Week 10- Flashcards
Regression
The regression method summarizes the relationship between two variables. It is used to estimate the average of one variable for a particular value (or range of values) of the other variable, while noting that individual values will vary around this average.
Responsevariable:
Variable we wish to learn about. Also called the outcome or dependent variable.
Notation: y
Explanatory variable:
Variable that is thought to explain the changes we see in the response variable. Also called the independent variable.
(Properties of correlation coefficient )
Value doesn’t depend onwhich variable is the
response variable orwhich is the explanatory
variable:
IfIswitchXandY, then correlation(r) doesn’t change.
(Properties of correlation coefficient )
Value doesn’t depend onunits ofmeasurement
IfImeasure ininches insteadof centimeters,then correlation (r)doesn’t change.
Outlierswilloftenchangethevalueofthecorrelation.
– Ifthey areon the samepatternasthe restofthe data,they willtypicallystrengthen the correlation.
– Ifthey areoffthe patternofthe restofthe data,they willtypicallyweaken the correlation.
Residual:
Verticaldistancebetween the regressionlineandaparticulardatapoint.