Course Topics

1
Course Topics

• Simple statistical methods for data analysis
  using Excel.
• descriptive statistics,
• an introduction to statistical inference, and
• linear regression models. 
• Excel workbooks for computing elementary
  statistics using the Data Analysis toolkit.  
• Transferring digital information (graphs and
  tables) into Word documents, developing
  presentations in Power Point.
• Publishing documents on the web

2
Optional Texts

• Statistics with Microsoft Excel by B.J. Dretzke
  (Recommended for students that are not familiar
  with Excel)
• Introduction to the Practice of Statistics, by
  David S. Moore and George P. McCabe
• Elementary Statistics (2002), by M. F. Triola.
• The Basic Practice of Statistics (2000), by D.S.
  Moore. 

3
Useful links

• Surfstat an online text in introductory
  Statistics http//www.anu.edu.au/nceph/surfstat/s
  urfstat-home/surfstat.html
• Statistics at Square One http//bmj.com/collectio
  ns/statsbk/index.shtml
• The DePaul University library offers a number of
  good books on Excel using books 24X7 IT Pro

4
Getting ready for the class

• Open Excel
• Check that the Tools menu contains the Data
  Analysis option
• If not, use ToolsAdd Ins and click on box
  labeled Analysis ToolPak

5
Exploratory Data Analysis

• The goal of data analysis is to gain information
  from the data.
• Long listings of data are of little value.
• Statistical methods come to help us.
• Exploratory data analysis set of methods to
  display and summarize the data.
• Data on just one variable the distribution of
  the observations is analyzed by
• Displaying the data in a graph that shows overall
  patterns and unusual observations (stem-and-leaf
  plot, bar chart, histogram, box plot, density
  curve).
• Computing descriptive statistics that summarize
  specific aspects of the data (center and spread).

6
Observed variables
Data contain information about a group of
individuals or subjects A variable is a
characteristic of an observed individual which
takes different values for different
individuals Quantitative variable
(continuous) takes numerical values. Ex.
Height, Weight, Age, Income, Measurements Qualitat
ive/Categorical variable classifies an individual
into categories or groups. Ex. Sex, Religion,
Occupation, Age (in classes e.g. 10-20, 20-30,
30-40) The distribution of a variable tells us
what values it takes and how often it takes those
values Different statistical methods are used to
analyze quantitative or categorical variables.
7
Graphs for categorical variables

• The values of a categorical variable are labels.
• The distribution of a categorical variable lists
  the count or percentage of individuals in each
  category.

Counts 212 168
20
A sample of 400 wireless internet users.
8
Another Example
9
Example On the morning of April 10, 1912 the
Titanic sailed from the port of Southampton (UK)
directed to NY. Altogether there were 2,201
passengers and crew members on board. This is the
table of the survivors of the famous tragic
accident.
Assigning Categories
10
The Histogram
Example CEO salaries Forbes magazine published
data on the best small firms in 1993. These were
firms with annual sales of more than five and
less than 350 million. Firms were ranked by
five-year average return on investment. The data
extracted are the age and annual salary of the
chief executive officer for the first 59 ranked
firms.
Salary of chief executive officer (including
bonuses), in thousands 145 621 262 208
362 424 339 736 291 58 498 643
390 332 750 368 659 234 396 300
343 536 543 217 298 1103 406 254
862 204 206 250 21 298 350 800 726
370 536 291 808 543 149 350 242
198 213 296 317 482 155 802 200
282 573 388 250 396 572
11
Drawing a histogram

• Construct a distribution table
• Define class intervals or bins (Choose intervals
  of equal width!)
• Count the percentage of observations in each
  interval
• End-point convention left endpoint of the
  interval is included, and the right endpoint is
  excluded, i.e. a,b)
• Draw the horizontal axis.
• Construct the blocks
• Height of block percentages!
• The total area under an histogram must be 100