Introduction to Statistics

1
Lesson 1-1 Introduction to Statistics
You will learn to define statistics define
vocabulary associated with statistics
2
The word statistics is derived from the Latin
word status, meaning state.
3
3 reasons for studying statistics
1) to understand results of studies done
2) to be able to conduct our own research
3) to become better consumers and citizens
4
Buying a car
5
Medicine
Source Viagra.com
6
Car insurance
842.30
18 year old male
7
Car insurance
661.70
18 year old female
8
Car insurance
9
(No Transcript)
10
(No Transcript)
11
Stats in USC Colleges

• Required
• College of Arts and Sciences Science
  Departments
• Moore School of Business
• College of Education any BS and Early Childhood
• College of Engineering and Information Technology
• College of Pharmacy
• Arnold School of Public Health

• Optional
• College of Arts and Sciences Arts Departments
• College of Education any BA and Elementary
• School of Music

12
Sample Schedule USC School of Business

• Third Semester
• ECON 221 Principles of Microeconomics
• MGSC 290 or Computers in Business or
• MGSC 291 Probability and Statistics
• MGMT 250/ENGL 463 or Professional Communication
  or ENGL 282-286 Fiction, drama, poetry, or
  American or British literature
• ACCT 225 Introduction to Financial Accounting
• Liberal Arts Philosophy, history, political
  science, geography, foreign language, etc.

13
USC NursingGeneral Education Requirements

• General education course selections must meet
  University general education requirements.
• English ENGL 101-102 or higher
• Social Sciences Two courses from one of these
  sociology or psychology. One course must cover
  life-span content.
• Analytical Reasoning To be satisfied in one of
  the following ways 1) STAT 110 and MATH 122 or
  2) STAT 110 and STAT 201

14
USC Hotel Recreation Tourism Management

• MATH 122 or 141, plus an additional course from
  PHIL 110 or 111, mathematics (at the next higher
  level), computer science (above CSCE 101), or
  statistics
• b. Two courses from one of the following
  fields--Philosophy (110 and 111 only) or computer
  science (above CSCE 101) or statistics

15
Majors of USC Students in one STAT 110
Nursing
HRTM
Early childhood
Nursing
French/Pub Rels
Entertain. Mgt
Crim Just
Poli Sci Cr J
Early childhood
Early childhood
Broadcast Jour
Nursing
HRTM
Poli Sci
Nursing
Jour/Mass Comm
Nursing
psych/premed
Business
Nursing
Broadcast Jour
Public Relations
Fashion Merch.
HRTM
Print Journalism
Crim Just
Early childhood
Broadcast Jour
Public Relations
16
What is Statistics?
Collect, Organize, Analyze, and Interpret Data
in order to Make Decisions
Statistics can be Hocus-Pocus!
17
What is data?
Data consists of information from observations,
counts, measurements, or responses.
examples 5 ft, 98, 2 hrs, 165 lb, male, 50
years old, 4 fat grams, 200 times at bat, 100,000
sold
18
Population
The collection of all things being studied.
X X X X X
X X X X X X X X X X
X X X X X X X X
X X X X X
X X X X X X X X X X
X X X X X X X X X
X X X X X X X X X
X X X X X
X X X X X
X X
Sample
A subset of the population.
19
Heights of Ridge View students
Heights of Ridge View students taking
probability statistics
1. Population?
All RV students
20
Heights of Ridge View students
Heights of Ridge View students taking
probability statistics
RV prob stats students
2. Sample?
21
Population Sample



