SO5032: Lab Materials

Table of Contents

1 Week 5 Lab

1.1 Predicting house prices

Data on house price and characteristics are available in this do file.


Using t-tests on individual parameters, and overall F-tests/adjusted R2, search for a good model to predict house price. Use dummy variables where appropriate (see note on dummy variables in Lab 4).

Are any of the explanatory variables "multi-collinear"? Note what happens to the model when you add a variable that is collinear with one already in the equation.

1.2 Non-linearity

1.2.1 Sketch a quadratic function

Using pen and paper and/or Excel, plot the curve \(Y=20+0.75X-0.03X^2\).

1.2.2 Model a non-linear relationship

Run this do-file to load data on


Fit models predicting birth rate using GNP as

  • a linear effect
  • a quadratic effect (GNP plus squared GNP)
  • logged GNP and
  • a grouped effect.

Consider the fit of the four models.

Plot the four predicted values as lines/curves on the same graph: how do they compare? Plot the residuals as well.

Author: brendan

Created: 2018-02-26 Mon 09:52

Emacs 26.0.50 (Org mode 8.2.10)