Exam One - Sampling in PT literature

Question 1

Generalization

Answer 1

process of drawing conclusions (that apply to all) from a small number of observations

Question 2

population

Answer 2

larger group to which results are generalized

Question 3

sample

Answer 3

a subgroup of the population used for estimating characteristics of that population

Question 4

inclusion criteria

Answer 4

description of the traits that qualify someone to be a subject
to whom can we generalize these results to?

Question 5

exclusion criteria

Answer 5

description of factors that preclude participation
factors are generally confounding to the results

Question 6

What is the value of inclusion and exclusion criteria?

Answer 6

• define your population
• limit the influence of confounding subject characteristics

Question 7

efficacy

Answer 7

very strict inclusion and exclusion criteria minimize selection bias and increase your ability to make cause/effect conclusions

Question 8

efficacy trials =

Answer 8

high control, limited bias

Question 9

effectiveness

Answer 9

less strict inclusion and exclusion criteria. increase risk for bias, limit control, and offer less confidence in cause/effect conclusions

Question 10

effectiveness trials

Answer 10

limited control, greater bias

Question 11

probability sampling

Answer 11

randomization involved at some point in the process

Question 12

non-probability sampling

Answer 12

no randomization
must question ability to generalize
far more common in clinical research

Question 13

What are the main types of probability sampling

Answer 13

• simple random sampling
• systematic sampling
• stratified sampling
• cluster sampling

Question 14

simple random sampling

Answer 14

each member of the population of interest is equally likely to be selected
(requires entire pop to be known)

Question 15

systematic sampling

Answer 15

participants chosen from a list (every Kth name)
no independent chance of being selected
need a list of the entire population

Question 16

stratified sampling

Answer 16

limits sampling error associated with pure random sampling b/c its possible to randomly over/undersample on some key variable
- random sampling from subgroups

Question 17

cluster sampling

Answer 17

divide pop into clusters, randomly sample clusters, measure all units within sampled clusters and then extrapolate to entire population

Question 18

What are some types of nonprobability sampling

Answer 18

1 - convenience sampling
2 - quota sampling

Question 19

convenience sampling

Answer 19

“they are there” very common
- subjects chosen based on availability
- subjects typically from one clinical site
- volunteers tend to have greater motivation
- enrollment typically as participants become available

Question 20

quota sampling

Answer 20

• nonprobability of stratified sampling
  0 subgroups of subjects that vary on some characteristic are recruited until appropriate sample size is reached

Question 21

The more subjects you analyze, the _________ confident you can be that your sample represents the pop characteristics you with to measure

Answer 21

more

Question 22

internal validity

Answer 22

the degree that a cause and effect relationship is free from the effects of confounding variables
- our confidence that a change in one thing CAUSED a change in the outcome of interest

Question 23

what are 3 requirements for internal validity

Answer 23

1 - temporal precedence
2 - covariation of cause and effect
3 - no plausible alternative explanations

Question 24

temporal precendence

Answer 24

the change in outcome must occur after a change in the treatment

Question 25

covariation of cause and effect

Answer 25

outcome only occurs in the presence of the intervention or greater intervention, greater outcome

Question 26

no plausible alternative explanation

Answer 26

rule out competing reasons for the observed change in the outcome of interest besides the intervention

Question 27

What are some threats to internal validity?

Answer 27

- history - maturation - testing - instrumentation - mortality/attrition - regression to the mean

Question 28

history effects

Answer 28

events unrelated to the study that may influence the dependent variable

Question 29

maturation effects

Answer 29

changes occur in the outcome of interest as a result of the passing of time or time might change the outcome measure

Question 30

testing effects

Answer 30

repeated test taking may improve scores

Question 31

instrumentation effects

Answer 31

a change in instrumentation that affects the outcome of interest

Question 32

mortality/attrition effects

Answer 32

subjects are "dying" with respect to your study (dropping out)

Question 33

regression to the mean effects

Answer 33

statistical phenomenon that affects studies where groups are selected based on extreme scores to a single test

Question 34

How do you stop the outcome of interest being affected by any interaction of the subject with the investigator

Answer 34

blinding the subjects and/or investigator

Question 35

What are two types of social threats to internal validity?

Answer 35

- performance bias - attention bias

Question 36

Performance bias (2 types)

Answer 36

- contamination - conintervention

Question 37

performance bias

Answer 37

inconsistency in the application of the experimental condition

Question 38

contamination

Answer 38

members of the control group receive the intervention

Question 39

cointervention

Answer 39

subjects seek/receive another form of treatment that influences the DV during the experiment

Question 40

attention bias (2 types)

Answer 40

- hawthorne effect - reverse hawthorne effect

Question 41

hawthorne effect

Answer 41

people's behavior and performance improve following any new or increased attention

Question 42

reverse hawthorne effec

Answer 42

peoples behavior and performance decline if they perceive they are not receiving equal attention and care

Question 43

recall bias

Answer 43

error associated with self-report tools asking for subjects to recall past events

Question 44

external validity

Answer 44

can you generalize your results to other patients, settings, or times?

Question 45

people threat to EV

Answer 45

selection process yields sample that does not represent the pop the researches hope to apply the results to

Question 46

place threat to EV

Answer 46

outcomes affected by the setting in which the data were collected

Question 47

ecological validity

Answer 47

study atmosphere resembles real life

Question 48

time threats to EV

Answer 48

results of an experiment specific to the era the data were collected