chapter 3 (central tendency & dispersion) Flashcards
measures of central tendency
stats that summarize a distribution of scores by reporting the most typical or representative value of distribution. 3 most common: mean, median, mode.
measures of dispersion
stats that indicate the amount of variety/heterogeneity in a distribution of scores. most common: range and standard deviation.
dispersion
amount of variety or heterogeneity in distribution of scores.
mode
most common value in distribution/largest category of variable. nominal variables well suited.
index of qualitative variation (IQV)
ratio of the amount of variation actually observed in a distribution of nominal or ordinal level variable scores to the maximum variation that could exist in that distribution.
median (Md)
point in a distribution of scores above and below which exactly half of the cases fall. ordinal and interval-ratio variables.
range (R)
highest score (H) minus lowest score (L). prone to outliers.
outliers
extreme high or low scores in distribution.
interquartile range (Q)
the distance from the third quartile to the first quartile. less prone to outliers.
Q = Q3 - Q1
boxplot
graphic device based on the median, interquartile range, and range. displays centre, dispersion, and overall range of scores in distribution of ordinal or interval-ratio level variable scores. based on info from 5 number summary.
five number summary
group of stats including lowest score, first quartile, median, third quartile, and highest score of distribution of scores, and the basis for the boxplot.
mean
point in distribution of scores above and below which exactly half of the cases fall. susceptible to outliers.
skew
extent to which a distribution of scores has a few scores that are extremely high (positive skew) or extremely low (negative skew). important characteristic of distribution shape. mean less than median = negative skew. mean greater than median = positive skew.
deviations
distances between the scores and the mean. bigger = more variation.
mean deviation
average of the absolute deviations of the scores around the mean.