Transcript Scientific Method Overheads

Agenda for January 25th

Administrative Items/Announcements







Follow up from last week



Attendance
Handouts: course enrollment, RPP instructions
Course packs available for sale in 208 Porter Hall
Selection of presentation week/topic
Anyone with special needs: come see me
Pictures on Thursday!
Results from in-class study
Quiz example (“feedback exercise”)
Begin this week’s topic: Research Methods
Follow-Up From Last Week

1.
Quiz example:
(a) What is the central tension between
emotion theorists who take a social
constructivist position vs. those who take
an evolutionary position? (b) Explain one
piece of evidence that supports each of
these positions.
An Open Mouth Increased Perceived
Humorousness of the Cartoon
4.00
3.50
3.00
2.50
2.00
1.50
1.00
0.50
0.00
Lips Apart
Lips Closed
M closed = 2.92, M open = 3.62, F (1) = 6.61, p < .05
Scientific Method
in Decision Science
Basic belief that there are
consistencies that can be
uncovered
 Science as an ongoing process

Goals
1. Measurement and Description
 2. Understanding and Prediction
 3. Application and Control

Steps in the Scientific
Investigation





Step 1: Formulate a testable
hypothesis
Step 2: Select the research method
and design the study
Step 3: Collect the data
Step 4: Analyze the data and draw
conclusions
Step 5: Report the findings
Hypothesis

a tentative statement about the
relationship between two or
more variables
Operational Definition

describes the actions that will
be made to measure or control
a variable
Subjects/Participants

person’s or animals whose
behavior is systematically
observed in a study
Steps in the Scientific
Investigation





Step 1: Formulate a testable hypothesis
Step 2: Select the research method and
design the study
Step 3: Collect the data
Step 4: Analyze the data and draw
conclusions
Step 5: Report the findings
Types of Research Methods

A. Descriptive Research


1.
2.
Case Studies
Observational Studies






3.
4.
a. Naturalistic Observation
b. Laboratory Observation
Surveys
Tests
B. Correlational Studies
C. Experimental Research
A. Descriptive Research
allow researcher to describe
and predict behavior
 do not show causality

1. Case Studies

detailed description of a
particular individual under study
or treatment
2. Observational Studies

researcher carefully and
systematically observes and
records behavior without
interfering in any way with the
behavior
a. Naturalistic Observation
used to describe behavior as it
occurs in the natural
environment
 measure behavior in a
systematic way

b. Laboratory Observation
descriptive study
 takes place in the lab

Types of Research Methods

A. Descriptive Research


1.
2.
Case Studies
Observational Studies






3.
4.
a. Naturalistic Observation
b. Laboratory Observation
Surveys
Tests
B. Correlational Studies
C. Experimental Research
3. Surveys

questionnaires and interviews
that ask people directly about
their experiences, attitudes, or
opinions
4. Tests

procedures used to measure
personality traits, emotional
states, aptitudes, interests,
abilities, and values
Validity

refers to the degree to which
the content of a test is
representative of the domain it
is supposed to cover
Reliability

whether a test yields consistent
results from one time to
another
B. Correlational Studies
Correlation - a measure of how
strongly two or more variables
are related to each other
 Usually used when cannot
control the variables to be
measured

Positive Correlation
High values of one variable are
associated with high values of
another
 Low values of one variable are
associated with low values of
another

Scatter Plot Examples

Put up overhead transparency
Negative Correlation
High values of one variable are
associated with low values of
the other variable
 If there is no relationship
between the variables, they are
uncorrelated

Correlation Coefficient
Correlations are measured using
the correlation coefficient (r)
 r ranges in value from -1.00 to
+1.00.

Causality

Correlational studies give us
information about relationships,
but they cannot tell us anything
about causality
Types of Research Methods
A. Descriptive Research
 B. Correlational Research
 C. Experimental Research

C. Experimental Research
Used to understand causality
 Control situation being studied

Variables

Two types of variables
 1.
 2.
Independent Variables
Dependent Variables
Independent Variable
Variable that is manipulated
 Hold everything constant except
for the independent variable

Dependent Variable

Variable affected by the
manipulation
Experimental and
Control Groups
Experimental group - group
exposed to the manipulation
 Control group - group not
exposed to the manipulation

Random Assignment
Participants randomly assigned
to either the experimental or
control group. This avoids
selection effects.
 Balances individual differences
among participants across
groups

Avoiding Bias


Single-Blind Study - subjects are
not told what condition they are in
Double-Blind Study - person
running experiment does not know
which participants are in which
groups during data collection. This
avoids experimental demand.
Statistics
Statistical analyses used to
quantify strength of association
between variables
 Involves the use of
mathematics to organize,
summarize, and interpret
numerical data

Descriptive Statistics



Used to organize and summarize
data
Provide an overview of numerical
data
Two main components:
 Central
Tendency
 Variance
Central Tendency

Three components to
understanding the typical or
average score
 median
 mean
 mode
Median
Score that falls exactly in the
center of the distribution of
scores
 Half of the scores fall above the
median and half fall below the
median

Mean

Arithmetic average of the scores
in the distribution
Mode

the most frequent score in the
distribution
Variance
How much the scores in the
data set vary from each other
and the mean
 Standard Deviation - index of
the amount of variability in a
set of data

Inferential Statistics

Used to evaluate the probability
that results might be due to
chance
Statistical Significance
Statistical significance - when
low probability that observed
findings are due to chance
 Very low usually means less
than 5 chances in 100
