Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Random Tips > Biostats > Flashcards

Biostats Flashcards

1
Q

Selection bias

A

How were patients selected, are groups similar?

Big with case control, also see with meta analysis

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

Allocation bias

A

Group assignments, randomization

*groups not representative of population being studied

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

Misclassification bias

A

Participant placed in the wrong category

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

Measurement bias

AKA detection bias

A

Data collection issue

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

Attrition bias

A

Patient drop out

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

Compliance bias

A

Was compliance assessed/ could compliance effect results

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

As treated analysis

A

All patients randomized according to therapy they actually received

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

Per protocol

A

Only pts who followed protocol were analyzed

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

ITT

A

Analyzed according to intended therapy

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

Nominal data examples

A

ADR rate Yes/no, gender, race, presence or absence of dx, death, hospitalization

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

Ordinal examples

A

Likert, NYHA functional class, years of therapy 0-5 5-10 10-20, age <50 50-75 75-100

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

Continuous data examples

A

Lab values, age, weight, time to event

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

HR vs RR

A

HR is for survival analysis

HR is weight RR over time

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

Kaplan meirer

A

How survival analysis (log rank test) is presented - paired with HR

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

Cox proportional

A

Most common stat test for survival analysis - used for mutivariate analyses

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

Mx comparisons procedure issue and fix

A

Increased risk type 1 error

Correct: bonferroni, tukeys, scheffe, dunnetts, hochberg

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Funnel plot shows what?

A

Publication and selection bias

Want symmetry around the middle (shows no bias)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Cohort v case control

A

Cohort is prospective, case control is retrospective

Cohort: start w/ risk factory

Case: starts w/ cases

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Hawthorne effect

A

People modify behavior bc they know they are being observed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Cost of illness

A

Cost of dx for define population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Cost minimization

A

Intervention cost differences b/w similar alternatives

Identifies least costly alternative when consequences are the same

Ex. Losartan vs valsartan

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Cost benefit

A

Identifies net cost impact of an interventions

Compares programs or agents with different objectives

Strengths and weakness of interventions (cost of intervention vs cost that we get back via benefit)

Example: building cost $100 to make but will yield $200 in profit ($200-$100)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Cost effectiveness

A

Net cost divided by health outcomes

Ex. Cost per case of dx prevented or per death averted,

Ex. Years if life saved, number symptom free days, BG, BP

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Cost utility

A

Sunset of cost effectiveness

When tx affects quality of life QALY

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Which type of data should not report means and SDs?

A

Ordinal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

Types of quantitative data

A

Discrete : 1, 2, 3 etc

Continuous:
-interval: zero is arbitrary (degrees F)
-ratio: absolute zero (HR, BP, distance, kelvin)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

When can you use mean

A

Continuous and normally distributed

NOT ordinal!

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

When to use median?

A

Ordinal or continuous

Good for skewed data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

When to use SD

A

Continuous and normally distributed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

SD meaning

A

1: 68%
2: 95%
3: 99%

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

Kolmogorov-smirnov

A

Formal test for normal distribution

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

CI vs p-values

*important slide!

A

CI helps us determine importance of findings! Clinical significance

P-value tells us nothing of importance, only of certainty

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

F test

A

Difference in variance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

Mantel haenszel

A

For independent nominal 3+ groups

Controls for confounders

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

Pearson v spearman

A

Pearson: correlation of continuous normally distributed

Spearman: correlation of non-normally distributed continuous data or ordinal data

36
Q

r vs r2

A

R is correlation and r2 is regression

-Correlation cannot show causality but regression can
-correlation can be negative or positive but regression cannot show direction

37
Q

Log rank test

A

For survival analysis of two independent groups (presented via Kaplan Meier curve)

38
Q

Cox proportional hazards

A

Survival analysis for more than 3+ groups or paired groups

Or for prediction..?

39
Q

Which type of bias do we see with case control studies?

A

Recall bias

Also selection

40
Q

When can you not assess NNT /NNH?

A

When results are not significant!

41
Q

Observation or information bias

A

Incorrect determination of outcomes or exposure

Ex. Inaccurate recording of risk factor

42
Q

Recall bias

A

Recollection of past events. Cases more likely to recall exposure than controls (big for case-control studies)

43
Q

Interview bias

A

Interviews not conducted in uniform manner

44
Q

Publication bias

A

Positive results more likely to be published

45
Q

Differential vs non-differential bias

A

Differential effects one group more

Non-diff effects both equally (systematic error)

46
Q

Observational studies

A

Case control and cohort

*shows correlation but not causation

47
Q

Cross sectional

A

Snapshot in time- prevalence study

Not as good as case control or cohort

48
Q

Incidence vs prevalence

A

Incidence: # of new cases per time period

Prevalence: number of cases at a given time

49
Q

Pragmatic trial

A

More real life conditions- less internal validity

50
Q

ITT, per protocol, as treated

A

ITT: underestimates benefit. Preferred in superiority trial

Per protocol: overestimates benefit (results only for adherent pts- reduced external validity). Preferred in non-inferiority trial

As tx: interpret with caution! Destroys randomization for non-adherent patients

51
Q

Systematic review vs meta analysis

A

Meta analysis uses mathematic analysis

52
Q

SEM calulcario

A

SD/sqrt of n

53
Q

How to get 95% CI from SEM

A

SEM x1.96

Add and substract that from the mean

54
Q

When to use fischers exact over chi squared

A

All values in 2x2 table are at least 5 to use chi squared- otherwise uses Fischers exact

55
Q

Kendal

A

Correlation of ordinal values

56
Q

Linear vs logistic regression

A

Linear: continuos outcome

Logistic: categorical outcome

57
Q

Why are composite outcomes even used?

