week 9 Flashcards
Regression
no longer simply about whether the two variables are related. But also allows us to predict values of one variable based on the values of another
R2
the proportion of variance in the outcome variable accounted for by the predictor
F-ratio
the ratio of model variance; whether the the regression model is significance
Intercept
the value of the outcome variable, when the predictor=0
Slope
the rate of change in the outcome variable in relation to the change in the predictor
Unstandardised beta
the change in Y for a one unit change x
Standardised beta
the standardised change in Y for one standard deviation change in X
When do you use unstandardised b
when you want coefficients to refer to meaningful units
When you want regression equation to predict values of Y
When to use standardised B
when you want an effect size measure, when you want to compare the strength of relationship between the predictor and the outcome
R2 in regression
the proportion of variance accounted for in the outcome variable due to the predictor
Covariance
the extent to which variables co-vary
High covariance
means there is a large overlap between the pattern of change observed in each variable
Outlier
How influential an outlier is depends on: distance between Yobs and Ypred
Leverage
Cases with standardised residual or predictors in excess of +3.29
deal with outliers
justified to remove outliers that are due to error in data entry or participant procedure following
Outliers can represent genuine data-for every 100 people, you should expect one score beyond
Assumptions of Linear regression
Linearity: the outcome is linearly related to the predictors
Independence: observations are randomly and independently chosen from population
Normality of residuals: the residuals are normally distributed
Homogeneity variance: the variability of the residuals is the same for all levels of the predictors
