Ch 2; Describing Distributions w/ Numbers Flashcards
Using Numerical Summary of Distribution (2)
Center & Variability
Measures of Center (2)
Mean (x̃) & Median (M)
Mean
Ordinary arithmetic average. (Add values & divide by # of values) (x̃ = (x1, x2, …, xn) / n)
Median
Midpoint of distribution. (# where 1/2 observations smaller & 1/2 observations bigger)
How to Find M
1) Arrange observations from smallest to largest
2) Odd # observations (M is center observation), Even # observations (M is midway b/w 2 center observations)
3) Locate median by counting (n+1/ 2) observations from start of list
Comparing Mean & Median in a Symmetrical Distribution vs a Skewed Distribution
Symmetrical; Mean & Median the same or very close
Skewed; Mean farther out in tail than median
How to Measure Variability
Quartiles
How to Find Quartiles
1) Arrange observations in increasing order & locate median
2) First Quartile is the median of observations to left of overall median
3) Third Quartile is the median of observations to right of overall median
4) If odd # median, leave out overall median when determining quartiles. If even # median use all observations.
The 5 Number Summary
Consists of smallest observation, first quartile, median, third quartile, largest observation.
Box Plot
A graph of the 5 number summary. Central box spans quartiles, line in box marks the median, lines extending from box go out to largest/smallest observations
Interquartile Range (IQR)
Distance b/w Q1 & Q3 or range that encloses middle 50%.
The 1.5 x IQR Rule for Outliers
Call an observations an outlier if falls more than 1.5 x IQR above Q3 or below Q1
Resistant Measure
Any aspect of distribution relatively unaffected by changes in the numerical value of a small proportion of the total # of observations, no matter how large changes.
Which Measures are Resistant (2)
Median & Quartiles
Which Measures are Not Resistant (2)
Mean & Standard Deviation