Chapter 3 Section 2: Measure Of Dispersion Flashcards
Standard deviation
A measure of how much we might expect a typical member of the data set to differ from the mean
Coefficient of variation
The ratio of the standard deviation to the mean as a percentage; allows comparison of the spreads of data from different sources, regardless of differences in units of measurement
Variance
The square of the standard deviation
Empirical rule
Used with the bell-shaped distributions of data to estimate the percentage of values within the standard deviations of the mean
Chebyshev’s theorem
Gives a minimum estimate of the percentage of data within a few a standard deviations of the mean for any distribution
Range
Largest data value in a data set - smallest data value in a data set
Properties of the range
1) easiest measure of dispersion to calculate
2) only affected by the largest and smallest values in the data set , so it can be misleading
Population standard deviation
Theta symbol
Sample standard deviation
S
Properties of standard deviation
1) easily computed using a calculator or computer
2) affected by every value in the data set
3) population standard deviation and sample standard deviation formulas yield different results
4) interpreted as the average distance a data value is from the mean; thus it cannot take on negative values
5) same units as the units of the data
6) larger standard deviation indicated that data values are more spread out, smaller standard deviation indicated that data values lie closer together
7) if it equals 0 then all of the data values are equal to the mean
8) equal to the square root of the variance
Population/ sample variance
Standard deviation squared
Properties of variance
1) easily computed using a calculator or computer
2) affected by every value in the data set
3) population variance and sample variance formulas yield different results
4) difficult to interpret because of its unusual squared units
5) equal to the square of the standard deviation
6) preferred over the standard deviation in many statistical tests because of its simpler formula
Empirical rule for bell-shaped distributions
Approx 68% of data values lie within one standard deviation of the mean
Approx 95% of data values lie within two standard deviations of the mean
Approx 99.7% of data values lie within three standard deviations of the mean
Chebychev’s theorem
K=number of classes
When k=2 75% of the data lie within 2 standard deviations of the mean
When k=3 88.9% of the data lie within 3 standard deviations of the mean