Azeem Majeed, Martin Bardsley, David Morgan, Caoimhe O'Sullivan, Andrew B Bindman
Majeed A, Bardsley M, Morgan D, O'Sullivan C, Bindman A B.
Cross sectional study of primary care groups in London: association of measures of socioeconomic and health status with hospital admission rates
BMJ 2000; 321 :1057
doi:10.1136/bmj.321.7268.1057
True but less valid
The results of the study by Majeed and colleagues are very important,
are compatible with the findings of others, fit into the current political
landscape and intuitively make sense. Many of the conclusions are based on
the secondary analysis of aggregate data, often generated using different
sampling frames. While I enjoyed reading the paper, I would be grateful
for an explanation why this is a cross sectional rather than an ecological
study. This distinction is more than just academic as the primary
objective of an ecological study is to generate new hypotheses. Results of
ecological studies cannot imply causality.
Competing interests: No competing interests