2021-09-12
00:00 |
Shrinkage for Gaussian and t copulas in ultra-high dimensions
Anatolyev, Stanislav ; Pyrlik, Vladimir
Copulas are a convenient framework to synthesize joint distributions, particularly in higher dimensions. Currently, copula-based high dimensional settings are used for as many as a few hundred variables and require large data samples for estimation to be precise. In this paper, we employ shrinkage techniques for large covariance matrices in the problem of estimation of Gaussian and t copulas whose dimensionality goes well beyond that typical in the literature. Specifically, we use the covariance matrix shrinkage of Ledoit and Wolf to estimate large matrix parameters of Gaussian and t copulas for up to thousands of variables, using up to 20 times lower sample sizes. The simulation study shows that the shrinkage estimation significantly outperforms traditional estimators, both in low and especially high dimensions. We also apply this approach to the problem of allocation of large portfolios.
Detailed record
|
2021-09-12
00:00 |
Make your own luck: the wage gains from starting college in a bad economy
Bičáková, Alena ; Cortes, G. M. ; Mazza, J.
Using data for nearly 40 cohorts of American college graduates and exploiting regional variation in economic conditions, we show robust evidence of a positive relationship between the unemployment rate at the time of college enrollment and subsequent annual earnings, particularly for women. This positive relationship cannot be explained by selection into employment or by economic conditions at the time of graduation. Changes in major field of study account for only about 10% of the observed earnings gains. The results are consistent with intensified effort exerted by students who experience bad economic times at the beginning of their studies.
Detailed record
|
2021-09-12
00:00 |
Shifting punishment on minorities: experimental evidence of scapegoating
Bauer, Michal ; Cahlíková, J. ; Chytilová, Julie ; Roland, G. ; Želinský, T.
This paper provides experimental evidence showing that members of a majority group systematically shift punishment on innocent members of an ethnic minority. We develop a new incentivized task, the Punishing the Scapegoat Game, to measure how injustice affecting a member of one’s own group shapes punishment of an unrelated bystander (“a scapegoat”). We manipulate the ethnic identity of the scapegoats and study interactions between the majority group and the Roma minority in Slovakia. We find that when no harm is done, there is no evidence of discrimination against the ethnic minority. In contrast, when a member of one’s own group is harmed, the punishment ”passed” on innocent individuals more than doubles when they are from the minority, as compared to when they are from the dominant group. These results illuminate how individualized tensions can be transformed into a group conflict, dragging minorities into conflicts in a way that is completely unrelated to their behavior.
Detailed record
|
2021-08-22
00:07 |
Paternal circular migration and development of socio-emotional skills of children left behind
Adunts, Davit
This study investigates the short-run effect of paternal absence due to circular migration on the socio-emotional skills of their children left behind. To address the endogeneity of the migration decision, and building on previous studies, this study focuses on children whose fathers have all engaged in circular migration. Furthermore, using quasi-exogenous variation in the timing of return migration induced by bilateral migration laws between Ukraine and Poland, I circumvent the bias related to the return migration decision. The findings of this study suggest that current paternal absence due to circular migration negatively affects the socioemotional skills of children left behind. Overall, this result suggests that circular migration is not necessarily a „triple-win“ solution that benefits all involved parties.
Detailed record
|
2021-08-22
00:07 |
Firm relocations, commuting and relationship stability
Hrehová, Kristína ; Sandow, E. ; Lindgren, U.
In this paper, we study the impact of firm relocations on commuting distance and the probability of married couples and cohabiting couples with children separating. We use Swedish register data for 2010-2016 and select employees of relocating firms with one workplace and more than 10 employees. Focusing on this sample allows us to use plausibly exogenous variation in the commuting distance arising from the relocation. We extend the literature on the effect of commuting on relationship stability by reducing the possibility for unobserved time-variant factors to bias our estimates. While previous literature has focused on the difference between short- and long-distance commuting, we focus on changes in the commuting distance that are externally induced by firm management. We find a small but statistically significant negative effect of increased firm relocation distance on family stability. A 10 km change in commuting distance leads to a 0.09 percentage point higher probability of separation if the commuter remains with the firm for the next 5 years.
Detailed record
|
2021-08-22
00:07 |
Revealing private information in a patent race
Kocourek, Pavel
In this paper I investigate the role of private information in a patent race. Since firms often do their research in secrecy, the common assumption in patent race literature that firms know each other’s position in the race is questionable. I analyze how the dynamics of the game changes when a firm’s progress is its private information, and I address the question whether revealing it might be to a firm’s advantage. I find that a firm has an incentive to reveal its breakthrough only if its rival has not done so, and only if the research is costly.
Detailed record
|
2021-08-22
00:07 |
Sequential vote buying
Chen, Y. ; Zápal, Jan
To enact a policy, a leader needs votes from committee members with heterogeneous opposition intensities. She sequentially offers transfers in exchange for votes. The transfers are either promises paid only if the policy passes or paid up front. With transfer promises, a vote costs nearly zero. With up-front payments, a vote can cost significantly more than zero, but the leader is better off with up-front payments. The leader does not necessarily buy the votes of those least opposed. The opposition structure most challenging to the leader involves either a homogeneous committee or a committee with two homogenous groups. Our results provide an explanation for several empirical regularities: lobbying of strongly opposed legislators, the Tullock Paradox and expansion of the whip system in the U.S. House concurrent with ideological homogenization of parties. We also discuss several extensions including private histories and simultaneous offers.
Detailed record
|
2021-07-11
00:00 |
Detailed record
|
2021-06-27
00:00 |
Detailed record
|
2021-06-27
00:00 |
Práce z domova: možnost, nebo nutnost?
Grossmann, Jakub ; Korbel, Václav ; Münich, Daniel
Studie mapuje rozsah vyuţívání práce z domova v České republice během koronavirového roku 2020 napříč sociodemografickými skupinami. Ukazuje, jak s přechodem na práci z domova souvisí charakteristiky pracujících, jako jsou vzdělání, odvětví, pohlaví, péče o menší dítě v domácnosti. Analýza také odhaluje vnímané překáţky a výhody práce z domova.
Detailed record
|
|
|
|
guest ::
