# New Directions in Econometric Practice: General to Specific Modelling, Cointegration, and Vector Autoregression

By Wojciech W. Charemza; Derek F. Deadman | Go to book overview

Chapter 2
Data Mining

2.1
Model Selection through 'Data Mining'
'Data mining' in its various forms reflects the general problem of not being in a position to conduct controlled experiments. This may lead to procedures which use a fixed data sample in some sequential manner to arrive at the final model specification. Suppose that we define a 'good' model as a specification which exhibits a high coefficient of determination, 'significant' Student-t ratios and possibly a Durbin-Watson statistic close to 2. A tempting and quite common practice is the taking of the widest possible set of variables (called here the 'candidates') which might eventually enter the model, running numerous regressions using as the regressors subsets of the entire set of the 'candidates', and then selecting the 'best' regression, that is that with the highest coefficient of determination or with the highest Student-t ratios.Imagine that the aim is to model the consumption function. The investigator might prepare a set of potential regressors such as lagged consumption, total personal disposable income, expected income (measured, for instance, as the one-step-ahead prediction of income), income adjusted for the stock of liquid assets, total wealth of the last period and total wealth averaged over the last two periods. These variables can in turn be deflated by at least two different price indices: the retail price index and the cost-of-living index. This gives rise to a set of 12 potential explanatory variables and enables the formulation of some sensible looking consumption functions defined for a particular choice of deflator, such as:
 1 consumption explained by its own lagged value and current unadjusted income; 2 consumption explained by current and expected income; 3 consumption explained by its own lagged value and current and adjusted income; 4 consumption explained by current unadjusted income and lagged wealth.

By changing the deflator, another four equations can be formulated. Why not estimate them all and choose the one that has good Student-t ratios and a high R2? If, on these criteria, the 'best' is equation 4 and the 'worst' is equation 2, we may even conclude that the analysis shows the significant impact of current income on consumption and that expected income does not influence current consumption. Would such a conclusion be justified?

-11-

If you are trying to select text to create highlights or citations, remember that you must now click or tap on the first word, and then click or tap on the last word.
One moment ...
Default project is now your active project.
Project items
Notes

#### Cited page

Style
Citations are available only to our active members.
Buy instant access to cite pages or passages in MLA 8, MLA 7, APA and Chicago citation styles.

(Einhorn, 1992, p. 25)

(Einhorn 25)

(Einhorn 25)

1. Lois J. Einhorn, Abraham Lincoln, the Orator: Penetrating the Lincoln Legend (Westport, CT: Greenwood Press, 1992), 25, http://www.questia.com/read/27419298.

#### Cited page

New Directions in Econometric Practice: General to Specific Modelling, Cointegration, and Vector Autoregression

Settings

#### Settings

Typeface
Text size Reset View mode
Search within

Look up

#### Look up a word

• Dictionary
• Thesaurus
Please submit a word or phrase above.

Why can't I print more than one page at a time?

Help
Full screen
Items saved from this book
• Bookmarks
• Highlights & Notes
• Citations
/ 344

### How to highlight and cite specific passages

1. Click or tap the first word you want to select.
2. Click or tap the last word you want to select, and you’ll see everything in between get selected.
3. You’ll then get a menu of options like creating a highlight or a citation from that passage of text.

## Cited passage

Style
Citations are available only to our active members.
Buy instant access to cite pages or passages in MLA 8, MLA 7, APA and Chicago citation styles.

"Portraying himself as an honest, ordinary person helped Lincoln identify with his audiences." (Einhorn, 1992, p. 25).

"Portraying himself as an honest, ordinary person helped Lincoln identify with his audiences." (Einhorn 25)

"Portraying himself as an honest, ordinary person helped Lincoln identify with his audiences." (Einhorn 25)

"Portraying himself as an honest, ordinary person helped Lincoln identify with his audiences."1

1. Lois J. Einhorn, Abraham Lincoln, the Orator: Penetrating the Lincoln Legend (Westport, CT: Greenwood Press, 1992), 25, http://www.questia.com/read/27419298.

## Thanks for trying Questia!

Please continue trying out our research tools, but please note, full functionality is available only to our active members.

Your work will be lost once you leave this Web page.