1-29-08--Preparing for Research

download report

Transcript 1-29-08--Preparing for Research

Preparing for Research
INFO 271B LECTURE 3
COYE CHESHIRE
Today’s Topics:
2
 Constructs, Variables and Causation
 Research Problems
Info 271B
Types of Variables
3
 Nominal
 Categorical
 Dichotomous, Binary,
Dummy Variables
 Qualitative Variables
 Ordinal
 Rank Variables
 Metric
 Interval Variables
 Ratio Variables
Info 271B
Nominal Variables
4

Binary/dichotomous

Example: Gender, event occurred
or did not occur, etc.

When coded as 0/1, also called
‘dummy variables’
Three New Dummy Variables:

Nominal/non-ordered
polytomous

Example: Employment Status
• 1= Employed
• 2= Unemployed
• 3= Retired
Info 271B
Employed (0,1)
Unemployed (0,1)
Retired (0,1)
Ordinal Variables
5

Info 271B
Ordered polytomous

Example: Likert scales

Any ordered, categorical variable
where the distance between
categories may not be equal and
meaningful
Metric Variables
6

Interval
Distance between attributes has
meaning
 Example: Celsius temperature,
“likert-scale” questions


Ratio
Distance between attributes has
meaning, and there can be a
meaningful zero.
 Example: Kelvin temperature,
Count variables

Info 271B
7
Constructs, Variables and Causation
Info 271B
Info 271B
Time spent
Exercising between
Time 1 and Time 2
Difference in Weight
Scores between Time1
And Time 2
Gender
(Male =1,
Female =2)
Scale 1-5 of attitude
About Presidential
Candidate
Ethnic Identity
(10 Racial Types)
Owns and iPod or not
8
An example theoretical model
9
Socioeconomic
Status
Academic
Achievement
Academic Ability
Info 271B
Theoretical Model with Variables
10
Income
Job
Prestige
Socioeconomic
Status
Academic
Achievement
Academic Ability
Grades
Math skills
Info 271B
Language
skills
Level of
Schooling attained
Causation and Causal Paths
11
 Direct causal paths
X
Y
 Reciprocal causation
X
Y
 Indirect causation
X
Info 271B
Z
Y
Conditions of Causality
12
 Covariation
 Non-spurious
relationship
X
 Logical time ordering
 Mechanism to explain
how X causes Y
Info 271B
Y
Hypothesis
13
 “hypothesis
statements contain two or
more variables that are measurable or
potentially measurable and that specify
how the variables are related” (Kerlinger
1986)
Info 271B
Propositions and Hypotheses
14
 Propositions link concepts together with specific
relationships
Drug Use
Violence
 Hypotheses link variables together with specific
relationships
Number of Times
Person Consumed
Drug X over Time T
Info 271B
Observed ‘violent acts’
Over time Y
Next Class: Criteria for a Research Problem
(1) What are we going to learn
as the result of the
proposed project that we
do not know now?
(2) Why is it worth knowing?
(3) How will we know that the
conclusions are valid?
15