Population Census. This paper describes three methods used to evaluate the accuracy of the Population Census: (1) comparison of the Census results with the Basic Resident Registers; (2) age cohort analysis; and (3) analysis of the results of the Post Enumeration Survey.

Paper presented at the 21th Population Census Conference, Analysis of the 2000 Round of Censuses, Kyoto, Japan, 19 - 21 November 2003.

Undercounts in Censuses of Population and Housing

Jan Beise — Thu, 07 Aug 2008 09:12:00 GMT

By Australian Bureau of Statistics, 2006

Whenever a Census is undertaken, questions about the completeness and accuracy of the Census count invariably arise. In such a large and complex exercise, it is inevitable that some people will be missed (undercount) and some will be included more than once (overcount).

This publication presents estimates of net undercount for the 2006 Census in Australia, as well as information on how the estimates were calculated.

Evaluating Censuses of Population and Housing

Jan Beise — Tue, 05 Aug 2008 04:38:00 GMT

Document by the U.S. Bureau of Census

The purpose of this manual is to describe methods and techniques for the evaluation of censuses of population and housing, with emphasis on techniques with are applicable in developing countries. The manual is intended for use as a basic reference in the design and implementation of census evaluation program. As such, the rationale and theory behind each method and some of the major porblems encountered in its application are covered in sufficient detail so as to guide key decision-makers and technicians of developing country statistical organizations in designing and implementing their own evaluation programs.

The approaches chosen for emphasis in the manual are: (1) the use of post-enumeration surveys (PES), and (2) the use of demographic methods, particularly those based upon the analysis of two or more successive censuses. Other approaches to census evaluation are also described in the manual but are considered in less detail.

U.S. Bureau of the Census. Evaluating Censuses of Population and Housing. Statistical Training Document, ISP-TR-5, Washington D.C., 1985.

[Please note: The document is saved as external link]

An overview of Editing and Imputation methods for the next Italian Censuses

Jan Beise — Fri, 23 May 2008 09:51:00 GMT

Paper by National Institute of Statistics of Italy

The National Institute of Statistics of Italy is preparing the next Population and Housing Censuses that will be held on 2011. In this paper, a short description of the main editing procedures for the 2011 Census is given. The impact of some likely census innovations on the editing and validation is also reviewed.

Paper presented at the Joint UNECE/Eurostat Meeting on Population and Housing Censuses, Geneva, 13-15 May 2008.

[Paper also available in French and Russian]

Validation of census data in France

Jan Beise — Fri, 23 May 2008 09:49:00 GMT

Paper by National Institute for Statistics and Economic Studies, France

This document describes the procedures developed by the National Institute for Statistics and Economic Studies for the validation of census data in France. It sets out the method adopted for calculating the population of a given district, followed by the validation procedures applied to all the data sources used in calculating the population of a district.

Paper presented at the Joint UNECE/Eurostat Meeting on Population and Housing Censuses, Geneva, 13-15 May 2008.

[Paper also available in French and Russian]

Census Quality Evaluation: Considerations from an international perspective

Jan Beise — Thu, 22 May 2008 10:10:00 GMT

Paper by by Bernard Baffour and Paolo Valente (UNECE)

Regardless of the methodology used and of the measures that can be taken to assure the best quality, the population census cannot be a perfect operation and there will always be some errors affecting the quality of the census results in terms of coverage and content. For this reason, the agencies responsible for the census should always conduct an evaluation of the quality of the census and provide an assessment of the census coverage and content errors. This is particularly important considering the huge resources invested in the census and the key role played by the census results for the national statistical systems and as primary source of statistical data for the countries. Measuring the census quality, however, is not an easy task, in particular when non-traditional census methods are adopted, for which established census evaluation techniques like the Post Enumeration Survey cannot be applied. In this paper, some issues concerning census quality evaluation are discussed for each of the most common census methodologies,considering the implications on the different dimensions of quality. Some considerations are also presented on census quality evaluation from an international perspective, and on the role that InternationalOrganisations can play in this field.

Paper presented at the Joint UNECE/Eurostat Meeting on Population and Housing Censuses, Geneva, 13-15 May 2008.