SPSS
Regression
All about ANOVAs!
GLM-Wild Card
What Kind of Analysis? Part I
What Kind of Analysis? Part II
100
Complete this APA statement for this one-way ANOVA output in SPSS:
F( , )=___, p_____
We do (retain/reject) the null hypothesis.
F(2,27)= 4.46, p<.05. We reject the null hypothesis.
100
In multiple regression analyses, proportion of variance accounted for is indicated by this symbol.
Hint: Be specific!
What is R2?
100
Whether or not the audience has an effect on individuals depends on levels of the ______ factor. This is called a _______ effect.
What is self esteem?
What is an interaction effect?
100
This is the procedure you do before including categorical (nominal) variables as predictors in a regression analysis.
What is dummy coding?
100
One possible reason for why birds migrate and others maintain year round residency in a single location is intelligence. Specifically, birds with small brains, relative to their body size, are simply not smart enough to find food during the winter and must migrate to warmer climates where food is easily available (Sol et al., 2005). Birds with bigger brains, on the other had, are more creative and can find food even when the weather turns harsh. Use this kind of test to compare brain sizes across three samples of birds: Non-Migrating, Short-Distance Migrants, and Long-Distance Migrants.
What is a one-way ANOVA?
100
Sales figures show a positive relationship between temperature and ice cream consumption; as temperature increases, ice cream consumption also increases. You find that when temperature increases, both ice cream consumption and crime rates tend to increase. Use this kind of analysis to determine the true relationship between ice cream consumption and crime rate.
What is correlation?
200
True or False: According to this Bonferroni comparisions output, all group means ( Under 40; 40-59; and 60 and over) are significantly different from each other at the .05 level.
What is true?
200
Complete the following sentence using the SPSS output for a simple linear regression:
For every one SD increase in hours slept, happy mood should increase by __ SD units.
For every one SD increase in hours slept, happy mood should increase by .853 SD units.
200
For Result B we find: 
What is an interaction effect?
No main effects.
200
The ___ gives the predicted change in Y for every one unit increase in X.
What is slope (b, regression coefficient, etc.)?
200
A pharmaceutical company has developed a drug that is expected to reduce hunger. To test the drug, two samples of rats are selected with n=20 in each sample. The rats in the first sample receive the drug every day and those in the second sample are given the placebo. The dependent variable is the amount of food eaten by each rat over a 1-month period.
BOTH of these hypothesis tests could help us determine significant differences between these two groups.
What are:
t-test for independent samples &
one-way ANOVA?
200
Participants in a study on delayed discounting in were asked how much they would take today instead of waiting for a specific delay period to receive $1,000. Each participant responds at 1 month and 6 months.
Use this kind of hypothesis test to determine whether there are significant differences among the different delay periods.
What is a repeated measures t-test?
300
Based on this SPSS output for a t-test for independent means, you would use this t obtained value. Fill in the blanks here: t( )= ______, p_____
What is -3.656?
t(169.70)= -3.656, p<.001
300
Use the multiple regression output below to complete the following unstandardized regression equation:
What is :
300
For Result C, we find:
What is a main effect of task difficulty?
What is a main effect of arousal?
There is no interaction.
300
This classic statistical GLM procedure is useful when all of the independent variables are factors (qualitative variables).
What is ANOVA (Analysis of Variance).
300
1) Use this kind of test to determine homogeneity of variance for two independent samples?
2) Researchers ideally want to (retain/reject) the null hypothesis for this kind of hypothesis test.
You must get both parts correct to score on this question.
What is the Levene's Test for Equality of Variances?
What is retain the null?
300
The distribution of scores on the SAT is approximately normal with a mean of µ=500 and a population standard deviation is σ=10. What would we do to determine what score would someone need to end up in the top 40%?
Z Score Conversion to Raw Score/ Probability
400
This degrees of freedom (within) is used to compute F statistics for all three hypotheses investigated in this two-way ANOVA. Give the exact value.:
What is 92? (dfError)
400
Complete the following statement using the multiple regression SPSS output below:
There were __ predictors in the equation (____ and ___). The DV was ____. The omnibus model could account for ____% of variance in the DV.
There were two predictors in the equation (YearsService and Responsibility). The DV was Satisfaction. The omnibus model could account for 34.6% of variance in the DV.
400
Use the SPSS output below to complete the following statement:
The first main effect tested ______ (was/was not) statistically significant.
