RESS3

Question 1

What is a clinical audit?

Answer 1

measures existing practice against evidence-based clinical standards

Question 2

What is a service evaluation?

Answer 2

evaluates a proposed service or current practice with the intention of generating information to inform local decision making

Question 3

What is your outcome?

Answer 3

your health or healthcare issue

Question 4

What is your exposure?

Answer 4

factors affecting the outcome

Question 5

What does PECOS stand for?

Answer 5

Patient/participant/people
Exposure/event/experimental intervention
Comparison
Outcome
Study design

Question 6

What are examples of sampling bias and define them

Answer 6

external validity- non-representative samples

confounding- selection influences outcome and exposure

Question 7

What are examples of measurement bias and define them

Answer 7

information bias- extent of information varies among participants
observer bias- influenced by prior knowledge or belief
recall/response/prestige bias- influenced by prior knowledge or belief

Question 8

What are examples of analytical bias and define them

Answer 8

loss to follow up- specific participants excluded
omitted variable bias- imprecise adjustment for confounding
attributional bias- interpretation of causality

Question 9

What is an example of dissemination bias and define it

Answer 9

publication bias- ‘eventful’ results more likely to be published

Question 10

Examples of descriptive (inductive) studies

Answer 10

case control
cross sectional (descriptive)

Question 11

Examples of Analytical (deductive) studies

Answer 11

Observational:

• cross sectional (analytical)
• case/control
• cohort

Experimental:
-trial

Question 12

What is the hierarchy of analytical study design

Answer 12

meta-analysis (reproducibility)
trail (causality)
cohort (directionality)
case control (between samples)
cross sectional (within a sample)

Question 13

Ethics, governance and consent

Answer 13

ethics- ensuring that projects minimise risks and maximise benefits
governance- ensuring that projects have appropriate permissions
consent- ensuring participation is voluntary and without ‘cost’

Question 14

What types of projects do not require formal ethical approval?

Answer 14

secondary research (data already published)
non-human research
audit/service evaluation (using only existing management data)
service evaluation (collecting new information only on existing service delivery)

Question 15

What types of projects do require formal ethical approval?

Answer 15

Non-human subject covered by the 1986 animal act
service evaluation involving vulnerable groups
experimental research
some non-experimental research

Question 16

What is a sample?

Answer 16

a collection of data drawn from a population

Question 17

What is the target population?

Answer 17

the total finite population we wish to know about from which your sample is drawn

Question 18

What is the study sample?

Answer 18

the units/participants drawn from the target population that constitute our date set

Question 19

What is a complete sample? Pros and cons

Answer 19

the entire study population
P: no bias
c: expensive

Question 20

What is un-stratified random sampling? Pro and cons

Answer 20

every member of the target population has the same chance of being sampled
P: easy to design and conduct
C: smaller groups can be under presented by chance

Question 21

What is stratified random sampling?

Answer 21

randomly sample from the target population within strata
P: representative
C: population may not easily be divided into strata, strata may not be known until after sampling

Question 22

What is the difference between a null and alternative hypothesis

Answer 22

null- no effect, no difference between groups

alternative- a effect, a difference between groups

Question 23

What is the p-value?

Answer 23

the p value is a measure of the probability of obtaining the results of the test given that the null hypothesis is true.
the smaller the p value the less likely the result is to have occurred by chance alone
when the p-value is less than 0.05 the the results are statistically significant

Question 24

what is odds?

Answer 24

odds is the number of times the event occurs divided by the number of times it does not occur. Odds ratio calculates relative risk

Question 25

What does a 95% confidence interval mean?

Answer 25

if the 95% confidence interval does not include the null (odds ratio =1) then the association is significant (p=0.05). As we increase our sample size, our estimates become more accurate, so our confidence intervals shrink

Question 26

What is power?

Answer 26

power is the probability of rejecting the null hypothesis when the null hypothesis is false. I.e. the probability of finding an association if it is there to be found Usually the aim is 80% power i.e. probability of 0.8 of finding a difference/ detecting an association

Question 27

What is odds ratio

Answer 27

a measure of telling us how much more likely an event is to occur amongst those who are exposed if no effect the odds ratio =1 even if your odds ratio is above 1 if the confidence intervals include 1 then it is not significantly different to the null for a study of this sample size

Question 28

What are co-variates

Answer 28

variables that affect the exposure and/or outcome

Question 29

What is a confounder?

Answer 29

variables that affect both the exposure and the outcome

Question 30

What is a mediator?

Answer 30

variables that cause the outcome and are caused by the exposure

Question 31

What is a competing exposure?

Answer 31

Variables that cause the outcome

Question 32

What does DAG stand for?

Answer 32

directed acyclic graphs

Question 33

What is a prospective study and give examples

Answer 33

they record variables over the study period, with the outcome measured subsequently cohort (directionality)

Question 34

What is a retrospective study and give examples

Answer 34

measure the outcome then look backwards to measure the exposure and other variables case-control or studies using patients records

Question 35

What is response bias?

Answer 35

what the interviewer wants/gets

Question 36

what is prestige bias?

Answer 36

what appears favourable

Question 37

What is recall bias?

Answer 37

prospective/retrospective

Question 38

What is R2 (squared)

Answer 38

the proportion of variation explained by the linear model takes a value between 0 and 1 higher values indicate that more of the variation is explained by your model, i.e. it is a better fit 1 is a perfect fit so your model perfectly predicts the outcome

Question 39

What are the 3 key concepts in economics?

Answer 39

opportunity cost efficiency marginal analysis

Question 40

What is opportunity cost?

Answer 40

the value of something when a particular course of action is chosen

Question 41

What is efficiency and what are the two types?

Answer 41

maximising the benefit for the resource used technical: meeting a given objective at least cost allocative: producing the output (supply) that matches consumer want (demand)

Question 42

What does marginal analysis involve?

Answer 42

comparing the benefit from that next step (marginal benefit) with the cost of taking the next step (marginal cost)

Question 43

What is economic evaluation?

Answer 43

a comparison of two or more alternative courses of action in terms of their costs and their outcomes

Question 44

what is cost effectivness analysis?

Answer 44

benefits measured in terms of standard clinical outcome. | also considers life years gaines

Question 45

what is cost utility analysis?

Answer 45

considers both quality and quantity life

Question 46

what is cost benefit analysis?

Answer 46

considers resource use and health beneifts in monetary terms

Question 47

What is option appraisal?

Answer 47

another type of economic evaluation | a structured process for identifying, describing and evaluations alternative methods of acheiving an agreed objective

Question 48

What is the ICER?

Answer 48

incremental cost effectiveness ration cost effectiveness analysis calculates the expected cost per additional unit of health produced by a new intervention compared to current practice

Question 49

What is the cost effectiveness threshold?

Answer 49

maximum amount the health service will pay per unit of health gained. it represents the maximum opportunity cost consistent with improving population healthy by introducing a new intervention