Table 3.

Posterior mean ($\widehat{\sigma }$), estimated error, and 95% credible intervals for dialect and speaker-level parameters related to obstruent voicing included in the model of log-transformed vowel duration.

Level	Parameter	$\widehat{\sigma }$	Est.Error	95% CrI
Dialect	Intercept	0.05	0.01	[0.03, 0.07]
	Obstruent Voicing	0.09	0.01	[0.07, 0.12]
	Voicing : Manner	0.12	0.02	[0.09, 0.16]
	Voicing : Height	0.04	0.01	[0.01, 0.06]
	Voicing : Class	0.06	0.01	[0.04, 0.09]
	Voicing : Mean Rate	0.02	0.01	[0.00, 0.05]
	Voicing : Local Rate	0.05	0.01	[0.03, 0.07]
Speaker	Intercept	0.10	0.00	[0.09, 0.10]
	Obstruent Voicing	0.08	0.00	[0.07, 0.08]
	Voicing : Height	0.11	0.01	[0.10, 0.12]
	Voicing : Manner	0.11	0.01	[0.10 0.13]
	Voicing : Class	0.13	0.01	[0.11, 0.14]
	Voicing : Local Rate	0.09	0.01	[0.08, 0.11]