Lecture 4: Multiple Regression
DGGB 7840
Prof. Nagaraja
Fordham University
Prof. Nagaraja, Fordham University
1 / 45
Simple to Multiple Regression
simple linear regression:
y
= 0 + 1 x +
estimate 0 , 1 , 2
multiple regression:
y
= 0 + 1 x1 + 2 x2 + + k x
ECON 2142 Statistical Decision Making
Solutions to Chapter 11 Problem Set
1) A department store wishes to determine if customers from New York City
tend to spend more than customers from the suburbs. A sample of 20 New
York City residents is chosen; the m
ECON 2142 Statistical Decision Making
Fordham University
Department of Economics
Solutions to Sample Midterm
PART 1 FILL-INS
1) What is a Type I error?
rejecting the null hypothesis when it is true
2) What is a null hypothesis?
A statement that is assumed
ECON 2142 Statistical Decision Making
Solutions to Chapter 10 Problem Set
1) The Domino Company produces sugar packets that are supposed to
contain 3.5 grams of sugar. Suppose that the FDA wishes to determine if
Dominos sugar packets are filled correctly;
ECON 2142 Statistical Decision Making
Chapter 13 Solutions to Problem Set #1
1) A manufacturer wants to determine if the standard deviation of the length
of its steel rods exceeds 0.02 inches. If so, changes will be made to the
manufacturing process. A sa
ECON 2142 Statistical Decision Making
Chapter 13 Solutions to Problem Set #2
1) A bank wants to determine if the number of customers that enter the bank
each hour follows the Poisson distribution with an average of three
customers per hour. A sample of 10
ECON 2142 Statistical Decision Making
Solutions to Chapter 13 Problem Set #3
1) A researcher has observed 100 shoppers from three different age
groups entering a large department store and determined the
departmen
ECON 2142 Statistical Decision Making
Solutions to Chapter 10 Problem Set #2
1) In previous years, the proportion of students passing the CPA exam was
44%. In the past few years, new study materials have been made
available in order to increase the propor
ECON 2142 Statistical Decision Making
Chapter 11 Solutions to Problem Set 2
1) A new drug is being tested to determine if it lowers cholesterol. A sample
of 8 volunteers is chosen; the cholesterol readings of the volunteers before
taking the drug and afte
Stat Decision Making
1.
Class 20: Model Building
R.J. Brent
Introduction.
Here we extend the regression model to situations where the underlying
relation is not linear. There are two basic approaches:
A non-linear (polynomial) model may be applied to the
Stat Decision Making Class 22:Time Series and Forecasting 1 R.J. Brent
1.
Introduction
(i)
Extension of the regression model:
Time series data: Data consists of observations that are a sequence
over regular time intervals.
So instead of a sample xj wher
Q21 (14.50) Franchise headquarters claims it randomly selected the
local franchises that received surprise visits during the past year. The
sequence of visits is as shown below for male (M) versus female (F)
mangers. Using the 0.10 level of significance,
Stat Decision Making Class 14: Simple Linear Regression 1 R.J. Brent
1.
Introduction.
In the previous part of the course, hypothesis testing, we looked at
two (or more) means to see if the difference was significant or not.
In this chapter we look at al
Stat Decision Making Class 11: Nonparametric Methods 1
R.J. Brent
1.
Introduction.
(i)
Nonparametric tests, like parametric tests, are based on the
principles of hypothesis testing.
(ii)
These tests do not assume that the population from which the
sample
Stat Decision Making
1.
Class 17: Multiple Regression 1
R.J. Brent
Introduction.
This is an extension of the linear regression model to more than
one (multiple) independent variable. This is called multiple
regression.
The relationship between the depen
Stat Decision Making
Class 8: Chi-Square Applications
R.J. Brent
In Chapter 11, and for much of Stats 1, we assumed that the population
distributions were normally distributed.
Now we show how we can test this or other distributional assumptions
(e.g., in
Stat Decision Making
Class 4: Analysis of Variance (ANOVA)
R.J. Brent
Chapter 11 showed how to compare two means to see if the difference is
statistically significant.
Now extend this comparison to the case where there is more than two sample
means.
1.
Ke
Homework 2 Solutions: SDGB 7840
Instructor: Prof. Nagaraja
All data files can be loaded from Blackboard. Write concisely, neatly, and clearly and present
your complete solutions in order. Include only relevant R output, charts, and graphs. Staple
your hom
Lecture 3 Exercise Solutions: SDGB 7840
Instructor: Prof. Nagaraja
How is the flow of investors money into stock mutual funds related to the flow of money
into bond mutual funds? Data on the net new money flowing into stock and bond mutual
funds in the ye
Homework 2: SDGB 7840
Instructor: Prof. Nagaraja
Due: 3/3 in class
All data files can be loaded from Blackboard. Write concisely, neatly, and clearly and present
your complete solutions in order. Include only relevant R output, charts, and graphs. Staple
Homework 1 Solutions: SDGB 7840
Instructor: Prof. Nagaraja
All data files can be loaded from Blackboard. Write concisely, neatly, and clearly and present
your complete solutions in order. Include only relevant R output, charts, and graphs. Staple
your hom
Solutions to R Exercises: SDGB 7840
Instructor: Prof. Nagaraja
Try the following exercises to test your R proficiency (or brush up your skills). You should
be able to do these problems comfortably to be successful in this course.
1. Create the following v
Homework 1: SDGB 7840
Instructor: Prof. Nagaraja
Due: 2/11 in class
All data files can be loaded from Blackboard. Write concisely, neatly, and clearly and present
your complete solutions in order. Include only relevant R output, charts, and graphs. Staple
Homework 3: SDGB 7840
Instructor: Prof. Nagaraja
Due: 4/14 in class
The Gini index is a measure of inequality, most often used to describe income inequality
in populations. In this assignment you will use multiple regression to model the Gini index across
R Exercises: SDGB 7840
Instructor: Prof. Nagaraja
Try the following exercises to test your R proficiency (or brush up your skills). You should
be able to do these problems comfortably to be successful in this course.
1. Create the following vector and cal