Omitted Variable Bias of Lasso-Based Inference Methods Under Limited Variability: A Finite Sample Analysis

2019 ◽  
Author(s):  
Kaspar Wuthrich ◽  
Ying Zhu
Keyword(s):  
Finite Sample ◽  
Sample Analysis ◽  
Omitted Variable Bias ◽  
Variable Bias ◽  
Inference Methods

scholarly journals Omitted Variable Bias of Lasso-Based Inference Methods: A Finite Sample Analysis

2021 ◽  
pp. 1-47
Author(s):  
Kaspar Wüthrich ◽  
Ying Zhu
Keyword(s):  
Sample Size ◽  
Finite Sample ◽  
Sample Analysis ◽  
Asymptotic Inference ◽  
Omitted Variable Bias ◽  
Practical Guidance ◽  
Variable Bias ◽  
Inference Methods ◽  
Inference Theory

Abstract We study the finite sample behavior of Lasso-based inference methods such as post double Lasso and debiased Lasso. We show that these methods can exhibit substantial omitted variable biases (OVBs) due to Lasso not selecting relevant controls. This phenomenon can occur even when the coeffcients are sparse and the sample size is large and larger than the number of controls. Therefore, relying on the existing asymptotic inference theory can be problematic in empirical applications. We compare the Lasso-based inference methods to modern highdimensional OLS-based methods and provide practical guidance.

Physical Ability-Task Performance Models: Assessing the Risk of Omitted Variable Bias

2008 ◽  
Author(s):  
Jr. Vickers ◽  
Hodgdon Ross R. ◽  
Beckett James A. ◽  
Marcie B.
Keyword(s):  
Task Performance ◽  
Performance Models ◽  
Physical Ability ◽  
Omitted Variable Bias ◽  
Variable Bias

scholarly journals Omitted Variable Bias in GLMs of Neural Spiking Activity

2018 ◽  
Vol 30 (12) ◽  
pp. 3227-3258 ◽  
Author(s):  
Ian H. Stevenson
Keyword(s):  
Neural Activity ◽  
Single Neuron ◽  
Linear Models ◽  
Theory And Practice ◽  
Parameter Estimates ◽  
Omitted Variables ◽  
History Effects ◽  
Omitted Variable Bias ◽  
Wide Range ◽  
Variable Bias

Generalized linear models (GLMs) have a wide range of applications in systems neuroscience describing the encoding of stimulus and behavioral variables, as well as the dynamics of single neurons. However, in any given experiment, many variables that have an impact on neural activity are not observed or not modeled. Here we demonstrate, in both theory and practice, how these omitted variables can result in biased parameter estimates for the effects that are included. In three case studies, we estimate tuning functions for common experiments in motor cortex, hippocampus, and visual cortex. We find that including traditionally omitted variables changes estimates of the original parameters and that modulation originally attributed to one variable is reduced after new variables are included. In GLMs describing single-neuron dynamics, we then demonstrate how postspike history effects can also be biased by omitted variables. Here we find that omitted variable bias can lead to mistaken conclusions about the stability of single-neuron firing. Omitted variable bias can appear in any model with confounders—where omitted variables modulate neural activity and the effects of the omitted variables covary with the included effects. Understanding how and to what extent omitted variable bias affects parameter estimates is likely to be important for interpreting the parameters and predictions of many neural encoding models.

scholarly journals Lock-In and Team Effects

2015 ◽  
Vol 18 (4) ◽  
pp. 376-387
Author(s):  
Trey Dronyk-Trosper ◽  
Brandli Stitzel
Keyword(s):  
Set Covering ◽  
Future Research ◽  
Prior Work ◽  
Omitted Variable Bias ◽  
Specific Effects ◽  
Heterogeneous Effects ◽  
Team Success ◽  
Variable Bias ◽  
Lock In ◽  
Least Squares Approach

How important is recruiting to a football program’s success? While prior research has attempted to answer this question, we utilize an extensive panel set covering 13 years of games along with a two-stage least squares approach to investigate the effects of recruiting on team success. This article also includes new control variables to account for omitted variable bias that prior work may have missed. We also split our sample to investigate whether recruiting displays heterogeneous effects across schools. Additionally, we find evidence that the benefits of recruiting are driven by team-specific effects, indicating that team success may be more heavily derived from the ability of teams to harness and improve their recruits than their ability to utilize each athlete’s raw abilities. This leads to important revelations regarding future research into both the value of recruits and what drives a football team’s success.

