Final: Lecture 13

Question 1

Absolute Differences

Answer 1

Subtracting frequencies (subtracting Counts) assume that….

• 135 outcomes in Group 1 & 25 outcomes in Group 2
• • Group 1 had 110 more outcome occurrences, or…
• • Group 2 had 110 FEWER outcome occurrences

Question 2

Relative Differences

Answer 2

Ratio of Frequencies (division of counts). Still assuming..

• 135 outcomes in Group 1 & 25 outcomes in Group 2
• -Group 1 had over 5 time the number of cases (over 500% increase)
• -Group 2 had less than 20% of the outcomes seen in Group 1

Question 3

Risk a.k.a, Incidence Risk (IR)

Answer 3

• Probability of outcome in Exposed (risk in exposed)
• A ÷ (A+B)
• Probability of outcome in Non-Exposed (risk in Non-exposed)
• C ÷ (C+D)

Question 4

Risk Ratio (RR) or “Relative Risk”

Answer 4

Ratio of the Risk from 2 different groups

• Risk Exposed ÷ Risk Non-exposed
• a risk ratio of 1 says there is NO difference in risk of disease between exposed and non-exposed

Question 5

When is a Risk Ratio/Relative Risk (RR) customarily used?

Answer 5

In studies when the subjects are allocated based on exposure (y/n) and evaluated for disease (outcome) e.g. cohort studies. Think 2 x 2 table

Question 6

What is Risk?

Answer 6

A PROPORTION PART÷WHOLE

Question 7

Interpreting Ratio’s, Risk (RR), Odds (OR), Hazard (HR):

When the ratio is equal to 1

Answer 7

No difference (no increase/no decrease in risk/odds/ratio

Question 8

Interpreting Ratio’s, Risk (RR), Odds (OR), Hazard (HR):

When the ratio is >1.0

Answer 8

Increased “ratio” (RR/OR/HR)

• +1.00001 to +1.99= use decimal value (converted to %) for interpretation
• if RR =1.53 then a 53% increased ( or greater) risk in the comparator group. Increased because “ratio” value is above 1.0

Question 9

Interpreting Ratio’s, Risk (RR), Odds (OR), Hazard (HR):

When the ratio is ≥ 2.0

Answer 9

use statement of “times Control” for interpretation
+2.0 to ∞
- if OR= 6.18, then comparator group is 6.18 times greater odds. Greater because “ratio” value is above 1.0

Question 10

Interpreting Ratio’s, Risk (RR), Odds (OR), Hazard (HR):

when the ratio is < 1.0

Answer 10

Decreased “ratio” (RR/OR/HR)
0.00001 to 0.99 = subtract decimal value from 1 (answer converted to %) for interpretation

If HR = 073, then a 27% lower probability of the hazard outcome, LOWER b/c “ratio” value is BELOW 1.0

Question 11

Absolute Risk Reduction (ARR) [a.k.a. Attributable Risk (AR)]

Answer 11

Simple “absolute” difference (subtraction) in risks
-if Risk in “exposed” = 1.5 & risk in “unexposed” = 1.2 then… “exposed” had a 0.3 times (or 30%) greater risk (compared to “unexposed”)

AR defines the excess risk of the outcome among “exposed” that can be “attributed” to the actual exposure.

Question 12

Relative Risk Reduction (RRR)

Answer 12

(ARR) ÷ R unexposed. From the ARR example note card, 0.3 ÷ 1.2 = 25% relative greater risk i “exposed”

Question 13

Number Needed to Treat (NNT) & Number needed to Harm (NNH)

Answer 13

interpretation: number of (whole) patients needed to be treated to receive the stated benefit/harm

1 ÷ Absolute Risk Reduction (1/ARR)

From ARR note card 1 ÷ 0.3 = 3.33; [ 4 patients ]

Question 14

Odds

Answer 14

Odds of exposure vs. odds of NOT being exposed (in cases)
A ÷ C (not a simple percentage)

Odds of exposures vs. odds of NOT being exposed (in Controls)
B ÷ D (not a simple Percentage)

Question 15

Odds Ratio (OR)

Answer 15

Odds of exposure in Cases vs. odds of exposure in Controls.

Odds of Exposure (in cases) ÷ odds of exposure (in controls) *** calculated as [(A ÷ C) ÷ (B ÷ D)]

• you can also cross-multiply in 2x2 table to get same answer

Question 16

When are Odds Ratio (OR) customarily used?

Answer 16

In studies where subjects are allocated based on disease presence (y/n) and evaluated for exposure. e.g. Case-Control Studies

Question 17

What is Z for?

Answer 17

ZAK, which isn’t funny.