PBSI 245 Chapter 3: What Do Samples Tell Us?

Vocabulary flashcards covering key concepts from PBSI 245 Chapter 3, including parameters, statistics, sampling variability, bias, margin of error, and confidence statements.

Parameter

A number that describes a population, whose value is unknown but exists and cannot be accessed from the entire population.

Statistic

A number that describes a sample, whose value is known once data is collected and varies across samples from the same population, used to estimate a parameter.

Proportions

Percentages that can be expressed as decimals, fractions/ratios, or percentages.

Population proportion (p)

The percentage of individuals in the population who support a particular policy or possess a certain characteristic (a parameter).

Sample proportion (p̂)

The percentage of individuals in a sample who support a particular policy or possess a certain characteristic (a statistic), used to estimate the population proportion.

Sampling Variability

The phenomenon where statistics differ across multiple samples drawn from the same population.

Bias (in sampling)

Systematically favoring certain outcomes over others, either by selecting specific individuals into a sample or by systematically under- or over-estimating a population parameter.

Good sampling methods

Methods characterized by small bias and small sampling variability.

Effect of larger sample size

Produces less sampling variability across samples.

Margin of Error (MOE)

A measure that quantifies the uncertainty in an estimate, indicating how close the sample statistic is thought to be to the population parameter.

Confidence Interval (CI)

A range of values computed from a sample statistic and margin of error (p̂
R MOE, p̂ + MOE), which, for a given confidence level, is expected to contain the population parameter.

Confidence Statement

An interpretation of a confidence interval, articulating how close the statistic is to the parameter (margin of error) and the percentage of all possible samples in which the confidence interval includes the parameter (level of confidence).

Level of Confidence

The percentage of all possible samples (commonly 95%) in which the confidence interval includes the population parameter.

Effect of population size on variability

Population size does not affect sampling variability if the population is at least 20 times larger than the samples.