Final

Question 1

test threshold

Answer 1

probability below which a diagnostic test will not be ordered or performed b/c the possibility of the diagnosis is so remote

Question 2

treatment threshold

Answer 2

probability above which a diagnostic test will not be ordered b/c the possibility of the diagnosis is so great that immediate treatment is indicated

Question 3

sensitivity

Answer 3

correctly IDs people who have the disorder - true positives

- SN-NOUT - if a test is highly sensitive, then a negative test means you can rule out the disorder

Question 4

specificity

Answer 4

correctly IDs people without the disorder - true negative

- SP-PIN - of a test is highly specific, then a positive test means you can rule in the disorder

Question 5

positive predictive value

Answer 5

ability of the test to correctly determine the % of people WITH the disorder from all the people with + test results

Question 6

negative predictive value

Answer 6

ability of the test to correctly determine the % of people WITHOUT the disorder from all the people with a - test result

Question 7

LR + and what numbers would indicate a LR +

Answer 7

likelihood that a POSITIVE test result was observed in a person WITH the disorder vs a person WITHOUT the disorder

• how the probability of disease shifts when the finding is +
• LR+ > 1, closer to 1 means it is closer to chance

Question 8

LR - and what numbers would indicate a LR -

Answer 8

likelihood that a NEGATIVE test result was observed in a person WITH the disorder vs a person WITHOUT the disorder

• how probability of disease shifts when the finding is -, disease is absent
• LR - < 1, closer to 1 means it is closer to chance

Question 9

LR + chart numbers to know

Answer 9

2 - 15% increase
5 - 30% increase
10 - 45% increase

Question 10

LR - chart numbers to know

Answer 10

1/2 (0.5) - 15% decrease
1/5 (0.2) - 30% decrease
1/10 (0.1) - 45% decrease

Question 11

P-value

Answer 11

probability that the result occurred due to chance

• lower the better
• 1 means it was 50/50

Question 12

case control study

Answer 12

• retrospective
• 1 group w/ disorder and 1 group w/o
• look at proportion of each group who had the risk factor or prognostic indicator of interest

Question 13

cohort study

Answer 13

• prospective
• 2 or more groups before they have the disorder
• monitor to see who develops the disorder

Question 14

what is a survival curve

Answer 14

looks at mortality rate in people w/ or w/o certain quality

- ex: knee extensor strength of < or > 40% on survival in people who undergo dialysis

Question 15

odds ratio

Answer 15

the odds that an individual w/ the prognostic or risk factor will develop the outcome of interest

Question 16

negative odds ratio > or < 1

Answer 16

• OR > 1 - odds are in favor of adverse outcome (problem will develop)
• OR < 1 - odds are against an adverse outcome (prognostic factor is protective against problem)
  ex: death - want - OR bc that means you’re less likely to die

Question 17

positive odds ratio > or < 1

Answer 17

+ OR > 1 - odds are in favor of a positive outcome

+ OR < 1 - odds are against a positive outcome (prognostic factor is harmful)

Question 18

relative risk > 1

Answer 18

there is an increased risk of an adverse outcome

Question 19

relative risk < 1

Answer 19

there is a decreased risk of an adverse outcome

Question 20

what does a standard effect score > 0.8 mean?

Answer 20

big treatment effect

Question 21

what does a standard effect score of 0.2-0.49 mean?

Answer 21

treatment effect is small enough that we can not see it with the naked eye

Question 22

If correlation is >0, variables are ________ correlated

Answer 22

positively

Question 23

If correlation is 0, the variables are _______ correlated

Answer 23

variables are not related

Question 24

If correlation is <0, the variables are _______ correlated

Answer 24

inversely related

Question 25

The closer the correlation is to +1 or -1, the ________ the association between the variables

Answer 25

stronger

Question 26

type 1 vs type 2 error

Answer 26

1 - null hypothesis is rejected when it is true

2 - null hypothesis is NOT rejected when it is false