scholarly journals Panel experiments and dynamic causal effects: A finite population perspective

2021 ◽  
Vol 12 (4) ◽  
pp. 1171-1196 ◽  
Author(s):  
Iavor Bojinov ◽  
Ashesh Rambachan ◽  
Neil Shephard
Keyword(s):  
Fixed Effects ◽  
Serial Correlation ◽  
Finite Population ◽  
Relative Effectiveness ◽  
Randomization Test ◽  
Causal Effects ◽  
Probability Limit ◽  
Population Probability ◽  
Potential Outcomes Framework ◽  
Randomization Distribution

In panel experiments, we randomly assign units to different interventions, measuring their outcomes, and repeating the procedure in several periods. Using the potential outcomes framework, we define finite population dynamic causal effects that capture the relative effectiveness of alternative treatment paths. For a rich class of dynamic causal effects, we provide a nonparametric estimator that is unbiased over the randomization distribution and derive its finite population limiting distribution as either the sample size or the duration of the experiment increases. We develop two methods for inference: a conservative test for weak null hypotheses and an exact randomization test for sharp null hypotheses. We further analyze the finite population probability limit of linear fixed effects estimators. These commonly‐used estimators do not recover a causally interpretable estimand if there are dynamic causal effects and serial correlation in the assignments, highlighting the value of our proposed estimator.

scholarly journals Novel insights into the consequences of obesity: a phenotype-wide Mendelian randomization study

2022 ◽  
Author(s):  
Chang He ◽  
Miaoran Zhang ◽  
Jiuling Li ◽  
Yiqing Wang ◽  
Lanlan Chen ◽  
...  
Keyword(s):  
Instrumental Variables ◽  
Fixed Effects ◽  
Mendelian Randomization ◽  
Portion Size ◽  
Causal Effects ◽  
Calorie Intake ◽  
Smoking Behaviors ◽  
Prostate Cancers ◽  
The Uk ◽  
Consequences Of Obesity

AbstractObesity is thought to significantly impact the quality of life. In this study, we sought to evaluate the health consequences of obesity on the risk of a broad spectrum of human diseases. The causal effects of exposing to obesity on health outcomes were inferred using Mendelian randomization (MR) analyses using a fixed effects inverse-variance weighted model. The instrumental variables were SNPs associated with obesity as measured by body mass index (BMI) reported by GIANT consortium. The spectrum of outcome consisted of the phenotypes from published GWAS and the UK Biobank. The MR-Egger intercept test was applied to estimate horizontal pleiotropic effects, along with Cochran’s Q test to assess heterogeneity among the causal effects of instrumental variables. Our MR results confirmed many putative disease risks due to obesity, such as diabetes, dyslipidemia, sleep disorder, gout, smoking behaviors, arthritis, myocardial infarction, and diabetes-related eye disease. The novel findings indicated that elevated red blood cell count was inferred as a mediator of BMI-induced type 2 diabetes in our bidirectional MR analysis. Intriguingly, the effects that higher BMI could decrease the risk of both skin and prostate cancers, reduce calorie intake, and increase the portion size warrant further studies. Our results shed light on a novel mechanism of the disease-causing roles of obesity.

The Causal Effects of Proximity on Investment: Evidence from Flight Introductions

2019 ◽  
Vol 55 (6) ◽  
pp. 1978-2004 ◽  
Author(s):  
Jesse Ellis ◽  
Leonardo Madureira ◽  
Shane Underwood
Keyword(s):  
Mutual Funds ◽  
Fixed Effects ◽  
Investment Decisions ◽  
Relevant Information ◽  
Causal Effects ◽  
Superior Performance ◽  
Firm Level ◽  
Exogenous Shock ◽  
And Performance ◽  
Fund Investment

We use the introduction of direct flights as an exogenous shock to the travel time between mutual funds and firms to estimate the causal effects of proximity on fund investment decisions and performance. We find that a fund invests significantly more in firms that become more proximate following the introduction of direct flights and that these more proximate investments exhibit superior performance. Our findings are robust to including a variety of fixed effects and potential confounders such as firm-level shocks, fund-level shocks, and time trends. Collectively, our results indicate that proximity enhances investors’ ability to acquire value-relevant information about firms.

Testing for Serial Correlation in Fixed-effects Panel Models

2018 ◽  
Vol 18 (1) ◽  
pp. 76-100 ◽  
Author(s):  
Jesse Wursten
Keyword(s):  
Fixed Effects ◽  
Serial Correlation ◽  
Panel Models ◽  
First Order ◽  
Fixed Effects Models ◽  
Correlation Tests

Current serial correlation tests for panel models are cumbersome to use, not suited for fixed-effects models, or limited to first-order autocorrelation. To fill this gap, I implement three recently developed tests.

