Median is a good example of a resistant statistic. It "resists" the pull of outliers. The mean, on the other hand, can change drastically in the presence of an outlier.
The interquartile range is a resistant measure of spread.
Chat with our AI personalities
They are the mean, median and mode.
They are measures of the spread of the data and constitute one of the key descriptive statistics.
They describe the basic features of data. They provide summaries about the sample and the measures, and together with simple graphic analysis, they form the basis of virtually every analysis of data.
No. Descriptive statistics are those that characterise samples without attempting to draw conclusions. The purpose of them is to help investigators to form an understanding of what the data might be capable of telling them. Descriptive statistics include graphs as well as measures of location, scale, correlation, and so on. Parametric statistics are those that are based on probabilistic models (ie, mathematical models involving probability) that involve parameters. For instance, an investigator might assume that her results have come from a population that is normally distributed with a certain mean and standard deviation; this would be a parametric model. She could estimate this pair of parameters, the mean and standard deviation, using parametric statistics, or test hypotheses about them, again using parametric statistics. In either case the parametric statistics she uses would be based on the parametric mathematical model she has chosen for her data.
Of these three, the median is most resistant.