RV students
RV seniors
all courses
math courses
students in this class
students in this class
We get every measurement or count that is of
interest.
We may get only partial information, but that
might be the most economical way to get info.
Time Money
22
How many were surveyed?
Who was surveyed?
Explain At home 82.
Why do the percents add up to more than 100?
1746
university students
82 of those surveyed like to snack at home
multiple answers were allowed
23
Explain Cashiers 3,262,120 5.75.
Who was surveyed?
Who did the surveying?
of cashiers surveyed in 1996 median hourly
pay rate
employed American adults
US Labor Department
24
The U.S. Department of Energy conducts a survey
of 800 gasoline stations to determine the average
price per gallon.
3. Identify the population.
all gas stations
4. Identify the sample.
800 gas stations
5. What does the data set consist of ?
price per gallon ()
25
A study of 33,043 infants in Italy was conducted
to find a link between a heart rhythm abnormality
and sudden infant death syndrome.
6. Identify the population.
all infants
7. Identify the sample.
33,043 infants
8. What does the data set consist of ?
heart rate in beats per minute
26
A survey of 546 women found that more than 56
are the job of paying bills in their household.
9. Identify the population.
all women
10. Identify the sample.
546 women
11. What does the data set consist of ?
Yes or No Are you the primary person in your
household who pays the bills?
27
Parameter
P
A numerical description of a population.
data from the population
Statistic
S
A numerical description of a sample.
data from a sample
28
Is the fact a parameter or statistic?
12. The average income of all people in the U.S.
in 2002.
13. The average income of people from three U.S.
states in 2002.
14. A survey of a sample of workers reported
their starting salary
Parameter
Statistic
29
Is the fact a parameter or statistic?
15. Starting salaries for the 2005 graduates
from USC
16. The number of students with Cingular cell
phone service in a random check of classrooms
Parameter
Statistic
30
Parameter
P
A numerical description of a population.
data from the population
Statistic
S
A numerical description of a sample.
data from a sample
why?
Parameters are fixed in value, while statistics
vary in value.
31
Two Branches of Statistics
1) Descriptive Statistics
report the facts discovered in the survey
2) Inferential Statistics
use sample data to make conclusions about an
entire population
estimation, prediction, probability
32
Whole Population Available Find the average
height of women 18 - 24
Collect Data

POPULATION of women N 130,000,000

Describe Population
Descriptive Statistics
33
Whole Population NOT Available Find the average
height of women 18 - 24
Take Sample


