Common Errors in Statistics (and How to Avoid Them), 4th Edition
by Phillip I. Good, James W. Hardin
TO LEARN MORE
For more on the contrast between fixed-effect “assumption-free” methods, and random-effect “assumed-representativeness” methods, see Section 5.17 of http://www.ctsu.ox.ac.uk/reports/ebctcg-1990/section5.
See Hardin and Hilbe [2003, p. 28] for a more detailed explanation of specifying the correlation structure in population-averaged GEEs. See Zeger and Liang [1986] for detailed investigations of efficiency and consistency for misspecified correlation structures in population-averaged GEEs.
See McCullagh and Nelder [1989] and Hardin and Hilbe [2007] for the theory and application of GLMs. See Skrondal and Rabe-Hesketh [2004] for extensions of GLMs to include latent variables, and to structural equation models. For more information on longitudinal data analysis utilizing specific software, Stata users should see Rabe-Hesketh and Skrondal [2008] and SAS users should see Cody [2001].
Notes
1 As first defined by Nelder and Wedderburn [1972].
2 They do not have a log-normal distribution as reported by Saslaw [2008].
3 Durbin [1954], Wu [1973], and Hausman [1978] independently discuss this test.
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access