Chapter 8 Flashcards
The degree to which two measured variables are related
Bivariate Correlation
What kind of graphs do we use for correlations
Scatterplot
What does the +/- sign indicate about a correlation
the direction
What does the number indicate about a correlation
the strength of the correlation
Pearson Correlation Coefficient
only used when looking at 2 variables
only goes -1/1
r-values determine strength
Confidence Intervals
tells us the precision of estimate of statistical significance
if it includes zero it is not significant
What factors distort correlations?
restricted range
curvilinear relationships
outliers
introduce erroneous variability/ “noisy data”
unreliable measures
a variable that, depending on size, effects the correlational relationship
moderator
temporal precedence highlights what problem
directionality problem
what causes what
Criteria for causation with bivariate correlations
builds a case for causing using multivariate techniques
plausible 3rd variable
third variable problem
more than 2 measured variables
multivariate technique
What are the 2 ways to build causation using multivariate techniques
multiple regression analysis
pattern and parimosity approach
allows us to rule out alternative explanations and increases internal variability
multiple regression
Criterion Variable
the dependent variable
most interested in
first variable in a regression table
Predictor Variable
in
Pattern and Parimosity
researchers investigate causality by using a variety of correlational studies that all point in the same causal direction
look at the pattern of results across a variety of correlational studies that all point in a single causal direction
pattern
we aim for the simplest explanation of pattern of data
