EconStor >
Forschungsinstitut zur Zukunft der Arbeit (IZA), Bonn >
IZA Discussion Papers, Forschungsinstitut zur Zukunft der Arbeit (IZA) >

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10419/51798
  
Title:Calculating confidence intervals for continuous and discontinuous functions of estimated parameters PDF Logo
Authors:Ham, John C.
Woutersen, Tiemen
Issue Date:2011
Series/Report no.:Discussion paper series // Forschungsinstitut zur Zukunft der Arbeit 5816
Abstract:The delta method is commonly used to calculate confidence intervals of functions of estimated parameters that are differentiable with non-zero, bounded derivatives. When the delta method is inappropriate, researchers usually first use a bootstrap procedure where they i) repeatedly take a draw from the asymptotic distribution of the parameter values and ii) calculate the function value for this draw. They then trim the bottom and top of the distribution of function values to obtain their confidence interval. This note first provides several examples where this procedure and/or delta method fail to provide an appropriate confidence interval. It next presents a method that is appropriate for constructing confidence intervals for functions that are discontinuous or are continuous but have zero or unbounded derivatives. In particular the coverage probabilities for our method converge uniformly to their nominal values, which is not necessarily true for the other methods discussed above.
Subjects:confidence intervals
simulation
structural models
policy effects
JEL:C12
C15
Persistent Identifier of the first edition:urn:nbn:de:101:1-201107042650
Document Type:Working Paper
Appears in Collections:IZA Discussion Papers, Forschungsinstitut zur Zukunft der Arbeit (IZA)

Files in This Item:
File Description SizeFormat
669597325.pdf260.85 kBAdobe PDF
No. of Downloads: Counter Stats
Download bibliographical data as: BibTeX
Share on:http://hdl.handle.net/10419/51798

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.