advanced terms

Normal Probabilities | |||||||||

The normal curve
results when a large number of observations are piled together. The area under
any normal curve
is 1. The probability that a variable lies within an interval
is given by the area under the curve. Below is an unlabeled example:
Each curve is distinguished from other normal curves by two features: a mean (m), which tells where the center of the distribution is, and standard deviation (s), which tells how wide the distribution is. The examples below assume a mean of 40 and a standard deviation of 1.
| |||||||||

Hypothesis Tests t and z | |||||||||

hypothesis test |
|||||||||

A hypothesis is a claim about a parameter (e.g., mean, variance, correlation, proportion). The hypothesis comes in two statements: a null hypothesis - which states that there is no difference between the parameter and say 10, and an alternate hypothesis - which states that there is a difference. | |||||||||

t-test |
|||||||||

The t-test compares the
mean of one set of data against the mean of another set.
A one-sample t-test compares the mean of a data set against an already known population mean. For instance, a set of IQ tests is measured against the national average IQ of 100. A two-sample t-test compares the mean of one data set against the mean of another data set. For instance, a set of men's IQ scores might be compared with a set of women's IQ scores. The difference between the z-test and the t-test is the formula used to compute the statistic. |
|||||||||

z-test |
|||||||||

The z-test compares the
mean of one set of data against the mean of another set.
A one-sample z-test compares the mean of a data set against an already known population mean. For instance, a set of IQ tests is measured against the national average IQ of 100. A two-sample z-test compares the mean of one data set against the mean of another data set. For instance, a set of men's IQ scores might be compared with a set of women's IQ scores. The difference between the z-test and the t-test is the formula used to compute the statistic. |
|||||||||

Confidence Intervals | |||||||||

A 95% confidence interval is an interval that you are 95% confident contains the mean. This does not mean that when you grab a sample from the population, 95% of the time, the mean will fall into that interval. The mean is the mean of the population. It doesn’t change – ever. What it means is this: Each sample has a related confidence interval. 95% of those intervals will contain the population mean. |