RESEARCH DESIGN Flashcards
1
Q
PICO
A
P- population/patient/problem
I- intervention
C- comparison
O- outcome
2
Q
research design is overall plan for
A
answering research question
3
Q
your questions should have
A
- nature of comparison
- type of setting
- population, sample
- independent and dependent variable
4
Q
comparisons between 2 groups or more
A
- single group: 2 or more points in time (pre/post)
- single group under different circumstances or experiences (group v individual therapy)
- based on relative rankings (severe v mild autism)
- compare with samples from other studies
5
Q
research designs methods to be used to control
A
variables (isolate dependent and independent variables)
6
Q
control variables
A
external things that will affect dependent and independent variables
7
Q
research designs timing and frequency of
A
data collection (when, relative to other events) overtime looking at change
8
Q
research designs setting
A
(naturalistic v laboratory)
9
Q
research designs nature of communications with subjects
A
(fully divulge or not)
are you going to tell them they’re subjects
10
Q
dimensions along which designs can be described
A
- experimental vs non-experimental
- degree of structure imposed
- time dimension
- type of group comparisions betwene subjects and within subjects
- non-experimental
11
Q
experimental
A
quantitative
12
Q
non-experimental
A
qualitative
13
Q
degree of structure imposed
A
how much we are controlling
14
Q
time dimension
A
- longitudinal
- cross-sectional
15
Q
multiple points of data collection secondary to
A
- study time related processes
- determine time sequences
- developing comparisons
- enhancing research control
16
Q
trend studies
A
- looking at impact of something that is happening over time
- multiple periods of time
- observing what’s going on with trends
17
Q
cohort
A
- when you take small population (by age)
- study them over time with respect to a phenomenon (subject)
18
Q
panel studies
A
take same cohort and measure across 2 periods of time
19
Q
follow up studies
A
how they feel about same topic in a period of time (5 years down the road)
20
Q
cross section cohort
A
comparing 2 different cohorts
21
Q
follow up study can be
A
panel study
22
Q
type of group comparisons between subjects and within subjects
A
2 subjects at the same time
23
Q
within subjects
A
in same group of people (more control of variables)
24
Q
between subjects
A
different group of people
25
non-experimental
not manipulating anything (qualitative)
- retrospective
- prospective
26
retrospective
- have an outcome
| - want to knwo what causes are (antecedent) study prior to habits
27
prospective
- know causing variables
- going forward in time
- see how many develop outcomes
28
cons of retrospective
- memory might not be accurate
- might get defensive
- might not be telling the truth
29
usually do prospective after you gain evidence from
retrospective
30
good design must be
appropriate to question asked
31
good design minimize
biases that can distort results of study
32
biases result from
1. differences among participants in groups (non-random groups)
2. researcher's preconceptions minimize this (can do double blind study)
3. use triangulation to reduce bias
33
good design precision must be enhanced
sensitivity with which effect of independent variable relative to effects of (confounding) extraneous variable can be detected, want it high
34
good design power should be adequately dealt with
- ability of design to create maximal contrast amongst group being compared
- one can detect relationship between variables
35
true experimental designs
- manipulation
- control
- randomization
36
manipulation
independent variables
37
control
not getting any treatment
| outside things impact treatment
38
randomization
pick random from different population
- extreme view will be cancelled
- equal chance that they can be picked for any group
39
examples of randomization
- table of random #'s
- flipping a coin
- most reliable method for equating groups on all possible characteristics that could effect outcome of study
40
cluster randomization
picking people in clusters, random, pick a bunch to represent zip code
41
matching
people in each group match and have equal numbers
42
experimental designs: basic
- posttest only
| - pretest/posttest
43
posttest only
someone's been given a treatment and measuring outcome after the fact
44
pretest/posttest
measuring outcomes before and after
45
solomon four group design
take into account influence of pretesting on subsequent posttest results
46
factorial design
1 independent and 1 dependent
47
main effects
1 variable
48
interaction effects
combine independent varibales
49
repeated measures design (cross over)
each patient is randomly assigned to a sequence of treatments
50
randomized control trials
population receiving the program or policy intervention is chosen at random from eligible population, and control group is also chosen at random from the same eligible population
51
quasi experimental designs
- manipulation and control or randomization
- non-equivalent control group design
- time series designs
- time series- non-equivalent control group design
52
non-experimental designs
- why choose them?
- 2 broad classes
- ex-post facto research
- descriprive
53
ex-post facto research
after-the-fact research is a category of research design in which the investigation starts after the fact has occurred without interference from the researcher
54
descriptive
- descriptive correlational
- univariate descriptive
- retrospective
- prospective
55
other non-experimental types
- survey research
- evaluation research
- needs assessment
- secondary analysis
- meta analysis
- historical research
- case studies (single subject designs)
56
strategies in a research study
- triangulation
- mixed methods
- fully integrated
57
triangulation
collecting data from 3 ways
58
mixed methods
mixing methods from different parts of continuum
59
fully integrated
different methods work hand in hand
60
integrated research designs 2 broad categories in multi-method research
- component
| - integrated
61
component
- triangulated
- complementarity
- expansion
62
integrated
- iterative
- embedded or nested
- holistic
- transformative
63
advantages of experimental design
most powerful method available for testing hypotheses of cause and effect relationships between varaibles
64
disadvantage of experimental designs
- many situations in which experimental design is impossible
- secondary to ethical or protocol considerations
- artificiality of setting
- randomness not always real
65
hawthrone effect
- placebo effect
| - knowledge of being included in study may be sufficent to cause people to change their behavior
66
study could have double hawthorne effect
- when those conducting study also change their behvaior
| - therefore, do double blind study so neither researcher nor subject know
67
repeated measures design
- one group tested under all conditions
| - within subjects design
68
repeated measures design strong design because of
ability to control potential influence of individual differences
69
repeated measure design disadvantage is
- practice effects
- exposure to test
- one way to combat this is increase length of time between treatments, so subject's scores can go back to baseline
70
one way repeated measure design
1 group of subjects exposed to all levels of 1 independent variable
- order effects can occur
- that is potential biasing effect of test sequence
- so randomize order of presentation for each subject
- 1 way ANOVA test
71
ANOVA
- Analysis of variance
| - find out whether differences between groups of data are statistically significant
72
crossover design
when there are only 2 levels of independent variable
- 1/2 recieve treatment A, then treatment B
- 1/2 recieve treatment B followed by treatment A
- again add time in between to remove any testing effect or treatment residual effect
- 2 way ANOVA, paired t-test
73
paired t-test
interested in the difference between two variables for the same subject
74
two way design with two repeated measures
- 2 independent variables with 2 levels each
- subjects get all 4 conditions
- 2 way ANOVA
75
correlational
degree of association among variables
| -it is function of covariation in data
76
descriptive correlational
describe nature of existing relationships
77
univariate descriptive
1 variable
78
restrospective
examine data collected in past
79
prospective
current data and follow up in future
80
survey research
statistical
81
evaluation research
how well something is doing (standardize)
| what is going on
82
needs assessment
collect data on what place is like/what they need may have multiple needs
83
secondary analysis
take existing data set ask different research question and analyze
84
meta analysis
take a bunch of studies that are asking same question and study in different population combine statistically (quanitiative)
85
content analysis
can be numerical/qualitative
| frequency of idea
86
historical research
go back and look at old records/artifacts to recreate history
87
case studies
look at individual in depth every client factor
| look at them holistically
