ECON 3790Statistics for Business and
Economics
Prerequisite: Math 1549, 1552, 1570, or 1571
Classroom Instructor: Tod Porter
Office hours: Monday & Wednesday 1:00‐2:00, Tuesday & Thursday 10:00‐11:00, or by appointment
My office is located in the Economics Department suite, room 303
Computer Lab Instructor: Ross Munroe
Points in Course• Homeworks and quizzes (75 pts.)• Three midterm exams (225 pts.)• Final exam (100 pts.)• Computer lab (100 pts.)
15%
45%
20%
20%
Chart Title
Homework and quizzes
Midterm exams
Final exam
Computer lab
Grading Scale• A, 85-100%• B, 75-84%• C, 65-74%• D, 55-64%• F, 0-54%
Other
• Course materials will be posted on my web site, www.as.ysu.edu/~tsporter
• See me privately if you need special accommodations due to a disability
• Cell phones MUST be turned off during quizzes and exams
• This is a course where it is essential for you to keep up with the material
Where is Statistics Used?• Accounting• Marketing• Finance• Economics
For Today’s Graduate, Just One Word: Statistics By STEVE LOHRPublished: August 5, 2009 MOUNTAIN VIEW, Calif. — At Harvard, Carrie Grimes majored in anthropology and archaeology and ventured to places like Honduras, where she studied Mayan settlement patterns by mapping where artifacts were found. But she was drawn to what she calls “all the computer and math stuff” that was part of the job.
“I keep saying that the sexy job in the next 10 years will be statisticians,” said Hal Varian, chief economist at Google. “And I’m not kidding.”The rising stature of statisticians, who can earn $125,000 at top companies in their first year after getting a doctorate, is a byproduct of the recent explosion of digital data. In field after field, computing and the Web are creating new realms of data to explore — sensor signals, surveillance tapes, social network chatter, public records and more. And the digital data surge only promises to accelerate, rising fivefold by 2012, according to a projection by IDC, a research firm.
For TodayBy STEVE
Objectives of the Course
• Teach you how to apply basic statistical techniques
• Make you a knowledgeable consumer of more advanced statistical techniques
Chapter 1Data and Statistics
Making Inferences about Populations
Population – The set of all elements of interest in a particular study
Sample – A subset of the population
Making Inferences about Populations
PopulationSample
Draw sample
Infer population characteristics
Describe sample characteristics
Descriptive vs. Inferential Statistics
Descriptive statistics – Summaries of the characteristics of data
Inferential statistics – Techniques used to infer the characteristics of the population using the sample data
Data and Data Sets
Data – The set of all elements of interest in a particular study
Data set – All of the data collected for a particular study
Components of a Data Set
Element – The entities on which data are collected
Variable – A characteristic of interest for the elements
Observation – Set of measurements for a specific element
Example of a Data SetEmployee Age Gender Degree Tenure SalaryBob 45 M HS 27 $35,000
Sue 60 F HS 42 $75,000
Frank 35 M BA 12 $55,000
Mary 25 F MA 2 $50,000
Employee Age Gender Degree Tenure SalaryBob 45 M HS 27 $35,000
Sue 60 F HS 42 $75,000
Frank 35 M BA 12 $55,000
Mary 25 F MA 2 $50,000
Scales of Measurement
Nominal Scale – When the data for a variable consists of labels or names used to identify some attribute
Ordinal Scale – Nominal data where the order or rank of the data is meaningful
Scales of Measurement, cont.
Interval Scale – When the data show the properties of ordinal data the interval between values is express in terms of a fixed unit of measure
Ratio Scale – The data have all the properties of interval data and the ratio of two variables is meaningful (must have a zero value)
Example of Interval Scale
Dress Size Waist, in inches8 24
10 26
12 28
14 30
16 32
A size 0 dress would correspond to a 8 inch waist
Scales of Measurement, cont.
