Distribution of Sample Means University Of （大学样本均值的分布）.pdf

Distribution of Sample Means The distribution of the means of an infinite number of samples of a certain size selected from a population Before, we talked about distributions of scores, but now we are talking about the distribution of all possible sample means of a specific size from a population SAMPLING ERROR: •The amount of error, or the difference, between a sample statistic and the corresponding population parameter •If we start with a population, and take a number of samples from that population, each of the sample means will be different from the population mean in varying degrees CENTRAL LIMIT THEOREM For samples of size n taken from a population with mean, µ, and a standard deviation, σ, – µX = µ σ σ = – X n – As n increases, the sampling distribution approaches € the normal distribution – Holds for all population distributions € • in other words, as long as your sample size is large (30 or above usually) the sampling distribution will be normal even if the population (parent distribution) from which it was sampled is not 1 Central Limit Theorem Population σ = 20 € µ = 100 Sampling Distribution Though the population σ = 20 distribution is skewed the X n sampling distribution will still be normal as long as you have a