The Study of Instructional Improvement (SII; Hill, Rowan, and Ball, 2004) was
carried out by researchers at the University of Michigan to study the math achievement
scores of first- and third-grade students in randomly selected classrooms from a national U.S. sample
of elementary schools.
Usage
data(classroom)
Format
A data frame with 1190 observations on the following 12 variables.
: Student math score in the spring of their kindergarten year
mathgain
: Student gain in math achievement score from the spring of kindergarten to the spring of first grade (the dependent variable)
ses
: Student socioeconomic status
yearstea
: First grade teacher years of teaching experience
mathknow
: First grade teacher mathematics content knowledge: based on a scale based composed of 30 items (higher values indicate higher content knowledge)
housepov
: Percentage of households in the neighborhood of the school below the poverty level
mathprep
: First grade teacher mathematics preparation: number of mathematics content and methods courses
classid
: Classroom ID number
schoolid
: School ID number
childid
: Student ID number
References
Hill, H.C., Rowan, B., and Ball, D.L. (In Press). Effect of Teacher's Mathematical Knowledge for Teaching on Student Achievement,
American Educational Research Journal, Learning Mathematics for Teaching (LMT) Project.
West, B., Welch, K. & Galecki, A, Linear Mixed Models: A Practical Guide Using Statistical Software,
Chapman Hall / CRC Press, first edition, 2006.
Examples
attach(classroom)
#### Boxplots for Figure 4.2
classroom.first8 <- classroom[classroom$schoolid <= 8,]
par(mfrow=c(4,2))
for (i in 1:8)
{boxplot(classroom.first8$mathgain[classroom.first8$schoolid==i] ~ classroom.first8$classid[classroom.first8$schoolid==i],ylab="Mathgain", xlab="classid" )}