Non-experimental

Research Designs

NURSING 503
Week 5, October 5, 2005

Dr. K KovacsBurns 1
 Overview – Main topics
 Non-experimental vs experimental
designs
 When to use non-experimental designs
 The types of non-experimental designs
 Advantages & disadvantages
 Studies using surveys
 Epidemiologic research designs
Dr. K KovacsBurns 2
 A continuum of quantitative
research design

Experimental Quasi-experimental Non-experimental

l_____________l_____________l

Dr. K KovacsBurns 3
Reasons for Undertaking
Nonexperimental Studies
 Number of human characteristics/ independent
variables are not subject to experimental
manipulation or randomization
 Some variables cannot ethically be manipulated
 For some research, it is not practical to conduct a
true experiment/manipulate variables
 For some situations, it is more realistic to explore
phenomena in more natural manner
 Nonexperimental research is often needed to scope
out the experimental one
Dr. K KovacsBurns 4
 Key Characteristics

 A research design in which a researcher

observes a phenomenon without
manipulating the independent variables(s)
 No manipulation
 Independent variables have already
occurred, so no control over them
 Clear, concise problem statement that is
based on a theoretical framework, or natural
phenomenon. Dr. K KovacsBurns 5
Classification of
NonExperimental designs:

 Descriptive/exploratory survey studies

 Interrelationship/difference
 Correlational studies
 Ex post facto studies
 Prediction studies
 Developmental studies
 Cross-sectional & longitudinal studies
 Retrospective & prospective studies
Dr. K KovacsBurns 6
 Descriptive/Exploratory Survey
 Broadest category
 Detailed observations, descriptions &
documentation of existing variables
 Little is known about the phenomenon
 Justifies, assesses current conditions/practice
 Variables of interest: opinions, attitudes or facts
 Determines differences between variables
 Data collected by questionnaire or interview
 Researchers only relate one variable to another,
no attempt to determine causation
Dr. K KovacsBurns 7
Exploratory Survey Research
 Designed to obtain information about
 prevalence
 distribution
 interrelations of variables within a population
 Census vs. sample surveys
 Self-reporting
 Flexibility and broadness
 Superficiality – extensive vs. intensive
analysis
Dr. K KovacsBurns 8
 Two aspects about surveys:
Survey Content Survey Administration
 Direct questioning  Different data
 Answering how, collection methods
what,and to what  Personal interviews
extent questions  Telephone interviews
 Usually focus on what
 Self-administered
was done and what questionnaires
people plan to do in (SAQs)
the future  Mixed-mode strategy
Dr. K KovacsBurns 9
 How surveys inform practice
 Needs assessment – estimate needs of a group,
community or organization; & make
recommendations for priorities
 Face-to-face interviews using surveys yields quality
data about the person being interviewed & the
question posed
 Delphi surveys for short-term forecasting based on
panel of experts’ opinions, predictions, and judgment
about a topic
 Secondary analysis of surveys yields more details
 Meta-analysis of similar studies to integrate large
body of findings & observations
Dr. K KovacsBurns 10
Descriptive Research
 Purpose is to
 observe, describe, & document aspects of a
situation as it naturally occurs
 serve as a starting point for hypothesis
generation or theory development
 Types:
 Descriptive Correlational Studies
 Univariate Descriptive Studies
 Prevalence Studies
 Incidence Studies

Dr. K KovacsBurns 11
Descriptive Correlational Studies

 Describes the relationship among

variables rather than infer cause-and-
effect relationships

 Are usually cross-sectional

Dr. K KovacsBurns 12
Univariate Descriptive Studies
 Could focus on one or more variables
 Undertaken to describe the frequency
of occurrence of a behavior or
condition or each variable rather than
relationships between or among them
 Types:
 Prevalence Studies
 Incidence Studies
Dr. K KovacsBurns 13
Prevalence Studies
 Done to determine the prevalence rate
of some condition at a specific point in
time
 Data is obtained from the population at
risk for the condition – cross sectional
design
Prevalence Rate (PR) = # cases with condition X K
# in population at risk

