Show:
MANOVA
quartimax, varimax aka orthogonal!
Factor analysis goods
Regression
Misc.
100
I am used when wanting to compare the cases in each IV level on their performance on 2 or more DV's. During this analysis, the DV's are treated together as a set rather than being analyzed in isolation.
What is MANOVA
100
Typically, ? designs are those that include only one dependent variable in the analysis. ? designs can be conceptualized in a couple of different ways – either as a design that has several dependent variables, or as a design in which several variables are being combined to form a composite variable. What two types of designs are being compared?
What is univariate vs. multivariate.
100
I am not affected by the correlations between the predictors, but those beta coefficients and squared semi-partial correlations are... What am I
What is structure coefficients.
100
The primary goal of this method is to build a model with only the important predictors in it. This method is a combination of the forward and the backward methods. This method begins with an empty model and builds by adding the largest predictor to the model one at a time (same as the forward method). What method is being described?
What is stepwise regression.
100
Requires a minimum of 3 variables: 1 categorical between-subjects IV, 1 categorical within-subjects IV, and 1 continuous DV. What kind of design am I?
What is mixed design.
200
I am very similar to this other type of analysis. This is because a weighted linear composite of the DV's is used.
What is multiple regression.
200
I am used to restrict the alpha level to reduce this type of error. You calculate me by dividing your alpha level (usually .05) by the number of comparisons that you intend to make, then use this new value as the required alpha level. For example, if we wanted to maintain our alpha level of .05 and perform 10 comparisons, we would have to use an alpha level of .005 for each of the comparisons in order to maintain our overall alpha at .05 and protect from Type I error. What concept is being described and what type of error does this involve?
What is bonferroni correction & type I error.
200
You just use me for my looks. You're always pointing out where my curve stops and where I begin to flatten out. What am I? What does my flattening out really mean?
What is scree plot! The flattening out indicates a transition point between components with high and low eigenvalues (point of diminishing returns).
200
I am a variant of multiple regression that allows you to specify a fixed order of entry for variables in order to control for the effects of covariates or to test the effects of certain predictors independent of the influence of others. In the first stage the independent variables that we want to control for are entered into the regression. In the second stage, the independent variables whose relationship we want to examine after the controls are entered. A statistical test of the change in R squared from the first stage is used to evaluate the importance of the variables entered in the second stage and so on. What form of regression am I?
What is hierarchical regression.
200
What are the 2 broad categories of rotation? Name the rotational techniques that fall under both rotations.
What is orthogonal: Varimax, Quartimax, Equamax. The most common orthogonal technique is Varimax which attempts to minimize the number of variables that have high loadings on each factor. Oblique: Direct Oblimin, Promax. The most common oblique technique is Direct Oblimin.
300
.05/#of DV's
What is Bonferroni correction
300
Values in a structure matrix are what is known as structure coefficients, the correlation of each variable with each factor. Here we want to be sure that none of our variables are cross-loading between factors. What am i used for?
What is interpreting factors in a structure matrix for a factor analysis procedure!
300
Give the raw score regression equation. What is the difference between me and the other form of a regression equation? Describe all parts of me.
What is Y = a + bX -a = constant, the predicted value of Y when X = 0. -b = regression coefficient, the weight given to x to maximize the predictability of Y. The regression coefficient is the slope of the linear function & represents the amount of change expected in Y for every 1 unit change in X. -The standardized regression equation uses standardized z-scores.
300
Given that the two variables in question are grams of sugar consumed (SUG) and weight gain (LBS), how would you compare such variables via a simple effects test?
What is \EMMEANS=TABLES (SUG*LBS) COMAPARE (SUG) adj (bonferroni) \EMMEANS=TABLES (SUG*LBS) COMAPARE (LBS) adj (bonferroni)
400
I fall within the bounds of a Bonferroni correction and an alpha level of .05. I am significant but you won't necessarily report me as such. Who am I?
What is a trend!
400
What threshold should be applied when interpreting factors for a factor analysis procedure?
What is .7, something like .68 is ok too.
400
I am the correlation between each of the variables contained in the linear composite and the variate as a whole. In other words, I'm the bivariate correlation between a particular independent variable and the predicted (not the actual) score. In factor analysis, I'm also known as a factor loading (correlation between the variable and the factor). In regression, I measure the correlation between the predictor and the variate . Stronger correlations indicate that the predictor is a stronger reflection of the construct underlying the variate
What is structure coefficient.
400
I am a certain kind of correlation is symbolized by R. I tell you the strength of this linear relationship between one variable and a set of other variables (i.e., how much variance in the criterion is accounted for by the combination of predictors). I am a measure of effect size that is interpreted as the percentage of variance in the DV accounted for by the set of predictors (aka the variate). What am I?
What is squared multiple correlation.
400
When asked to graph an interaction, how do we know there is a statistically significant interaction?
What is the absence of two or more parallel lines.
500
The goal of this process is to attain simple structure( correlations of the variables with the factors would be either very high-values near- or very low-values near 0). This process does not change the amount of variance accounted for, but simply redistributes the variance across the factors to facilitate interpretation by trying to achieve simple structure.
What is factor rotation.
500
I am the easiest to interpret but the researcher must assume that the underlying constructs are independent (uncorrelated). Therefore, my strategy keeps the factors independent of each other during this process. Geometrically, factors are ? if they cross each other at 90 degrees. What is being described?
What is orthogonal rotation.
500
I represent the proportion of variance of the DV uniquely explained by an IV when the other predictors are taken into consideration. It doesn’t take into account the shared variance. It represents the extent to which variables do independent work when combined with the other predictors in the model.
What is squared semi-partial correlation.
500
With respect to question 2 on the practice final, give the values for all degrees of freedom for the within subjects table.
What is look to practice final.