NonExperimental Research Designs

1
Non-Experimental Research Designs
2
Non-Experimental Designs

• Purpose Examines a present situation or
  population as it naturally exists
• 1st step in inductive process of theory
  development
• No treatment or intervention
• Does not determine cause effect

Not determined by methods!
3
Non-Experimental Designs

• Descriptive (demographic)
• Correlational
• Causal Comparative

4
Non-Experimental Designs

• Descriptive (demographic)
• Correlational
• Causal Comparative

5
Descriptive Designs

• Purpose Describes a present situation or
  population as it naturally exists
• Typical methods survey or observation
• Research question common
• Research hypothesis??

Not determined by methods!
6
Non-Experimental Designs

• Descriptive (demographic)
• Correlational
• Causal Comparative

7
Correlational Research

• Explores relationships to explain individual
  variation
• Uses statistical technique of correlation or
  regression
• Criterion variables
• Predictor variables

8
Purpose of Correlational Research

• Used to predict future events even when we do not
  know why they occur
• Supports or refutes theory - preliminary to
  hypothesis testing

9
Correlation Coefficient

• Direction
• Strength

10
Strongest?
Positive?
Negative?
11
Correlation Coefficient
r
-1.0 0 1.0
12
Correlational Research

• Simple Correlation (bivariate)
• Multiple Correlation
• Canonical Correlation

13
Using Correlation for Prediction

• Simple regression (bivariate)
• Multiple Linear Regression
• Regression (prediction) equation

14
?
15
Spurious Relationships

• Relationship between 2 variables is explained by
  a third variable
• Balding Heart attacks hormone levels
• Height - Heart attacks childhood nutrition
• Controlled with partial correlation

16
Partial Correlation Technique
17
Partial Correlation Technique
18
Partial Correlation Technique
19
Examples of Correlational Research

• A researcher measured students self esteem and
  linked these scores to hours that students
  participated in recreational activities
• Causal mechanism

parental support
20
Examples of Correlational Research

• A researcher measured students self esteem and
  linked these scores to ratings of their physical
  attractiveness
• A researcher measured how quickly students
  complete a test to see if their speed was
  associated with test scores

21
Examples of Correlational Research

• A researcher investigated the relationship
  between age and reaction time in a simple task
  (push the left button to a red light, the right
  button to a green light)
• A researcher studied a group of 20-yr olds by
  examining the association between height and the
  age (in weeks) when they first began walking

22
Flawed Interpretations of Correlational Research

• Positive correlation between babies born and
  population of storks around the calendar year
  storks cause babies.
• Causal mechanism Climate

23
Flawed Interpretations of Correlational Research

• Positive correlation between speed of test taking
  and scores on test speed causes better
  performance.
• Causal mechanism Students who take test faster
  may have prepared better, which makes them score
  high and take the test more quickly

24
Flawed Interpretations of Correlational Research

• Positive correlation between of churches and
  of liquor stores in American cities going to
  church causes you to drink.
• Causal mechanism Larger cities have more
  churches and more liquor stores.

25
Statement of the Problem

• The problem was to determine the extent to which
  participants in outdoor recreation programs in
  college drop out and the reasons for their
  dropping out.

• Correlational Design
• IV, DV
• Research Hypothesis or Question
• Partial Correlation Control

26
Caution!!!

• Do not assume cause-and-effect

27
Non-Experimental Designs

• Descriptive (demographic)
• Correlational
• Causal Comparative

28
Causal Comparative Research

• Groups classified according to common preexisting
  characteristic and compared on some other measure
• No intervention, manipulation, or random
  assignment

29
What causes lung cancer?

• Finding People with lung cancer smoke more than
  people without lung cancer. There are no other
  differences in lifestyle characteristics between
  the groups.
• Conclusion Smoking is a possible cause of lung
  cancer.
• Caution A third factor? Proper matching?

30
Value of Causal Comparative Research

• Uncovers relationships to be investigated
  experimentally
• Used to establish cause-effect when experimental
  design not possible
• Less expensive and time consuming than
  experimental research

31
Two Variations

• IV presumed cause DV presumed effect
• Groups formed on the basis of how much TV they
  watch, and compared on academic achievement
  (GPA).
• Groups formed on the basis of gender, and
  compared on strength of career aspirations.

