BIOL/WFS 4220/5220 Biostatistics Exam I Study Guide Vocabulary

Vocabulary flashcards covering key terms and concepts for BIOL/WFS 4220/5220 Exam I, including experimental design, basic probability, summary statistics, and data visualization.

Manipulative studies

Studies in which experimental conditions or treatments are directly manipulated by the researcher.

Observational studies

Studies where variables are observed and measured without direct intervention or manipulation by the researcher.

Natural experiments

Observational studies where natural events or variations alter experimental conditions without researcher intervention.

Continuous variables

Quantitative variables that can take on an infinite number of possible values along a numerical continuum, typically displayed using histograms.

Discrete variables

Quantitative variables with distinct, countable values that cannot take on arbitrary fractional values, typically displayed using bar graphs.

Categorical variables

Variables whose values represent distinct categories or non-numeric classifications.

Explanatory variables

Variables manipulated or categorized by the investigator to test their potential effect on an outcome.

Response variables

Variables measured to observe the outcome or effect produced by explanatory variables.

Population

The entire collection of individuals or units about which a researcher wants to draw conclusions.

Sample

A subset of individuals or measurements selected from a population.

Stratified (randomized block) sampling

A sampling method where the population is divided into subgroups (strata) and random samples are drawn from each subgroup.

Volunteer sampling

A non-random sampling technique relying on individuals who self-select or volunteer to participate in a study.

Opportunity sampling

A non-random sampling method based on selecting subjects that are conveniently available to the researcher.

Controls

Experimental units that do not receive the active treatment, serving as a baseline standard for comparison.

Treatments

The specific experimental conditions or manipulations applied to experimental replicates.

Pseudoreplication

The statistical error of treating non-independent replicates or repeated observations as if they were independent replicates.

Balanced design

An experimental design characterized by an equal number of replicates across all treatment groups.

Independence of treatments

The experimental condition wherein the application or effect of one treatment does not influence or depend upon another treatment.

Confounding effects

Distortions caused by unmeasured extraneous factors that correlate with both explanatory and response variables, obscuring true relationships.

Blinding

An experimental procedure used to prevent bias by withholding treatment assignment information from subjects, researchers, or both.

Single-blind trial

An experimental design in which the subjects do not know which treatment group they have been assigned to.

Double-blind trial

An experimental design in which neither the subjects nor the investigators evaluating them know which treatment group subjects belong to.

Blocking

The experimental technique of grouping homogeneous replicates into blocks to control for known sources of variation.

Event

A specific outcome or collection of outcomes of interest resulting from a probabilistic process.

Outcome

A single possible result of a probability experiment or observation.

Sample space/set

The set containing all possible outcomes of a probabilistic experiment.

Mutually exclusive outcomes

Outcomes that cannot occur at the exact same time in a single trial.

Exhaustive outcomes

A set of outcomes that encompasses every possible result of a probabilistic experiment.

Addition rule

A probability calculation rule used to determine the probability that at least one of multiple mutually exclusive events occurs.

Multiplication rule

A probability calculation rule used to determine the joint probability of two or more independent events occurring together.

Probability tree

A visual diagram illustrating sequential random events and their associated conditional probabilities along branching lines.

Conditional probabilities

The probability of an event occurring given that another event is already known to have occurred.

Bayes' theorem

A mathematical formula used to calculate and update conditional probabilities based on prior knowledge and new evidence.

Law of total probability

A fundamental probability rule expressing the marginal probability of an event across all distinct conditional possibilities.

Sampling with replacement

A sampling procedure where every selected unit is returned to the population prior to selecting subsequent units.

Sampling without replacement

A sampling procedure where selected units are not returned to the population, causing probabilities to change with successive draws.

Measures of location (central tendency)

Summary statistics that describe the center or typical value of a data distribution, such as the mean, median, and mode.

Measures of spread

Summary statistics that quantify the dispersion, variability, or scatter of data points within a distribution.

Arithmetic mean

The conventional average of a dataset, computed by summing all values and dividing by the total number of observations.

Geometric mean

A measure of central tendency calculated as the nth root of the product of n positive numerical values.

Harmonic mean

A measure of central tendency computed as the reciprocal of the arithmetic mean of the reciprocals of a dataset.

Median

The middle value in an ordered set of data that divides the distribution into two equal halves.

Mode

The value or category that appears most frequently in a dataset.

Accuracy

The closeness of a measured or estimated value to the true parametric value.

Precision

The closeness or repeatability of agreement among independent measurements obtained under identical conditions.

Systematic errors

Predictable, consistent biases in measurements that affect the mean and reduce accuracy.

Random errors

Unpredictable, chance variations in measurements that affect precision.

Parametric values

True numerical quantities or parameters that characterize an entire population.

Statistical values

Numerical values calculated from a sample used to estimate unknown population parameters.

Unbiased estimate

A sample statistic whose expected average value across repeated sampling equals the true parametric value.

Skewness

A measure of the asymmetry of a numerical data distribution around its central mean.

Kurtosis

A measure describing the peakedness or tail weight of a probability distribution compared to a normal distribution.

Confidence interval

A calculated range of values based on sample statistics that contains the true population parameter with a specified level of confidence.

Table

An organized arrangement of data in rows and columns used to present detailed quantitative or qualitative information concisely.

Figure

A visual representation of data, such as a chart, graph, diagram, or plot.

Dot plot

A simple visual display where individual numerical data points are plotted as dots along a single axis.

Stem-and-leaf plot

A display for showing individual numerical data split into stems (leading digits) and leaves (trailing digits).

Pie graph

A circular visual representation where proportional slices represent categorical data relative to a whole.

Bar graph

A graphical display featuring separated rectangular bars used to present discrete or categorical data frequencies.

Histogram

A graphical display of contiguous vertical bars representing the frequency distribution of continuous quantitative data.

Frequency polygon

A line graph constructed by connecting the midpoints of histogram bars to illustrate continuous distribution shapes.

Error bars

Graphical lines drawn on data points or bars to indicate variability, standard error, or confidence intervals.