Sample Issues and Field Work
Session VLusaka, January 20, 2003Juan Munoz and Francesca Recanatiniwww.worldbank.org/wbi/governance
Motivation
The team has defined:The purpose of the assessmentThe variables to studyThe empirical tool to useThe process to employ
But, who should be targeted?
Basic Definitions
Sampling allows to measure characteristics of a population, when accessing the whole population is not possible because of economic, practical or physical considerations.
Sampling allows to select a subset of a population to study a specific issue in a meaningful way
Basic Definitions
Population: the sum of all the observations within a specified setTarget population: all statistical units of interest for the purposes of analysis Working population: all statistical units that can be surveyed
Basic Sampling Techniques
The three basic techniques of probability sampling:
Simple Random SamplingMulti-stage SamplingStratified Sampling
Most household and firm surveys use a combination of these three techniques.
Assuring good field work
What happens when fieldwork is poor?
A long and frustrating process of “data cleaning” becomes unavoidable
The data loose their policy-making relevance
Data quality is not guaranteed
The process converges (at best) to databases that are internally consistent
The process entails a myriad of decisions, generally undocumented
Users mistrust the data
Key factorsManage the survey as an integrated projectImplement the team concept in the organization of field operationsIntegrate computer-based quality controls to field operationsEstablish strong supervision proceduresEnsure sufficient trainingWork with a reduced staff over an extended period of data collection
Management levels
Core staffSurvey managerField operations managerData manager
Tactical options for the organization of field teams
Mobile teams with fixed data entryMobile teams with integrated data entrySometime in the future: the paperless interview
Mobile teams with fixed data entry
Cote d’Ivoire (1984)Peru (1985)GhanaPakistanGuinea-ConakryMozambique
Composition of a field team
Supervisor Interviewers Data entry
operator
The team and its tools
Supervisor Interviewers Data entryoperator
Antropo-
metrist
Two PSUs visited in a four-week period
Alama Bamako
Regional Office
First weekAlama Bamako
Regional Office
Operator remains in Regional
Office
Rest of the team
travels to Alama
First weekAlama Bamako
Regional Office
Operator remains in Regional
Office
Rest of the team
travels to Alama
First weekAlama
Bamako
Regional Office
Operator remains in Regional
Office
Rest of the team
travels to Alama
First weekAlama
Bamako
Regional Office
Operator remains in Regional
Office
Rest of the team
travels to Alama
First weekAlama
Bamako
Regional Office
Operator remains in Regional
Office
Rest of the team
travels to Alama
First weekAlama Bamako
Regional Office
Operator remains in Regional
Office
Rest of the team
travels to Alama
They complete
first half of questionnair
es in all selected
households
First weekAlama Bamako
Regional Office
Operator remains in Regional
Office
Rest of the team
travels to Alama
First weekAlama Bamako
Regional Office
Operator remains in Regional
Office
Rest of the team
travels to Alama
First weekAlama
Bamako
Regional Office
Operator remains in Regional
Office
Rest of the team
travels to Alama and
back
First weekAlama Bamako
Regional Office
Supervisor gives Alama questionnair
es to DEO
Rest of the team
travels to Alama and
back
Second weekAlama
Bamako
Regional Office
Operator enters first
week data from Alama
Rest of the team
travels to Bamako
Second weekAlama
Bamako
Regional Office
Operator enters first
week data from Alama
Rest of the team
travels to Bamako
Second weekAlama
Bamako
Regional Office
Operator enters first
week data from Alama
Rest of the team
travels to Bamako
They complete
first half of questionnair
es in all selected
households
Second weekAlama
Bamako
Regional Office
Operator enters first
week data from Alama
Rest of the team
travels to Bamako and back
Second weekAlama
Bamako
Regional Office
Supervisor gives
Bamako questionnaires to DEO. DEO gives
back Alama questionnair
es with flagged
inconsistencies
Rest of the team
travels to Bamako and back
Third weekAlama
Bamako
Regional Office
Operator enters first week data from Bamako
Team completes second half of
questionnaires. They correct
inconsistencies from first half
Fourth weekAlama Bamako
Regional Office
Operator enters second week data
from Alama. Corrects
inconsistencies from first round
Team completes second half of
questionnaires. They correct
inconsistencies from first half
Fourth week
Regional Office
The result is a clean data set on
diskette, ready for analysis
immediately after data collection
Mobile teams with integrated data entry
Nepal (1992)ArgentinaParaguayBangladesh (2000)
Mobile teams with integrated data entry
Regional Office
Alama
Bamako
Cocody
Team works with portable
computers and printers
Mobile teams with integrated data entry
Regional Office
Alama
Bamako
Cocody
Operator travels with the rest of the field team
Mobile teams with integrated data entry
Regional Office
Alama
Bamako
Cocody
Data entry and validation almost
immediate
Mobile teams with integrated data entry
Regional Office
Alama
Bamako
Cocody
Reduced trips to and from
Regional Office to selected PSUs
Mobile teams with integrated data entry
Regional Office
Alama
Bamako
Cocody
Benefits of integrationProvides reliable and timely databasesProvides immediate feedback on the performance of the field staff, allowing early detection of inadequate behaviorsEnsures that all field staff applies uniform criteria throughout the full period of data collection Solves inconsistencies through direct verification of households reality, rather that through office guessworkIs consistent with the total quality culture
Supervision tasks
Verification of questionnaires for completenessRandom re-interviews of householdsObservation of interviews
Selecting and training field staff
Why is it importantHow long does it takeHow is it organized
Example: Day 2 of interviewer training for household survey
Definition of household (and dwelling, family, etc.)Pictorial of a sample householdSlide with an empty roster (explain case conventions, encoding, skip patterns, etc.)
Example, cont.
Fill the roster for the sample household (need for legible handwriting, recording of ages, use of a calendar of events, etc.)Role playing (trainer as a respondent, simulating borderline cases)Role playing (trainees interview each other)