HW 1
1. experimental data (in which the values of some of the X variables are
deliberately set by the experimenter) ascertaining nonspuriousness is
effective, since the value of the "treatment" has been deliberately
dissociated (through random assignment)
Study Aid 2
Mean squares are sums of squares divided by their respective degrees of
freedom (df).
In particular, MSE = SSE/(n - p) is again the estimate of 2, the common
variance of and of Y.
5. ANOVA Table
Analysis of variance results are summarized in a
Study Aid 1
3. (Optional) Alternative Geometry for First-Order Multiple Regression
Model
There is an alternative geometry for multiple regression that represents the
problem in n-dimensional space, where n is the number of observations. Then
the vector yo
Lecture 4 Notes
3. The Mechanism of Specification Bias aka Spuriousness
The mechanism of spuriousness aka specification bias is presented graphically
in the context of the D-Score example in the next exhibit.
Although spuriousness often creates the appear
Lecture 3 Notes
3. Applying the Elaboration Model to Yule's Data
The technique of "testing" the coefficient of a variable X 1 for spuriousness by
introducing in the model additional variables X2, X3, etc., measuring potential
confounding factors is called
Lecture 2 Notes
1. The First Modern Multiple Regression Analysis
The use of multiple regression analysis as a means of controlling for possible
confounding factors that may spuriously produce an apparent relationship
between two variables was first propos
Lecture 1 Notes
Motivations for Multiple Regression Analysis
The 2 principal motivations for models with more than one independent
variable are:
to make the predictions of the model more precise by adding other
factors believed to affect the dependent var
In Class Assignment 2
1. The k are sometimes called partial regression coefficients, but more often
just regression coefficients, or unstandardized regression coefficients (to
distinguish them from standardized coefficients discussed below.)
Mathematicall
HW 3
1. The response function (also called regression function or response
surface) defines a hyperplane in p-dimensional space. When there are
only 2 predictor variables (besides the constant) the response surface is a
plane.
2. Example: In the trimmed m
Study Aid 3
Hypothesis Tests for k
1. Two-Sided Tests
The most common tests concerning k involve the null hypothesis that k = 0.
The alternatives are
H0: k = 0
H1: k <> 0
The test statistic is
t* = bk/scfw_bk
where scfw_bk is the estimated standard deviat