Transcript Statistics: A Tool For Social Research Seventh Edition Joseph F. Healey

Statistics: A Tool For
Social Research
Seventh Edition
Joseph F. Healey
Chapter 1
Introduction
Chapter Outline
 Why Study Statistics?
 The Role of Statistics in Scientific
Inquiry
 The Goals of This Text
 Descriptive and Inferential Statistics
 Discrete and Continuous Variables
 Level of Measurement
In This Presentation
 The role of statistics in the research
process
 Statistical applications
 Types of variables
The Role Of Statistics
 Statistics are mathematical tools
used to organize, summarize, and
manipulate data.
Data
 Scores on variables.
 Information expressed as numbers
(quantitatively).
Variables
 Traits that can change values from
case to case.
 Examples:




Age
Gender
Race
Social class
Case
 The entity from which data is gathered.
 Examples
 People
 Groups
 States and nations
The Role Of Statistics:Example
 Describe the age of students in this
class.
 Identify the following:




Variable
Data
Cases
Appropriate statistics
The Role Of Statistics: Example
 Variable is age.
 Data is the actual ages (or scores
on the variable age): 18, 22, 23, etc.
 Cases are the students.
The Role Of Statistics: Example
 Appropriate statistics include:
 average - average age of students in
this class is 21.7 years.
 percentage - 15% of students are older
than 25
Statistical Applications
 Two main statistical applications:
 Descriptive statistics
 Inferential statistics
Descriptive Statistics
 Summarize variables one at a time.
 Summarize the relationship between
two or more variables.
Descriptive Statistics
 Univariate descriptive statistics
include:
 Percentages, averages, and various
charts and graphs.
 Example: On the average, students are
20.3 years of age.
Descriptive Statistics
 Bivariate descriptive statistics
describe the strength and direction of
the relationship between two
variables.
 Example: Older students have higher
GPAs.
Descriptive Statistics
 Multivariate descriptive statistics
describe the relationships between
three or more variables.
 Example: Grades increase with age for
females but not for males.
Inferential Statistics
 Generalize from a sample to a
population.
 Population includes all cases in
which the research is interested.
 Samples include carefully chosen
subsets of the population.
Inferential Statistics
 Voter surveys are a common
application of inferential statistics.
 Several thousand carefully selected
voters are interviewed about their voting
intentions.
 This information is used to estimate the
intentions of all voters (millions of
people).
 Example: The Republican candidate will
receive about 42% of the vote.
Types Of Variables
 Variables may be:
 Independent or dependent
 Discrete or continuous
 Nominal, ordinal, or interval-ratio
Types Of Variables
 In causal relationships:
CAUSE

EFFECT
independent variable  dependent variable
Types Of Variables
 Discrete variables are measured in
units that cannot be subdivided.
 Example: Number of children
 Continuous variables are measured
in a unit that can be subdivided
infinitely.
 Example: Age
Level Of Measurement
 The mathematical quality of the
scores of a variable.
 Nominal - Scores are labels only, they
are not numbers.
 Ordinal - Scores have some numerical
quality and can be ranked.
 Interval-ratio - Scores are numbers.
Nominal Level Variables
 Scores are different from each other
but cannot be treated as numbers.
 Examples:
 Gender
 1 = Female, 2 = Male
 Race
 1 = White, 2 =Black, 3 = Hispanic
 Religion
 1 = Protestant, 2 = Catholic
Ordinal Level Variables
 Scores can be ranked from high to
low or from more to less.
 Survey items that measure opinions
and attitudes are typically ordinal.
Ordinal Level Variables:
Example
 “Do you agree or disagree that
University Health Services should
offer free contraceptives?”
 A student that agreed would be more in
favor than a student who disagreed.
 If you can distinguish between the
scores of the variable using terms such
as “more, less, higher, or lower” the
variable is ordinal.
Interval-ratio Variables
 Scores are actual numbers and have
a true zero point and equal intervals
between scores.
 Examples:
 Age (in years)
 Income (in dollars)
 Number of children
 A true zero point (0 = no children)
 Equal intervals: each child adds one unit
Level of Measurement
 Different statistics require different
mathematical operations (ranking,
addition, square root, etc.)
 The level of measurement of a
variable tells us which statistics are
permissible and appropriate.