Updated March 4, 2006 Here is the output you should get if you run the R code in "GLMM.txt". Opening it in a spreadsheet program will allow you to further manipulate the numbers in the tables, if you so desire. The lmer function (and lme4 and Matrix more generally) is currently undergoing some revision, so your results may not look exactly like the following. > # First analysis (ignoring order): > > lmer(Judgment ~ Topic*Adjunct + (1|Speaker), data = minexp, + family = "binomial", method = "Laplace") Generalized linear mixed model fit using Laplace Formula: Judgment ~ Topic * Adjunct + (1 | Speaker) Data: minexp Family: binomial(logit link) AIC BIC logLik deviance 771.5728 793.8802 -380.7864 761.5728 Random effects: Groups Name Variance Std.Dev. Speaker (Intercept) 0.53545 0.73175 # of obs: 640, groups: Speaker, 20 Estimated scale (compare to 1) 0.9800041 Fixed effects: Estimate Std. Error z value Pr(>|z|) (Intercept) 0.813645 0.187014 4.3507 1.357e-05 *** Topic 0.254166 0.089300 2.8462 0.004424 ** Adjunct -0.189972 0.089230 -2.1290 0.033253 * Topic:Adjunct 0.034397 0.089146 0.3858 0.699610 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Correlation of Fixed Effects: (Intr) Topic Adjnct Topic 0.040 Adjunct -0.029 -0.013 Topc:Adjnct -0.004 -0.054 0.074 > > # Second analysis (testing satiation in main factors): > > lmer(Judgment ~ Order*Topic + Order*Adjunct + (1|Speaker), + data = minexp, family = "binomial", method = "Laplace") Generalized linear mixed model fit using Laplace Formula: Judgment ~ Order * Topic + Order * Adjunct + (1 | Speaker) Data: minexp Family: binomial(logit link) AIC BIC logLik deviance 764.6315 795.8618 -375.3158 750.6315 Random effects: Groups Name Variance Std.Dev. Speaker (Intercept) 0.56206 0.7497 # of obs: 640, groups: Speaker, 20 Estimated scale (compare to 1) 0.9801053 Fixed effects: Estimate Std. Error z value Pr(>|z|) (Intercept) 0.37836602 0.24620527 1.53679 0.124345 Order 0.02734948 0.00986858 2.77137 0.005582 ** Topic 0.24863315 0.18330930 1.35636 0.174985 Adjunct -0.50695034 0.18193761 -2.78640 0.005330 ** Order:Topic 0.00091537 0.01003204 0.09125 0.927298 Order:Adjunct 0.01956481 0.00993520 1.96924 0.048925 * --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Correlation of Fixed Effects: (Intr) Order Topic Adjnct Ordr:T Order -0.631 Topic 0.035 -0.040 Adjunct 0.002 -0.037 -0.011 Order:Topic -0.037 0.070 -0.871 0.001 Ordr:Adjnct -0.022 0.058 0.002 -0.869 0.005 > > #Third analysis (removing nonsignificant interactions): > > lmer(Judgment ~ Topic + Order*Adjunct + (1|Speaker), + data = minexp, family = "binomial", method = "Laplace") Generalized linear mixed model fit using Laplace Formula: Judgment ~ Topic + Order * Adjunct + (1 | Speaker) Data: minexp Family: binomial(logit link) AIC BIC logLik deviance 762.6397 789.4085 -375.3198 750.6397 Random effects: Groups Name Variance Std.Dev. Speaker (Intercept) 0.56337 0.75058 # of obs: 640, groups: Speaker, 20 Estimated scale (compare to 1) 0.980101 Fixed effects: Estimate Std. Error z value Pr(>|z|) (Intercept) 0.3791795 0.2462069 1.5401 0.123540 Topic 0.2632579 0.0902108 2.9183 0.003520 ** Order 0.0272944 0.0098434 2.7729 0.005556 ** Adjunct -0.5070159 0.1819844 -2.7860 0.005336 ** Order:Adjunct 0.0195619 0.0099349 1.9690 0.048951 * --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Correlation of Fixed Effects: (Intr) Topic Order Adjnct Topic 0.008 Order -0.630 0.040 Adjunct 0.002 -0.022 -0.037 Ordr:Adjnct -0.022 0.014 0.057 -0.870