1. Which of these do NOT effect correlations?
- Negative skew and Kurtosis
- Outliers and influential points
- Homo/Hetero Scedasticity
- Singularity and Multi - Collinearity
1 of 20
Other questions in this quiz
2. In order to work out the f-ratio for a regression, we need MSm and MSr. How do we work out MSm?
- MSm = dfm/MSm (Degree's of Freedom Model/ Model Mean Squares) Remember, model mean squares is the amount of variables in the model.
- MSm = dfm/SSr (Degree's of Freedom Model/ Residual Sum of Squares) Remember, the degree's of freedom for the model are the amount of variables in the model.
- MSm = SSm/dfm (Model Sum of Squares / Degree's of Freedom Model) Remember, dam is simply the number of variables in the model.
- MSm = SSr/dfr (Residual Sum of Squares / Residual Degree's of Freedom) Remember, residual degrees of freedom is the amount of variables in the model.
3. The general equation for multiple regression is as follows...
- y ̂ = b0+b1x1+b2x2+......bpxp
- y ̂ = b1+b1+b2+b2+....bpxp
- y ̂ =b1xb2xb3xb6
- y ̂ = b1x2+b0x2+b2x3
4. 'Anscombe's Quartet' reminds us to check what in terms of the distribution of variables before analysing?
- Mean, Variance, Correlation, Regression line
- Mean, F-score, Variance and Correlation scores
- Variance, Mean, Regression Line and MSe
- Mean, Variance, Homogeneity of scores, and spread of data
5. What does a good regression do?
- Leads to easily interpretable graphs, and creates a small difference between estimated type I error rate and actual observed Type I error rate
- Leads to a large improvement in prediction due to the mode, and there is a small difference between the model and the data
- Leads to a large improvement of the detection of error, and improves the ability to recognise strong correlations
- Leads to a small improvement in prediction due to error, and there is a small difference between the regression line and the error