Week 2 revision Flashcards
Explain the difference between treatment variance and error variance
Treatment variance is variance due to an effective IV manipulation, error variance is due to unexplainable variance in the data; e.g. Due to an unmeasured variable, indivudal differences, or biased populations.
Explain the sources of variance in a one-way ANOVA, and how these are related to error variance and treatment variance
In ANOVA total variation is broken into between-groups variance (treatment variance) and within-groups variance (error variance).
In conceptual terms (i.e., in words), explain what is meant by SStreatment, SSerror, MStreatment, and MSerror in 1-way ANOVA
SStreatment is the index of variability among treatment means, MS treatment is the standardization of that.
SSerror is the index of variability among participants within a specific cell, SSerror is the standardization of that.
State how the F ratio is calculated in a 1-way ANOVA
Mstreat/Mserror
Explain the structural model (also known as the linear or conceptual model) of 1-way ANOVA.
XJI=U.+Ti+eij (Any DV score in a one way nova is the sum of the grand mean, plus the effect of the jth treatment, plut the error for i person in the jth treatment.
List the research questions that can be addressed in a 2-way factorial ANOVA
Has Factor A had a main effect on variance?
Has Factor B had a main effect on variance?
Is there an interaction between Factor A and B that is causing variance in the data?
Explain how variance is partitioned in a 2-way factorial ANOVA
Variance is partitioned into a main effect of A, a main effect of B, AxB interaction, and error.
In conceptual terms (i.e., in words), explain what is represented by each of the following:
SS for each main effect =
SS for the interaction =
SS error =
SS for each main effect = The sum of squares for a variability explainable by the IV.
SS for the interaction = The sum of squares for a variability explainable by an interaction.
SS error = The sum of squares for variability explained by error.
In a 2-way factorial ANOVA, explain what the null hypothesis represents in tests of the main effects and the 2-way interaction
ME = There is no effect of the IV on DV variability.
Interaction = There is no interaction that effects variability within the DV
What are the three omnibus tests in a two-way design?
Main effect A
Main effect B
Interaction
What is the difference between the omnibus tests and the follow-up tests?
Follow up tests are done post-hoc, and have a more specific statistical analysis and scope.
Explain the structural model of 2-way factorial ANOVA
Xijk = U. + aj + Bk + aBjk + eijk
A DV score is a combination of the grand mena, the effect of jth treatment in factor a, the ffect of kth treatment in factor b, the effects of differences in factor a treatments at different levels of factor b treatments, and the error for ith person in the jth and kth treatments.
List the main assumptions of ANOVA
population (2), sample (3), DV score (1)
Homogenous variability
Normally distributed population
Independent samples
Independent random sampling
minimum of 2 observations with equal N
Continuous scale
When the F ratio is calculated for each omnibus test in a 2-way ANOVA, identify which MS terms are used in the numerator and denominator in each case
ME A = MSa / MSerror
ME B = MSb / MSerror
IN AB = MSab / MSerror
In a 2-way factorial ANOVA, explain what each of the following tell you:
a significant F test (p < .05) for the main effect of Factor A =
a significant F test (p < .05) for the A x B 2-way interaction =
There is statistically different scores on the DV across groups in Factor A.
The variability of factor A on the DV is moderated by the effects of factor B.
