Témata prací (Výběr práce)Témata prací (Výběr práce)(verze: 368)
Detail práce
   Přihlásit přes CAS
A Meta-Analysis of the Estimates of the Armington Elasticity
Název práce v češtině: Metaanalýza odhadů Armingtnových elasticit
Název v anglickém jazyce: A Meta-Analysis of the Estimates of the Armington Elasticity
Klíčová slova: Armington elasticity, meta-analysis, Bayesian model averaging, publication bias
Klíčová slova anglicky: Armingtonova elasticita, metaanalýza, bayesovská statistika, publikační vychýlení
Akademický rok vypsání: 2016/2017
Typ práce: bakalářská práce
Jazyk práce: angličtina
Ústav: Institut ekonomických studií (23-IES)
Vedoucí / školitel: prof. PhDr. Tomáš Havránek, Ph.D.
Řešitel: skrytý - zadáno vedoucím/školitelem
Datum přihlášení: 09.11.2016
Datum zadání: 09.11.2016
Datum a čas obhajoby: 15.06.2017 09:00
Místo konání obhajoby: Opletalova - Opletalova 26, O314, Opletalova - místn. č. 314
Datum odevzdání elektronické podoby:17.05.2017
Datum proběhlé obhajoby: 15.06.2017
Oponenti: Mgr. Petr Polák, M.Sc., Ph.D.
 
 
 
Kontrola URKUND:
Seznam odborné literatury
1. Stanley, Tom D., and Hristos Doucouliagos. Meta-regression analysis in economics and business. Vol. 5. Routledge, 2012.
2. Feenstra, Robert C., et al. In search of the Armington elasticity. No. w20063. National Bureau of Economic Research, 2014.
3. Gallaway, Michael P., Christine A. McDaniel, and Sandra A. Rivera. "Short-run and long-run industry-level estimates of US
Armington elasticities." The North American Journal of Economics and Finance 14.1, 2003: 49-68.
4. McDaniel, Christine A., and Edward J. Balistreri. "A review on Armington trade substitution elasticities.", 2002.
5. Schürenberg-Frosch, Hannah. "We couldn’t care less about Armington elasticities–but should we?." 2015.
6. Flores, Manuel, and Adriana Cassoni. "Armington elasticities: estimates for Uruguayan manufacturing sectors." Departamento de
Economía, Universidad de la República Serie Documentos de Trabajo 07/10 2010.
Předběžná náplň práce v anglickém jazyce
Research question and motivation
The so-called Armington elasticity is elasticity between domestic and foreign goods. It is based on the Paul Armington’s assumption that the products are differentiated by country of origin in international trade. It has become a standard assumption of international general equilibrium models. In comparison with models with homogenous products, these models evince more realistic response of trade to price changes. Therefore I found important to conduct meta-analysis in this field. The one of the most remarkable merit of meta-analysis approach is revealing the publication bias of the estimates reported in literature. First estimates of Armington elasticities were conducted in US by Shiells & Stern (1986), or Reinert & Roland-Holst (1992). At these days there are more than fifty articles, working papers and researches subjected to this topic across countries and continents. Some of them (e. g. McDaniel & Balisteri, 2002; Cassoni & Flores, 2010) summarize the results and compare them. They found that long-run elasticities are higher than short-run ones, micro elasticities are higher than macro ones. Another factors, which affect the results are time-frequency and type of data. But no one made an overall meta-analysis of this topic up till now. I am going to investigate which variable influence the results the most. I am interested in findings of publication bias in this literature as well. Therefore I will cover in my analysis many other variables like midyear of data, length of time period, model used, estimation method, impact, or citations of the primary article.

Contribution
Meta-analysis is modern approach of summarizing and qualifying primary researches. Moreover it can correct potential biases in estimates, explain heterogeneity, or give the direction to future empirical investigation. Surprisingly, there is still no meta-analysis of the estimates of the elasticity between domestic and foreign goods. Therefore I want to fill-in this niche.

Methodology
I am going to conduct meta-regression analysis (MRA) on this topic. MRA is the statistical analysis of previously reported, or published research findings on a given empirical effect, or phenomenon. It is a systematic review of all relevant researches about a specific topic. The first step is the collection of primary studies. I will search for them by using Google Scholar and Repec Ideas. For using modern meta-analysis method and correction for publication bias, I need the standard error of each elasticity (or another statistical tool from which standard error could be computed). After making whole dataset of estimates and their related differences, such as standard error, model used, estimation method, midyear of data, type of data, level of aggregation etc., I will run a linear regression on the data set. Hence I will interpret what and how influence the estimates. After that I will use funnel graphs, chronological ordering of data, or summary statistics to expound the data in more agreeable way to the reader.

Outline
1. Motivation: There is no meta-analysis on the Armington elasticity. There is just few researches summarizing previous results, e.g. McDaniel, Balisteri, 2002. But none of them is comprehensive enough. No one reporting publication bias, influencing the results of length of time period of collecting data, midyear of data, model, or estimation technique used.
2. Studies on Armington elasticity: I will delineate how people conduct estimates of Arminton elasticity.
3. Data: I will clarify how I will collect estimates from primary studies.
4. Methods: I will explain and use meta-analysis methods, such as funnel graphs, chronological ordering of data, summary statistics, or regressions.
5. Results: I will discuss my robustness checks and regressions.
6. Concluding remarks: I will encapsulate my findings and present their benefits for future researches.
 
Univerzita Karlova | Informační systém UK