scholarly journals A Unified Framework for Specification Tests of Continuous Treatment Effect Models

Author(s):  
Wei Huang ◽  
Oliver Linton ◽  
Zheng Zhang
2014 ◽  
Vol 104 (5) ◽  
pp. 212-217 ◽  
Author(s):  
Angela Vossmeyer

This article develops a Bayesian framework for estimating multivariate treatment effect models in the presence of sample selection. The methodology is applied to a banking study that evaluates the effectiveness of lender of last resort (LOLR) policies and their ability to resuscitate the financial system. This paper employs a novel bank-level dataset from the Reconstruction Finance Corporation, and jointly models a bank's decision to apply for a loan, the LOLR's decision to approve the loan, and the bank's performance a few years after the disbursements. This framework offers practical estimation tools to unveil new answers to important regulatory questions.


2008 ◽  
Vol 14 (6) ◽  
pp. 837-842 ◽  
Author(s):  
PS Sorensen ◽  
N Koch-Henriksen ◽  
EM Flachs ◽  
K Bendtzen

Objective To establish whether multiple sclerosis (MS) patients, who have lost the therapeutic effect of interferon-beta (IFN-β) owing to neutralizing antibodies (NAbs) and subsequently revert from a NAb-positive to a NAb-negative state under continued IFN-β-1b therapy, regain clinical effect after reversion. Background Several studies have shown that a significant proportion of patients treated with IFN-β develop NAbs that hamper or abolish the therapeutic effect of IFN-β. However, some patients, who become NAb-positive under treatment with IFN-β-1b, may revert to a NAb-negative state under continuous treatment. Methods We identified 40 patients from the Danish IFN protocol, who fulfilled the criteria: NAb-positive status for at least 12 months followed by reversion to NAb-negative state for at least 12 months. For comparison, we included 64 matching cases that had remained NAb-negative during an observation time of at least 36 months. The two groups were clinically and demographically alike. We measured NAb-neutralizing capacity using a clinically validated cytopathic effect assay. A blood sample with a neutralizing capacity of 20% or more was considered as NAb-positive. A patient was defined as NAb-positive after two consecutive blood tests separated by at least 6 months. Reversion to a NAb-negative state required at least two consecutive negative tests. To allow for the confounding effect of time we employed a mixed Poisson model. Results Patients who had been NAb-positive and reverted to a NAb-negative state regained treatment effect with the relapse rate as before the NAb-positive period adjusting for the effect of time, and the relapse rate was the same as in the permanently NAb-negative patients in corresponding time periods. The relapse rate ratio comparing the NAb-positive with the NAb-negative periods was 1.98 (95% confidence interval: 1.32–2.97). Conclusion Under NAb-positive periods, the clinical effect of IFN-β was abolished. When NAbs disappeared spontaneously under continued treatment, patients regained the full effect of INF-β-1b therapy with no negative carry-over effect from the previous NAb-positive period.


2012 ◽  
Author(s):  
Luc Behaghel ◽  
Bruno Crepon ◽  
Marc Gurgand ◽  
Thomas Le Barbanchon

2015 ◽  
Vol 97 (5) ◽  
pp. 1070-1080 ◽  
Author(s):  
Luc Behaghel ◽  
Bruno Crépon ◽  
Marc Gurgand ◽  
Thomas Le Barbanchon

Sign in / Sign up

Export Citation Format

Share Document