correlation,regression, and SEM Flashcards
multiple regression
1- extenssion of correlation
(measures relationships among variables)
what is the difference between regression
use languague of prediction
can use 1 or more variables to predict changes in another variable
Regression models predictive relationships
PREDICTOR- score in one variable to predict changes in another variable CRITERION
When we have a good reason that one of the
variables could change the other
when is it used ?
when u cant manipulate variables,can only measure them
ex:pratical problems
Common in personality, health, &
longitudinal developmental research
correlation vs regression
temporal pressidence (regression has one variable come first)
ex : Correlation Question:
- Is there a relationship between social
support received from one’s spouse in
the morning and arthritis pain in the
afternoon?
- Regression Question:
Does the amount of social support
received in the morning predict how
much pain is felt in the afternoon?
equation
Y=a+bx
Y=criterion
X= predictor/1
b=slope(rise over run)
a=intercept=0
benefits of regression framework
-models predictive relationships
-can investigate the effect of multiple predictors on the criterion at the same time(in correletion u can only have to variable)
Multiple Regression enables investigation
of how well many predictors
simultaneously predict the criterion
Multiple Regression Equation
-What is the unique contribution of each
predictor to the prediction of criterion?
y=a+ b1X1+ b2X2+ b3X3
change in y for a one unit change in X1 (predictor 1)
b2 = Change in y for a one unit change in X2 (predicto
b3 = Change in y for a one unit change
features of multiple regression
-can have any number of predictors
-need to collect data on each predictor
-Calculate the contributions of each
predictor individually on predicting
criterion (b’s)
Calculate the contribution of all predictors
combined for predicting criterion
- Called the Multiple Correlation (R) but
discussed as R2
R2 is the proportion of variance in the criterion
that can be explained by all predictors combined
R2
proportion
of variance in
the criterion that
can be explained
by all predictors
combined
Partial Correlation & the 3rd Variable
Problem
3rd variable problem
-another variable driving relationship between x and y
-Statistically “control for” 3rd variable
Trying to remove the effects
of a variable we know likely
influences both variables of
interest
Measure all three variables
Structural Equation Modeling
What are the relationships amongst the
variables?
₋ Model how multiple variables relate to
(correlate with) each other and/or
“predict” others
regression in asteroids
but often data is cross-sectional