32
Two Variations (cont.)

• IV presumed effect DV presumed cause
• Groups formed on the basis of whether they
  dropped out of high school, and compared on lack
  of mentoring relationship.
• Groups formed on the basis of difficulty in
  learning to read, and compared on time parent
  spent reading to child.

33
Strengthening CC Designs

• Strong inference
• Time sequence
• Common prior antecedents
• Matched group design
• Extreme groups design
• Statistical control

34
Common IVs in C-C Research

• Sex
• Ability
• Personality
• Socioeconomic status
• Preschool experiences

35
Examples of Causal Comparative Research

• A researcher measured the mathematical reasoning
  ability of young children who had enrolled in
  Montessori schools and compared the scores with a
  group of similar children who had not been to
  Montessori schools.
• A researcher measured the frequency of students
  misbehavior at schools which use corporal
  punishment and compared that to schools which did
  not use corporal punishment.

36
Examples of Causal Comparative Research

• A researcher compared the high school dropout
  rate between students who had been retained (held
  back) in elementary school vs. similar students
  who had not been retained
• A researcher formed 3 groups of preschoolers
  those who never watched Sesame Street, those who
  watched it sometimes, and those who watched it
  frequently and then compared the 3 groups on a
  reading readiness test

37
Common Methods Used in Non-Experimental Designs

• Survey (poll, census)
• Observation
• Ethonographic (qualitative, naturalistic)

38
Common Content Areas that Use Non-Experimental
Designs

• Historical
• Epidemiological
• Normative
• Developmental (longitudinal vs. cross-sectional)

39
Developmental Research

• Longitudinal
• Powerful (within subject)
• Time consuming
• Attrition
• Testing effect

• Cross Sectional
• Less time consuming
• Cohorts problem

40
Methodological Problems of Developmental Research

• Unrepresentative scores
• Unclear semantics
• Lack of reliability
• Statistical problems

For children
41
Medford Boys Growth Study
Initial assessments
20 years
10 years
Final
1956 1961 1966 1971 1976
1981 1986
42
Overhand Throw for Distance
K 1 2 3
Males
Females
43
Overhand Throwby Grade and Gender
44
Use of Non-Experimental Designs

• Naturalistic
• vs.
• Positivistic

45
Statement of the Problem

• The problem was to determine the extent to which
  participants in outdoor recreation programs in
  college drop out and the reasons for their
  dropping out.

• Descriptive Design
• IV
• DV
• Research Hypothesis or Question

46
Statement of the Problem

• The problem was to determine the extent to which
  participants in outdoor recreation programs in
  college drop out and the reasons for their
  dropping out.

• Descriptive Design Developmental Study
• IV
• DV
• Research Hypothesis or Question

47
Statement of the Problem

• The problem was to determine the extent to which
  participants in outdoor recreation programs in
  college drop out and the reasons for their
  dropping out.

• Descriptive Design using Poll Method
• IV
• DV
• Research Hypothesis or Question

48
Statement of the Problem

• The problem was to determine the extent to which
  participants in outdoor recreation programs in
  college drop out and the reasons for their
  dropping out.

• Descriptive Design using Case Study Method
• IV
• DV
• Research Hypothesis or Question

49
Statement of the Problem

• The problem was to determine the extent to which
  participants in outdoor recreation programs in
  college drop out and the reasons for their
  dropping out.

• Correlational Design using Survey Method
• IV
• DV
• Research Hypothesis or Question

50
Statement of the Problem

• The problem was to determine the extent to which
  participants in outdoor recreation programs in
  college drop out and the reasons for their
  dropping out.

• Causal Comparative Design
• IV, DV
• Research Hypothesis or Question
• Strengthen??

51
Statement of the Problem

• The problem was to determine the extent to which
  participants in outdoor recreation programs in
  college drop out and the reasons for their
  dropping out.

• Causal-Comp Design Developmental Study
• IV, DV
• Research Hypothesis or Question
• Strengthen?

52
Summary

• Design should be chosen according to
• What will best examine the problem you have
  developed?
• What is ethical?
• What is feasible?