Ch 12: Biostatistics and Pharmacoeconomics

Question 1

spread

Answer 1

how similar or how varied values are. uses range and std deviation

Question 2

gaussian distribution

Answer 2

normal dist, bell shaped curve of continuous values. symmetrical with 1/2 values on left and 1/2 on right. mean = median = mode. 68% of values are within 1 SD, 95% are in 2 SDs of mean. otherwise not gaussian –> skewed.

Question 3

null vs alt hypothesis

Answer 3

null = no difference, trying to reject with statistical significance. alt = difference, trying to prove.

Question 4

confidence interval

Answer 4

if narrow, high precision. if wide, low precision. % chance of no error with tx effect (range). if alpha is 0.05, CI is 95%. if alpha is 0.01, CI is 99%. if CI contains 0 - not significant.

Question 5

alpha level

Answer 5

max permissible error margin (% chance of error), usually set at 5% or 0.05 as threshold for rejecting null hypothesis. smaller can be chosen but requires more data, pts, and money or larger tx effect

Question 6

p value

Answer 6

if less than alpha - reject null. if equal or more than - accept null (failed to reject null, not statistically significant)

Question 7

type I error

Answer 7

alpha. false pos, when null is rejected in error.

Question 8

type 2 error

Answer 8

beta. false neg. null is accepted when should have been rejected.

Question 9

study power

Answer 9

probability that a test will reject the null hypothesis correctly, power to avoid a type 2 error. as power inc, type 2 error dec. power = 1 - beta. power determined by number of outcome values, different in outcome rates between groups, and significance level.

Question 10

relative risk (RR)

Answer 10

aka risk ratio. %risk tx / %risk control. 1 is no diff. >1 more risk of outcome. <1 less risk of outcome. calculated as decimal.

Question 11

risk (R)

Answer 11

pts with event (regardless of tx or control) / #total in study

Question 12

relative risk reduction (RRR)

Answer 12

how much risk is reduced in tx group compared to control group. (%risk control - %risk tx)/%risk control. OR 1-RR. calculated as decimal.

Question 13

absolute risk reduction (ARR)

Answer 13

%risk control - %risk tx. includes reduction in risk and incidence rate. net effect beyond the effect obtained from placebo.

Question 14

number needed to treat (or harm)

Answer 14

1/ARR. # patients that need to receive tx for 1 patient to be harmed or receive benefit of tx. always round up to next whole number for NNT and down for NNH.

Question 15

odds ratio

Answer 15

estimate risks with tx in case-controls. calculate odds that outcome will occur with exposure compared to odds without exposure. (see flash where OR = AD/BC). = 1 no diff in events (CI does not cross 0). >1 tx has more events. <1 tx has less events.

Question 16

hazard ratio

Answer 16

survival analysis uses hazard instead of risk - ex. cancer. rate of an unfavorable event occurring within short period of time. ratio between hazard rate tx and hazard rate control. = 1 no diff in events (CI does not cross 0). >1 tx has more events. <1 tx has less events.

Question 17

discrete data

Answer 17

nominal or ordinal

Question 18

nominal

Answer 18

categories like male and female

Question 19

ordinal

Answer 19

has logical order like pain scale or NYHA class, steps on scale are not divisible (unlike ratio and interval data)

Question 20

continuous data

Answer 20

interval and ratio. both continuously inc by same amt.

Question 21

interval data

Answer 21

no meaningful zero (zero does not equal none). ex. fahrenheit temp scale, 0 is not “no temp” its cold.

Question 22

ratio data

Answer 22

has meaningful zero (zero equals none). majority of med studies. ex. HR, 0 is death.

Question 23

student t tests

Answer 23

significance in studies with continuous data values. commonly if studies have 2 independent sample groups (tx and control)

Question 24

ANOVA

Answer 24

aka F test. used for 3 or more samples of continuous data. (similar to student t test but more than 2 groups)

Question 25

chi square test

Answer 25

tests discrete (nominal or ordinal) data for significance. usually for observational studies for 1-2 groups.

Question 26

independent variable

Answer 26

changed by researcher to see if there is effect on dependent variable

Question 27

dependent variable

Answer 27

effect. ex. disease progression or a1c

Question 28

composite endpoint

Answer 28

combines multiple endpoints into 1 measurement, must be similar in magnitude and have similar/meaningful importance to pt. sum of individual endpoints will not correlate to composite endpoint.

Question 29

spearman’s rank-order correlation

Answer 29

aka rho. tests correlatino in ordinal, ranked data.

Question 30

pearson’s correlation coefficient

Answer 30

aka r. calculated score to indicate strenth and direction of relationship between 2 variables.

Question 31

regression

Answer 31

3 types: linear for continuous data, logistic for categorical data, cox for categorical data in survival analysis. describes the relationship between dependent variable and 1+ independent variables OR how much the dependent variable changes when independent variable/s changes. common in observational studies to control for confounding factors

Question 32

equivalence trial

Answer 32

demonstrate new tx has similar effect as the old tx. 2 way margin.

Question 33

non inferiority trials

Answer 33

demonstrate new tx is not much wore than old tx. 1 way margin. more common

Question 34

sensitivity

Answer 34

true positive. how efficiently test IDs pts with condition. #pos results with condition/#with condition

Question 35

specificity

Answer 35

true negative. how accurately a test IDs pts without condition. #neg results wihtout condition/#without condition.

Question 36

forest plot

Answer 36

meta analysis. if 95% CI used, then result is sig if at 0.05 level aka does not cross 0.

Question 37

case control study

Answer 37

compares pts with disease to those without disease. retrospective. chart review.

Question 38

cohort study

Answer 38

compares outcomes of group of pts exposed and not exposed to a tx. prospective or retrospective.

Question 39

cross sectional study

Answer 39

relationship between variables and outcomes (prevalence) at 1 time point in defined population. hypothesis generating.

Question 40

parallel study

Answer 40

most common RCT. pts are given tx or placebo during entire study.

Question 41

crossover study

Answer 41

pts are given tx or placebo then switched after a washout period. pts serve as own control.

Question 42

factorial study

Answer 42

randomizes to more than the usual 2 groups to test a number of interventions

Question 43

meta analysis

Answer 43

combines results from multiple studies to form greater statistical power than any individual study alone.

Question 44

systematic review

Answer 44

summary of clinical lit focusing on specific topic or question.

Question 45

If using conventionally accepted standards, for any given study result you’ve got a…

Answer 45

• 5% chance Type I Error
• 20% chance Type II Error
• 5% degree of uncertainty (from the 95% CI) that the study result applies to the entire tx pop

Question 46

ECHO model

Answer 46

economic, clinical, humanistic outcomes

Question 47

economic outcomes

Answer 47

direct, indirect, and intangible costs of drug compared to medical intervention

Question 48

clinical outcomes

Answer 48

medical events that occur as result of tx or intervention

Question 49

humanistic outcomes

Answer 49

consequences of disease or tx as reported by the pt or caregiver (qol, satisfaction)

Question 50

humanistic outcomes

Answer 50

consequences of disease or tx as reported by the pt or caregiver (qol, satisfaction)

Question 51

incremental cost ratio

Answer 51

(cost2 - cost1)/ (effect2 - effect1)

Question 52

average cost effectiveness ratio

Answer 52

cost per outcome of 1 tx alt (independent of other alts)

Question 53

average cost effectiveness ratio

Answer 53

cost per outcome of 1 tx alt (independent of other alts)

Question 54

cost minimization analysis

Answer 54

limited to comparing alts with demonstrated equiv outcomes (2 diff ACEI ex.). comparing cost of each intervention in $$.

Question 55

cost benefit analysis

Answer 55

calculating and comparing benefits and costs of intervention in $$. costs and benefits of all kinds are translated into dollars and adjusted for present day. hard to quanitify qol.

Question 56

cost effectiveness analysis

Answer 56

outcomes are easier to quantify. most common . inability to directly compare different types of outcomes. outcomes need to be the exact same to be compared (ex. cannot compare asthma exacerbations to BG values)

Question 57

cost utility analysis

Answer 57

includes qol assoc with morbidity using quality-adjusted life years (QALYs) and disability adjusted life years (DALYs)