Data Interpretation, Spring 2008 - Notes.

Notes on Lab 1: source commands from first lecture. . Use source("SF.txt") to run the commands. To go to the next command, right click in the graphics window.
Notes 2: source commands from second and third lecture. . Use source("SFb.txt") to run the commands. To go to the next command, right click in the graphics window.
Notes 3: Modstart.q . Exploring the car data. Use source("Modstart.q") to run the commands. To go to the next command, right click in the graphics window.
Notes 3b: Modfull.q . Model Selection. Use source("Modfull.q") to run the commands. To go to the next command, right click in the graphics window.
Notes 3c: ModSel.q . Model Selection - on random splits of the data. Use source("ModSel.q") to run the commands. To go to the next command, right click in the graphics window.
Notes 3d: cars2.dat . The car data.
Handout 4a: The South African heart disease data .
Handout 4b: Heart Disease - demo start.
Handout 4c: Model Selection.
Handout 4d: CART.
Handout 4e: CART classification and GLM.
Handout 5a: The wine data .
Handout 5b: CART wine data.
Handout 5c: Logistic regression - wine.
Handout 6a: Cluster analysis of the wine data.
Handout 6b: Cluster analysis of the heart disease data .
Handout 7a: The glass training data , and the The glass test data .
Handout 7b: GlassData - classification .
Handout 7c: ClusterGlass - clustering the glass data.
Handout 8: Bagging - wine data .
Handout 9c: The pollution data , and the The training data and test data .
Handout 9b: pollstart - exploring the pollution data.
Handout 9c: ModSelpoll - model selection.
Handout 9d: ModSelpollrep - Stability of model selection.
Handout 9e: Predpoll - prediction errors and regularized regression .
Handout 9f: CARTpoll - regression tree analysis. .

Back to : Data Interpretation

01/17/05