All Rights Reserved
AccessEcon LLC 2006, 2008.
Powered by MinhViet JSC

Kavita Sardana
''Double truncation in choice-based sample: An application of on-site survey sample''
( 2021, Vol. 41 No.2 )
In this paper, I derive the distribution of an on-site survey sample that is truncated from above. By bootstrapping the conditional expectation with and without upper truncation, I show that the differences are statistically significant. I conclude that ad-hoc truncation (upper truncation) might not be the best solution to homogenize the population, rather semi-parametric methods such as Latent Class Models should be used to identify different classes of homogeneous population.
Keywords: Choice-based sample, On-site survey sample, Truncated distribution, ad-hoc truncation, bootstrap.
JEL: C5 - Econometric Modeling: General
C1 - Econometric and Statistical Methods: General
Manuscript Received : Jan 27 2021 Manuscript Accepted : Apr 09 2021

  This abstract has been downloaded 734 times                The Full PDF of this paper has been downloaded 156012 times