Statistics

Question 1

null hypothesis

Answer 1

assumes there is not significance between control and treatment groups
studies try to disprove the null hypothesis

Question 2

alternate hypothesis

Answer 2

states there is a difference between control and treatment groups
research tries to prove this

Question 3

alpha

Answer 3

maximum permissable margin of error
normally 0.05
if P-value < alpha, reject null, accept alternate - significant result
if P-value > alpha, accept null, reject alternate - NOT significant result

Question 4

confidence interval

Answer 4

if it crosses 0, not significant

Question 5

type 1 error

Answer 5

false positive

when null hypothesis is rejected in error

Question 6

type 2 error

Answer 6

false negative

when null hypothesis is accepted in error

Question 7

relative risk (RR)

Answer 7

risk in treatment group / risk in control group

Question 8

relative risk reduction (RRR)

Answer 8

1 - relative risk (RR)

Question 9

number needed to treat (NNT)

Answer 9

1 / (risk in control - risk in treatment) or 1 / ARR

Question 10

odds ratio (OR)

Answer 10

odds outcome occurs w/ treatment vs. occurs w/o treatment

Question 11

hazard ratio (HR)

Answer 11

HR = hazard rate in treatment / hazard rate in control

Question 12

OR or HR = 1

Answer 12

event rate same in treatment and control

no advantage to treatment

Question 13

OR or HR > 1

Answer 13

event rate higher in treatment than control

don’t use treatment

Question 14

OR or HR < 1

Answer 14

event rate lower in treatment than control

treatment is beneficial

Question 15

nominal (categorical) data

Answer 15

categories, names

ex. male, female

Question 16

ordinal data

Answer 16

logical order or scale

pain scale

Question 17

continuous data

Answer 17

measurement, unlimited options

weight, temperature

Question 18

T-test

Answer 18

assess significance w/ continuous data

used for 2 sample groups

Question 19

ANOVA

Answer 19

used for 3+ sample groups

Question 20

Chi-Square

Answer 20

for discrete date (nominal or ordinal)

gender, ethnicity, pain scales

Question 21

independent variable

Answer 21

manipulated by researcher

Question 22

dependent variable

Answer 22

affected by change to independent variable

Question 23

composite endpoint

Answer 23

combines multiple endpoints
all must be similar in magnitude, importance
sum of individuals will NOT equal composite endpoint

Question 24

intent to treat

Answer 24

analysis of all patients, even if dropped from study

Question 25

per protocol

Answer 25

analysis of only those who completed trial per protocol

Question 26

sensitivity

Answer 26

how effectively it identifies those w/ condition

Question 27

specificity

Answer 27

how effectively it identifies those w/o condition

Question 28

case control study

Answer 28

compares pts w/ disease to those w/o, retrospective

cause/effect not determined

Question 29

cohort study

Answer 29

compares outcomes of exposed group to non-exposed group, prospective

Question 30

cross-sectional survey

Answer 30

estimates prevalence at one time in defined group

do not determine causality