http://science.sciencemag.org/content/187/4175/398
Sex Bias in Graduate Admissions: Data from Berkeley
P. J. Bickel1, E. A. Hammel1, J. W. O’Connell1
Science 07 Feb 1975:
Vol. 187, Issue 4175, pp. 398-404
DOI: 10.1126/science.187.4175.398
A type of Simpson’s paradox
https://en.wikipedia.org/wiki/Simpson‘s_paradox
https://en.wikipedia.org/wiki/Monty_Hall_problem
collider bias
QT:{{”
In 1965, the English statistician Sir Austin Bradford Hill proposed a set of nine criteria to provide epidemiologic evidence of a causal relationship between a presumed cause and an observed effect. (For example, he demonstrated the connection between cigarette smoking and lung cancer.) The list of the criteria is as follows
“}}
https://en.wikipedia.org/wiki/Low-density_parity-check_code
turbo codes
QT:{{”
2G cell phones used “soft decoding” (i.e., probabilities) but not belief propagation. 3G cell phones used Berrou’s turbo codes, and 4G phones used Gallager’s turbo-like codes.
“}}
[from book!]
https://select-statistics.co.uk/blog/hidden-data-and-surviving-a-sinking-ship-simpsons-paradox/
continuous version of the paradox
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3804872/
QT:[[”
Genome-wide association studies (GWAS) have enabled significant progress in the past 5 years in investigating genetic susceptibility to lung cancer. Large scale, multi-cohort GWAS of mainly Caucasian, smoking, populations have identified strong associations for lung cancer mapped to chromosomal regions 15q [nicotinic acetylcholine receptor (nAChR) subunits: CHRNA3, CHRNA5], 5p (TERT-CLPTM1L locus) and 6p (BAT3-MSH5). Some studies in Asian populations of smokers have found similar risk loci, whereas GWAS in never smoking Asian females have identified associations in other chromosomal regions, e.g., 3q (TP63), that are distinct from smoking-related lung cancer risk loci. GWAS of smoking behaviour have identified risk loci for smoking quantity at 15q (similar genes to lung cancer susceptibility: CHRNA3, CHRNA5) and 19q (CYP2A6).
“]]
linkstream2 microblog 