Misspecification of the random effect structure: Implications for the linear mixed model

2020 ◽  
Author(s):  
Brandon LeBeau
Keyword(s):  
Fixed Effects ◽  
Serial Correlation ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Type I Error ◽  
Random Effect ◽  
Correlated Data ◽  
Unbiased Estimation ◽  
Type I ◽  
Nested Data

<p>The linear mixed model is a commonly used model for longitudinal or nested data due to its ability to account for the dependency of nested data. Researchers typically rely on the random effects to adequately account for the dependency due to correlated data, however serial correlation can also be used. If the random effect structure is misspecified (perhaps due to convergence problems), can the addition of serial correlation overcome this misspecification and allow for unbiased estimation and accurate inferences? This study explored this question with a simulation. Simulation results show that the fixed effects are unbiased, however inflation of the empirical type I error rate occurs when a random effect is missing from the model. Implications for applied researchers are discussed.</p>

scholarly journals Deriving the GLS Transformation Parameter in Elementary Panel Data Models

2005 ◽  
Vol 49 (1) ◽  
pp. 45-48 ◽  
Author(s):  
Philip N. Jefferson
Keyword(s):  
Fixed Effects ◽  
Serial Correlation ◽  
Generalized Least Squares ◽  
Panel Data Models ◽  
Complete Understanding ◽  
Quadratic Formula ◽  
Error Terms ◽  
Elementary Statistics ◽  
The Relationship ◽  
Mean Variance

The Generalized Least Squares (GLS) transformation that eliminates serial correlation in the error terms is central to a complete understanding of the relationship between the pooled OLS, random effects, and fixed effects estimators. A significant hurdle to attainment of that understanding is the calculation of the parameter that delivers the desired transformation. This paper derives this critical parameter in the benchmark case typically used to introduce these estimators using nothing more than elementary statistics (mean, variance, and covariance) and the quadratic formula.

Estimation of marginal causal effects in the presence of confounding by cluster

Biostatistics ◽  
2019 ◽  
Author(s):  
Arvid Sjölander
Keyword(s):  
Fixed Effects ◽  
Causal Effects ◽  
Binary Outcomes ◽  
Exposure Level ◽  
Large Set ◽  
Hyperactivity Disorder ◽  
Fixed Effects Models ◽  
Wide Range ◽  
Log Linear ◽  
And Control

Summary A popular way to control for unmeasured confounders is to utilize clusters (e.g. sets of siblings), in which a potentially large set of confounders are constant. By estimating the exposure–outcome association within clusters, rather than between unrelated subjects, all cluster-constant confounders are implicitly controlled for. To analyze such clustered data, it is common to use fixed effects models, which absorb all cluster-constant confounders into a cluster-specific intercept. In this article, we show how linear and log-linear fixed effects models can be used to estimate marginal counterfactual means. These counterfactual means can be estimated and presented for each exposure level separately, or contrasted to form a wide range of marginal causal effects. For binary outcomes, we propose to estimate marginal causal effects with marginal logistic between-within models. These models include a constant intercept common for all clusters, and control for unmeasured cluster-constant confounders by adding the mean exposure level in each cluster to the model. We illustrate the proposed methods by re-analyzing data from a co-twin control study on birth weight and Attention-Deficit/Hyperactivity Disorder.

Out of Control: The (Over)Use of Controls in Accounting Research

2021 ◽  
Author(s):  
Robert L. Whited ◽  
Quinn T. Swanquist ◽  
Jonathan E. Shipman ◽  
James R. Moon
Keyword(s):  
Measurement Error ◽  
Fixed Effects ◽  
Causal Effects ◽  
Methodological Issues ◽  
Control Variables ◽  
Treatment Assignment ◽  
Accounting Research ◽  
Empirical Tests ◽  
Selection Of

In the absence of random treatment assignment, the selection of appropriate control variables is essential to designing well-specified empirical tests of causal effects. However, the importance of control variables seems underappreciated in accounting research relative to other methodological issues. Despite the frequent reliance on control variables, the accounting literature has limited guidance on how to select them. We evaluate the evolution in use of control variables in accounting research and discuss some of the issues that researchers should consider when choosing control variables. Using simulations, we illustrate that more control is not always better and that some control variables can introduce bias into an otherwise well-specified model. We also demonstrate other issues with control variables including the effects of measurement error and complications associated with fixed effects. Lastly, we provide practical suggestions for future accounting research.

Sign in / Sign up

Export Citation Format

Share Document