COWLES FOUNDATION FOR RESEARCH IN
ECONOMICS Box 208281
COWLES FOUNDATION DISCUSSION PAPER NO. 1857 Improved Estimates of Using Luminosity as a Proxy for
Economic Statistics: William Nordhaus and Xi Chen March 2012 Previous work has analyzed whether luminosity data contain useful
information for estimating economic output and concluded that there was significant
promise for regions with poor quality economic statistics. The present paper examines
alternative measures of the precision of the estimates using bootstrap and prior estimates
of the errors for both the luminosity quality and the national accounts quality. Based on
the new results, we conclude: First, for countries with high quality systems, there is no
reason to use luminosity data as a supplement to standard data in any context where
standard data are available. Second, we find that there is no advantage at present of
using lights data for time-series corrections for any purposes where standard data are
available. Third, for countries with low quality statistical systems, the estimates
suggest that there may be substantial information in the luminosity data for
cross-sectional estimates of output. Fourth, the major concerns about the use of lights as
a proxy involve uncertainties about the precision of standard national accounts data.
Finally, we recommend that future work be concentrated on integrating luminosity data into
the cross sectional estimates of national and regional output primarily for countries with
poor quality statistical systems. |
