30 native speakers of Italian decide whether each of 60 Italian words is a word; the outcome is whether the response was correct. For mixed-effects logistic regression.
Format
A tibble with 1800 rows and 5 columns:
- participant
Participant ID,
P01toP30.- word
Word ID,
w01tow60.- log_freq
log10 word frequency, 1 to 6.
- freq_c
log_freq, centred on the mean of the 60 words.- correct
1 for a correct response, 0 for an error.
Details
True model, in log-odds: 1.5 + u0 + w0 + (0.8 + u1) * freq_c.
By-participant intercepts u0 have SD 0.8 and slopes u1 SD 0.3
(uncorrelated); by-word intercepts w0 have SD 0.5.
Examples
if (requireNamespace("lme4", quietly = TRUE)) {
m <- lme4::glmer(correct ~ freq_c + (1 + freq_c || participant) + (1 | word),
data = lexical_accuracy, family = binomial)
summary(m)
}
#> Generalized linear mixed model fit by maximum likelihood (Laplace
#> Approximation) [glmerMod]
#> Family: binomial ( logit )
#> Formula: correct ~ freq_c + ((1 | participant) + (0 + freq_c | participant)) +
#> (1 | word)
#> Data: lexical_accuracy
#>
#> AIC BIC logLik -2*log(L) df.resid
#> 1686.6 1714.1 -838.3 1676.6 1795
#>
#> Scaled residuals:
#> Min 1Q Median 3Q Max
#> -7.8242 -0.3672 0.3045 0.5102 2.8066
#>
#> Random effects:
#> Groups Name Variance Std.Dev.
#> word (Intercept) 0.10757 0.3280
#> participant freq_c 0.07574 0.2752
#> participant.1 (Intercept) 0.59914 0.7740
#> Number of obs: 1800, groups: word, 60; participant, 30
#>
#> Fixed effects:
#> Estimate Std. Error z value Pr(>|z|)
#> (Intercept) 1.47165 0.16659 8.834 <2e-16 ***
#> freq_c 0.85216 0.08532 9.988 <2e-16 ***
#> ---
#> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#>
#> Correlation of Fixed Effects:
#> (Intr)
#> freq_c 0.164
