Epidemiology and Data Presentation

Flashcards covering key terminology, data types, graphical presentations, measures of central tendency and variation, and bivariate associations in epidemiology.

Population

Collection of people who share common observable characteristics. Example: Inhabitants of a country.

Parameter

Measurable attribute of a population. Example: Average age of the population.

Sample

Subgroup that has been selected, by using one of several methods, from population.

Universe

Total set of elements from which a sample is selected.

Statistics

Numbers that describe a sample.

Representativeness

Degree to which characteristics of the sample correspond to characteristics of the population from which the sample was chosen.

Estimation

Using sample-based data to infer conclusions about the population.

Rationale for Using Samples

To estimate and assess parameter estimates, and for possible cost savings over studying the whole population.

Sampling bias

Creation of nonrepresentative samples.

Simple random sampling

Samples selected by a random process that is unbiased, where the average of sample estimates over all possible samples (of size $n$ from $N$) is equal to the population parameter.

Qualitative data

Measured as categories; include nominal and ordinal data. Examples: Marital status, sex, pain level.

Quantitative data

Reported as numerical quantities; include discrete and continuous data. Examples: Blood pressure, household size.

Interval scale

Equal intervals between points on a measurement scale with no true zero point. Example: Fahrenheit temperature scale.

Ratio scale

Same properties as an interval scale but has a true zero point. Example: Weight in pounds.

Data cleaning

Review of data for accuracy and completeness, making a data set ready for coding and analysis.

Bar chart

Type of graph that shows the frequency of cases for categories of a discrete variable, such as a Yes/No variable.

Histogram

A chart similar to a bar chart but used for continuous variables, with no gaps between bars.

Line graph

Used to display trends, such as time trends.

Pie chart

A circle that shows the proportion of cases according to several categories, with the size of each piece proportional to the frequency of cases.

Mode

The number occurring most frequently in a set or distribution of numbers.

Median

The middle point of a set of numbers.

Mean

The arithmetic mean or average, calculated as the sum of all values divided by the number of values, i.e., $\bar{X} = \frac{\sum X}{n}$

Normal distribution

A symmetrical distribution, often represented by a bell-shaped curve, with standard deviation indicating dispersion.

Skewed distributions

Distributions that are not symmetrical, for which the median is a better measure of central tendency.

Multimodal Curve

A curve that has several peaks in the frequency of a condition, with the mode being the category with the highest frequency of cases. Possible reasons include changes in lifestyle and immune status or latency effects.

Latency

The time period between initial exposure and a measurable response.

Epidemic curve

A graphic plotting of the distribution of cases by time of onset, which aids in investigating outbreaks by providing information on the start/end and peak of an outbreak, incubation period, and possible exposures.

Pearson Correlation Coefficient (r)

A measure of association used with continuous variables that varies from $-1$ to $0$ to $+1$. A value of $0$ means no association, and as $r$ approaches $-1$ or $+1$, the association becomes stronger. When $r$ is negative, the association is inverse.

Scatter Plot

A diagram that plots two variables, one on the X-axis (horizontal) and one on the Y-axis (vertical), with measurements for each case plotted as a single data point. The closer the points lie to the straight line of best fit (regression line), the stronger the association.

Dose-Response Curve

A plot of a dose-response relationship, which is a type of correlative association between exposure and effect.

Threshold

In a dose-response relationship, it refers to the lowest dose at which a particular response occurs.

Contingency Table

A method for demonstrating associations by tabulating data according to two dimensions (rows and columns).

Marginal totals

The column and row totals in a contingency table.

A (in Contingency Table)

Represents cases where exposure is present and disease is present.

B (in Contingency Table)

Represents cases where exposure is present and disease is absent.

C (in Contingency Table)

Represents cases where exposure is absent and disease is present.

D (in Contingency Table)

Represents cases where exposure is absent and disease is absent.

Point estimate

Uses a single value for estimation.

Interval estimate

Uses a range of values for estimation.

95% Confidence Interval (CI) formula

$$95\%\,CI = \bar{X} \pm 1.960 \frac{S}{\sqrt{n}}$$