Глава 2. От государственных пиратов до морских свинок: становление причинного вывода
Глава 2. От государственных пиратов до морских свинок: становление причинного вывода
Galton’s explorations of heredity and correlation are described in his books (Galton, 1869, 1883, 1889) and are also documented in Stigler (2012, 2016).
For a basic introduction to the Hardy-Weinberg equilibrium, see Wikipedia (2016a). For the origin of Galileo’s quote “E pur si muove,” see Wikipedia (2016b). The story of the Paris catacombs and Pearson’s shock at correlations induced by “artificial mixtures” can be found in Stigler (2012, p. 9).
Because Wright lived such a long life, he had the rare privilege of seeing a biography (Provine, 1986) come out while he was still alive. Provine’s biography is still the best place to learn about Wright’s career, and we particularly recommend Chapter 5 on path analysis. Crow’s two biographical sketches (Crow, 1982, 1990) also provide a very useful biographical perspective. Wright (1920) is the seminal paper on path diagrams; Wright (1921) is a fuller exposition and the source for the guinea pig birth-weight example. Wright (1983) is Wright’s response to Karlin’s critique, written when he was over ninety years old.
The fate of path analysis in economics and social science is narrated in Chapter 5 of Pearl (2000) and in Bollen and Pearl (2013). Blalock (1964), Duncan (1966), and Goldberger (1972) introduced Wright’s ideas to social science with great enthusiasm, but their theoretical underpinnings were not well articulated. A decade later, when Freedman (1987) challenged path analysts to explain how interventions are modelled, the enthusiasm disappeared, and leading researchers retreated to viewing SEM as an exercise in statistical analysis. This revealing discussion among twelve scholars is documented in the same issue of the Journal of Educational Statistics as Freedman’s article.
The reluctance of economists to embrace diagrams and structural notation is described in Pearl (2015). The painful consequences for economic education are documented in Chen and Pearl (2013).
A popular exposition of the Bayesian-versus-frequentist debate is given in McGrayne (2011).
More technical discussions can be found in Efron (2013) and Lindley (1987).
Blalock, H., Jr. (1964). Causal Inferences in Nonexperimental Research. University of North Carolina Press, Chapel Hill, NC.
Bollen, K., and Pearl, J. (2013). Eight myths about causality and structural equation models. In Handbook of Causal Analysis for Social Research (S. Morgan, ed.). Springer, Dordrecht, Netherlands, 301–328.