|
|
Income Inequality and Economic Growth: A Meta-Analysis
Posvyanskaya, Alexandra ; Havránková, Zuzana (advisor) ; Bauer, Michal (referee)
The impact of inequality on economic growth has become a topic of broad and current interest. Multiple researches investigated the issue but the disparity of opinions and empirical results is huge. The present thesis revises the pri- mary literature through a meta-analytical approach applying Bayesian Model Averaging (BMA) estimation technique. We examine 562 estimates collected from 58 studies published between 1991 and 2015. I find the evidence of the publication bias presence in the literature. The authors of primary studies tend to report preferentially negative and significant estimates. The BMA results suggest that the effect of inequality on growth is not straightforward and is likely not linear. A single pattern for inequality/growth relationship is not fea- sible since the results vary across used income inequality measures, estimation methods and data structure and quality. JEL Classification D31, O10, C11, C82 Keywords meta-analysis, inequality, economic growth, Bayesian model averaging, publication bias Author's e-mail 23376990@fsv.cuni.cz Supervisor's e-mail zuzana.havrankova@fsv.cuni.cz
|
|
|
A Meta-Analysis of FDI Spillovers in China
Herman, Dominik ; Havránek, Tomáš (advisor) ; Semerák, Vilém (referee)
Assessment of the foreign direct investment (FDI) spillovers in the People's Republic of China (PRC) has become a lively area of research in the past decades; nonetheless, the existing primary literature seems to be inconclusive. The present thesis revises the literature through a meta-analytical approach using Bayesian Model Averaging (BMA). Considering that the previous liter- ature reviews are of either inferior quality or incomparable focus, our research is based on a collection of 1081 estimates from 14 primary studies published between 2007 and 2017 comprising data from 1995 to 2012. A variety of 85 characteristics of the observations is coded whilst we employ at least 30 of these within each BMA estimation. Through separate testing of individual spillover measures (horizontal, forward, and backward), an extensive evidence of publication bias is collected for horizontal spillovers in PRC-exaggerating the mean magnitude of the reported estimates. Finally, the thesis identifies that the spillover effect from FDI inflows originating from the area of Hong Kong, Macau, and Taiwan is systematically different from the others. JEL Classification O1, O3, O4 Keywords FDI, spillover effect, China, PRC, meta- analysis, publication bias, BMA Author's e-mail hermandominik@gmail.com Supervisor's e-mail...
|
|
|
Impacts of Ethanol Policy on Corn Prices: A Meta-Analysis
Horáček, Přemysl ; Havránek, Tomáš (advisor) ; Janda, Karel (referee)
Deflecting a significant portion of corn production to ethanol for fuelling purposes increases the prices of corn. Although many studies examined the relationship between biofuels and agricultural commodity prices in the last decade, their estimates vary broadly (from nil to 85%). Without knowing the precise estimates of these impacts, policymakers can hardly set the biofuel policies optimally. I conduct a meta-analysis of over 150 estimates of the effect of corn ethanol production on corn prices to bring more clarity to the issue. Furthermore, I detect substantial selective reporting bias in the literature. After controlling for this bias with the use of various methods including the mixedeffects multilevel model, the results show that the true effect of a one billion gallon expansion in corn ethanol on corn prices is about 2-3%, which is less than commonly thought.
|
|
|
A Meta-Analysis of the Estimates of the Armington Elasticity
Bajzík, Josef ; Havránek, Tomáš (advisor) ; Polák, Petr (referee)
Josef Bajzík Abstract We examine determinants of Armington elasticities throughout history and nations employing 3,524 observations from 42 studies. We conduct meta-analysis using Bayesian model averaging approach to test the most influential factors. We explore more than 30 variables and compare our results with previous summarizing articles. In this thesis is, for instance, the first comparison of employment of different type of models in this area. Finally, we find out that the level of aggregation of the data used for estimation matters as well as the power of the currency. On the other hand, we discover that there is no significant distinction between long-run and short-run estimates. Moreover, we test for publication bias and we find evidence for it in this field.
|
|
|
Methodological innovations in psychological research
Frollová, Nikola ; Vranka, Marek (advisor) ; Fabianová, Ivana (referee)
The year 2012 opened an intense debate about the methodological problems of psychological research that lead to excessive publication of unreliable and nonreplicable results. The proposed improvements consist of conducting more replication studies, sharing data openly, limiting the "degrees of researcher freedom ", and improving the understanding and application of statistical methods for data analysis. This bachelor thesis aims to map the aforementioned problems, proposed solutions, as well as possible criticisms and problems with their implementation in practice. The research proposal consists of measuring the prevalence of questionable scientific practices among psychologists in Czech Republic.
