Chapter 3 Flashcards
(11 cards)
descriptive statistics
quantities that capture important features of frequency distributions
What are the most important descriptive stats for numerical data?
those measuring LOCATION of a frequency distribution (tells us avg) and its SPREAD (tells how variable the measurements are around the center)
What are the most important descriptive stats for categorical data?
proportion (measures fraction of observations in a given category)
Coefficient of variation
the st.dev expressed as a % of the mean
high CV, more variability
Interquartile Range
the span of the middle half of the data, from the 1st quartile to the 3rd
Boxplot
displays median and IQR along with other quantities of the frequency distribution
When data is skewed/has extremities, is IQR or st.dev better as an indicator of the spread?
IQR
Quantile
(of a measurement) specifies the fraction of observations less than or equal to it
Identify 3 measures of location
mean, median, mode
Identify 3 measures of variability
SD, variance, range
Standard deviation
measure of the spread that indicates how different measurements are from the mean