Diff for "HLPMiniCourseSession2"

Differences between revisions 5 and 14 (spanning 9 versions)

Session 2: Issues in linear regression

June 5 2008

Materials

attachment:lexdecRT.R

Reading

G&H07	Chapter 4 (pp. 53-74)	Linear regression: before and after fitting the model
Baa08	Sections 6.2.2-6.2.4 (pp. 198-212)	Collinearity, Model criticism, and Validation
	Section 6.4 (pp. 234-239)	Regression with breakpoints

Notes on the readings

Additional terminology

Feel free to add terms you want clarified in class:

Questions

Q: Determining the significance of a coefficient: one-tailed or two-tailed t test?
A: It's a two-tailed test because we cannot a-priori assume which direction the coefficient will go. I guess if one had a really strong theoretical reason

to assume one direction, you could do a one-tailed test (which is less conservative).

Topics

More on outliers
- detect outliers
  - boxplot(), scatterplots plot(), identify()BR
- dealing with outliers
  - exclusion subset()BR robust regression (based on t-distribution): tlm() (in package hatt)BR
Overly influential cases (can be, but don't have to be outliers)
- lm.influence(), also library(Rcmdr)BR
Collinearity:
- tests: vif(), kappa(), summary of correlations between fixed effects in lmer() BR
- countermeasures:
  - centering and/or standardizing scale()} BR
  - use of residuals resid(lm(x1 ~ x2, data)) BR
  - principal component analysis (PCA) princomp() BR
Model evaluation: Where is the model off?
- case-by-case: residuals(), predict()BR
- based on predictor: residuals() against predictors, calibrate()BR
- overall: validate()BR
Corrections:
- correcting for clusters (violation of assumption of independence): bootcov()BR

-  ⇤ ← Revision 5 as of 2008-06-04 20:53:46 → 
  Size: 1962
  Editor: static-74-41-89-18
  Comment:
+   ← Revision 14 as of 2008-06-05 16:43:17 → ⇥
  Size: 2610
  Editor: static-69-95-227-215
  Comment:
-Deletions are marked like this.
+Additions are marked like this.
 Line 1:
-#acl HlpLabGroup:read,write,delete,revert All:read
+#acl HlpLabGroup,TanenhausLabGroup:read,write,delete,revert,admin All:read
 Line 7:
-'''June 3 2008'''
+'''June 5 2008'''

=== Materials ===

 * attachment:lexdecRT.R
-Line 23:
+Line 27:
- * Q:
+ * Q: Determining the significance of a coefficient: one-tailed or two-tailed t test?
 * A: It's a two-tailed test because we cannot a-priori assume which direction the coefficient will go. I guess if one had a really strong theoretical reason 
to assume one direction, you could do a one-tailed test (which is less conservative).
-Line 30:
+Line 36:
-Send your solutions to Andrew Watts, who will upload them here. Please send them by Wednesday 3:30pm or upload them yourself to this page by 10pm.
+Upload your solutions to this page by 10pm.
-Line 37:
+Line 43:
+[[AttachList]]
-Line 45:
+Line 51:
-       {{{boxplot()}}}, scatterplots {{{plot(), identify()}}[[BR]]
+       {{{boxplot()}}}, scatterplots {{{plot(), identify()}}}[[BR]]
-Line 48:
+Line 54:
-       robust regression (based on t-distribution): {{{tlm()}}} (in package {{{hatt}}}))[[BR]]
+       robust regression (based on t-distribution): {{{tlm()}}} (in package {{{hatt}}})[[BR]]
-Line 51:
+Line 57:
+ * Collinearity:
   * tests: {{{vif(), kappa()}}}, summary of correlations between fixed effects in {{{lmer()}}} [[BR]]
   * countermeasures: 
     * centering and/or standardizing {{{scale()}}}} [[BR]]
     * use of residuals {{{resid(lm(x1 ~ x2, data))}}} [[BR]]
     * principal component analysis (PCA) {{{princomp()}}} [[BR]]
-Line 55:
+Line 68:
-   * overall: {{{validate()))[[BR]]
+   * overall: {{{validate()}}}[[BR]]

G&H07	Section 4.9 (p.76)	Exercise 4
Baa08	Section 6.7 (p. 260)	Exercise 1, 8