A

Increase power and decrease sample size requirements

Note: components should be physiologically linked!!!

58
Q

Effect size (delta) relationship to power

A

Increased effect size increases power and allows for smaller sample size

59
Q

Another benefit of survival analysis

A

Loss to follow up- you can still use data up til the loss to follow up

60
Q

Why are systematic reviews highest level of evidence

A

They reduce bias

61
Q

Confounding by indication

A

Lipid lowering drug compared to non lipid lowering drug…therefore actually kinda comparing high cholesterol to low cholesterol

People who take a drug are inherintly different from those who don’t d/t dx it’s treating, not the drug itself

62
Q

95% CI equation

A

2x SEM in both directions

SEM= SD/sqrt of n

63
Q

Coefficient if variation equation

A

SD/mean X 100

64
Q

Uspstf

A

Recommends health screening

65
Q

FEMA

A

Federal emergency management agency

For emergency preparedness

66
Q

Emergency response groups

A

American Red Cross, national pharmacy response team, disaster medical assistance team

67
Q

Ethnics framework

A

For cultural competence
Explanation, treatment, healers, negotiation, intervention, collaboration, spirituality

68
Q

CLAS

A

Culturally and linguistically appropriate services

69
Q

When to use mantel-haenszel

A

It control for confounding- like Ancova

70
Q

Regression- simple vs mx, linear vs logistical

A

Simple - 1 dependent variable
Mx- 2+ dependent variables

Linear- continuous
Logistic- categorical

71
Q

Measurement of collection for cohort vs case control

A

Cohort: RR
Case control: OR

72
Q

Reporting guidelines for clinical studies

A

Consort, strobe (observational), prisma (meta analysis) was previously quorum, equator

73
Q

OR

A

(A/B)/(C/D)

                        Outcome I No outcome Intervention.            A.                   B No intervention       C.                   D
74
Q

RR

A

(A/A+B)/(C/C+D)

                        Outcome I No outcome Intervention.            A.                   B No intervention       C.                   D
75
Q

ARR

A

(C/C+D) - (A/A+B)

                        Outcome I No outcome Intervention.            A.                   B No intervention       C.                   D
76
Q

RRR

A

1-RR

77
Q

NNT/ NNH

A

1/ARR round down for NNT and up for NNH

78
Q

Cochran Q

A

Traditional test for heterogeneity
P< 0.05= high heterogeneity

79
Q

I^2 (I squared)

A

Degrees of heterogeneity
0-25% = low
26-50%= moderate
>50%= high

Don’t want high heterogeneity in a meta analysis

80
Q

Fixed effect vs random effect

A

Use fixed effect if low heterogeneity and random effect if high heterogeneity

81
Q

Non-inferiority margins questions

A

Words question: to be NI, CI cannot cross the bound if the NI margin
-for
Superiority CI can’t contain 0 or 1 (duh)

Pictures:
-superiority: doesn’t cross middle line
-NI: can cross middle line but not the upper or lower limit of the CI
-equivalent: upper and low limit are the same as upper upper and low limit of CI

82
Q

Specificity and sensitivity

A

Specificity: True negative rate, low
Number of false positives
D/B+D

Sensitivity: True positive rate, low number of false negatives
***A/A+C+++

             Truth (+) I  Truth (-) Test (+).       A.               B  Test (-).        C.               D
83
Q

Positive and negative predictive value

A

PPV: probability that person with positive test has a the condition
A/A+B

NPV: probability that person with negative test does not have the condition
D/C+D

             Truth (+) I  Truth (-) Test (+).       A.               B  Test (-).        C.               D
84
Q

PFS bias types

A

-measurement bias
-assessment time bias- difficult to determine exact progression date

85
Q

Oncology endpoints

A

ORR (objective response rate): dx activity (in metastatic setting)- does drug effect the dx after

pCR (pathological response): determines dx activity (in neoadjuvant setting)- does drug effect dx before

RFS (relapse free) or DFS: determination of dx recurrence or death

PFS: determination of dx progression (in metastatic setting)- time until progression or death

OS- survival

86
Q

Correlation coefficient and coefficient of determination

A

Correlation coefficient: r (correlation)- strength and direction of relationship

Coefficient of determination: r2 (regression)- estimates the variation in the outcome due to the independent variable

Random Tips (7 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions