chapter 12, Understanding Research Reults: Describing vraibles and relationships among them Flashcards
histogram
uses bars to display a frequency distrivution for a queantitative variable
descriptive statistics
stastical measures that describe the results of a study; descriptions stastitics include measure of central tendency, variability, and correlation
variabliltiy
exists in a set of scores. A measure of variablity is a number that characterizes the amount of spread in a distribution of a scores
strandard deviation
symbolized a s, which indicates the average deviation of score from the mean.
variannce
symbolizes as s2( s squared). a easure of the variability of scores about a mean; the mean f the sum of squared deviations of scores from the group mean
Correlation coeeficient
is a stastica that describes show strongly variables are relatd to one another
Peason product-moment coeeficient (Called the pearson r)
is used when both variables have iterval or ratio scale propertied. Values of a person r can range from 0 to + or - . ONLY DETECTS LINEAR RELAITONSHIPS
scatterplot
in which each pair of scores is plotted as a single point in a diagram
restriction of range
occurs when the individuals in our sample are very similar or homogenous on the variable ou are study
Effect size
is a gernal term that refers to the strenght of the association betweeen variable
r2 or squared correlation coeeficient
value is sometimes referred to as the percent of shared vraiance between two variables
Cohen’s d
to describe the amgnitude of the effect of the independent vara
regression equations
are caculations used to predit a person’s score on one variable when that person’s score on anohter variable is already known
criterion variable
the outcome variable that is being predicted in a multiple regression analysis
predictor variable
the variable used to predict chages in the criterion (or outcome) varialbe in a multiple regression analysis
multiple corelation
is used to combine a number of predictor variables to increase the accuracy of prediciton of a given crieterion or outcome variable
squared mutilple coreelation coefficient
is interpreted in much the same way as the squared correlation coeeficient r2. That is R2 tells you the precentage of vraible in the criterion variable that is accouted for by the comined set of predictor variables
multiple regression
models the unique relationship between each predictor and the crieterion
partial correlation
provides a way of statistically controlling thrid variables in the non-experiments
Structural equation modelling (SEM)
is a general term to refer to these techniques