correlations and linear regression Flashcards
How do you look for associations between correlations?
Look at 2 sets of measurements, to assess the shape and strength of the association.
What is the correlation?
Used to test whether there is a linear association between 2 sets of measurements taken from a single population. Can be used when neither of he variables is independent of the other.
r = 1 over n-1, with the total of (xi-mean of x ) over sx, and (yi-mean of y0 over sy.
what does this mean?
this is to calculate regression. x bar is the mean of x. n is the number of observations. xi is the value of x which is given.
what is a parametric test and a non parametric test?
A parametric test is a test that assumes certain parameters and distributions are known about a population, contrary to the nonparametric one. The parametric test uses a mean value, while the nonparametric one uses a median value.
What is regression?
Allows you to identify which values have an impact on a response variable.
You need a defined dependent variable that you hypothesize is influence by the independent variables.
Y = bx + a + ε.
explain
X is the independent variable, y is the dependent variable, A is the y intercept. B is the slope of regression line, and e is the random error terms, which is different between the actual value of a dependent variable.
what is the slope of regression?
R is the correlation between x and y, Sx and Sy are the SD of them both.
Finding the intercept: if there is an intercept or a relationship, you can estimate the mean of X from Y. no matter the rate of regression, the line passes between the mean of x and the mean of y.
What is R squared?
Represents the proportion of the variance for a dependent variable that’s explained by an independent variable.
r squared- 1, - the explained variation over the total variation.
