Starnes, The Practice of Statistics, 6e, Chapter 10

sampling distribution of p̂₁ - p̂₂

The distribution of values taken by the statistic p̂₁ - p̂₂ in all possible samples of size n₁ from population 1 and all possible samples of size n₂ from population 2. (p. 623)

two-sample z interval for a difference between two proportions

Confidence interval used to estimate a difference in the proportions of successes in two populations/treatments. (p. 626)

pooled or combined sample proportion

The overall proportion of successes in the two samples is p̂ = count of successes in both samples combined ÷ count of individuals in both samples combined = X₁ + X₂ ÷ n₁ + n₂ (p. 632)

two-sample z test for the difference between two proportions

A test of the null hypothesis that the proportions of successes in two populations/treatments are equal. (p. 634)

randomization distribution

Distribution of a statistic (like p̂₁ - p̂₂ or x̄₁ - x̄₂) in repeated random assignments of experimental units to treatment groups assuming that the specific treatment received doesn't affect individual responses. (p. 636)

sampling distribution of x̄₁ - x̄₂

The distribution of values taken by the statistic x̄₁ - x̄₂ in all possible samples of size n₁ from population 1 and all possible samples of size n₂ from population 2. (p. 647)

two-sample t interval for a difference between two means

Confidence interval used to estimate a difference in the means of two populations/treatments. (p. 651)

two-sample t test for the difference between two means

A test of the null hypothesis that the means of two populations/treatments are equal. (p. 658)

paired data

The result of recording two values of the same quantitative variable for each individual or for each pair of similar individuals. (p. 673)

paired t interval for a mean difference

Confidence interval used to estimate a population (true) mean difference. (p. 677)

one-sample t interval for a mean difference

Confidence interval used to estimate a population mean. (p. 679)

paired t test for a mean difference

A test of the null hypothesis that a population (true) mean difference is equal to a specified value, usually 0. (p. 680)