scholarly journals Multiple robustness in factorized likelihood models

Biometrika ◽  
2017 ◽  
Vol 104 (3) ◽  
pp. 561-581 ◽  
Author(s):  
J. Molina ◽  
A. Rotnitzky ◽  
M. Sued ◽  
J. M. Robins
Keyword(s):  
Multiple Robustness

scholarly journals Bank Liquidity Hoarding Strategies in Uncertain Times: New Evidence from an Emerging Market with Bank-level Data

2021 ◽  
Vol 12 (2) ◽  
pp. 377-398
Author(s):  
Van Dan Dang ◽  
Hoang Chung Nguyen
Keyword(s):  
Banking Sector ◽  
Emerging Market ◽  
Balance Sheet ◽  
Cross Sectional ◽  
Level Data ◽  
Balance Sheet Liquidity ◽  
The Impact ◽  
New Evidence ◽  
Multiple Robustness ◽  
Estimate Uncertainty

The paper explores the impact of uncertainty on bank liquidity hoarding, particularly providing new insights on the nature of the impact by bank-level heterogeneity. We consider the cross-sectional dispersion of shocks to key bank variables to estimate uncertainty in the banking sector and include all banking items to construct a comprehensive measure of bank liquidity hoarding. Using a sample of Vietnamese banks during 2007–2019, we document that banks tend to increase total liquidity hoarding in response to higher uncertainty; this pattern is still valid for on- and off-balance sheet liquidity hoarding. Further analysis with bank-level heterogeneity indicates that the impact of banking uncertainty on liquidity hoarding is significantly stronger for weaker banks, i. e., banks that are smaller, more poorly capitalized, and riskier. In testing the “search for yield” hypothesis to explain the linkage between uncertainty and bank liquidity hoarding, we do not find it to be the case. Our findings remain extremely robust after multiple robustness tests.

A Bi-Level Multi-Objective Robust Design Optimization Method With Multiple Robustness Index Capabilities

2011 ◽  
Author(s):  
Todd Letcher ◽  
M.-H. Herman Shen
Keyword(s):  
Robust Optimization ◽  
Optimization Problem ◽  
Optimization Problems ◽  
Optimization Method ◽  
Robust Design Optimization ◽  
Nsga Ii ◽  
Worst Case ◽  
Multi Objective ◽  
Robustness Index ◽  
Multiple Robustness

A multi-objective robust optimization framework that incorporates a robustness index for each objective has been developed in a bi-level approach. The top level of the framework consists of the standard optimization problem formulation with the addition of a robustness constraint. The bottom level uses the Worst Case Sensitivity Region (WCSR) concept previously developed to solve single objective robust optimization problems. In this framework, a separate robustness index for each objective allows the designer to choose the importance of each objective. The method is demonstrated on a commonly studied two-bar truss structural optimization problem. The results of the problem demonstrate the effectiveness and usefulness of the multiple robustness index capabilities added to this framework. A multi-objective genetic algorithm, NSGA-II, is used in both levels of the framework.

Multiple Robustness Enhancements for Image Adaptive Steganography in Lossy Channels

2020 ◽  
Vol 30 (8) ◽  
pp. 2750-2764 ◽  
Author(s):  
Yi Zhang ◽  
Xiangyang Luo ◽  
Yanqing Guo ◽  
Chuan Qin ◽  
Fenlin Liu
Keyword(s):  
Adaptive Steganography ◽  
Multiple Robustness

Too Scared to Learn? The Academic Consequences of Feeling Unsafe in the Classroom

2016 ◽  
Vol 55 (10) ◽  
pp. 1385-1418 ◽  
Author(s):  
Johanna Lacoe
Keyword(s):  
New York ◽  
Test Scores ◽  
Negative Relationship ◽  
School Students ◽  
Data Set ◽  
Academic Consequences ◽  
Survey Responses ◽  
The Relationship ◽  
Multiple Robustness ◽  
Insight Into

A safe environment is a prerequisite for productive learning. Using a unique panel data set of survey responses from New York City middle school students, the article provides insight into the relationship between feelings of safety in the classroom and academic achievement. The survey data include the reported feelings of safety for more than 340,000 students annually from 2007 to 2010 in more than 700 middle schools. Findings show a consistent negative relationship between feeling unsafe in the classroom and test scores. The study provides insight into the mechanisms through which feeling unsafe in the classroom relates to test scores and presents multiple robustness checks to support the central finding.

scholarly journals The consequences of unconventional monetary policy in euro area in times of monetary easing

2018 ◽  
Vol 9 (4) ◽  
pp. 581-615 ◽  
Author(s):  
Martin Pažický
Keyword(s):  
Monetary Policy ◽  
Interest Rate ◽  
Financial Crisis ◽  
Euro Area ◽  
Global Financial Crisis ◽  
Value Added ◽  
Structural Var ◽  
Unconventional Monetary Policy ◽  
Robustness Check ◽  
Multiple Robustness

Research background: In this research paper, an attempt is made to evaluate the impacts of ECB’s unconventional monetary policy which has been applied after Global Financial Crisis. Because of the new economic and monetary conditions, the effectiveness of conventional monetary tools has been questioned. Purpose of the article: Designed models examine the consequences of unconventional monetary policy for macroeconomic variables, monetary variables and interest rates in the euro area. Particular attention is paid to the response of the price level, represented by HICP, to various monetary policy innovations. Except a shock in credit multiplier and asset purchase programme (APP), also the effectiveness of a conventional monetary tool, such as main refinancing operation (MRO) interest rate, is inspected. Methods: Use has been made of impulse responses from structural VAR models to analyze a large sample that covers the time horizon of 1999 to 2016. Several econometric tests are performed to provide a profound analysis. The conclusions from baseline models are verified in multiple robustness check models, which are specified under alternative conditions. Findings & Value added: It has been found that, in the aftermath of the Global Financial Crisis, conventional monetary instruments are effective in the short-run. In the long-run, unconventional monetary policy has a greater potential to stabilize the economy than the traditional interest rate transmission channel. The conclusions from the baseline models are verified in multiple robustness check models, which are specified under alternative conditions.

scholarly journals Multiply robust bootstrap variance estimation in the presence of singly imputed survey data

2020 ◽  
Author(s):  
Sixia Chen ◽  
David Haziza ◽  
Zeinab Mashreghi
Keyword(s):  
Survey Data ◽  
Simulation Study ◽  
Coverage Probability ◽  
Variance Estimation ◽  
Item Nonresponse ◽  
Robustness Property ◽  
Single Imputation ◽  
Point Estimators ◽  
Multiple Robustness ◽  
Imputation Procedure

Abstract Item nonresponse in surveys is usually dealt with through single imputation. It is well known that treating the imputed values as if they were observed values may lead to serious underestimation of the variance of point estimators. In this article, we propose three pseudo-population bootstrap schemes for estimating the variance of imputed estimators obtained after applying a multiply robust imputation procedure. The proposed procedures can handle large sampling fractions and enjoy the multiple robustness property. Results from a simulation study suggest that the proposed methods perform well in terms of relative bias and coverage probability, for both population totals and quantiles.

Sign in / Sign up

Export Citation Format

Share Document