Topic 1 Statistical Control and Regression Diagnostics

specification errors

where the idea or theory a model is based on or its operationalisation is poor or doesnt make sense

total variance (SStotal)

the difference between each individual outcome score and the mean outcome score

explained variance (SSregression)

the difference between each predicted outcome score and the mean outcome score

unexplained variance (SSresidual)

the difference between the actual outcome score and the predicted outcome score

what does SS residual consist of?

random and measurement error, and error based on variables not included in the model

unstandardised regression coefficient

the change in the outcome for every one-unit increase in the given predictor, while holding other predictors constant

standardised regression coefficient (beta)

the change in the outcome for every one-unit increase in the given predictor, while holding all other predictors constant, when all variables are converted to the same unit of measurement (standard deviation units)

semi partial correlation

the association between the predictor and outcome when the influence of any other predictors is removed from the given predictor only

partial correlation

the association between the given predictor and outcome when the influence of all other predictors has been removed from both the given predictor and the outcome

covariates / nuisance variables

variables known to influence the outcome but are not of interest to the given model

outliers

datapoints that are unusual based on their score on the outcome variable

measures of outliers

studentised residuals and the studentised residual plot

influential scores

datapoints that are unusual based on their pattern of scores on the predictor/s

measures of influence

Mahalanobis distance, leverage

discrepant scores

datapoints that are unusual based on their pattern of scores between the outcome and predictor/s

measures of discrepancy

Cook’s distance

the blue score is:

discrepant

the red score is:

influential

assumptions of standard linear regression

linearity of associations between variables, normal distribution of residuals, homogeneity of variance, independence of observations

what is shaded in black?

R squared/ total variance

what is shaded in pink?

unique variance / sr squared for boredom

what is shaded in green?

unique variance / sr squared for ADHD

what is shaded in blue?

the shared variance