alternative hypothesis - a hypothesis that a population parameter assumes some set of values other than the one value assigned in the null hypothesis. This hypothesis is typically denoted HA.
critical value - a value or pair of values that mark off a proportion of α (the level of significance) of the standard normal distribution (or t-distribution).
hypothesis - a claim, assertion or belief that can be tested by observation.
hypothesis test - a method in statistical inference of testing a claim by collecting and observing a sample of data, and determining how consistent the claim is with the observed data.
level of significance - the probability α of rejecting the null hypothesis when it is true.
null hypothesis - a hypothesis that a population parameter assumes some specific value. This hypothesis is typically denoted H0.
one-sided hypothesis test - a test in which the alternative hypothesis asserts that the population parameter is specifically greater than (conversely, specifically less than) the value assigned in the null hypothesis.
P-value - for a given test statistic, the probability of observing a test statistic as extreme as this given test statistic on the assumption that the null hypothesis is true.
power - the probability of not committing a Type II error, (1 - β).
region of rejection - the region within the standard normal distribution or t-distribution, marked off by the critical value(s), that contains a proportion of α of the distribution.
test statistic - a z-score (or t-score) of a sample statistic that indicates the position of the sample statistic in the standard normal distribution (or t-distribution) on the assumption that the null hypothesis is true.
two-sided hypothesis test - a test in which the alternative hypothesis asserts that the population parameter is not equal to the value assigned in the null hypothesis.
Type I error - the error of rejecting the null hypothesis when it happens to be true. The probability of this is the level of significance, denoted α.
Type II error - the error of not rejecting the null hypothesis when it happens to be false. The probability of this is denoted β.