Numerical summaries (mean, median, variance, sd, IQR). Bivariate data: correlation, two-way tables Flashcards
Mean μ
Average of all data points.
Add all numbers together then divide by the total number of numbers.
Median
The centre number in the ordered sequence of data points.
Mode
The number that occurs the most in a data set.
Standard deviation σ
How measures are spread out from the mean.
Low σ means numbers are close to the mean
High σ means numbers are spread out from the mean.
Variance σ^2
Distance each number is from the mean.
Range
Difference between highest and lowest values.
max - min = range
Inter quartile range
Middle 50% of the data.
Q3 - Q1 = IQR
Correlation coefficient r
r = -1 : as y decreases, x increases - negative linear r = 0 : no linear model - no association r = 1 : as x increases so does y - positive linear
How to best represent data for 1 qualitative and 1 quantitative variable?
Side-by-side boxplot
How to best represent data for 2 quantitative variables?
Scatterplot
Bivariate data
For each x data point there is a corresponding y data point