The name is absent

Appendix B Comparing Countries in the World Values Survey

A few low-income countries in certain waves of the World Values survey were explicitly not designed to be
representative of their entire population. These selected samples add measurement error that is, in many cases, correlated
with income, education, and other factors that are related to subjective well-being. In most cases these non-representative
samples will lead average subjective well-being to be over-estimated relative to the population mean. Moreover, non-
representative sampling typically occurred in countries with low per capita GDP. For many of these countries, the
sampling frame changed in successive waves to become representative of the entire population (and this change occurred
in parallel with rising GDP). As such, we should expect that for these countries average subjective well-being in the
population will decline over time as more rural, low-income, and low-education citizens are included in the sampling
frame.

In the results presented throughout the paper, we have excluded a few countries in particular waves because the
survey notes that the sampling frame was specifically not representative of the entire country and no compensatory
sampling weights are provided.⁴⁴ In this appendix we detail the reasons why these observations were excluded and show
how our results are impact when these country-wave observations are included. We begin by documenting the sampling
issues specific to countries which are impacted:

Argentina was surveyed in all four waves; however in the first 3 waves sampling was limited to the urbanized central
portion of the country and resulted in a wealthier, more educated sample of Argentineans compared with the
population average. In the 1999-2004 the sample was designed to be representative of the entire country. We include
in our analysis only observations from Argentina in the 1999-2004 wave.

Bangladesh was included in two waves. In the 1994-99 wave the survey oversampled men and people in urban areas
"to reflect the fact that awareness is more widespread in the urban areas".⁴⁵ Sampling weights are not provided and it
is therefore not possible to correct for the oversampling. The 1999-2004 wave was designed to be representative. We
include in our analysis only observations from Bangladesh in the 1999-2004 wave.

Chile was included in three waves; however in the 1989-93 and 1994-99 waves the sample was limited to the central
portion of the country, which covers slightly less than two-thirds of the population and has an average income about
40% higher than the national average. In the 1999-2004 survey the sample was drawn from 29 selected cities. As a
result of these partial-country samples, we exclude Chile from all of our analysis.

China was included in three waves. For the 1989-93 wave, the survey notes state that they “undersampled the
illiterate portion of the public and oversampled the urban areas and the more educated strata.” Moreover, the survey
notes explicitly state that “the oversampled groups tend to have orientations relatively similar to those found in
industrial societies” and that “the data probably underestimate the size of cross-national differences.”⁴⁶ In the 1994-

⁴⁴ Many samples over-sample specific groups, but sampling weights are provided in order to yield nationally representative estimates.
Sampling weights cannot adjust for the fact that some groups were not samples at all.

⁴⁵ http://www.worldvaluessurvey.com/ Survey notes for Bangladesh (BD_WVS 1995).

⁴⁶ http://www.worldvaluessurvey.com/ Survey notes for China (CN_WVS 1990).

Appendix—3

<<   35   36   37   38   39   40   41   >>

More intriguing information