unit 5 correlation and measures of center Flashcards
data is skewed right
mean is greater than median,median greater than mode, tail is on the right
data is skewed left
mean is less than median, median less than mode,
tail end is to the left, contains low values, it pulls down the mean below the median
which measure of center is unaffected by outliers
median
r^2
correlation coefficient, measure strength of correlation
1- strong neg/pos correlation
0- no correlation/weak
symmetric distribution
mean = median = mode
distribution
arragement of data points on a graph
5 number summary
lowest #, q1, median, q3, highest number
iqr
interquartile range, gives you the range of the middle half of a data set (q3-q1)
correlation
the relationship between two variables
form
shape of distribution (linear/non linear)
direction
is the correlation positive/negatve? going upwards/downwards?
mean
(sum of all values)/(total number of values)
median
middle value (be sure to order the values first). If there are two middles, average them
measures of central tendency
mean, median, mode
identifying bimodal distribution
look for two distict modes
range
highest-lowest data value
rule of thumb range
(highest-lowest value)/4, bused to estimate standard deviation when not clear data set is given
mode
the most common value
how does variation affect. distribution?
more variation= wider distrib, less variation= more narrow distrib
rule of thumb range
range/4, used to estimate standard deviation
standard deviation
the distance each value is from the mean
how to calculate SD
take the value-mean, square those answers, add those squared variances together then divide the whole thing by the number of values-1, then take the square root, and you get the SD
