Applied statistics/Related Articles: Difference between revisions
Jump to navigation
Jump to search
imported>Nick Gardner |
imported>Nick Gardner |
||
| Line 1: | Line 1: | ||
==Glossary== | ==Glossary== | ||
{{r|Chi-squared goodness of fit test}} | {{r|Chi-squared goodness of fit test}} | ||
Revision as of 13:47, 1 July 2009
Glossary
- Chi-squared goodness of fit test [r]: a test for comparing a mathematical probability distribution with observed data. [e]
- Binomial distribution [r]: Describes the probability of success when repeatedly tossing a (fair or unfair) coin. [e]
- Confidence interval [r]: the range of a random variable, such as the mean of a sample, that — with a specified probability — contains the true value for the population. [e]
- Confidence level [r]: the probability that the true value of a random variable lies within the estimated (or predicted) confidence interval. [e]
- Deterministic [r]: the predictable effect of known causes (used in contrast to stochastic). [e]
- False positive rate [r]: the proportion of tests that yield a positive result when the true result is negative. [e]
- False negative rate [r]: the proportion of tests that yield a negative result when the true result is positive. [e]
- Mean [r]: e.g. "arithmetic mean", being the sum of n observations divided by n, or "geometric mean", being the nth root of the product of n observations. [e]
- Median (statistics) [r]: The value of a numerical or linearly ordered sample for which one half of the observations lie above and one half lie below that value. [e]
- Mode (statistics) [r]: the most frequently ocurring value. [e]
- Normal distribution [r]: a symmetrical bell-shaped probability distribution representing the frequency of random variations of a quantity from its mean. [e]
- Population (statistics) [r]: the totality of the people or things that constitute the category that is the subject of a statistical investigation, and from which a sample is drawn. [e]
- Prevalence [r]: The total number of cases of a given disease in a specified population at a designated time. It is differentiated from incidence, which refers to the number of new cases in the population at a given time. [e]
- Probability [r]: a numerical measure - on a scale of 0 to 1 - of the likelihood of an event, based either upon objective evidence or upon subjective judgement. [e]
- Random variable [r]: a variable whose value is determined by chance rather than as a result of a known cause. [e]
- Sample (statistics) [r]: An instance of a random variable used to estimate one or several of its parameters. [e]
- Significance level [r]: the chosen probability of wrongly rejecting a null hypothesis (usually set at 5%). [e]
- Standard deviation [r]: A statistical measure for the fluctuation of a random variable about its mean value (the square root of the variance). [e]
- Standard error [r]: the standard deviation of the variation of a statistic that would occur if the same sampling method were applied repeatedly: for example, the standard error of the mean is measured as the standard deviation of the observed (sample) mean as measured in independent samples of a given size. [e]
- Stochastic [r]: of a random nature (sometimes contrasted with deterministic). [e]
- Type I error [r]: the error that occurs when a null hypothesis is wrongly rejected. [e]
- Type II error [r]: the error that occurs when the null hypothesis is not rejected although it is false. [e]
- Variance [r]: A statistical measure of the variability of a random quantity (defined as the mean squared deviation from the mean value). [e]