Chapter 5, Alternatives to Experimentation: Correlational and Quasi- Experimental Designs

Ex Post Facto

"After the fact" A researcher examines the effects of already existing subject variables (like gender, or personality types), but doesn't manipulate them

Quasi

"Seeming like"

Linearity

A property of Pearson correlation coefficient; How the relationship between X and Y can be plotted as a line (linear relationship) or a curve (curvilinear relationship)

Sign

A property of Pearson correlation coefficient; Refers to whether the correlation coefficient is positive or negative

Probability

A property of Pearson correlation coefficient; The liklihood of obtaining a correlation coefficient of this magnitude due to chance

Magnitude

A property of Pearson correlation coefficient; The strength of the correlation coefficient, ranging from -1 to +1

Absolute Value

The ____ of a correlation coefficient indexes its strength.

Causal Direction

A could cause B just as readily as B could cause A. X>Y Y>X

A Regression Line

A line of best fit on a scatterplot.

Pretest/Posttest Designs

A researcher measures behavior before and after an event. This is quasi-experimental because there is no control condition

Cross-Lagged Panel Design

A researcher measures relationships over time and these are used to suggest a casual path

Third Variable Problem

A third variable, family conflict, may create the appearance that insomnia and depression are related to each other Z>X Z>Y

Range Truncation

An artificial restriction of the range of X and Y that can reduce the strength of a correlation coefficient; Removes outliers

Non Equivalent Groups

Design compares the effects of treatments on preexisting groups of subjects -A researcher could install fluorescent lighting in Company A and incandescent lighting in Company B and then assess productivity

Correlational Study

Designed to determine the correlation, or degree of relationship, between two traits, behaviors, or events -values of a correlation coefficient can only range between -1.00 and +1.00

Coefficient of Determination (r^2)

Estimates the amount of variability that can be explained by a predictor variable

Outliers

Extreme Scores; They usually affect correlations by disturbing the trends in the data

Linear Regression Analysis

Researchers can use this to estimate the score on one variable when we only know their score on a second variable.

Multiple Regression Analysis

Researchers can use this to predict the score on one behavior from scores on two related behaviors.

Multiple Regression

Researchers use this to predict behavior measured by one variable based on scores on two or more other variables -We could estimate vocabulary size using age and television watching as predictor variables

Multiple Correlation (R)

Researchers use this when they want to know whether there is a relationship among three or more variables

Cross-Sectional Studies

Subjects at different developmental stages (classes) are compared at the same point in time

Quasi Experiments

Superficially resemble experiments, but lack their required manipulation of antecedent conditions and/or random assignment to conditions

Confounding

The inability to establish cause with certainty in research

Longitudinal Designs

The same group of subjects is measures at different points of time to determine the effect of time on behavior

Bidirectional Causation

Two variables (like insomnia and depression) may affect each other X<>Y

Pearson Correlation Coefficient

Used to calculate simple correlations (between two variables) and may be expressed as: r(50)=0.70, p=0.001

Correlational Designs

Used to establish relationships among preexisting behaviors and can be used to predict one set of behaviors from others EX: Such as predicting your college grades from scores on your entrance exams

Partial Correlation

We should compute this when we want to hold one variable (age) constant to measure its fluence on a correlation between two other variables (television watching an vocabulary)

Path Analysis

When a researcher creates and tests models of possible casual sequences using multiple regression analysis where two or more variables are used to predict behavior on a third variable

Casual Modeling

the creation and testing of models that suggest cause-and-effect relationships between behaviors