OLS Residual Models for Seniors (N=613):
Predicted Level of Academic Challenge =
48.638 + .602*selectivity + 2.234*sector - 1.125*Extensive - .816*Intensive + 1.266*Liberal arts + .300*General
+ .460*Other Carnegie + 1.533*on campus + 4.245*female + 6.586*full-time - 2.153*humanities – 3.025*math – 6.684*preprofessional - 5.772*multiple - 4.899*Alien + 4.486*Asian + 1.062*Black + 3.131*Latina/o + 9.621*Native American + 3.946*Unknown
Adjusted R2=.56

Predicted Active and Collaborative
Learning
=
34.963 + 1.839*sector + 1.184*rural + 1.132*small town + .932*large town + .987*fringe1
+ .598*mid-size - .452*fringe2 - .079*enrollment - 2.392*Extensive - 1.938*Intensive + .114*Liberal arts - .069*General + .730*Other Carnegie + 5.904*female + 9.331*full-time - .008*humanities + 4.894*math + 4.039*preprofessional + 2.936*multiple - 3.934*Alien – 3.470*Asian + 4.624*Black + 4.760*Latina/o + 27.944*Native American + 5.445*Unknown
Adjusted R2=.44

Predicted Student-faculty Interaction =
40.864 + 2.178*sector + 1.849*rural + 1.802*small town + 1.766*large town + 1.042*fringe1 + .639*mid-size - .526*fringe2 - 2.553*Extensive - 1.378*Intensive + 3.242*Liberal arts + .461*General + .328*Other Carnegie + 4.896*on campus + 5.452*female + 9.382*full-time - .350*age - 2.938*humanities - .135*math + 4.243*preprofessional - 3.791*multiple - 2.745*Alien –10.524*Asian + 6.357*Black + .938*Latina/o + 20.284*Native American - .905*Unknown
Adjusted R2=.66

Predicted Enriching Educational Experiences =
44.007 + .553*selectivity + 2.556*sector - 1.198*rural - 1.055*small town + 1.189*large town - .350*fringe1
+ .129*mid-size - 1.971*fringe2 - .336*Extensive - .107*Intensive + 3.397*Liberal arts + .651*General - 1.793*Other Carnegie + 5.093*on campus + 6.799*female
+ 10.219*full-time - .381*age + .638*humanities - .5.722*math – 7.917*preprofessional - 4.557*multiple + 9.586*Alien + 3.349*Asian + 6.903*Black + 5.804*Latina/o
+ 36.270*Native American + 8.162*Unknown
Adjusted R2=.66
Predicted Supportive Campus Environment =
49.198 + 5.086*sector + 2.598*rural + 3.017*small town + 4.188*large town + 1.796*fringe1 + 1.666*mid-size + 1.027*fringe2
- 3.073*Extensive - 2.257*Intensive + .584*Liberal arts + .564*General + .418*Other Carnegie + 2.668*on campus + 3.449*female + 4.342*full-time + .216*humanities - 4.450*math - .643*preprofessional - 4.510*multiple - 2.159*Alien + .161*Asian - 1.208*Black + 4.857*Latina/o + 15.056*Native American - 8.693*Unknown
Adjusted R2=.48

Notes:
  1. Residual models initially contained all independent variables listed below. Model reduction proceeded one variable at a time; each iteration removed the variable associated with the largest p value. For all but dummied variables with more than two categories, we removed variables that did not yield significant coefficients (p<.05 with two-tailed tests). For urbanicity, 2000 Carnegie Classification, major field, and race/ethnicity, we tested whether all dummy coefficients for each variable were simultaneously equal to zero. If Wald tests suggested that we could not reject the null hypothesis (chi-square, p<.05), we dropped the variable from the model (with its attendant dummy variables), and
  2. As the independent variables were not mean-centered in any way, model intercepts have no special interpretation.