How to deal with quality aspects in estimating national results Annalisa Pallotti Short Term Expert Asa 3st Joint Workshop on Pesticides Indicators Valletta.

Slides:



Advertisements
Similar presentations
Innovation data collection: Advice from the Oslo Manual South East Asian Regional Workshop on Science, Technology and Innovation Statistics.
Advertisements

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.
Statistics for Improving the Efficiency of Public Administration Daniel Peña Universidad Carlos III Madrid, Spain NTTS 2009 Brussels.
Module B-4: Processing ICT survey data TRAINING COURSE ON THE PRODUCTION OF STATISTICS ON THE INFORMATION ECONOMY Module B-4 Processing ICT Survey data.
“... providing timely, accurate, and useful statistics in service to U.S. agriculture.” Using Mixed Methods to Evaluate Survey Questionnaires Heather Ridolfo,
Copyright 2010, The World Bank Group. All Rights Reserved. Agricultural Data Collection Procedures Section A 1.
The estimation strategy of the National Household Survey (NHS) François Verret, Mike Bankier, Wesley Benjamin & Lisa Hayden Statistics Canada Presentation.
Deliverable 2.8: Outliers Gary Brown Office for National Statistics UK.
Quality assurance -Population and Housing Census Alma Kondi, INSTAT, Albania.
National Institute for Statistics and Geography (INEGI) is, from 2008, an autonomous institute in Technical and Managing matters. According to Mexican.
Survey Design Steps in Conducting a survey.  There are two basic steps for conducting a survey  Design and Planning  Data Collection.
NLSCY – Non-response. Non-response There are various reasons why there is non-response to a survey  Some related to the survey process Timing Poor frame.
Documentation and survey quality. Introduction.
Aaker, Kumar, Day Ninth Edition Instructor’s Presentation Slides
Chapter Three Research Design.
Multiple Indicator Cluster Surveys Data Interpretation, Further Analysis and Dissemination Workshop Overview of Data Quality Issues in MICS.
FINAL REPORT: OUTLINE & OVERVIEW OF SURVEY ERRORS
MICS Data Processing Workshop Multiple Indicator Cluster Surveys Data Processing Workshop Data Quality Tables.
Arun Srivastava. Types of Non-sampling Errors Specification errors, Coverage errors, Measurement or response errors, Non-response errors and Processing.
Power Point Slides by Ronald J. Shope in collaboration with John W. Creswell Chapter 13 Survey Designs.
Eurostat Statistical Data Editing and Imputation.
Copyright 2010, The World Bank Group. All Rights Reserved. Estimation and Weighting, Part I.
State Plant Protection Service 26 September 2007 ISTAMBUL 2005 Transition Facility Programme PESTICIDES USE SURVEY IN LITHUANIA Danguolė Krepštulienė,
Nonresponse issues in ICT surveys Vasja Vehovar, Univerza v Ljubljani, FDV Bled, June 5, 2006.
Chapter Nine Copyright © 2006 McGraw-Hill/Irwin Sampling: Theory, Designs and Issues in Marketing Research.
Q2010, Helsinki Development and implementation of quality and performance indicators for frame creation and imputation Kornélia Mag László Kajdi Q2010,
United Nations Regional Workshop on the 2010 World Programme on Population and Housing Censuses: Census Evaluation and Post Enumeration Surveys Bangkok,
Exploratory Research Design Week 02
Research Design.
Brown, Suter, and Churchill Basic Marketing Research (8 th Edition) © 2014 CENGAGE Learning Basic Marketing Research Customer Insights and Managerial Action.
Chap 1-1 Statistics for Managers Using Microsoft Excel ® 7 th Edition Chapter 1 Defining & Collecting Data Statistics for Managers Using Microsoft Excel.
European Conference on Quality in Official Statistics Session 26: Quality Issues in Census « Rome, 10 July 2008 « Quality Assurance and Control Programme.