The second main effect tested ______ (was/was not) statistically significant.
The interaction effect of ______ X _____ (was/was not) statistically significant.
The first main effect tested, Sensitivity, was not statistically significant.
The second main effect tested, Test Difficulty, was statistically significant.
The interaction effect of Sensitivity X Test Difficulty was statistically significant.
400
_____s may be used to compare the relative predictive effects of independent variables.
What are beta weights?
Also acceptable: standardized weights, standardized regression coefficients
400
A developmental psychologist is examining the development of language skills from age 2 to 4. Three different groups of children are obtained, one for each age, with n=16 children in each group. Each child is given a language-skills assessment test. This kind of test would be used to determine mean differences between age groups.
What is a one-way ANOVA?
400
After obtaining a significant result for an omnibus ANOVA for three different groups, you will follow up with this kind of analysis to determine the significant mean differences.
Hint: Just provide the general term.
***Also, know what an omnibus ANOVA is!!!
What is a post hoc test?
500
Complete the following sentence using the SPSS output for a simple linear regression: The __ weight would yield the same numerical value as ____ because there are no other predictors in the equation.
The beta weight would yield the same numerical value as Pearson's r because there are no other predictors in the equation.
500
In multiple regression, the ___ ____ coefficients tell us the proportion of the explained effect that can be accounted for by a single predictor, regardless of the contributions of other predictors in the same regression equation.
These coefficients are useful when there is some degree of correlation among our predictors because it tells us the relationship a variable has with y-hat.
What is the squared structure coefficient?
rs2= the proportion of the effect that can be explained by the predictor alone
500
A store manager says, "how old people are doesn't matter, it's how long they spend in the store." If she said that after seeing the results of one of these, she was most likely looking at this scenario.
What is none of the above?
500
True or False:
A GLM analysis applied to a non-experimental procedure does not permit us to make inferences about causality (e.g., X --> Y).
What is true?
Three criteria need to be met to establish causality:
1) temporal precedence (i.e., X must precede Y)
2) correlation between X & Y
3) rule out all other potential causes
500
A researcher is planning a study comparing Facebook users with non-Facebook users at the middle school, high school and college levels. The results are presented in a matrix of 6 groups. The researcher should use this kind of test to evaluate the mean differences.
Hint: Be VERY specific.
What is a 2 (Facebook User; Non-Facebook User) x 3 (Middle School; High School; College) factorial analysis of variance?
500
Use this kind of test to determine the effect of Number of Churches (X1) and Population Size (X2) on Number of Crimes (Y).
Hint: The IVs are continuous variables, not nominal.
What is multiple regression?
600
Take a look at this syntax and describe what the command, "/SAVE PRED" is creating to show up in the data view of your SPSS file.
Say something like:
What are y-hats?
600
This is one assumption we can test for in a regression analysis using the syntax line "/SCATTERPLOT = (*ZRESID, *ZPRED)
Say one of the following:
1) Homoscedasticity (constant error variance)
2) Outliers
3) Make conclusions about linearity
Here are the characteristics of a well-behaved residual vs. fits plot and what they suggest about the appropriateness of the simple linear regression model:
- The residuals "bounce randomly" around the 0 line. This suggests that the assumption that the relationship is linear is reasonable.
- The residuals roughly form a "horizontal band" around the 0 line. This suggests that the variances of the error terms are equal.
- No one residual "stands out" from the basic random pattern of residuals. This suggests that there are no outliers.
600
True or False: There is a main effect of the Exercise condition and the Diet condition.
What is false?
600
The Pearson r value between an IV and a DV is the same as beta for the IV when there is only one predictor in a regression, OR when the predictors are ____.
What is orthogonal?
600
You would use this kind of analysis if you had one categorical independent variable and a normally distributed continuous dependent variable that was repeated at least twice for each subject. This is the equivalent of the paired samples t-test, but allows for two or more levels of the categorical variable.
What is a split-plot ANOVA?
Also acceptable:
Mixed-Design ANOVA
Between & Within Subjects Design
600
Say, for instance, you wish to understand the effect of gender, reading scores and social studies scores on writing ability (and ordinal variable: high, medium, low).
True or False: It is appropriate to proceed with a standard multiple regression.
FALSE!
This is a scenario that should be answered using analyses beyond the general linear model! For instance: Ordinal logistic regression.