Interpreting evidence 1

Question 1

Absolute Risk Reduction (ARR)

Answer 1

“the proportion of patients who are spared the adverse outcome as a result of having received the experimental rather than the control therapy

Question 2

Relative Risk (RR)

Answer 2

atio of the risks for an event for the exposure group to the risks for the non-exposure group

Question 3

Number Needed to Treat (NNT)

Answer 3

The number of patients you need to treat to prevent one additional bad outcome (death, stroke, etc.)

Question 4

Variability

Answer 4

between people and within people

Question 5

Null hypothesis (Ho )

Answer 5

there is no difference in haemoglobin levels between patients receiving oral compared with intravenous iron supplementation

Question 6

Alternative hypothesis H1 (Research Hypothesis)

Answer 6

there IS a difference in haemoglobin levels between patients in the two treatment groups

Question 7

confidence interval

Answer 7

gives a range of plausible values for the unknown, population, parameter (mean in this case)

Question 8

odds ratio

Answer 8

a measure of association between an exposure and an outcome

Question 9

T-test

Answer 9

allows us to statistically compare means between two groups, determining whether two means are significantly different from each other

• 1 dependent continuous variable (e.g height)
• 1 independent binary categorical variable (e.g. sex)

Question 10

Chi-square-test

Answer 10

allows us to statistically compare frequencies

• 1 dependent categorical variable (e.g. alternative drug types)
• 1 independent categorical variable (e.g. Deprivation category)

Question 11

p-value

Answer 11

Gives a probability (p-value) that such a difference in means (or a greater difference) would be found by chance, IF THE NULL HYPOTHESIS IS TRUE

Question 12

probability value - p-value

Answer 12

When p-value for a test statistic is below 0.05, we ‘reject’ the Null Hypothesis

Question 13

• P>0.05 =

Answer 13

sample means not significantly different

Question 14

Chi-square test

Answer 14

• Allows us to statistically determine if the difference between the observed and expected numbers in each cell is significant (GIVEN THE SAMPLE SIZE)
• A difference implies a ‘relationship’ or ‘association’

Question 15

Type I error is

Answer 15

rejecting true Null Hypothesis

• `i.e a “false positive” finding

Question 16

• Bonferroni correction

Answer 16

• If do 5 tests then for each test only accept as significant tests with p-value< 0.05/5 = 0.01
• If do n tests then for each test only accept as significant tests with p-value< 0.05/n
• This means that across all n tests you have only a 5% chance of a false positive

Question 17

Correlation

Answer 17

Measures the strength of relationship between two numerical variables

Question 18

Linear Regression

Answer 18

• Used to predict relationship between independent variables and an outcome (dependent) variable
• Must be a linear relationship between independent and outcome