1/23
Vocabulary flashcards covering probability calculations, two-way tables, risk, tree diagrams, Venn diagrams, the normal distribution, and experimental distributions.
Probability
A measure of how likely something is to happen, quantified on a scale from 0 (impossible) to 1 (certain).
Two-way table
A table that classifies counts of data by two variables simultaneously, where inner cells represent intersections of both categories and margins show row, column, and grand totals.
Conditional probability
The chance of an event occurring given that another event has already happened, denoted as P(A∣B), where the restricted group specified after "given" serves as the denominator.
Addition rule ("or" in a two-way table)
A rule for finding the probability of either event A or event B occurring, calculated by adding the row total and column total, then subtracting the overlap cell once to prevent double counting.
Expected number
The predicted count of individuals with a given outcome in a group, calculated as expected number=probability×size of the group and rounded to a whole number in context.
Absolute risk
The proportion or probability of a specific outcome occurring within a single group, calculated as risk=total in the groupnumber with the outcome.
Relative risk
A ratio comparing the risk of an outcome in one group to the risk in another baseline group, calculated as relative risk=risk in group Brisk in group A.
Baseline group
The comparison group positioned in the denominator of the relative risk ratio, determining the direction and interpretation of the ratio.
Tree diagram
A diagram mapping multi-stage events where branches represent possible outcomes labelled with probabilities, all branches emerging from any single point sum to 1, and complete paths represent overall outcomes.
Complement rule ("at least one")
A calculation method stating that the probability of at least one occurrence is equal to one minus the probability of none: P(at least one)=1−P(none).
Sampling with replacement
A process where a selected item is returned to the pool before the next draw, keeping pool totals unchanged and making stages independent with identical probabilities.
Sampling without replacement
A process where a selected item is not returned to the pool, reducing both the overall total and the category count by 1, which makes subsequent stages dependent conditional probabilities.
Venn diagram
A diagram representing events as overlapping circular regions within a universal rectangle, illustrating intersections ("and"), unions ("or"), and non-occurring outcomes ("neither").
Mutually exclusive events
Events that cannot happen simultaneously (P(A and B)=0), represented by non-overlapping circles on a Venn diagram.
Independent events
Events whose outcomes do not influence each other's chances of occurring, satisfying the mathematical relationship P(A and B)=P(A)×P(B).
Normal distribution
A symmetric, bell-shaped continuous probability distribution with a total area of 1, fully defined by its mean (μ) and standard deviation (σ).
68–95–99.7 rule
A rule stating that in a normal distribution, roughly 68% of values fall within 1 standard deviation of the mean, 95% fall within 2, and 99.7% fall within 3.
z-score
A standardised value indicating how many standard deviations a raw score x lies above or below the mean, calculated as z=σx−μ.
Inverse normal problem
A calculation where a probability or tail area is given and the corresponding value x is determined by converting the area to a z-score and using x=μ+zσ.
Theoretical probability
A probability determined mathematically from an assumed model or structure before any empirical trials take place.
Experimental probability
The relative frequency of an event calculated directly from trial data as experimental probability=number of trialsnumber of times it happened.
Long-run relative frequency
The statistical tendency where an experimental probability stabilizes and converges closer to the theoretical probability as the number of trials increases.
Shape (of a distribution)
A distribution feature describing symmetry, modality, or skewness, named after the side toward which the longer tail stretches.
Spread (of a distribution)
A measure describing the degree of dispersion or scatter in a dataset, quantified using statistics such as range, interquartile range, or standard deviation.