What scale of measurement would be used for the following variables?• Distance from car to class• Football jersey number• Temperature• Ranking of satisfaction (5 = extremely
satisfied, 1 = extremely dissatisfied)
Qualitative vs. Quantitative Data
Qualitative – Labels or names used to identify the attribute of each element (Nominal or ordinal measurement)
Quantitative – Numeric values that indicate how much or how many of something (Interval or ratio measurement)
Types of Data
Cross-sectional – Data collected at approximately the same point in time
Time series – Aggregated values collected at different points in time
Panel – Data collected from the same elements at different points in time
Types of Statistical Studies
Experimental – Researcher has direct control over the variable being studied
Observational – The researcher can only observe the variable being studied
Practice Homework
Pages 20-21, #10, 12, 13
Practice homework will not be graded, the answers are in the back of the book
Chapter 2Descriptive Statistics:Tabular and Graphical
Presentations
Frequency Distribution
A tabular summary of data showing the number (frequency) of items in non-overlapping classes
Frequency Distribution
Employee Age Gender Degree Tenure SalaryBob 45 M HS 27 $35,000
Sue 60 F HS 42 $75,000
Frank 35 M BA 12 $55,000
Mary 25 F MA 2 $50,000
Degree FrequencyHS 2
BA 1
MA 1
Relative and PercentFrequency Distributions
Relative Frequency of a Class = (Frequency of the class)/n
Percent Frequency of a Class = 100 x (Frequency of the class)/n
Frequency Distribution
Employee Age Gender Degree Tenure SalaryBob 45 M HS 27 $35,000
Sue 60 F HS 42 $75,000
Frank 35 M BA 12 $55,000
Mary 25 F MA 2 $50,000
Degree FrequencyRelative Frequency
Percent Frequency
HS 2 0.5 50%
BA 1 0.25 25%
MA 1 0.25 25%
Bar Graph of Frequency Distribution
High School Bachelors Masters0
0.5
1
1.5
2
2.5
Education
Pie Chart of Frequency Distribution
Education
High SchoolBachelorsMasters
Frequency Distributions and Quantitative Data
Building a frequency distribution for quantitative data:1. Choose number of classes2. Determine the width of each class3. Define the class limits, the classes must
include all values and be mutually exclusive
Frequency Distributions and Quantitative Data
Approximate class width =
(Largest data value – Smallest data value)(Number of classes)
Frequency Distributions and Quantitative Data
Class limitsLower class limit – the smallest possible data value assigned to the class
Upper class limit – the largest possible data value assigned to the class___________________________________
Class midpoint = (Lower class limit + Upper class limit)/2
Frequency Distributions and Quantitative Data
Employee SalaryBob $35,000
Sue $75,000
Frank $55,000
Mary $50,000
Fred $80,000
Jim $65,000
Ed $25,000
Ellie $95,000
Rosie $40,000
Jane $45,000
Gary $60,000
Martha $70,000
Assuming five classes, the approximate class width would be ($95,000 - $25,000)/5 = $14,000, round to $15,000
Class Frequency$25,000 up to $40,000 2
$40,000 up to $55,000 4
$55,000 up to $70,000 2
$70,000 up to $85,000 3
$85,000 up to $100,000 1
Frequency Distributions and Quantitative Data
General principles for creating classes:1. Minimize empty classes and classes with
very low values, but don’t make classes so large important information is obscured (4 to 20 classes)
2. Choose class limits that are rounded to some easy-to-read value
3. Make sure the classes include all values are mutually exclusive
HistogramClass Frequency$25,000 up to $40,000 2
$40,000 up to $55,000 4
$55,000 up to $70,000 2
$70,000 up to $85,000 3
$85,000 up to $100,000 1
024
Histogram of Salaries
Frequency Distributions and Quantitative Data
What to do in the case of extreme values?
Employee SalaryBob $35,000
Sue $75,000
Frank $55,000
Mary $50,000
Fred $80,000
Jim $65,000
Ed $25,000
Ellie $1,025,000
Rosie $40,000
Jane $45,000
Gary $60,000
Martha $70,000
Class width = ($1,025,000 - $25,000)/5= $200,000
Class Frequency$25,000 up to $225,000 11
$225,000 up to $425,000 0
$425,000 up to $625,000 0
$625,000 up to $825,000 0
$825,000 to $1,025,000 1
For data sets with extreme values:- Use classes of unequal width- Use open-ended classes
Frequency Distributions and Quantitative Data
Class Frequency$25,000 up to $40,000 2
$40,000 up to $55,000 4
$55,000 up to $70,000 2
$70,000 up to $85,000 3
Over $85,000 1
OgiveA graphical representation of a cumulative frequency distribution.
Class FrequencyUp to $40,000 2
Up to $55,000 6
Up to $70,000 8
Up to $85,000 11
Up to $100,000 12
$25,0
00
$40,0
00
$55,0
00
$70,0
00
$85,0
00
$100
,000
02468
101214
Ogive of Salaries