Exam One - Clinical Relevance of Change

Question 1

5 standards of clinical relevance

Answer 1

• effect size
• standard mean difference
• standard error of the measurement
• minimum detectable difference
• minimum clinically important difference

Question 2

alpha level

Answer 2

your tolerance for declaring a sample mean “significantly different” if it falls outside the expected range by choice

Question 3

P<0.05

Answer 3

statistically significant
reject the null hypothesis
“unlikely enough” to conclude the observed result did not occur by chance

Question 4

P>0.05

Answer 4

not statistically significant
fail to reject the null hypothesis
“not unlikely enough” to conclude the observed result was not a chance occurrence

Question 5

problems with black and white philosophy??

Answer 5

P<0.05 is arbitrary and subjective

Question 6

do we ONLY want to know if the difference could be attributed to chance alone?

Answer 6

no! We also care if the change was clinically relevant!

Question 7

What measure evaluates treatment effect, independent of sample size?

Answer 7

effect size! (ES)

Question 8

ES =

Answer 8

(change score)/(average standard deviation)

Question 9

Es is the expression of the magnitude of the difference _____________

Answer 9

between 2 means

Question 10

what measure is a comparison of 2 treatment effects, independent of sample size?

Answer 10

Standard mean difference (SMD)

Question 11

SMD =

Answer 11

(treatment A change - Treatment B change)/(average SD)

Question 12

SMD is the expression of the magnitude of the difference _______________-

Answer 12

between 2 CHANGE scores (4 means)

Question 13

ES, SMD interpretation scale

Answer 13

> .8 BIG treatment effect
.4-.8 effect is big enough we can be confident a true effect exists
.2-.4 treatment effect is small enough that clinician may not perceive a benefit/harm
<.2 what treatment effect??

Question 14

What are two other standards to measure clinical significance?

Answer 14

• Minimum clinically important difference (MCID)
• minimum detectable difference (MDD or MDC)

Question 15

MCDI is…

Answer 15

• the smallest diff a patient would perceive as beneficial
• specific to the individual patient goals and values

Question 16

with MDD/MDC we must ask ourselves…

Answer 16

is the effect outside the bounds of potential measurement error?

Question 17

What formula do we use when considering the MDD/MDC?

Answer 17

Standard error of measurement (SEM)

Question 18

SEM =

Answer 18

SD * sqrt (1-ICC)

Question 19

MDD95

Answer 19

the difference required to be 95% confident the effects are not due to measurement error

Question 20

MDD95 =

Answer 20

2.77*SEM

Question 21

measures with low MDD are considered _________-

Answer 21

responsive

Question 22

What are the measures to judge the relevance of continuous effects?

Answer 22

• effect size
• standard mean difference
• standard error of the measurement
• minimum detectable difference
• minimum clinically importance difference

Question 23

What are the measures to judge discrete effects?

Answer 23

• absolute benefit increase/risk reduction
• relative benefit increase/risk reduction
• number needed to treat

Question 24

Many studies use______ to measure effects of an intervention

Answer 24

discrete
ex - success vs failure

Question 25

discrete results are often analyzed by _____-

Answer 25

count (# or %)

Question 26

Number needed to treat (NNT)

Answer 26

number of patients who must receive the intervention to produce one positive outcome or avoid one adverse event (relative to control condition)

Question 27

ARR =

Answer 27

absolute risk reduction = % controls w?prob - % therapy group w/ prob

Question 28

RRR =

Answer 28

relative risk reduction = (% controls w?prob - % therapy group w/ prob)/(% of controls w/ prob)

Question 29

NNT =

Answer 29

1/ARR
(1/% controls w?prob - % therapy group w/ prob)

Question 30

ABI

Answer 30

absolute benefit increase = % therapy group w/ outcome - % control group with outcome

Question 31

RBI

Answer 31

relative benefit increase = (% therapy group w/ outcome - % control group with outcome)/(% of controls w/ outcome)

Question 32

NNT =

Answer 32

1/ABI
(1/% therapy group w/ outcome - % control group with outcome)

Question 33

ceiling effects

Answer 33

scores that are already high are not likely to go higher

Question 34

floor effects

Answer 34

scores that are already low are not likely to go lower

Question 35

change scores should be interpreted with respect to…

Answer 35

baseline scores