Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
9 Cards in this Set
- Front
- Back
|
correlation analysis
|
used to measure how associated a relation is.
how related the y's are the x variables, or in other words how related the dependent variables are to the independent variables. we always test it this way! |
|
|
Positive correlation
|
when the independent variable increases so does the dependent variable. they move together.
|
|
|
negative correlation
|
an inverse relationship
|
|
|
Test statistic t
|
t=b sub i/ s sub b sub i
the t test will test for significance. |
|
|
SSR
|
explained variation
|
|
|
SSE
|
unexplained variation between dependent variables to independent ones
there is actual formula to calculate this on its own |
|
|
SST
|
total variation
|
|
|
when testing multiple independent variables, compute the t's for each,
|
and whichever ones lay in reject h0 region is a variable which should be included and therefore kept in the model. by rejecting h0 this variable is saying that there is a significant relationship between xs and ys. h0 stands for no relationship. vars that dnr h0 are therefore insignificant as they prove the h0 claim that there is no relationship.
|
|
|
std deviation of the model=
|
standard error of the estimate
standard error on the regression summary output.. found by sq root of sse/n-k-1 a smaller std erro would be preferable this is defined as the variation of the y values around the regression line or model. |
