1. These slides are based on:
CHAPTER 4
TOOLS OF THE FORECASTER
4.1 The Information Set
4.1.1 Some Information Sets Are More Valuable than Others
Table 4.1 OLS Regression Results: House Prices and Mortgages Rates
Model (i)
Model (ii)
These slides are based on:
González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.
Slides adapted for this course. We thank Gloria González-Rivera and assume full responsibility for all errors due to our changes which are mainly in red

2. 4.2.1 Forecasting Environments
Figure 4.1 Forecasting Environments: Recursive Scheme
One-step ahead
prediction at
time t
t +1
t +j
Estimation sample
(t+1 observations)
t+1
t+2 T
Prediction sample
(t observations) t
(t+j observations)
t+j
t+j+1 .
Update the estimation sample with new observations as they become available
Prediction sample
González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

3. Figure 4.2 Forecasting Environments: Rolling Scheme
t+j .
Estimation sample
(t observations)
t +1
t+1
t+2 T
Prediction sample
One-step ahead
prediction at
time t
t+j+1 1 j
Doesn’t enlarge the estimation sample as new observations become available, as old observations should not have much weight (breaks, evolving dynamics)
González-Rivera: Forecasting for Economics and Business,
Copyright © 2013 Pearson Education, Inc.

4. Figure 4.3 Forecasting Environments: Fixed Scheme
Estimation sample
(t observations)
t+1
t+2 T
Prediction sample
One-step ahead
prediction at
time t
t observations)
t+j
t+j+1
…………
Update information set
Update
Doesn’t enlarge the estimation sample for model parameters as new observations become available.
New observations are used with the same model estimated at time t
Prediction sample
González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

5. Ex-ante forecasting Ex-post forecasting (t observations) t+1 T
Estimation sample
(t - k observations) t
Prediction sample
(t observations)
t+1 T
Ex-ante forecasting
Ex-post forecasting

6. Figure 4.4 Symmetric Loss Functions
4.3 The Loss Function
4.3.2 Examples
Figure 4.4 Symmetric Loss Functions
Quadratic loss function Absolute value loss function
L(e) e
González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

7. Figure 4.5 Asymmetric Loss Functions
L(e) e
Lin-lin function
Linex function
González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

8. ….. 4.3.3 Optimal Forecast: An Introduction
Figure 4.6 The Forecasting Problem
time
Conditional density 1 2 3 4 t
t+h
……….
…..
Information set
time
González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

9. ….. Figure 4.7 Optimal Forecast Under Quadratic Loss time 1 2 3 4 t
t+h
……….
…..
Information set
González-Rivera: Forecasting for Economics and Business, Copyright © 2013 Pearson Education, Inc.

10. Distinguish between unconditional expectation and conditional expectation