Title: Statistics For Economics: An Intuitive Approach
Author: Alan S. Caniglia,
Publisher: Harpercollins College Div
List Price: 95.85 USD
_. relafionskgf between the Size,
(ClMtej (Ountbly ',n-F;,.;~t-9 0,
uMou/rtably imcinlte) 01]: the son/lg
5/4? and the Sula/oft
n. : n(nI)/Y\) [ 0) A Fad'o/m)
K ; k.\[n-h\l 50p?/)<)=$unoort
a: )( Two t/fes DF (hula
Supplementary notes for STA131A spring 2017
Dr. Susan Alber
These notes are not meant to either replace the book or lecture notes. They are
notes I prepared for a previously taught intro probability theory class that you may
find useful. This is my attemp
Lecture 2: Measuring the Macroeconomy
Income per person in the United States
$2,800 in 1870
$44,000 in 2012
Many countries have not experienced similar increases
in living standards.
The analysis of economic growth helps explain
Lecture Note 1
Analysis of Variance : an outline
Principles of experimental design
R.A. Fisher (1935), The Design of Experiments :
Replication: deals with variation/uncertainty, allows for generalization
Randomization: deals with co
(a) We are interested in comparing the two population means #1 2.
What do we do?
(b) What about Ho: 112.111: vs Ha :11] 75 p2? How do we test this
("Hf (r: H) (c) TEST STATISTIC:
(d) DISTRIBUTION OF THE TEST STATISTIC UNDER H02
/ (e) P-VALUE
A quick review and a brief introduction
1. WHAT DOES A STATISTICIAN DO? INFERS ABOUT THE POPU-
LATION BASED ON A RANDOM SAMPLE
2. Population (Mode1+parameter) => Random Sample (Data) => Summarise
Data :> Use the summarized data to INFER about th
1 Lecture 3 continued
1. In the last class we started discussing if a cause effect relationship exists between the explanatory variable
(X: package design) the response variable (Y: sales gures).
2. The data which we had can be summarized in the
the training center was NOT randomly assigned to the subjects, each trainee had the choice of choosing their
own training centre but the program was randomly allotted. So the two independent (explanatory) variables
are Center and Program and the dependent
1 Chapter 3
1.1 Learning Objectives of Chapter 3
3.1 What do each of these terms mean: Probability, Event, Experiment, Sample Space?
3.2 Learning to count: Tree diagrams and (2).
3.3 Different kinds of events: Sure, Impossible, Complementary, Mu
2.3 Different kinds of events: Sure, Impossible, Complementary, Mutu-
ally Exclusive, Independent
Example 1: Lets go back to the experiment: A box contains 100 tokens each colored red. You are asked
to perform the following experiment: Draw a token at ran
What did we do so far?
1. Dened the terms: Probability, Event, Experiment, Sample Space
Sample Space is a set.
Event is a subset of the Sample Space.
Tree diagram, (if)
Discussed Sure and Impossible events
What is a sure
1. We know the difference between a discrete random variable and a continuous random variable.
2. We know what the term distribution means in the context of a discrete random variable
3. We know how to find the mean p. the variance 02 and the st
What did we do so far?
1. Defined the terms: Probability, Event, Experiment, Sample Space
2. Sample Space is a set.
3. Event is a subset of the Sample Space.
4. Tree diagram, N
5. Discussed Sure and Impossible events
6. What is a sure event? A
Study guide for Midterm 3
1. Chapter 4: Sections 4.8 and 4.9
2. Important questions from Chapter 4: The questions from sampling distribution in Feb 24th preannouncement. This the pdf document titled
lec11,12,12b(sampling- distribution).pdf. The
1. Suppose you have the following dataset:
16, 1, 10.2, 7.8, 1.8, 2, 3, 4.6, 7.1, 9.9, 10.1, 14
What is the 75th percentile?
The sorted list is
1, 1.8, 2, 3, 4.6, 7.1, 7.8, 9.9, 10.1, 10.2, 14, 16
and there are 12 m
1. A normal random variable X has mean 35 and standard deviation 10. Find a value of
X that has area .01 to its right. This is the 99th pecentile of this normal distribution.
Draw the picture!
The value we need to s
1. An experiment can result in one of five equally likely simple events, E1 , E2 , . . . , E5 .
Events A, B and C are defined as follows:
A = cfw_E1 , E3 and P (A) = .4
B = cfw_E1 , E2 , E4 , E5 and P (B) = .8
C = cfw_E3 ,
1. A random variable X can assume five values: 0,1,2,3,4. A portion of the probability
distribution is shown here:
a) Find p(3)
b) Construct a probability histogram for p(x)
c) Calculate the ex
1. Explain what it means for a point estimator to be unbiased.
A point estimator is unbiased if its expected value is the parameter. For example,
E(X) = , so X is unbiased for . Intuitively, this means that when we