POPULATION of women N 130,000,000
SAMPLE of women n 1000
Collect Data
Use sample to estimate description of population
Inferential Statistics
34
17. 1000 U.S. teens were surveyed. 72 of the
girls and 58 of the boys had after school jobs.
Descriptive statistics
72 of the girls and 58 of the boys had after
school jobs.
Inferential statistics
We predict that a higher percentage of teen girls
have after school jobs.
35
18. In a recent survey of 1000 adults, 47 said
using a cell phone while driving should be
illegal.
Descriptive statistics
47 of 1000 U.S. adults believed that using a
cell phone while driving should be illegal.
Inferential statistics
Based on a recent survey, about half of the
population believe that using a cell phone while
driving should be illegal.
36
Its Time to Practice!
Assignment 1.1
37
Lesson 1-2 Types of Data
You will learn to classify data identify
types of measurements
38
Qualitative data
Data that cannot be measured or counted
characteristic or categorical
Examples
gender, favorite class, religious preference,
eye color, hair color, geographical location, zip
code
39
Quantitative data
Data that can be measured or counted
numerical data
Examples
age, heights, weights, temperatures, grades,
time, money
40
Qualitative or Quantitative data?
1. ID numbers of the students in this class
2. temperature each day this week
3. jersey numbers of the players on a team
4. vehicle models
5. price of vehicles
qualitative
quantitative
41
Nominal Data
gt list of categories, names, labels, or
qualities
gt order (rank) cannot be assigned to the
categories
Examples
type of car you drive, your jersey number,
college you want to attend, eye color, hair
color, gender, zip code
42
Ordinal Data
gt data that is ordered or ranked
Examples
race outcomes (1st,2nd,3rd), grade (A,B,C,D),
top 5 sports teams, rating (good, better,
best)
43
Decide whether the data is nominal or ordinal.
Why?
1. highest level of education
2. marital status
3. zip code
4. rating for first impression of store
nominal
ordinal
44
Discrete Data
gt countable
gt usually integers only no decimals or
fractions
9.9, 9.5, 8.8, 10.0, 9.3
Examples
number of courses you are taking, number of
pairs of shoes you own, number of CDs you
own, score at figure-skating competition cost of
concert tickets
45
Continuous Data
gt not countable
gt weight or measurement
time is continuous
Examples
weight of a bookbag, minutes it takes for you to
get to school, inches of rain fall
46
Decide whether the data is continuous or
discrete. Why?
1. students wearing blue jeans
2. height of students
3. money each student has
4. weight of each bag of MMs
continuous
discrete
47
nominal
qualitative
ordinal
variable
discrete
quantitative
continuous
48
Lesson 1-3 Statistical Design
You will learn to identify ways to collect
data identify ways to get a sample of the
population for a study
49
The goal of every study is to collect data and
use it to make a decision.
If the data collection process is flawed, then
the results are not valid.
50
Designing a Statistical Study
1) identify data of interest identify
population
2) develop a plan for collecting data
3) collect data
4) report descriptive statistics
5) report inferential statistics
6) identify any possible errors
51
Data Collection
1) Take a Census
(entire population)
2) Use a Sampling
(part of a population)
3) Create a Simulation
(reproduce conditions - crash dummies)
4) Conduct an Experiment
(study group control group)
52
Which method of data collection?
1. the effect of changing flight patterns on
the number of airplane accidents
simulation
2. the effect of aspirin on preventing heart
attacks
experiment
3. the weights of all linemen in the National
Football League
census
4. U.S. residents approval rating of the
president
sample
53
Experiment
Everyone in class will look at a picture. Without
saying anything, you will write down what you
see in the picture.
If you are sitting in seat 1-13, close your
eyes, cover your eyes, or put your head down.
54
Do not say anything. Do not write anything.
Just look at the picture.
55
Without saying anything, write down what you see
in the picture.
56
Watch this video.
In this video, 3 kids have white shirts and 3
kids have black shirts. Focus on the kids in
white and count the number of times they pass the
ball to a different person.
57
When time and money prevent you from collecting
data from the entire population
58
Data Collection
1) Take a Census
(entire population)
2) Use a Sampling
(part of a population)
3) Create a Simulation
(reproduce conditions - crash dummies)
4) Conduct an Experiment
(study group control group)
59
5 Sampling Techniques
(ways to choose a sample)
60
Random Sample
gt Each member of the population has an equal
chance of being selected.
(heights of students)
61
Using the Calculator
gtMATH gt PRB gt randInt(
randInt (begin, end, in sample)
randInt (1, in population, in sample)
How can we all get the same data?
1 ? rand
62
Stratified Sampling
gt divide the population into groups using
some characteristic gt select a few members from
each group
63
Stratified Sampling
X
X
X
X
Low Income
Middle Income
X
X
High Income
64
Stratified Sampling
Freshmen
Sophomores
A Hall
D Hall
Juniors
Seniors
B Hall
C Hall
65
Proportional Stratified Sampling
500 families
2,000 families
select 50
select 200
Low Income
500 families
Middle Income
select 50
High Income
66
Cluster Sampling
gt population is divided into groups gt use one
group for the sample
67
Cluster Sampling
Low Income
Middle Income
High Income
68
Cluster Sampling
Freshmen
Sophomores
Juniors
Seniors
69
Systematic Sampling
gt every nth number from the population is
included in the sample
70
Systematic Sampling
Choose every household
3rd
X
X
X
X
X
X
71
Systematic Sampling
72
Convenience Sampling
gt subjects used because they are convenient
and available gt volunteer sampling
telephone survey
survey at a shopping center
73
Identify the sampling technique used for each
study.
5. select a class at random and question each
student in the class
6. divide the students by grade level and
question some students in each grade level
cluster
stratified
74
Identify the sampling technique used for each
study.
7. assign each student a number, generate
random numbers, and question each student whose
number is selected
8. choose a starting point and question every
25th student
random
systematic
75

• The commonly used sampling methods that often
  results in biased samples are
• _______________________
• Volunteer sampling
• Convenience sampling

76
Let's Review!
The Statistical Process
population
1) identify _________
2) plan __________
investigation
data
3) collect analyze ______
sample
4) describe ______
5) make inferences about __________
population
errors
6) Identify possible ________
77
Its Practice Time! Assignment 1.3
78
Ch 1 Review Assignment