the quality of the population census in france n.
Skip this Video
Loading SlideShow in 5 Seconds..
The quality of the population census in France PowerPoint Presentation
Download Presentation
The quality of the population census in France

The quality of the population census in France

202 Vues Download Presentation
Télécharger la présentation

The quality of the population census in France

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

  1. The quality of the population census in France Olivier Lefebvre, Insee

  2. Plan of the presentation • Short brief about french census • The management of the census quality • General principles • Sampling frames • Data collection • Data processing • Dissemination

  3. The method of the new census • Two major principles • Data collection in rotation (annual surveys) • Resorting to sample surveys for large communes (more than 10000 inhabitants) • The sampling base:the located buildings register (répertoire d’immeubles localisés - RIL) • Special case of persons not living in ordinary dwellings (institutions, homeless people, nomads)

  4. The proceedings of the census survey • The same modus operandi as in 1999 for the habitants : deposit-withdrawal of the questionnaires by the enumerator • A « non surveyed dwelling form » (called FLNE in french) in case of impossibility of contacting people or refusal

  5. The questionnaires • The dwelling data sheet • The individual bulletin

  6. Year N-1 Year N Juin Jui. Août Sep. Oct. Nov. Déc. Jan Fév. Mar Avril Mai Juin Jui. Août Sep. Nov. Déc. Jan The schedule of a campaign Oct. RIL Expertise Sampling Setting-up of organisation Preparation Training Communication Collection Reception Controls Data processing Dissemination

  7. Evaluation Campaign Improvements The management of the census quality • A continuous evaluation approach • Enabled through the annual feature of the operation • Based on systematic overall results

  8. The national commission for the evaluation of the census • Under the rule of the CNIS (National Council for Statistical Information) • Presided over by a senator • It associates communes, the data users (researchers, administrations, municipalities), the Insee • It enables an exchange on data collection, control protocols, useful in improving the processes • It must give an opinion on the texts governing the organisation of the census

  9. The management of quality, process by process • Sampling frames • Data collection • Data processing • Dissemination

  10. Sampling frames • The « quality » survey of the RIL • An annual survey to assess • The surpluses and the deficits • The surplus-deficit balance • The proportion of communes for which the quality is deemed mediocre • The sample : 190 000 addresses and 520 000 dwellings • The results • 0.9 % of dwellings in deficit, 1.4 % in surplus • one commune out of eight beyond 2.5% of deficit • A level of quality higher than that of usual geographical registers • A regular improvement process

  11. Sampling frames (2) • The action plans • To improve the quality of the RIL with targetted operations • Decided and implemented by the Regional Directorates in relation with the communes • As a function of the strong points and the weak points detected locally • Training of communes, fieldwork… • Allowing for an operational management of quality because targetted on specific problems and based on the closeness between the regional teams and the communes • The future efforts: reduce the surpluses and arrive at level surplus-deficit balance

  12. Data collection • The control procedures during the data collection • The follow-up and control upon the initiative of the communes • The controls at the Insee after the data collection (reception-control, in office control, controls in the field)

  13. The control procedure during data collection • A precise data collection protocol • Checked by the municipal officer • And by the supervisor

  14. Follow-up and control system upon the initiative of the communes • Upstream from the data collection • Validation of the sample • Control-validation of the field to be observed carried-out by the enumerator • Follow-up of the data collection • Follow-up of the progress of work of the enumerator • Follow-up of key indicators : FLNE, vacant dwellings, quality of the log book of the tour-visits

  15. The controls at the Insee after data collection • Successive « sorting » • The step of reception-registering of the questionnaires • Establishment of indicators • Communes with insufficient scores subject to in-depth control (approx. 10% of the communes) • Desk controls • Verification with the help of the housing Tax files • On the exhaustiveness of the dwellings, the FLNE, the structure of main/not main residence • In field controls

  16. The in-field controls • They are done by Insee agents • They relate to the communes whose quality is presumed insufficient • Most often, they confirm the data collection • The errors detected are corrected • N.B. these controls are not representative, therefore their results cannot be extrapolated

  17. The in-field controls 23 500 controls of dwellings Of which: 2 800 in the communes of more than 10 000 inhabitants  30 000 in-field controls 6 400 controls of addresses Of which: 3 600 in the communes of less than 10 000 inhabitants 500 controls by telephone

  18. Zoom on controls of dwellings 85 % : verification of a FLNE 9 % : verification of a main residence 6 % : verification of secondary residence, vacant dwelling or occasional dwelling

  19. Results of controls of FLNE • In 85% of the cases, the household enumerator finds the information • Most often, the FLNE does concern a main residence and the number of persons is correctly estimated • In 10 % of the cases, FLNEs have been wrongly provided (for non-main residences)

  20. Data processing • Data input • Quality criteria specifically defined in the specifications • securing of transports and data • maximum rate of error by category of variables • Control of discrepancies by « flashage » • … and evaluated by an independent control process (sample that has been input twice and arbitration)

  21. Data processing (2) • Encoding • Quality control work station for : • Assessing the quality of the automatic coding and manual correction • Estimating a « threshold » of percentage of bulletins « non codable » • The contributions of this approach : • adding to the expert systemfiles • the improvement of training and protocols (precisions added in codification rules) • A finer management of quality, without going in for « excess quality »

  22. Data processing (3) • Data editing and imputation • Anayse the share of non responses or incoherent responses • Imputation of missing data or data presumed non-coherent (hot-deck procedure) • They are fine-tuned year after year, in view of the quality of the variables produced

  23. Dissemination • A step prepared with the users • Define with them the products and services : two groups of the CNIS • Assess their satisfaction : groups of the CNIS and satisfaction surveys • A systematic validation of the data before dissemination • At the national level and in each regional directorate

  24. Any questions ?