Ph. Brion Insee The contribution of different ways of dealing with non-responses in french business surveys.

Slides:



Advertisements
Similar presentations
Implementation of 2008 SNA in Jamaica. Outline Policy issues - relationship with national accounts framework The Jamaican System of National Accounts.
Advertisements

Annual growth rates derived from short term statistics and annual business statistics Dr. Pieter A. Vlag, Dr. K. van Bemmel Department of Business Statistics,
Innovation data collection: Methodological procedures & basic forms Regional Workshop on Science, Technology and Innovation (STI) Indicators.
Innovation data collection: Advice from the Oslo Manual South East Asian Regional Workshop on Science, Technology and Innovation Statistics.
Innovation Surveys: Advice from the Oslo Manual South Asian Regional Workshop on Science, Technology and Innovation Statistics Kathmandu,
Innovation Surveys: Advice from the Oslo Manual National training workshop Amman, Jordan October 2010.
Catherine Renne Insee Measuring sampling error in business surveys The case of the French monthly industry survey.
ECONOMIC STATISTICS AND NATIONAL ACCOUNT IN ETHIOPIA By Sehin Merawi Central Statistical Agency of Ethiopia.
Sampling Strategy for Establishment Surveys International Workshop on Industrial Statistics Beijing, China, 8-10 July 2013.
Enhancing Data Quality of Distributive Trade Statistics Workshop for African countries on the Implementation of International Recommendations for Distributive.
QBM117 Business Statistics Statistical Inference Sampling 1.
Turnover in the Wholesale Trade Jonas Färnstrand Statistics Sweden
STAT262: Lecture 5 (Ratio estimation)
A new sampling method: stratified sampling
Report Preparation. Write to the audience  Who is the audience  What are its objectives and expectations  When there are two or more audiences use.
1 Marketing Research Aaker, Kumar, Day Ninth Edition Instructor’s Presentation Slides.
Trade and business statistics: use of administrative data Lunch Seminar Enrico Giovannini Italian National Statistical Institute (ISTAT) New York, February,
Seminar on Developing a Programme on Integrated Statistics in the Caribbean Saint Lucia The Components of an Integrated Business and International Statistics.
1 Lao Practices in Measuring Production of Manufacturing International Workshop From Data to Accounts: Measuring Production in National Accounting, Beijing,
Arun Srivastava. Types of Non-sampling Errors Specification errors, Coverage errors, Measurement or response errors, Non-response errors and Processing.
Combining administrative and survey data: potential benefits and impact on editing and imputation for a structural business survey UNECE Work Session on.
1 Development and Application of Statistical Business Registers in Africa Key findings Besa Muwele Besa Muwele Michael Colledge Michael Colledge 9th African.
Chapter 13: Inference in Regression
Electronic reporting in Poland 27th Voorburg Group Meeting Warsaw, Poland October 1st to October 5th, 2012 Central Statistical Office of Poland.
Chapter 7. Balancing supply and use Comments and suggestions. By Liv Hobbelstad Simpson. 1. Why SNA 1993 and not 2008 SNA The Global Office has decided.
Copyright 2010, The World Bank Group. All Rights Reserved. Estimating informal production, part 2 1 Business statistics and registers.
Joint UNECE/Eurostat Meeting on Population and Housing Censuses (28-30 October 2009) Accuracy evaluation of Nuts level 2 hypercubes with the adoption of.
Copyright 2010, The World Bank Group. All Rights Reserved. Estimation and Weighting, Part I.
Sampling: Theory and Methods
1 Workshop on Informal Employment and Informal Sector Data Collection: Strategy, Tools and Advocacy Amman, April 2008 Phase2: Sample design, measurement.
Rudi Seljak, Metka Zaletel Statistical Office of the Republic of Slovenia TAX DATA AS A MEANS FOR THE ESSENTIAL REDUCTION OF THE SHORT-TERM SURVEYS RESPONSE.
African Centre for Statistics United Nations Economic Commission for Africa Chapter 6: Chapter 6: Data Sources for Compiling SUT Ramesh KOLLI Senior Advisor.
The Statistical Business Register of Macao SAR Government of Macao SAR Statistics and Census Service.
Marketing Research Aaker, Kumar, Day Seventh Edition Instructor’s Presentation Slides.
Chap 20-1 Statistics for Business and Economics, 6e © 2007 Pearson Education, Inc. Chapter 20 Sampling: Additional Topics in Sampling Statistics for Business.
Chapter Twelve Census: Population canvass - not really a “sample” Asking the entire population Budget Available: A valid factor – how much can we.
Integrating administrative and survey data in the new Italian system for SBS: quality issues O. Luzi, F. Oropallo, A. Puggioni, M. Di Zio, R. Sanzo Nurnberg,
Use of Administrative Data in Statistics Canada’s Annual Survey of Manufactures Steve Matthews and Wesley Yung May 16, 2004 The United Nations Statistical.
A generic tool to assess impact of changing edit rules in a business survey – SNOWDON-X Pedro Luis do Nascimento Silva Robert Bucknall Ping Zong Alaa Al-Hamad.
Quality issues on the way from survey to administrative data: the case of SBS statistics of microenterprises in Slovakia Andrej Vallo, Andrea Bielakova.
1 Measuring the Agriculture indicators in South Africa Presentation to the ICAS IV 2007 conference delegates Lessons learned from the 2002 Census of Commercial.
Eurostat Overall design. Presented by Eva Elvers Statistics Sweden.
Q20101 National accounts revisions: Italian manufacturing productivity analysis Alessandro Faramondi Istat – National Statistical Institute.
Research Methodology Lecture No :14 (Sampling Design)
Copyright 2010, The World Bank Group. All Rights Reserved. Business tendency surveys, part 2 1 Business statistics and registers.
A Strategy for Prioritising Non-response Follow-up to Reduce Costs Without Reducing Output Quality Gareth James Methodology Directorate UK Office for National.
Stop the Madness: Use Quality Targets Laurie Reedman.
Using administrative registers in sample surveys European Conference on Quality in Official Statistics 3-–6 May 2010 Kaja Sõstra Statistics Estonia.
Small-area estimation in Official Statistics: ICT survey in Enterprises of the Basque Country Jorge Aramendi, Jose Miguel Escalada, Elena Goni & Anjeles.
Sampling Error Estimation – SORS practice Rudi Seljak, Petra Blažič Statistical Office of the Republic of Slovenia.
© Federal Statistical Office, Institute for Research and Development in Federal Statistics, Elmar Wein Federal Statistical Office Introducing and implementing.
Chapter 9 Introduction to the t Statistic. 9.1 Review Hypothesis Testing with z-Scores Sample mean (M) estimates (& approximates) population mean (μ)
Chapter Thirteen Copyright © 2004 John Wiley & Sons, Inc. Sample Size Determination.
Olivier Haag Helsinki - Q2010 Reengineering French structural business statistics: redesign of the annual survey.
Improving of Household Sample Surveys Data Quality on Base of Statistical Matching Approaches Ganna Tereshchenko Institute for Demography and Social Research,
Multivariate selective editing via mixture models: first applications to Italian structural business surveys Orietta Luzi, Guarnera U., Silvestri F., Buglielli.
Quality Analysis in a Survey on Transportation of Goods by Road Juris Breidaks University of Latvia Central Statistical Bureau of Latvia.
SA Economic Indicators: for the month of May 2013.
Trade Margins Johan Åhman Statistics Sweden
Ph. Brion Insee Redesigning French structural business statistics: first methodological studies Bonn, september 2006.
Marketing Research Aaker, Kumar, Day and Leone Tenth Edition Instructor’s Presentation Slides 1.
Random Sampling Error and Sample Size are Related
Redesigning French structural business statistics, using more administrative data ICESIII, Montréal, june 2007.
CHAPTER 29: Multiple Regression*
ESTP – Course Structural Business Statistics
Zsófia Ercsey - KSH – Hungary Marie-Madeleine Fuger - INSEE – France
Sampling and estimation
Methodological questions raised by the combined use of administrative and survey data for the French structural business statistics Work session on statistical.
ECONOMIC CLASSIFICATIONS Advanced course Day 2 – first morning session Statistical units and classification rules Zsófia Ercsey - KSH – Hungary Marie-Madeleine.
Presentation transcript:

Ph. Brion Insee The contribution of different ways of dealing with non-responses in french business surveys

Page 2 Introduction  The lecture will focus on annual enterprise surveys  For a general presentation of these surveys, see Rivière (Courrier des statistiques, 1997), particularly for the data editing method  Main subject of the lecture : the question of the timeliness (business surveys are mail surveys) and of the follow-up of non-respondents

Page 3 The treatment of non-responses  Sampling plan of the annual enterprise surveys : sampled strata (small and medium enterprises), exhaustive strata (big enterprises)  Non-responses : first, remind letters / visits of enumerators, depending on the size of the units  In the end, the treatment of « final » non-responses is also different according to the size of the enterprises  Small and medium enterprises : use of conventional statistical technics  Big enterprises : use of fiscal data (less complete than survey data)

Page 4 Two kinds of questions  1. Is it possible to define priorities for the follow-up of the non-respondents ? Is it possible to decide to publish some results, with given rates of responses ?  2. Generally, the estimation of the error is made, for the exhaustive part, as it was zero : is this approximation acceptable in this case ?  Use of a « framework » to quantify the amount of error due to each of the two categories of enterprises

Page 5 Formalizing the problem (1) : estimator used for small and medium entreprises

Page 6 Formalizing the problem (2) : estimator used for small and medium enterprises  Estimator of the total of a variable as the turnover of a given domain (economic sector), due to the stratum k :

Page 7 Formalizing the problem (3) : estimator used for big enterprises

Page 8 Formalizing the problem (4) : estimator used for big enterprises  For the big enterprises non-respondents, we get the value of the turnover in the fiscal source, and use the value of the APE (principal activity) code of the business register (approximation) : the estimator of the total of turnover due to the stratum h (for a given domain) is :

Page 9 Formalizing the problem (5) : estimator of the total (calculated on the two categories: small and medium, and big enterprises)  Sum on all strata (h and k)  Wrong classifying of some big enterprises introduces a bias  The two categories (small and medium, and big enterprises) give variance

Page 10 Formalizing the problem (6) : total mean square error  With :  And : is the « corrected » variance of

Page 11 Use of these indicators  During the execution of the survey : use of the values of A h, B h, S k calculated the previous year to decide to publish results for a given domain, by comparing the value of the mean square error to an expected level  « Remind strategy » : introducing cost elements : C1 = remind for a small or medium enterprise C2 = visit for a big enterprise  Minimize mean square error with a budget constraint

Page 12 First quantified results for the wholesale trade sector, variable = turnover ClassPrecision (coefficient of variation) Non-responses rate for big enterprises « Stability » rate for big enterprises Fee or contract basis 0.9%13%96.6% Agricultural raw materials, live animals 11%8%99.3% Food, beverages, tobacco 1.2%11%98.5% Household goods 2.4%14%97.2% Intermediate products 1.4%12%97.5% Machinery, equip., supplies 1.8%10%97.9% Other wholesale 7.8%16%98.3%

Page 13 First quantified results for the wholesale trade sector, variable = turnover ClassShare of the first term (square of bias) Share of 2nd term (variance big enterprises) Variance small medium enterprises Fee or contract basis 3%2.7%94.3% Agricultural raw materials, live animals --100% Food, beverages, tobacco 1.2%4.3%94.5% Household goods 1.4%1.3%97.3% Intermediate products 6%0.5%93.5% Machinery, equip., supplies -0.1%99.9% Other wholesale 0.6%7.1%92.3%

Page 14 Conclusion, further developments  Back to hypotheses  Further developments for other variables  Within the population of big enterprises, there are differences …  For small and medium enterprises, refine the treatment of non-respondents with the use of fiscal infra-annual data