Although it has been a lasting concern for statistical offices for years, the topic of quality has received explicit attention only relatively recently. Even if some forerunners tackled this problem since the end of the 70s or beginning of the 80s (USBC, UN, Statistics Canada), it was necessary to wait until 95 to see more and more organisations involved in an explicit quality policy (SMPQ Conference, Bristol, 1995). In order to understand better the diversity of approaches, it is convenient to use the ISO 8402 definition of quality, that is in practice the one used explicitly or implicitly by statistical organisations (SOs hereafter). This norm states that: “Quality is the totality of features and characteristics of a product or service that bear on its ability to satisfy stated or implied needs”. What is crucial is then users’ satisfaction, and the diversity of users may explain different behaviours of SOs.
[1]
C. Chatfield.
Model uncertainty, data mining and statistical inference
,
1995
.
[2]
L Kish,et al.
Multipopulation survey designs: five types with seven shared aspects.
,
1994,
International statistical review = Revue internationale de statistique.
[3]
C. Särndal,et al.
Calibration Estimators in Survey Sampling
,
1992
.
[4]
David A. Belsley,et al.
Regression Analysis and its Application: A Data-Oriented Approach.@@@Applied Linear Regression.@@@Regression Diagnostics: Identifying Influential Data and Sources of Collinearity
,
1981
.
[5]
Bronwyn H Hall,et al.
Estimation and Inference in Nonlinear Structural Models
,
1974
.