Biostats

Cross Sectional

Data from a group of people to assess frequency of dz at a particular point in time.
Asks "what is happening?

Case-control

Compares a group of people without a dz to a group with dz.
Asks "what happened?"
Retrospective
Patients with COPD had higher odds of a history of smoking than those without COPD.

Cohort

Compares a group with a given exposure or risk factor to a group without such exposure.
Looks to see if exposure increases likelihood of dz.
Prospective or retrospective
Asks "who will develop dz?" or "who developed the dz?"
Smokers had a higher risk of d

Twin concordance

Compares frequency with which both monozygotic twins or both dizygotic twins develop same dz.

Adoption study

Compares siblings raised by biological vs. adoptive parents.

Phase I of CT

Small number of healthy volunteers.
Safety
Toxicity
PCK
Pharmacodynamics

Phase II of CT

Small number of patients with dz of interest.
Treatment efficacy
Optimal dosing
Adverse effects

Phase III of CT

Large number of patients randomly assigned either to the treatment under investigation or to the best available treatment/placebo.
Compares new treatment to current standard of care.

Phase IV of CT

Postmarketing surveillance of patients after treatment is approved.
Rare or long-term adverse effects.

Selection bias

Error in assigning subjects to a study group resulting in an unrepresentative sample.

Recall bias

Awareness of disorder alters recall by subjects; common in retrospective studies.

Measurement bias

Information is gathered in a way that distorts it.

Procedure bias

Subjects in different groups are not treated the same.

Observer-expectancy bias

Researcher's belief in the efficacy of a treatment changes the outcome of that treatment.

Confounding bias

When a factor is related to both the exposure and the outcome, but not on the causal pathway; factor distorts or confuses effect of exposure on outcome.

Lead-time bias

Early detection time is confused with increased survival.

Mean

Most affected by outliers.

Median

If n=even number, the median will be the average of the middle two values.

Mode

Least affected by outliers.

Sample error of mean

SD
---
square root of n

SD distributions

1SD = 68%
2SD = 95%
3SD = 99.7%

Positive skew

Mean > median > mode
Long tail on
right

Negative skew

Mean < median < mode
Long tail on
left

Statistical hypotheses

Type I error

Stating there is an effect or difference when none exists.

Type II error

Stating there is not an effect or difference when one actually exists.

t-test

Checks difference between means of 2 groups.

ANOVA

Checks difference between means of
3 or more
groups.

Chi-square

Checks differences between 2 or more percentages or proportions of
categorical
outcomes.
Chi
tegorical outcomes.

Primary dz prevention

P
revent disease occurrence.

Secondary dz prevention

S
creening for early dz.

Tertiary dz prevention

T
reatment to reduce disability from dz.

Medicare is for (elderly/poor).

E
lderly

Medicaid is for (elderly/poor).

Poor =
D
estitute

Medicare part A

Hospit*A*l insur
A
A
pit*A*l insur*A*nce

Medicare part B

*B*asic medical
B
B
asic medical *B*ills

Medicare part C

Parts
A+B
delivered by approved private
C
ompanies

Medicare part D

Prescription
D
rugs