A semicontinuous variable has a portion of responses equal to a single valu
e (typically 0) and a continuous, often skewed, distribution among the rema
ining values. In cross-sectional analyses, variables of this type may be de
scribed by a pair of regression models; for example, a logistic model for t
he probability of nonzero response and a conditional linear model for the m
ean response given that it is nonzero. We extend this two-part regression a
pproach to longitudinal settings by introducing random coefficients into bo
th the logistic and the linear stages. Fitting a two-part random-effects mo
del poses computational challenges similar to those found with generalized
linear mixed models. We obtain maximum likelihood estimates for the fixed c
oefficients and variance components by an approximate Fisher scoring proced
ure based on high-order Laplace approximations. To illustrate, we apply the
technique to data from the Adolescent Alcohol Prevention Trial, examining
reported recent alcohol use for students in grades 7-11 and its relationshi
ps to parental monitoring and rebelliousness.