Dr. K KovacsBurns 14
 Incidence Studies
 Used to measure the frequency of developing new
cases
 Need longitudinal designs

Incidence Rate (IR)=

# new cases with condition over given period X K
# at risk of becoming a new case

 Relative Risk: an estimate of risk of “caseness” in

one group vs. another; contribution of risk factors
 E.g. males vs females for acquiring depression
Dr. K KovacsBurns 15
 Descriptive/Exploratory Survey (cont’d)

 Advantage:
 large amount of information can be
obtained from a large population in an
economical manner which is “surprisingly” accurate
 Disadvantages
 Info tends to be superficial as breadth is
emphasized
 Expertise in: sampling techniques, questionnaire
construction, interviewing and data analysis to
produce a reliable and valid study.
 Time-consuming & sometimes costly
Dr. K KovacsBurns 16
 Interrelationship/Difference Studies:
Correlational Studies
 Examines if variables covary
 Quantifies the strength or relationship between the variables (not cause &
effect)
 +ve or –ve direction relationship determined
 Advantages:
 Increased flexibility when investigating complex relationships among variables
 Efficient and effective method of collecting a large amount of data
 Potential for practical application in clinical settings
 Potential foundation for future, experimental studies
 Framework for exploring relationships that are not manipulated.
 Disadvantages:
 Unable to manipulate variable of interest
 No randomization in sampling
 Generalizability decreased as dealing with preexisting groups
 Unable to determine a causal relationship because of the lack of manipulation,
control and randomization.
Dr. K KovacsBurns 17
 Interrelationship/Difference Studies:
Ex Post Facto Studies
 Literally means ‘from after the fact’
 Also known as causal-comparative studies or
comparative studies
 Explores differences/relationships between variables
(similar to quasi-experimental designs)
 Advantages:
 Allows for establishment of a differential effect
 Similar to correlational designs
 Offers a higher level of control

 Disadvantages:
 Lack of control on variables
 Unable to draw causal linkage
 Problem of alternative hypothesis
Dr. K KovacsBurns 18
 Interrelationship/Difference Studies:
Developmental Studies

 Not only concerned with existing status &

interrelationship of phenomena but also with changes
from elapsed time.
 Cross sectional (one/more time points, perhaps
different groups) vs Longitudinal (several time points
with same group over extended period)
 Retrospective (dependent variable has already been
affected by independent variable, link present events to
past events) vs Prospective (link present events to
presumed future effect, less common, considered
stronger design)
Dr. K KovacsBurns 19
Others

Natural Experiments: study of a group

exposed to natural or other phenomenon
that have health or other consequences,
compared with a nonexposed group; people
are affected at random
Path Analytic Studies: using a technique
called path analysis, nonexperimental data
is tested against a hypothesized causal
inference
Dr. K KovacsBurns 20
Epidemiologic Research Designs
 Cohort studies: trend study in which specific
subpopulations (eg age specific) are examined
over time for generational differences
 prospective & retrospective

 Case-control study: comparison of

cases/subjects (with specific condition), with
controls (without condition); only difference
should be exposure to presumed cause
 Cross-sectional design: phenomena under
study are captured during one period of data
collection; one point in time
Dr. K KovacsBurns 21
 Weakest

_______________________________________
Design

ns
sig
22

De
ve
ipti
scr
De al
on
e lati
orr
eC
Continuum of designs for inferring

iv
ect
tr osp
Re al
tion
Non Experimental Designs

ela
orr
eC
ctiv
spe
Pro
gn

Dr. K KovacsBurns
esi
ti cD
aly
An
th
Pa
t
en
rim
pe
Ex
tu ral n
Na esi
g
D
tal
en
rim
pe
causality

Ex sig
n
Pre De
n tal
ri me

Strongest
pe
Ex gn
asi esi
Qu

Design
ta lD
en
rim
xpe
eE
Tru
Questions/Discussion

Dr. K KovacsBurns 23