This data, stored in substance-family.csv includes four attributes on \(n = 910\) 10th-grade students. These data come from Keith (2015). The attributes are:
substance_use: Composite based on student-reported use of cigarettes (How many cigarettes smoked per day), alcohol (In lifetime, number of times had alcohol to drink), and marijuana (In lifetime, number of times used marijuana). To compute this composite index, the three self-reported values were standardized and then averaged.
family_structure: Adult composition of the household with three levels (Two-parent family, One-parent, one guardian, andSingle-parent family)
female: Dummy-coded sex variable (0 = Not female; 1 = Female)
# A tibble: 910 × 4
substance_use family_structure female gpa
<dbl> <chr> <dbl> <dbl>
1 -0.129 Two-parent family 1 3.8
2 0.0143 Two-parent family 0 2.5
3 -0.594 Two-parent family 1 2.8
4 -0.439 Single-parent family 0 3.5
5 -0.284 Two-parent family 1 3.3
6 -0.284 Two-parent family 0 2.5
7 -0.594 Two-parent family 1 2.3
8 -0.284 Two-parent family 1 2.5
9 3.21 Two-parent family 0 3
10 -0.594 Two-parent family 0 3
# ℹ 900 more rows
References
Keith, T. V. (2015). Multiple regression and beyond: An introduction to multiple regression and structural equation modeling (2nd ed.). New York: Routledge.