PAL PSYU3349 Week 3

Which statement is correct for ANOVA via regression?

• The DV and the IVs are numeric

• The DV is numeric and the IVs are categorical (but don't need to be dummy coded)

• The DV is numeric and the IVs are categorical (and must be dummy coded)

• The DV is numeric and the IVs can be either categorical or numeric

If you a categorical IV with 3 levels, how many dummy codes do you need to include in your statistical analyses?

• 3 dummy codes

• 2 dummy codes

• 1 dummy code

• 0 dummy codes

If you run an ANOVA via regression and compare the results to a factorial ANOVA (using the same DV and IVs), which of the following would be correct?

• You would get the same results because both analyses are part of the General Linear Model

• You would not get the same results

• You would only get the same results if the IVs are orthogonal

• It is impossible to predict whether or not you would get the same results

What does circled number in the output indicate?

• The null hypothesis cannot be rejected

• There is a strong correlation (of approximately .71) between the IVs

• 70.75% of variance in the DV can be explained by the model

• 70.75% of variance in the model can be explained by the main effects

Which of the following is not true about the contrast command?

• It is a post-estimation command (must be performed after running a regression)

• It can be used to look at the significance of Main Effects

• It can be used to calculate effect sizes

• It can be used to look at the significance of Interactions

For the IV: eye_colour,

black eyes are coded as 1

blue/green eyes are coded as 2

brown eyes are coded as 3

In the following command, which group will be the reference category?

regress light_sensitivity i.eye_colour

• black eyes

• blue/green eyes

• brown eyes

In an additive model, you can substitute dummy variables into the prediction equation to replicate the observed means, when:

• there is no significant interaction

• there is no interaction whatsoever

• there is a significant interaction

• You can always replicate observed means (regardless of whether there is an interaction)

In an additive ANOVA via regression model, what does the constant (AKA a or y-intercept) represent?

• The mean for all predictors

• The difference between the mean score on the DV for a predictor and for the reference category

• The mean DV when all IVs = 0 (i.e. for individuals in the reference category of all IVs)

• The mean DV when one predictor = 0