Correlation and Multiple Regression Flashcards
Partial correlation allows you to examine the relationship between ____ _______ while …
two variables while statistically controlling for (getting rid of) the effect of another variable that you think might be contaminating or influencing the relationship.
In a partial correlation output, the word ‘none’ in the left-hand column indicates that…
no control variable is in operation.
Multiple regression is a family of techniques that can be used to explore the relationship between ___ _______, dependent _____ and a set of _____ _______. The dependent variable (the thing you are trying to explain or predict) needs to be a ______ variable with reasonably normally distributed scores. The independent (or predictor) variables can be ________ or _______ (___ _______).
one continuous
variable
independent variables
continuous
continuous or dichotomous
two categories
Which is better for real world studies (compared to lab ones?) Correlation, Partial Correlation, or Multiple Regression? Why?
Multiple Regression
It allows a more sophisticated exploration of the interrelationship within a set of variables.
3 of the main type of research question that multiple regression can help answer:
➢ how well a set of variables is able to predict a particular outcome
➢ which variable in a set of variables is the best predictor of an outcome
➢whether a predictor variable is still able to predict an outcome when the effects of another variable are controlled for (e.g. socially desirable responding).
Three types of multiple regression
➢ standard or simultaneous
➢ hierarchical or sequential
➢ stepwise.
In hierarchical multiple regression (also called sequential regression), the (1)_______ variables are entered into the model in the order specified by the researcher, based on (2)______ ______. Variables, or sets of variables, are entered in steps (or blocks), with each (3)______ variable being assessed in terms of what it adds to the prediction of the (4)_______variable after the previous variables have been controlled for. For example, if you wanted to know how well optimism predicts life satisfaction, after the effect of age is controlled for, you would enter age in Block ___ and total optimism in Block ___.
(1) independent
(2) theoretical grounds
(3) independent
(4) dependent
1
2
Multiple regression is not the technique to use on ____ samples, where the distribution of scores is very ______
small
skewed
Formula used to find required N for the overall multiple regression
N = 50 + 8*m
m = no. of IVs
Multicollinearity refers to… which you can check by…
Multicollinearity exists when the independent variables are _____ correlated ( r = __ and __).
refers to the relationship among the independent (predictor) variables, which you can check by generating a correlation matrix (chap 7).
highly correlated (r= .7 and above)
Singularity occurs when ____ _______variable is a combination of other _______ variables (e.g. when both subscale scores and the total score of a scale are included).
If you include highly intercorrelated variables in the model, multiple regression has difficulty ______ the ____ contribution of each predictor and may report them as not ______ _______.
one independent
independent
separating
unique
statistically significant
There are two types of outliers that might affect the results of a multiple regression analysis: _____ _____ and ______ ______
univariate outliers and multivariate outliers.
Univariate outliers can occur when …
a person or case has an unusual score on one of the predictor variables in the model (e.g. a very high income)
When do you check for univariate outliers? Which variables do you check?
How do you deal with them when found?
part of the initial data screening process.
You should do this for all the variables, both dependent and independent, that you will be using in your regression analysis.
Outlying scores or cases can be deleted or, alternatively, assigned a score that is high but not too different from the remaining cluster of scores.
Multivariate outliers occur when the person or case has an unusual _____ of scores on the _____ and _____ variables.
E.g.: with age and income
combination
dependent and independent
e.g. a young person who reports a high income.
They may not necessarily be an outlier on the individual age or income variables, but the combination is unexpected and likely to deviate from the model generated by multiple regression.
