Two predictor regression: Y B1 X 1 B2 X 2 B0 B0 = The intercept.
B1 = The partial regression coefficient for the regression of Y on X1, holding X2 constant
B2 = The partial regression coefficient for the regression of Y on X2, holding X1 constant
B1 = Ea

10/18/2015
Regression With Categorical
Predictors
1
Nominal Measurement
2
G mutually exclusive and exhaustive categories
No ordering
Examples:
gender: male, female
treatments: psychotherapy, drug treatment, control
religion: Catholic, Protestant, Jewish

10/13/2015
Nonlinear Relationship
2
Nonlinear Relationships
A functional
relationship between
an IV and DV that is
graphically represented
by a curved line.
1
Constant change in X is
NOT associated with a
constant change in Y,
regardless of the value
of X

Model Specification
Multiple Regression with p
Predictors
1
2
Y B0 B1 X 1 B2 X 2 . Bp X P
The regression coefficients (B1 to Bp) in the model
measures the relationship between each X and Y with the
other Xs partialled out or controlled. The intercept (B0

Questions
2
Suppression and Spurious Effect
1
Question 1: Suppose that both X1 and X2 are positively
correlated with Y. That means that if either of those variables
increases, we expect to see Y increase.
But suppose that the regression equation comes out

Sampling Distributions and
Statistical Inference
1
Overview
2
Statistical inference and hypothesis testing.
Procedure of hypothesis testing.
Sampling distribution.
Hypothesis testing for mean.
Sampling distribution of mean.
Type I error rate (significance

Road Map
2
2-Dimensional Data
1
Psyc 650/790
Graphical way to explore 2-dimensional
data_scatterplot.
Review of correlation.
Psyc 650/790
Scatterplot
Example 1
3
4
A good way to explore the relationship between two
variables.
A scatterplot can help us det

Road Map
2
1-Dimensional Data
1
Importance of 1-dimensional data description
Shape of univariate distributions, Normal distribution
Descriptive Statistics
Central tendency
Variability or dispersion
Skewness and kurtosis
Graphical ways to explore 1-dimensi

Overview
1
psyc 650/790
Can be used in survey
Why Multiple Regression (MR)?
2
MR is a general data-analytic system for the assessment
of the relationship of a set of variables (predictors or
independent variables) to a single variable (criterion,
outcome