Epidemiology 1

Front 1

Morbidity

Back 1

Any departure from a state of well-being

Front 2

Mortality

Back 2

You dead nigga

Front 3

Two ways of Measuring Risk

Back 3

-Probabilities

-Rates

Front 4

Probability

Back 4

Proportion of people unaffected at the beginning of study period, but who experience a risk event during the study period

Front 5

Rate

Back 5

Number of events that occur in a defined time period, divided by average number of people at risk (usually population of people at middle of period)

Rate = (Persons with disease/Persons at risk) x c

Front 6

Rate is a good approximation of risk if

Back 6

-Event in numerator occurs only once during study period

-Proportion of population affected by event is small

-Time interval is relatively short

Front 7

Measures of Morbidity

Back 7

-Incidence rate

-Prevalence "rate"

Front 8

Incidence Rate

Back 8

(# of new cases / population at risk) x k

Measures risk of developing a disease

Front 9

Prevalence "Rate"

Back 9

#Active Cases / Population at Risk

Measures proportion of persons with disease

Two types: period prevalence, point prevalence

Front 10

Measures of Mortality

Back 10

-Mortality Rate

-Case-fatality rate

-Proportionate mortality ratio

Front 11

(Crude) Mortality Rate

Back 11

#deaths/population

Measures risk of dying

Front 12

Cause-Specific Mortality Rate

Back 12

# deaths by disease / population

Measures risk of dying from a disease

Front 13

Case-fatality Rate

Back 13

# deaths by disease / population with disease

Measure of lethality

Front 14

Survival Rate

Back 14

1 - (case-fatality rate)

Front 15

Proportionate Mortality Ratio

Back 15

# deaths from one cause / all deaths

Not a measure of risk, measures relative importance of a specific cause of death relative to all deaths.

Front 16

Direct Standardization of Rates

Back 16

Use an external standard population to calculate expected number of deaths with ACTUAL rates of mortality. This is done to control for a specific variable.

Front 17

Standardized Mortality Ratio

Back 17

Used when rates are not available for given observed values. Similar process as standardization of rates.

Front 18

Relative Risk

Back 18

Risk with factor / Risk without factor

Measures strength of association between exposure and disease.

Front 19

Attributable Risk

Back 19

Risk with factor - Risk without factor

Measures the amount of absolute risk that is attributable to factor

Front 20

Attributable Risk Percent (Attributable Fraction)

Back 20

[Risk (Factor) - Risk (No Factor)] / Risk (Factor)

Front 21

Population Attributable Risk

Back 21

[Risk(pop)-Risk(no factor)]/Risk(pop)

Front 22

Study Validity

Back 22

When results of study are true and meaningful

Front 23

Internal Validity

Back 23

When results of study are true and meaningful for patricipants

Front 24

External Validity

Back 24

Generalizability of study

When results of study are true and meaningful for a larger population, not just participants

Front 25

Random Sampling

Back 25

Selecting small group (n) for study from larger population (N) by use of a random method (R)

Front 26

Simple Random Sampling

Back 26

-Assigning unique number to possible elements from N

-Selecting a small group (n) using a random procedure

Front 27

Systematic Random Sampling

Back 27

-Assign unique number to elements of N

-Order from smallest to highest

-Calculate N/n=k

-Use random method to select starting element

-Select elements sequentially every Kth element from N (Never use starting point as first element in n).

Front 28

Stratified Random Sampling

Back 28

-Organize your elements from N into homogeneous sub-populations ( strata)

-Perform simple or systematic random sampling on each strata to obtain your final population n.

-Helps avoid sampling errors

Front 29

Cluster Random Sampling

Back 29

-Identify groups (clusters) of elements

-Assign unique number to each cluster

-Use random method to select cluster

-Select all element from chosen clusters

Front 30

Standard Error of the Mean (SEM)

Back 30

Standard deviation of a Sampling Distribution

SEM = sd/sqrt(n)

Front 31

95% Confidence Interval

Back 31

Sampling Mean +/- 1.96 (SEM)

Front 32

As sample size increases, the confidence interval

Back 32

Gets narrower, SEM gets smaller

Front 33

As sample size decreases, the confidence interval

Back 33

Gets wider, SEM gets larger

Front 34

Type I error (alpha)

Back 34

Rejecting a Null Hypothesis when it is actually true. Same as p-value.

Front 35

Type II error (Beta)

Back 35

Accepting a Null Hypothesis when it is actually false.

Front 36

Statistical Power

Back 36

Ability of a test to reject null hypothesis when it is actually false.

Probability of not committing a Type II Error

Statistical Power = 1 - Beta

Front 37

Acceptable levels of significance and power

Back 37

Significance: alpha = 0.05

Power: 1 - Beta = 0.80

Front 38

z-test

Student's t-test

Back 38

Compare means of two groups

Requires a normal distribution (t-test)

Front 39

Analysis of Variance (ANOVA)

Back 39

Compare means of three or more groups

Requires a normal distribution

Front 40

Chi-Squared

Back 40

Compare proportions of two or more groups

Front 41

Fisher's exact test

Back 41

Compare proportions of two groups (if small "expected frequencies")

Front 42

Post-Hoc Analysis

Back 42

Situation in which you choose which comparisons to make AFTER you've looked at the data

Front 43

Mann-Whitney test

Back 43

Non-parametric test to compare two groups that do not have a normal distribution

Front 44

Kruskal-Wallis

Back 44

Non-parametric test to compare three or more groups that do not have a normal distribution