Stats Flashcards

(31 cards)

1
Q

t test and ANOVA

A

quantitative (ANOVA is means)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

chi square (2 groups of qualitative)

A

categorical

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

kaplan meyer

A

small groups; estimates survival

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

relative risk

A

incdience of exposed/incidence in unexposed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

power of test

A

probably of making correct consluion
1-probabily of TYPE II ERROR
0.8+ is adequate

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

power = 0.9

A

90% chance a positive value detects real difference
10% chance a negative value does not detect difference when there actually is one

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

accuracy equation

A

true positive + true negative / (ALL)e

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

deepdnency on prevalence

A

predictive value depends on prevalence

sens/spec does NOT depend on prevalence

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

NSQIP

A

outcome data for surgical QUALITY in US

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

JCAHO

A

side marking, timeout etc.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

REAIM

A

reach
effectiveness
adoption
implementation
mainteannce

for getting evidence based practice out there

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

QI types

A

lean process and six sigman p

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

lean process

A

continue to reevaluate and get rid of stuff that doesnt work; LEAN METHODOLOGY
outcomes will contineu to improve.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

six sigma

A

define measure analyze imrpove control

eiminate process errors
ERROR WASTE REDUCTION

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

median in kaplan meier survival curve

A

50% survival; what is the X value (time)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

NNT

17
Q

what bias in cross sectional study

A

no causality…

selection bias
survival bias

18
Q

case control bias

A

only study on outcome (some causal effect) with

selection bias
recall bias

19
Q

cohort study bias

A

some potential to establish causal effects

selection bias

20
Q

RCT is not good for…

21
Q

receiver operating curves

A

ROC used to eval what happens to sensitivity and specificity when threshold for positive vs negative test is changed

22
Q

largest area under ROC

A

optimized/highest possible combination of sensitiity and specificity for a test

23
Q

selection bias types

A

allocation bias, lead time bias, length time bias

24
Q

allocation bias tx

A

concealment of allocation

25
length time bias tx
pathologic grading comparison (instead of staging)
26
information bias types
recall, detection = observor bias, surveilalnce, hawthorne effect
27
levels of evidence 1A 1B
1A systematic review, meta-analysis of high quality RCTs 1B sys rev or meta of INDVIDIUAL RCTS
28
levels of evidence 2A 2B
2A sysrev or meta of COHORT studies 2B individual cohort studies or low quality RCTs
29
levels of evidence 3A and 3B
3A sys rev/meta of CASE CONTROl stduies 3B sys rev/meta of individual case control studies
30
levels of evidnece 4 vs 5
4: case series 5: expert opinions
31