Comparing binary variables between groups

Question 1

What is a binary variable?

Answer 1

categorical variable with 2 categories

eg mortality status, diabetes status

Question 2

How is proportion used to summarise binary variables for a single group

Answer 2

number of participants of interest / total number

0-1 value range (% = x100)

Question 3

How are odds used to summarise binary variables for a single group and why is it useful?

Answer 3

% category of interest / 100 - % category of interest

for comparing binary variables between groups in case-controlled studies

Question 4

What is the exposure variable?

Answer 4

exposure is the potential cause of outcome

Question 5

What absolute measure is used to compare binary variables between independent groups?

Answer 5

risk difference (% in group one - % in group 2)

Question 6

What relative measures are used to compare binary variables between independent groups?

Answer 6

Risk ratio and odds ratio

%/odds R with disease in intervention group / %/odds R with disease in control group

Question 7

what do different risk & odds ratio values mean?
= 0, > 0, < 0

(OR always further from 1 then RR)

Answer 7

=0 = groups equally likely to have disease

> 0 = first group more likely

<0 = second group more likely

Question 8

What does number needed to treat (NNT) show?

Answer 8

the number of people than need to receive an intervention before 1 person benefits as a result of treatment

Question 9

how is NNT calculated?

Answer 9

100 / risk difference (%)

Question 10

What does number needed to harm show

Answer 10

the number of people that receive the intervention until somebody is negatively effected

Question 11

How is relative risk reduction (RRR) calculated ?

Answer 11

1 - risk ratio x 100 = RRR %

Question 12

How is absolute risk reduction (ARR) calculated?

Answer 12

one percentage - the other = ARR %

Question 13

When is using risk difference and NNT better?

Answer 13

quantify the impact of an intervention for reducing disease in a given setting

Question 14

When is using Risk ratio & odds ratio better?

Answer 14

quantifying the strength of association between intervention and disease status

Question 15

When estimating confidence intervals what assumptions must be met?

Answer 15

total sample size is at least 40

at least 5 subjects in each category of the binary variable in each group

Question 16

How is expected value (if hypothesis were true) calculated from a 2x2 table

Answer 16

row total x column total / overall total

can also be worked out as %

Question 17

How is P value calculated when comparing binary variables between two independent groups

Answer 17

Chi-squared test (parametric (assumption based)) or Fisher’s exact test (non-parametric)

Tests quantify evidence against null hypothesis

Question 18

When is Fisher’s exact test used? (when chi-squared test assumptions are not met)

Answer 18

when there are fewer than 20 participants or when between 20-39 participants w/ expect value <5 in at least one cell

Question 19

Which test should be used for larger contingency tables?

Answer 19

Chi-squared if expected value is >5 in at least 80% of cells if not use Fisher