What Resistant is
In statistics, resistant refers to the ability of a statistic to remain unchanged when small numbers of outliers are present in the data. A resistant statistic is one that is not greatly affected by the presence of outliers.
The following steps can be used to determine the resistant of a statistic:
-
Calculate the statistic without the outliers.
-
Calculate the statistic with the outliers included.
-
Compare the two results. If the differences between the two results are small, then the statistic is resistant.
-
Analyze the outliers to determine if they are valid data points or if they are due to errors or inconsistencies.
-
If the outliers are valid data points, then the statistic is not resistant.
Examples
-
Resistant statistics can be used to identify outliers in data sets, allowing for more reliable and accurate analysis of the data.
-
Resistant statistics can be used to detect and identify anomalies in time series data, helping to identify potential trends or changes in behavior.
-
Resistant statistics can be used to identify and adjust for the effects of outliers in regression and correlation analysis.
-
Resistant statistics can be used to identify clusters or groups in large data sets, allowing for more detailed analysis and understanding.