yaish {gnm} | R Documentation |
A 3-way contingency table of father/son pairs, classified by father's
social class (orig
), son's social class (dest
) and son's
education level (educ
).
data(yaish)
A table of counts, with classifying factors educ
(levels 1:5
),
orig
(levels 1:7
) and dest
(levels 1:7
).
David Firth
Originally in Yaish (1998), see also Yaish (2004, p316).
Yaish, M (1998). Opportunities, Little Change. Class Mobility in Israeli Society: 1974-1991. D.Phil. Thesis, Nuffield College, University of Oxford.
Yaish, M (2004). em{Class Mobility Trends in Israeli Society, 1974-1991.} Lewiston: Edwin Mellen Press.
set.seed(1) data(yaish) ## Fit the "UNIDIFF" mobility model across education levels, leaving out ## the uninformative subtable for dest == 7: ## unidiff <- gnm(Freq ~ educ*orig + educ*dest + Mult(Exp(-1 + educ), -1 + orig:dest), family = poisson, data = yaish, subset = (dest != 7)) ## Deviance should be 200.3, 116 d.f. ## ## Look at the multipliers of the orig:dest association: coefs.of.interest <- grep("Mult1.*educ", names(coef(unidiff))) coef(unidiff)[coefs.of.interest] ## ## Mult1.Factor1.educ1 Mult1.Factor1.educ2 Mult1.Factor1.educ3 Mult1.Factor1.educ4 ## -0.8150195 -1.0403857 -1.5584007 -1.8538570 ## Mult1.Factor1.educ5 ## -3.0643114 ## ## Get standard errors for the contrasts with educ1: ## getContrasts(unidiff, coefs.of.interest) ## ## [[1]] ## Estimate Std. Error quasiSE quasiVar ## Mult1.Factor1.educ1 0.0000000 0.0000000 0.0975751 0.00952090 ## Mult1.Factor1.educ2 -0.2253661 0.1611886 0.1288595 0.01660478 ## Mult1.Factor1.educ3 -0.7433812 0.2335042 0.2118164 0.04486617 ## Mult1.Factor1.educ4 -1.0388374 0.3434049 0.3260719 0.10632288 ## Mult1.Factor1.educ5 -2.2492918 0.9452228 0.9354512 0.87506893 ## ## Table of model residuals: ## residuals(unidiff)