Methodology

Atin Basuchoudhary, James Bang and Tinni Sen
Additional contact information
Tinni Sen: Virginia Military Institute

Chapter Chapter 3 in Machine-learning Techniques in Economics, 2017, pp 19-28 from Springer

Abstract: Abstract In this chapter, we sketch the theory behind the estimation algorithms used later in the book. It serves as a primer for readers interested in theory. We then describe the techniques used to validate these algorithms. These validation techniques can help choose the most “predictive” algorithm. We specifically include this section to introduce the reader to the idea that there are multiple decision rules to choose the most predictive algorithm. Choosing the right rule depends on the user’s purpose. There is no “one size fits all” decision rule to choose the most predictive algorithm. We then describe the process through which individual variables can be rank ordered according to their predictive power. This is followed by a description of how the reader might discern the effect of any one of these variables on the target variable, i.e. growth and recessions.

Keywords: Classification And Regression Tree (CART); Learning Sample; Redistribution Estimates; Partial Dependence Plots (PDP); Desired Error Rate (search for similar items in EconPapers)
Date: 2017
References: Add references at CitEc
Citations: View citations in EconPapers (1)

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:spbchp:978-3-319-69014-8_3

Ordering information: This item can be ordered from
http://www.springer.com/9783319690148

DOI: 10.1007/978-3-319-69014-8_3

Access Statistics for this chapter

More chapters in SpringerBriefs in Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().