The Impact of ICT Investment on Establishment Productivity

2003 ◽  
Vol 184 ◽  
pp. 99-110 ◽  
Author(s):  
Thomas Zwick
Keyword(s):  
Panel Data ◽  
Unobserved Heterogeneity ◽  
Data Set ◽  
Omitted Variable Bias ◽  
Lagged Effects ◽  
Variable Bias ◽  
Employee Characteristics ◽  
The Impact ◽  
Establishment Panel Data

This paper finds substantial effects of ICT investments on productivity for a large and representative German establishment panel data set. In contrast to the bulk of the literature also establishments without ICT capital are included and lagged effects of ICT investments are analysed. In addition, a broad range of establishment and employee characteristics are taken account of in order to avoid omitted variable bias. It is shown that taking into account unobserved heterogeneity of the establishments and endogeneity of ICT investments increases the estimated lagged productivity impact of ICT investments.

scholarly journals Parsing Expression Grammars and Their Induction Algorithm

2020 ◽  
Vol 10 (23) ◽  
pp. 8747
Author(s):  
Wojciech Wieczorek ◽  
Olgierd Unold ◽  
Łukasz Strąk
Keyword(s):  
Genetic Programming ◽  
Roc Curve ◽  
Classification Performance ◽  
Grammatical Inference ◽  
Inference Algorithm ◽  
Finite Sample ◽  
Induction Method ◽  
Grammar Learning ◽  
Area Under Roc Curve ◽  
Inference Methods

Grammatical inference (GI), i.e., the task of finding a rule that lies behind given words, can be used in the analyses of amyloidogenic sequence fragments, which are essential in studies of neurodegenerative diseases. In this paper, we developed a new method that generates non-circular parsing expression grammars (PEGs) and compares it with other GI algorithms on the sequences from a real dataset. The main contribution of this paper is a genetic programming-based algorithm for the induction of parsing expression grammars from a finite sample. The induction method has been tested on a real bioinformatics dataset and its classification performance has been compared to the achievements of existing grammatical inference methods. The evaluation of the generated PEG on an amyloidogenic dataset revealed its accuracy when predicting amyloid segments. We show that the new grammatical inference algorithm achieves the best ACC (Accuracy), AUC (Area under ROC curve), and MCC (Mathew’s correlation coefficient) scores in comparison to five other automata or grammar learning methods.

scholarly journals Tracking Underreported Financial Flows: China’s Development Finance and the Aid–Conflict Nexus Revisited

2015 ◽  
Vol 61 (5) ◽  
pp. 935-963 ◽  
Author(s):  
Austin M. Strange ◽  
Axel Dreher ◽  
Andreas Fuchs ◽  
Bradley Parks ◽  
Michael J. Tierney
Keyword(s):  
Open Source ◽  
Reliable Information ◽  
African Countries ◽  
Financial Flows ◽  
Development Finance ◽  
Alternative Funding ◽  
Omitted Variable Bias ◽  
Chinese Official ◽  
Variable Bias ◽  
Project Level

China’s provision of development finance to other countries is sizable but reliable information is scarce. We introduce a new open-source methodology for collecting project-level development finance information and create a database of Chinese official finance (OF) to Africa from 2000 to 2011. We find that China’s commitments amounted to approximately US$73 billion, of which US$15 billion are comparable to Official Development Assistance following Organization for Economic Cooperation and Development definitions. We provide details on 1,511 projects to fifty African countries. We use this database to extend previous research on aid and conflict, which suffers from omitted-variable bias due to the exclusion of Chinese development finance. Our results show that sudden withdrawals of “traditional” aid no longer induce conflict in the presence of sufficient alternative funding from China. Our findings highlight the importance of gathering more complete data on the development activities of “nontraditional donors” to better understand the link between aid and conflict.

Causal Inference and Omitted Variable Bias in Financial Aid Research: Assessing Solutions

2008 ◽  
Vol 31 (3) ◽  
pp. 329-354 ◽  
Author(s):  
Stephanie K. Riegg
Keyword(s):  
Causal Inference ◽  
Financial Aid ◽  
Omitted Variable Bias ◽  
Variable Bias
Sign in / Sign up

Export Citation Format

Share Document