Week 4- Introduction to Evidence Flashcards

1
Q

What is internal validity?

A
  • Conduct of the research

- Are you confident that the research was well conducted so that effect you notice is from exposure or intervention

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is external validity?

A

-Generalisability of research findings from sample to reference population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Describe the difference between chance, bias and confounders

A

Chance: Random error, cannot be eliminated but minimised through having smaller sample size
Bias: Systematic error, errors in way research was undertaken, cannot be eliminated
Confounders: variables not taken into account, influencing outcome

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is marginal probability?

A

Probability of occurrence of single event

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is joint probability?

A

Probability that 2 events will occur simultaneously

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is conditional probability?

A

Probability of one event given another has occurred

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Describe sensitivity and what is the equation?

A

-Ability of a test to correctly identify positive results
-Sensitivity probability of test is positive when patients truly have disease
Sn= TP/TP+FN X 100

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Describe specificity and what is the equation?

A

-Ability of a test to correct identify negative results
-Specificity probability that test is negative when patients truly don’t have disease
Sp= TN/TN+FP x 100

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the true positive rate?

A

Patient has disease and test is positive

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is the false positive rate?

A

Patient does not have disease but test is positive
-Probability that diagnostic test results will be positive given individual truly does not have the condition
(Specificity)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is the true negative rate?

A

Patient does not have disease and test is negative

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is the false negative rate?

A

Patient has the disease but test is negative
-Probability that diagnostic test result will be negative given that individual truly has condition
(Sensitivity)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is the concept of odds ratio?

A

Measure of association between exposure and outcome
-Odds that outcome will occur given particular exposure when compared to odds of outcome occurring in absence of exposure

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the concept of risk ratio?

A

Measure of the risk of an outcome occurring in one group when compare to risk of same outcome occurring in another group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is risk difference?

A
  • Absolute difference between the risks in each group

- Difference in rate of events between 2 groups

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How is risk difference related to the concept of Number Needed to Treat?

A
  • NNT is a common measure used by health professionals, giving the number of people who need to receive the intervention for one additional person to experience or avoid an outcome
  • Risk difference required to calculated NNT (NNT=1/RD)
17
Q

What does the 68-95-99.7 rule refer to, and what is its role in health care?

A
  • Used for normal distribution (bell-shaped) curve only
  • Compare individual data or results to match population
  • 68% sit close to mean with 1 SD
  • 95% sit close to mean with 2 SD
  • 99% sit close to mean with 3 SD
  • Comparing individuals to remaining population
18
Q

What is the purpose of the Central Limit Theorem?

A
  • Cornerstone of statistics and research
  • CLT addresses simple question of how can we use the data from sample and make inference for reference population
  • States distribution of means is normal if sample size is large enough, regardless of underlying distribution of original measurements