HTHSCI 2S03 Lecture Notes - Lecture 4: Central Limit Theorem, Standard Score, Exclusive Or
Document Summary
With normally distributed data, the mean and variance aren"t dependent on each other - if we increase the mean, the variance should stay the same. If we drew a larger number of sample of reasonable size then the distribution of the means of those samples will always be normally distributed. Central limit theorem: states that if we draw equally sized samples from a non-normal distribution, the distribution of the means of these samples will be normal as long as the samples are large enough. Clt guarantees that, if we take enough even moderately sized samples ( enough is usually more than 30), the means will approximate a normal distribution. A way to transform all normal distributions so that they use the same scale. Idea is to specify how far away an individual value is from the mean by describing its location in standard deviation (sd) units.