Equations etc

Question 1

Define sensitivity

Answer 1

true positives rate

“how good is this test at picking up people who have the condition (the true positives)?”

“probability of a positive test in patients with disease”

Question 2

Sensitivity equation

Answer 2

a/(a+c)

Question 3

Define specificity

Answer 3

the true negatives rate

“how good is this test at picking up people who do not have the condition”

Question 4

Specificity equation

Answer 4

d/(d+b)

Question 5

Define PPV

Answer 5

the proportion of people with a positive test who have the target disorder

Question 6

PPV equation

Answer 6

a/(a+b)

Question 7

Define NPV

Answer 7

the proportion of people with a negative test who do not have the target disorder

Question 8

NPV equation

Answer 8

d/(d+c)

Question 9

Define likelihood ratio +

Answer 9

indicates how much more likely a positive test to be found in a person with, as opposed to without, the condition

probability of a POSITIVE test in patients WITH DISEASE/probability of a POSITIVE test in patients WITHOUT the disease

Question 10

Likelihood ratio + equation

Answer 10

sens/(1-spec)

i.e sensitivity = probability of a positive test in patients with the disease (true positives)

since specificity if the probability of a negative test in patients without disease (true negatives), 1-specificity will give the probability of a positive test in those without the disease

Question 11

Define likelihood ratio -

Answer 11

indicates how much more likely is a negative test to be found in a person without, as opposed to with, the condition

probability of a negative test in patients WITH disease/probability of a negative test in patients WITHOUT disease

therefore:

(1-sensitivity)/specificity

Question 12

Likelihood ratio - equation

Answer 12

(1-sens)/spec

Question 13

Define prevalence

Answer 13

the overall proportion of a population who suffer from the condition. Prevalence = incidence X duration (when incidence is approx stable over duration)

Question 14

Prevalence equation

Answer 14

(a+c)/(a+b+c+d)

Question 15

Experimental Event Rate (EER) equation

Answer 15

a/(a+b)

Question 16

Control event Rate (CER) equation

Answer 16

c/(c+d)

Question 17

Define absolute risk reduction

Answer 17

the absolute difference in the rates of events between the two groups

Question 18

ARR equation

Answer 18

CER-EER

Question 19

Define number needed to treat

Answer 19

the number of patients you need to treat to prevent one additional bad outcome; always rounded UP to the nearest whole number

Question 20

NNT equation

Answer 20

1/ARR

Question 21

Define relative risk (aka risk ratio)

Answer 21

how many times more likely it is that an event will occur in the intervention group relative to the control group

Question 22

Risk ratio equation

Answer 22

EER/CER

Question 23

define relative risk reduction

Answer 23

the reduction in rate of the outcome in the intervention group relative to the control group

Question 24

RRR equation

Answer 24

(CER-EER)/CER

Question 25

Odds Ratio equation (for case control study)

Answer 25

"cross products" ad/bc in the table, you get the disease vs. non disease state on the top, and the exposure versus no exposure on the side. i.e if you have 100 people who smoked, and 90 now have lung cancer and 10 dont; and 100 people who never smoked, and 10 of them have lung cancer and 90 dont. it would be "lung cancer yes or no" on the top and "smoking yes or no" down the left hand side. cross multiply and divide, and you get the odds ratio in this case, the odds ratio (which works out to be 81) states that if you have lung cancer you are 81X more likely to have smoked than if you dont have lung cancer

Question 26

What is a type I error

Answer 26

rejection of a null hypothesis that is true

Question 27

what is a type II error

Answer 27

failure to reject a null hypothesis that is false

Question 28

What is the confidence interval?

Answer 28

the confidence level sets the boundaries of a confidence interval, that is conventionally set at 95% to coincide with the 5% convention of statistical significance in hypothesis testing

Question 29

what is a p value?

Answer 29

a summary statistic representing the probability that results happened because of chance--a p value less than 0.05 means that the chances of the result occurring due to chance is less than 5%

Question 30

RR

Answer 30

relative risk, or risk ratio expresses how many times more (or less) likely an exposed person DEVELOPS AN OUTCOME relative to an unexposed person RR= (incidence of outcome with exposure)/(incidence of outcome without exposure) RR = 1 then there NO risk of the outcome RR > 1 then greater risk of outcome in exposed persons RR