Currency Unions and Trade: A PPML Re‐assessment with High‐dimensional Fixed Effects

2018 ◽  
Vol 81 (3) ◽  
pp. 487-510 ◽  
Author(s):  
Mario Larch ◽  
Joschka Wanner ◽  
Yoto V. Yotov ◽  
Thomas Zylkin
Keyword(s):  
Fixed Effects ◽  
High Dimensional ◽  
Currency Unions

scholarly journals Fast Poisson estimation with high-dimensional fixed effects

2020 ◽  
Vol 20 (1) ◽  
pp. 95-115 ◽  
Author(s):  
Sergio Correia ◽  
Paulo Guimarães ◽  
Tom Zylkin
Keyword(s):  
Least Squares ◽  
Fixed Effects ◽  
Maximum Likelihood Estimates ◽  
High Dimensional ◽  
Software Components ◽  
Iteratively Reweighted Least Squares ◽  
Convergence Properties ◽  
New Techniques ◽  
Boston College ◽  
Pseudo Maximum Likelihood

In this article, we present ppmlhdfe, a new command for estimation of (pseudo-)Poisson regression models with multiple high-dimensional fixed effects (HDFE). Estimation is implemented using a modified version of the iteratively reweighted least-squares algorithm that allows for fast estimation in the presence of HDFE. Because the code is built around the reghdfe package ( Correia, 2014 , Statistical Software Components S457874, Department of Economics, Boston College), it has similar syntax, supports many of the same functionalities, and benefits from reghdfe‘s fast convergence properties for computing high-dimensional leastsquares problems. Performance is further enhanced by some new techniques we introduce for accelerating HDFE iteratively reweighted least-squares estimation specifically. ppmlhdfe also implements a novel and more robust approach to check for the existence of (pseudo)maximum likelihood estimates.

scholarly journals Mastering Panel Metrics: Causal Impact of Democracy on Growth

2019 ◽  
Vol 109 ◽  
pp. 77-82 ◽  
Author(s):  
Shuowen Chen ◽  
Victor Chernozhukov ◽  
Iván Fernández-Val
Keyword(s):  
Panel Data ◽  
Statistical Inference ◽  
Fixed Effects ◽  
State Of The Art ◽  
Panel Data Analysis ◽  
High Dimensional ◽  
Econometric Methods ◽  
Long Run ◽  
Causal Impact ◽  
The Relationship

We revisit the panel data analysis of Acemoglu et al. (forthcoming) on the relationship between democracy and economic growth using state-of-the-art econometric methods. We argue that panel data settings are high-dimensional, resulting in estimators to be biased to a degree that invalidates statistical inference. We remove these biases by using simple analytical and sample-splitting methods, and thereby restore valid statistical inference. We find that debiased fixed effects and Arellano-Bond estimators produce higher estimates of the long-run effect of democracy on growth, providing even stronger support for the key hypothesis of Acemoglu et al.

scholarly journals Higher Sugar-Sweetened Beverage Retail Prices After Excise Taxes in Oakland and San Francisco

2020 ◽  
Vol 110 (7) ◽  
pp. 1017-1023 ◽  
Author(s):  
Jennifer Falbe ◽  
Matthew M. Lee ◽  
Scott Kaplan ◽  
Nadia A. Rojas ◽  
Alberto M. Ortega Hinojosa ◽  
...  
Keyword(s):  
San Francisco ◽  
Fixed Effects ◽  
Weighted Average ◽  
High Dimensional ◽  
Difference In Differences ◽  
Sugar Sweetened Beverage ◽  
Excise Taxes ◽  
Sweetened Beverage ◽  
Diet Soda ◽  
Retail Prices

Objectives. To examine how much sugar-sweetened beverage (SSB) excise taxes increased SSB retail prices in Oakland and San Francisco, California. Methods. We collected pretax (April–May 2017) and posttax (April–May 2018) retail prices of SSBs and non-SSBs from 155 stores in Oakland, San Francisco, and comparison cities. We analyzed data using difference-in-differences high-dimensional fixed-effects regressions, weighted by regional beverage sales. Results. Across all beverage sizes, the weighted average price of SSBs increased by 0.92 cents per ounce (95% confidence interval [CI] = 0.28, 1.56) in Oakland and 1.00 cents per ounce (95% CI = 0.35, 1.65) in San Francisco, compared with prices in untaxed cities. The tax did not significantly alter prices of water, 100% juice, or milk of any size examined. Diet soda only, among non-SSBs, exhibited a higher price increase for some sizes in taxed cities. Conclusions. Within 4 to 10 months of implementation, Oakland’s and San Francisco’s SSB excise taxes significantly increased SSB retail prices by approximately the amount of the taxes, a key mechanism for reducing consumption.