1 Dealing with Item Non-response in a Catering Survey Pauli Ollila Statistics Finland Kaija Saarni Finnish Game and Fisheries Research Institute Asmo Honkanen.
USING THE METADATA IN STATISTICAL PROCESSING CYCLE – THE PRODUCTION TOOLS PERSPECTIVE Matjaž Jug, Pavle Kozjek, Tomaž Špeh Statistical Office of the Republic.
Using administrative registers in sample surveys European Conference on Quality in Official Statistics 3-–6 May 2010 Kaja Sõstra Statistics Estonia.
Copyright 2010, The World Bank Group. All Rights Reserved. Managing Data Collection Section A 1.
MGT-491 QUANTITATIVE ANALYSIS AND RESEARCH FOR MANAGEMENT OSMAN BIN SAIF Session 5.
SEMESTER 1 FINAL EXAM REVIEW Vocabulary Review (All Gathering Data Vocabulary)
Quality Assurance Programme of the Canadian Census of Population Expert Group Meeting on Population and Housing Censuses Geneva July 7-9, 2010.
1 C. ARRIBAS, D. LORCA, A. SALINERO & A. COLMENERO Measuring statistical quality at the Spanish National Statistical Institute.
Developing and applying business process models in practice Statistics Norway Jenny Linnerud and Anne Gro Hustoft.
ICON-Institute Public Sector1 The project “Pesticide indicators” and the use of PPP’s in the context of the new Regulation on PPPs Riga, July 2007.
Sampling Design and Analysis MTH 494 Ossam Chohan Assistant Professor CIIT Abbottabad.
Transition Facility Multi-Beneficiary Statistical Co-operation Programme 2005 Lot 2: Pesticide Indicators Survey on Pesticide Use on Wheat Crops.
Pesticide use survey in Lithuania 2007 PESTICIDES USE SURVEY IN LITHUANIA SURVEY CROP – WINTER WHEAT Danguolė Krepštulienė, Statistics Lithuania Darius.
2nd Joint Workshop on Pesticide Indicators Pesticide Usage Survey on Wheat in Hungary Zsuzsanna Szabó Hungarian Central Statistical Office September.
First meeting of the Technical Cooperation Group for the Population and Housing Censuses in South East Europe Vienna, March 2010 POST-ENUMERATION.
PRIME MINISTRY REPUBLIC OF TURKEY TURKISH STATISTICAL INSTITUTE Agriculture and Environmental Statistics Department Agricultural Statistics Group 1 IMPLEMENTATION.
Chapter Fourteen Data Preparation 14-1 Copyright © 2010 Pearson Education, Inc.
1 Handbook on Population and Housing Census Editing Department of Economic and Social Development United Nations Statistics Division Studies in Methods,
Rudi Seljak, Aleš Krajnc
Sampling: Theory and Methods
Statistics and Research Desgin
An Active Collection using Intermediate Estimates to Manage Follow-Up of Non-Response and Measurement Errors Jeannine Claveau, Serge Godbout and Claude.
Survey phases, survey errors and quality control system
Sample surveys versus business register evaluations:
ESTP COURSE ON PRODCOM STATISTICS
Goals and objectives of Work package 2 of the ESSnet on Consistency of concepts and applied methods of business and trade-related statistics Norbert Rainer,
Survey phases, survey errors and quality control system
The European Statistical Training Programme (ESTP)
The main results of the Pesticides Survey
3rd Joint Workshop on Pesticide Indicators
Session 4 – From pilot to regular surveys: the costs aspects Introduction: cost impact of possible design strategies Malta, January 2008 Transition.
Workshop on Pesticide Indicators
Lot 2: Agricultural and Environmental Statistics
Automatic Editing with Soft Edits
Training course on developing and using questionnaires for agricultural surveys Field Testing Post evaluation methods Marco Ballin Istanbul, July.
Errors in Surveys Training Course «Quality Management and
ICON-Institute Public Sector
Presentation transcript:

