Transcript Handout 1

OPIM 5103 Statistics
Jan Stallaert
Professor OPIM
Educational Goals for the Course
• “Poets”
– Learn some basic
principles of data analysis.
– Learn enough so that you
will know what your
consultant is telling you.
• “Engineers”
– Sharpen quantitative skills.
– Practice explaining
technical material by
helping non-technical
people in your group.
Both groups should get something
out of this class.
Technical Goal
• Understand Multiple Regression
– Relationships between variables.
• Is weight or length more important for determining a car’s
gas mileage?
– Predict one variable using others.
• What profit should you expect when building a house
with X sq. ft. and Y bedrooms.
– Evaluate performance in the face of mitigating
circumstances.
• Set production goals for subordinates with different staff
sizes, regional economic conditions, etc.
From here to there...
Looking at data
Thinking about a process
Graphs
Probability
Numerical Summaries
What happens in the future?
Inference
Data Collection
Making guesses
Can we generalize our results?
Testing theories
Did one thing “cause” another?
Relationships: two
variables
Correlation
Regression
Relationships:
several variables
Multiple regression
Class Resources
• Textbook
– Does a better job explaining
theory.
– Not as many examples.
• PowerPoint presentation
– Usually available before our
meetings
• Lectures
– My chance to explain what the
reading is supposed to say.
• Homeworks/Examples
– Most of your learning occurs
here.
Intro to MS Excel
• I assume you know how to:
– Create formulas in cells
– Copy, cut and paste cells within a workbook
– Make simple charts
• E.g., Pie charts, bar charts
– Have the Data Analysis Add-in installed
– Do basic formatting
• E.g., numbers, percentages, etc.
Statistical Methods
• Descriptive statistics
– Collecting and describing data
• Inferential statistics
– Drawing conclusions and/or making decisions
concerning a population based only on
sample data
Inferential Statistics
• Estimation
– e.g.: Estimate the population
mean weight using the sample
mean weight
• Hypothesis testing
– e.g.: Test the claim that the
population mean weight is 120
pounds
Drawing conclusions and/or making decisions
concerning a population based on sample results.
Looking at Data
• Example:
– House Data
Types of Data
Data
Categorical
(Qualitative)
Numerical
(Quantitative)
Discrete
Continuous
Displaying Numerical Data
• Histogram example
Histogram
15
10
5
0
10
00
12
00
14
00
16
00
18
00
20
00
22
00
24
00
26
00
28
00
M
or
e
Frequency
20
Bin
Displaying Numerical Data
Histogram Portfolio B
20
18
16
14
12
10
8
6
4
2
0
120.00%
100.00%
Frequency
Frequency
Histogram Portfolio A
80.00%
60.00%
40.00%
20.00%
.00%
-15
-5
5
15
25
35
20
18
16
14
12
10
8
6
4
2
0
120.00%
100.00%
80.00%
60.00%
40.00%
20.00%
.00%
-15
45 More
-5
5
15
25
35
45 More
120.00%
Portfolio A
100.00%
Portfolio B
80.00%
60.00%
40.00%
20.00%
.00%
-15
-5
5
15
25
35
45
More
EXCEL Tutorial: Histograms
• Here’s a PDF document
Displaying Bivariate Numerical Data
• Scatterplots
Displaying Categorical Data
• Example: bar chart, pie chart, Pareto diagram
House Styles
36%
41%
Cape Cod
Two Story
Ranch
23%
Displaying Categorical Data
• Example: bar chart, pie chart, Pareto diagram
50
45
40
44
39
35
30
25
25
20
15
10
5
0
Cape Cod
Two Story
Ranch
Displaying Categorical Data
• Example: bar chart, pie chart, Pareto diagram
50
45
40
44
39
35
30
25
25
20
15
10
5
0
Ranch
Cape Cod
Two Story
Displaying Bivariate Categorical Data
• Contingency table
Basement
Style vs. basement
style
0
0
14
25
39
25
25
3
41
44
17
91
108
1
2
Grand Total
Grand
1
Total
EXCEL Tutorial: PivotTables
• Here’s a PDF document