2005
DOI: 10.2139/ssrn.825845
|View full text |Cite
|
Sign up to set email alerts
|

Censored Data and Truncated Distributions

Abstract: We detail the basic theory for regression models in which dependent variables are censored or underlying distributions are truncated. The model is extended to models for counts, sample selection models, and models hazard models for duration data. Entry level theory is presented for the practitioner. We then describe a few of the recent, frontier developments in theory and practice.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

1
43
0
3

Year Published

2009
2009
2023
2023

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 53 publications
(47 citation statements)
references
References 78 publications
1
43
0
3
Order By: Relevance
“…The use of a fixed effect Tobit model for panel data is, however, a problem in our case because of the restricted number of periods (See Greene 2006). The simple Tobit results on R&DI with RE or even FE, that are consistent with our results obtained with the RE Heckman model, are available upon request.…”
Section: Econometric Modelingsupporting
confidence: 72%
“…The use of a fixed effect Tobit model for panel data is, however, a problem in our case because of the restricted number of periods (See Greene 2006). The simple Tobit results on R&DI with RE or even FE, that are consistent with our results obtained with the RE Heckman model, are available upon request.…”
Section: Econometric Modelingsupporting
confidence: 72%
“…The majority of US consumers in previous studies preferred the taste of grain beef to grass beef; therefore, the TASTE_INFO coefficient is expected to be negative. Each participant is represented in the data six times, therefore, LIMDEP's panel data random effects linear regression procedure was used to estimate Equation (2) (Greene 2005).…”
Section: Econometric Analysismentioning
confidence: 99%
“…This involves using a probit model to estimate the a parameters and a truncated normal regression model to estimate the b parameters. Greene (2005) shows that as the tobit log likelihood is simply the sum of the probit and truncated regression log likelihoods, a simple test of the tobit model as a restriction on Cragg's model can be performed using a likelihood ratio test.…”
mentioning
confidence: 99%
“…In this case the selection mechanism is specified as a probability model to account for the latent selection variable. Another generalization is to allow nonlinear specification of the primary equation (see Greene 1992Greene , 2006andTerza 1995, 1998 for examples of the approach). 14 An increase in the entrant-to-bidder ratio error should be positively associated with gaining entry in the spectrum contest.…”
Section: Econometric Methodsmentioning
confidence: 99%