|
|
|
Does Daylight Saving Time Save Energy?: A Meta-Analysis
Herman, Dominik ; Havránek, Tomáš (advisor) ; Zeynalov, Ayaz (referee)
Daylight saving time energy savings have always represented a contentious topic requiring empirical evidence for, or against. Unfortunately, as the conclusions are miscellaneous-without an evident pattern of heterogeneity occurrence-insisting on particular case studies and narrative literature reviews seems to be insufficient. In this thesis, set of various studies concerning the effect of daylight saving time on energy savings is examined through meta-regression analysis to provide an accurate estimate of the effect corrected from publication bias, and other distorting and deflecting effects. We find that the mean reported estimate in the literature suggests 0.3% energy savings; our results suggest no signs of publication bias. On the contrary, the study design turned to be a substantial determinant of the primary literature findings. The thesis provides a unique overview for this is the first meta-analysis conducted on the daylight saving time energy savings. Powered by TCPDF (www.tcpdf.org)
|
|
|
A Meta-Analysis of the Effect of Minimum Wage Increases on Prices
Vavřičková, Jana ; Havránek, Tomáš (advisor) ; Švarcová, Natálie (referee)
As an economically as well as politically sensitive topic, labor market interventions stir up discussions among professionals as well as general public. Most economists take negative stance against minimum wage policies providing arguments backed by theoretical reasoning rather then sound empirical evidence. Knowledge of labor market outcomes and their transmission channel to other segments of the economy are till nowadays limited and inconsistent. Neither empirical research in the field contributes to a uniform consent on the impact of minimum wage hikes on the price level. Moreover, the reported estimates display large heterogeneity and after a brief inspection reveal that the field is infested with publication selectivity. A uniquely constructed dataset consisting of 469 estimates of the price effect of minimum wage changes and their associated characteristics is analyzed using a set of statistical tools generally known as meta-analysis. The method is a powerful tool nowadays widely used in empirical research to synthesize and systematically evaluate sometimes inconsistent research results. While the study finds no consistent evidence of an actual link between minimum wage hikes and inflationary pressures, the empirical results show strong presence of publication selectivity. Powered by TCPDF (www.tcpdf.org)
|
|
| |
|
|
Six Essays on Meta-Regression Analysis
Havránková, Zuzana ; Dědek, Oldřich (advisor) ; Cahlík, Tomáš (referee) ; Babecký, Jan (referee) ; Fidrmuc, Jarko (referee)
This dissertation thesis consists of six papers on macroeconomics, international economics, and energy economics. All the papers are tied together by the use of meta-regression analysis, which is essential for the derivation of robust policy-relevant conclusions from often conflicting results presented in the empirical literature. I use meta-analysis to quantitatively synthesize the reported research results on a given topic, correct the literature for publication selection bias, and filter out the effect of various misspecifications present in some primary studies. My results can be summarized as follows: 1) The elasticity of intertemporal substitution in consumption, a key input to all dynamic models in finance and macroeconomics, varies significantly across countries. The differences can be explained by the level of stock market participation, when countries with higher participation exhibit larger values of the elasticity; the mean reported elasticity is 0.5. 2) The effect of borders on international trade, which most authors find to be surprisingly large, can be explained away by innovations in methodology introduced in the last decade. When these innovations are taken into account jointly, the border effect disappears for developed countries, and is relatively small for developing countries. 3) When...
|
|
|
Publication Bias in Measuring Anthropogenic Climate Change
Rečková, Dominika ; Havránek, Tomáš (advisor) ; Zeynalov, Ayaz (referee)
People around the world are interested in climate changes. Especially the impact of human being on climate changes plays an important role in the policy discussion about environment. One of the measures of anthropogenic climate change is climate sensitivity. The main aim of this thesis is to apply meta-analysis methodology on relationship between human activity and climate change. Until now, tens to hundreds of studies have been written on this topic, but only few report the estimate of climate sensitivity. Despite majority of the studies refer to recognizable influence of human activity on the climate change, the results of individual studies do not correspond in absolute values perfectly. Until now only one meta-analysis concerns publication bias in literature covering climate change, it uses vote- counting and detects publication selectivity efforts. But no meta-regression analysis was published on this topic yet. The thesis investigates if the results of studies reporting climate sensitivity are influenced with the effort to publish only positive and significant estimates. It applies effective statistic instrument, meta- regression analysis, that allows systematic evaluation of an inconsistent sample of estimates. This method was applied on the data set consisting of 48 estimates coming from 16 studies....
|
guest ::