scholarly journals Recentered influence functions (RIFs) in Stata: RIF regression and RIF decomposition

2020 ◽  
Vol 20 (1) ◽  
pp. 51-94 ◽  
Author(s):  
Fernando Rios-Avila
Keyword(s):  
Fixed Effects ◽  
Decomposition Analysis ◽  
High Dimensional ◽  
Large Set ◽  
Influence Functions ◽  
Analysis Framework ◽  
Quantile Regressions ◽  
Rif Regression ◽  
Linear Regressions ◽  
Partial Effects

Recentered influence functions (RIFs) are statistical tools popularized by Firpo, Fortin, and Lemieux (2009 , Econometrica 77: 953–973) for analyzing unconditional partial effects on quantiles in a regression analysis framework (unconditional quantile regressions). The flexibility and simplicity of these tools have opened the possibility to extend the analysis to other distributional statistics using linear regressions or decomposition approaches. In this article, I introduce one function and two commands to facilitate the use of RIFs in the analysis of outcome distributions: rifvar() is an egen extension used to create RIFs for a large set of distributional statistics, rifhdreg facilitates the estimation of RIF regressions enabling the use of high-dimensional fixed effects, and oaxaca_rif implements Oaxaca–Blinder decomposition analysis (RIF decompositions).

Impact of Institutional Quality on Bilateral Exports: Exploring the role of Development

2021 ◽  
Vol 5 (2) ◽  
pp. 17-34
Author(s):  
Muhammad Zubair Chishti ◽  
Babar Hussain ◽  
Muhammad Aqib Khursheed
Keyword(s):  
Interaction Effect ◽  
Fixed Effects ◽  
Institutional Quality ◽  
High Dimensional ◽  
Future Research ◽  
Research Gaps ◽  
Heterogeneous Effect ◽  
Bilateral Exports ◽  
Econometric Technique

This study uses the gravity model to analyze the homogeneous and heterogeneous effect of institutional quality and development on bilateral exports. We use the panel data of 61countries for the period 2000 to 2016 and employ the Poisson Pseudo Maximum Liklihood (PPML) econometric technique with a High-Dimensional fixed effect (HDFE) for an estimation that allows the analysis in the presence of high dimensional fixed effects. The findings reveal that the direct effect of institutional quality and level of development on bilateral exports is positive and significant. Further, the institutional quality and the level of development of the exporter country have more impact on bilateral exports than that of the importer country. Our estimation results of homogeneity of institutions show that when both trading countries share the same level of institutional quality, it boosts the bilateral exports.  The major finding of this study reveals that the interaction effect of institutional quality and level of development on bilateral exports is positive and significant. High value of interaction term of exporter economy and low value of importer country suggest that interaction effect of institutional quality and level of development on bilateral exports of exporter country have a greater impact than the interaction effect of institutional quality and level of development of importer country due to having the more production and exports facilities in exporter country. Based on the findings, some essential policies are also recommended, followed by some future research gaps.

scholarly journals Fixed Effects Testing in High-Dimensional Linear Mixed Models

2020 ◽  
Vol 115 (532) ◽  
pp. 1835-1850
Author(s):  
Jelena Bradic ◽  
Gerda Claeskens ◽  
Thomas Gueuning
Keyword(s):  
Mixed Models ◽  
Fixed Effects ◽  
Linear Mixed Models ◽  
High Dimensional

Monte Carlo Appraisals of Gravity Model Specifications

2008 ◽  
Vol 8 (1) ◽  
pp. 1850129 ◽  
Author(s):  
Kurt C. Schaefer ◽  
Michael A. Anderson ◽  
Michael J. Ferrantino
Keyword(s):  
Monte Carlo ◽  
Gravity Model ◽  
Free Trade ◽  
Fixed Effects ◽  
Statistical Tests ◽  
Model Specification ◽  
Currency Unions ◽  
Trade Associations ◽  
Data Process ◽  
Data Generating Process

Many improvements have been proposed for the basic gravity model specification, most of which are confirmed by standard statistical tests due to the large number of observations often used to estimate such models. We use Monte Carlo experiments to examine situations in which features of models may be found statistically significant (or insignificant) when it is known ex ante that they are absent (or present) in the underlying data process. Erroneous assumptions about the presence or absence of lagged dependent variables, fixed effects, free-trade associations and custom unions are shown to introduce an economically important bias in estimates of the coefficients of interest, and in some cases to be confirmed spuriously. Policy effects for such initiatives as free trade associations and currency unions can also be confirmed spuriously when they do not exist in the data-generating process.

Sign in / Sign up

Export Citation Format

Share Document