Please note that LIFT does not warrant the correctness of the materials contained within the notes. Additionally, in some cases, these
notes were created for previous semesters and years. Courses are subject to change over time, both in content and scope
The model calc R adjusted, calc R2, test overall model (R2) for significance (F = MS regression/MS
residual)
Analysis of regression (test of R2) calc F from R2, calc F from SS (SSy = SS regression + SS residual)
Assessing the importance of predictors cant
IV has a sig effect which is of great interest to you
Control variable has a sig effect which is okay because it reduces error variance but interesting
Confound has a sig effect which is not wanted (additional systematic variance)
Main effect of blocking
Mauchlys test of sphericity sphericity is a more broad and less restrictive assumption than
compound symmetry, examines overall structure of covariance matrix, determines whether values
in the main diagonal (variances) are roughly equal and if values in t
MMR, steps for testing for moderation centre X and Z, calculate interaction term, test for sig
interaction, if interaction is sig then test for simple slopes, plot interaction on graph
Calculate interaction term mean-center (to avoid multicollinearity), s
2-way ANOVA sources of variance between groups variance > variance due to factor A, variance
due to factor B, variance due to A x B
Df df total (N-1), df factor (# of levels of the factor-1), df interaction (product of df for factors in the
interaction),
positive reinforcement of inappropriate behaviours and punishment of appropriate behaviours leads
to psych dysfunction
Principal modes of learning classical conditioning (Pavlov), operant conditioning, observational
learning/modelling
Operant conditioning
Orthogonal/independent contrasts E aj = 0 (sum of contrasts within A = 0), E ajbj = 0 (sum of
products of each j set of contrasts = 0)
Issues with follow-up comparisons redundancy (explaining the same mean difference more than
one, solution is orthogonal
ANCOVA covariate is used to remove error from both the error term and treatment effect, used to
control unwanted variation and to control for group differences
1-way ANCOVA structural model Xij = u., aj, BZij, Eij, BZIj (score on variable Z multiplied by