How to deal with quality aspects in estimating national results Annalisa Pallotti Short Term Expert Asa 3st Joint Workshop on Pesticides Indicators Valletta - Malta January 2008 Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics

Valletta, Malta January 200Annalisa Pallotti 1. Dimension of quality 2. Most important aspects 3. How to deal with aspects Contents of presentation Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics

Valletta, Malta January 200Annalisa Pallotti This system is the sum of different actions, finalized to treat the non sampling errors. It is possible to summarize this actions in 3 important phases: Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Dimension of quality

Valletta, Malta January 200Annalisa Pallotti QUALITY ASPECTS Preventing actions Actions to estimate the non sampling errors Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Actions during the survey

Valletta, Malta January 200Annalisa Pallotti Non-sampling error is the error attributable to all sources other than sampling error. Non-sampling errors arise during the planning, conducting, data processing and final estimation stages of all types of survey. Non sampling errors Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Preventing actions PLANNING THE SURVEY  Characteristics and reference period  Questionnaire- an important role in developing the questionnaire is played by experts  Survey organization – training of interwievers  Population and frame  Sampling design

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Actions during the survey Sampling, data collection and data entry  Drawing the sample  Data collection  Data entry Data control

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Actions during the survey Data collection: What kind of control we do during data collection? 1.Interviewer (face to face or telephone) 2.List of PPP 3.Comparare data with administrative source

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Actions during the survey After data collection and before data processing the following control phases has to be performed:  Controls by interviewers coordinator  Controls during data entry

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Actions during the survey Controls by interviewers coordinator In this phase the main controls are following: 1.Presence of data in corresponding section 2.Code of the interviewer 3. Main coherence among different section of questionnaire 4.Presence of notes for non-respondent units If some important inconsistencies are found by the supervisor, it is performed a telephone check

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Actions during the survey Controls during data entry In this phase the main controls are automatic control performed by the computer system Example: area cultiveted >= area treated

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Actions during the survey Non – response the non response problem can be summarized as follows : 1. Partial non -response (method of imputation depends on the type of farms and on type of variable to be imputed) 2. Total non response (unit non-response problem is faced by reweighting the respondent units).

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Actions to estimate the non sampling errors 1.Methods for handling missing or incorrect data items 2.Methods of estimation 3.Evaluation of estimates

Valletta, Malta January 200Annalisa Pallotti Two approaches are used to handle missing or incorrect data items: 1. The first approach is used to face the problem for influent farms (usually the big farms). In these case two actions: a comparison between collected data and administrative data (if available); a telephone check performed by survey staff 2. The second approach is used for the other farms (usually small farms) and it consists of 2 stage, summarized as follows: Methods for handling missing or incorrect data items Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics FIRST PHASE ERROR LOCALIZATION Systematic and deterministic errors Deterministic approach Editing approach combined with grafical data rappresentation (Latouche at al.1992) Editing approach combined with grafical data rappresentation (Latouche at al.1992) Influential outliers

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics FIRST PHASE ERROR LOCALIZATION Non influential outliers random origin Probabilistic Approach (Fellegi and Holt, 1976) Probabilistic Approach (Fellegi and Holt, 1976)

Valletta, Malta January 200Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics SECOND PHASE CORRECTION AND IMPUTATION Both interactive treatment (for outliers and influential errors) and authomatic approach are used Both interactive treatment (for outliers and influential errors) and authomatic approach are used

Valletta, Malta January 200Annalisa Pallotti preliminary quantitative check of the collected questionnaires; Identification and correction of influential errors with respect to the main quantitative variables. To summarize the methods for handling missing or incorrect data items Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics

Valletta, Malta January 200Annalisa Pallotti The survey estimates of total for national domain is produced using the following estimator: Where s r,d is the set of respondent, w k is the final weight of unit k and y k. is the variable of interest. The final weights will be obtained as a product of three factors:. Methods of estimation Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics

Valletta, Malta January 200Annalisa Pallotti Where d k = 1/ k is the sampling weight. The second factor, y 1k, is computed as the inverse of the response rate on each stratum. The third factor, y 2k, is used to achieve the consistency of sample estimates with respect to some known totals of the population. It is computed using the calibration theory explained in Estevao, Hidiroglou and Särndal (1995). Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics Methods of estimation

Valletta, Malta January 200Annalisa Pallotti The results has to be compared with other statistical and administrative source available. For example, the results of PPP’s use can be compared with PPP’s distributed on the market, or can be compared with specific results of organizations Evaluation of the results Annalisa Pallotti Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics

Valletta, Malta January 200Annalisa Pallotti THANK YOU FOR THE ATTENTION! Multi-Beneficiary statistical Co-operation Programme for Bulgaria, Croatia, Romania and Turkey 2005 Lot 2: Agricultural and Environmental Statistics