Numerical Summaries Median, 5-Number Summary, & Boxplots

Median

Is the middle value or in other words 50th percentile, does not really care much about those outliers

Outliers

Data point not representable of the population of interest. Ex: a person with a pulse of 200 does not belong to data because it’s a crazy pulse

“Resistant” statistics

Statistics not heavily influenced by outliers, high or low pulse values don’t really have outstanding effect on median.

Bell shaped/normal

If its a bell shaped normal or symmetrical it’s better to stick with mean

Measure of spread

You can see the shape and kind of the spread but both have different spreads and you can see the range

Range

Max - Mix= Range

Measures of Relative Standing

Shows where you stand, relative to everyone, other way that we look at the spread of a data set

Min= 0th percentile

Median= 50th percentile

Max= 100th percentile

Quartiles

One way that we look at variability in a data set is we just look at some kind of benchmark percentiles

Inter-Quartile Range (IQR)

Average Middle

IQR Test for Outliers

Lower bound= q1 - 1.5(IQR)

Upper bound= q3 + 1.5(IQR)

Any data outside the boundaries, flag as potential outliers

Five number summary

Min, Q1, Median, Q3, Max