Exam 2

Question 0

Practitioner’s Conundrum: Constructivism vs. Empiricism

Answer 0

• Constructivism: generate knowledge from the interpretations of their experiences
• Empiricism: generate knowledge by systematically testing hypotheses to prove or disprove them
• Need to live in BOTH worlds to maximize care

Question 1

Deductive vs. Inductive Reasoning

Answer 1

• Deductive: take info and make conclusion w/ other knowledge
• Inductive: make conclusion with what you observe

Question 2

Law vs. Theory

Answer 2

• Law: states that something happens, if A then B

- Theory: summarize/provide explanations for findings, stimulate development of new knowledge, don’t become laws

Question 3

Scientific Method

Answer 3

1. Ask research question
2. Do background research
3. Construct hypothesis
4. Test with an experiment
5. Analyze results and draw conclusions
6. Report Results
7. Think and try again if needed

Question 4

Components that describe Scientific Method

Answer 4

1. systematic = order for reliability
2. empirical = info gathered via observation or experiment
3. critical examination = statistics, report results

Question 5

Hierarchy of Evidence (highest to lowest)

Answer 5

1. RCT
2. Cohort studies
3. Case control studies
4. Case series studies
5. Expert opinion

Question 6

Types of Probability Sampling

Answer 6

1. simple random sampling
2. systematic sampling
3. stratified random sampling
4. disproportional sampling
5. cluster sampling

Question 7

Simple Random Sampling

Answer 7

table of random #s and computer randomly identifies starting point or who is selected

Question 8

Systematic Sampling

Answer 8

have a population of 10,000 and want a sample of 100 so you pick every 10th person

Question 9

Stratified Random Sampling

Answer 9

randomly select students from different schools but not equally proportional or represented from each school

Question 10

Disproportional Sampling

Answer 10

selecting same #s from same population, but it is disproportionate of population (10 girls and 6 boys, pick 2 of each)

Question 11

Cluster Sampling

Answer 11

population –> several clusters –> take sample from each cluster which is equal in size and similar

Question 12

Nonprobability Sampling Types

Answer 12

1. Convenience sampling
2. Quota sampling
3. Purposive sampling
4. Snowball sampling

Question 13

Convenience Sampling

Answer 13

based on availability, potential bias due to self selection

Question 14

Quota Sampling

Answer 14

picking an adequate number for each group

Question 15

Purposive Sampling

Answer 15

handpicked subjects for a purpose that is extremely specific

Question 16

Snowball Sampling

Answer 16

original sample provides selection for more subjects

Question 17

Validity

Answer 17

• believability

- degree to which the relationship between IV and DV is free from effects of extraneous factors

Question 18

Types of Experimental Design Validity

Answer 18

1. Statistical Conclusion Validity
2. Internal Validity
3. Construct Validity
4. External Validity
5. Face Validity?

Question 19

Statistical Conclusion Validity

Answer 19

• inappropriate use of statistics
• low statistical power
• violated assumptions of statistical tests
• reliability and variance
• error rate/overuse of statistics

Question 20

Internal Validity

Answer 20

• is there a causal relationship b/w IV and DV outside of what study is looking for?
  1. Single Group Threats
  2. Multiple Group Threats
  3. Social Threats

Question 21

Internal Validity: Group Threats to Validity- assignment, history, maturation, attrition, testing, instrumentation, regression

Answer 21

1. assignment- when putting participants in groups, are group characteristics equal or reported?
2. history- outside of control of study, related to ADLs
3. maturation- change internal to participants that occur over time
4. attrition- drop out rate/mortality, threat to intervention study
5. testing- learning effect, when having multiple tests & improvement in tests
6. instrumentation- choose wrong device or approach
7. regression to the mean- extreme baseline values result in next measurement closer to mean

Question 22

Internal Validity: Social Threats

Answer 22

1. diffusion or imitation of treatments- participants have contact and change treatment
2. compensatory equalization of treatment- control group receives something to make up for experiment group
3. compensatory rivalry or resentful demoralization- control group hears about exp group and rivalry (we’re gonna do better) or resent (why bother and drop out)

Question 23

Construct Validity

Answer 23

• to what theoretical constructs can results be generalized?
  1. poor operational definitions- can’t replicate
  2. multiple treatment interactions- different interventions influence results
  3. length of follow up- time may decrease importance of effect
  4. experiment bias- doing an experiment and Hawthorne effect where people modify behavior due to change in environment

Question 24

External Validity

Answer 24

* can the results be generalized to other persons, settings, or times? 1. biased sample selection- sample different than representative population 2. setting differences- where study conducted can it be generalized to clinic 3. time- older research, things change, circumstances and healthcare change

Question 25

Strategies to Minimize Threats to Validity

Answer 25

1. random assignment- groups similar with random selection 2. control groups- limit maturation 3. blinding- limit interaction of groups/investigators 4. operational definitions- define things well 5. dealing with attrition 6. minimizing intersubject differences

Question 26

Strategies to Minimizing Intersubject Differences

Answer 26

1. selection of homogenous subjects- groups well defined & similar 2. blocking- look at men separately than women 3. matching- male to male 4. using subjects as their own control- reduce variability 5. analysis of covariance- limit covariance of extraneous variables

Question 27

Handling Missing Data (reasons, what to do)

Answer 27

- Reasons: drop out of study, switch to another treatment group, refuse assigned treatment, non compliant - What to do: document why they had attrition, comparison of groups to look for differences, LOCF last observation carried forward as if they didn't get better, Intention to treat

Question 28

CONSORT Statement

Answer 28

go through aspects of study to see the things that need to be described or done in the study