Showing 1 - 9 of 9
Este trabajo utiliza la Ley de Newcomb-Benford y las pruebas de Beber y Scacco para analizar las elecciones presidenciales desde 1958 hasta el 2006, las presidenciales de 1922, las elecciones de Congreso en 2010, y las votaciones para Alcalde en Cali del 2007. Este es el primer estudio y...
Persistent link: https://www.econbiz.de/10009324137
Este trabajo utiliza la Ley de Newcomb-Benford y las pruebas de Beber y Scacco para analizar las elecciones presidenciales desde 1958 hasta el 2006, las presidenciales de 1922, las elecciones de Congreso en 2010, y las votaciones para Alcalde en Cali del 2007. Este es el primer estudio y...
Persistent link: https://www.econbiz.de/10009391750
Este documento describe la metodología utilizada para implementar el índice ω a las pruebas SABER 5◦ y 9◦ realizadas por el ICFES en el 2009. Para validar la utilización de este índice se calculan el error tipo I y II. Adicionalmente, se comparan el índice ω y el índice κ en...
Persistent link: https://www.econbiz.de/10009643988
Este trabajo implementa la metodología de detección de copia en exámenes de múltiples opciones expuesta en Sotaridona, van der Linden y Meijer [2006] basada en el índice Kappa de Cohen. Presentamos los resultados de aplicar esta metodología a las pruebas del Estado ICFES 2009 II. Este es,...
Persistent link: https://www.econbiz.de/10008468484
Multiple choice exams are frequently used as an efficient and objective instrument to evaluate knowledge. Nevertheless, they are more vulnerable to answer-copying than tests based on open questions. Several statistical tests (known as indices) have been proposed to detect cheating but to the...
Persistent link: https://www.econbiz.de/10010891590
We introduce new risk groups to a standard capitation formula and evaluate risk selection incentives of insurers. The study uses a unique data set of almost 24 million affiliates to Government’s mandatory health insurance system. This data set is very rich in the sense of reporting all claims...
Persistent link: https://www.econbiz.de/10010891592
This paper provides first order conditions for a very general class of single or multi-unit auctions. Under mild conditions we characterize bidding-behavior and generalize previous standard results in the literature. As an application we obtain sufficient conditions for truth-telling, monotonic...
Persistent link: https://www.econbiz.de/10005082474
We show that even under incomplete markets, the equilibrium manifold identifies aggregate demand and individual demands everywhere in their domains. Moreover, under partial observation of the equilibrium manifold, we we construct maximal domains of identification. For this, we assume conditions...
Persistent link: https://www.econbiz.de/10005767820
Aloisio Araujo and Alvaro Sandroni have shown in [1] that in a complete-markets economy in which there are no exogenous bounds to financial trade, existence of equilibrium requires agents with prior beliefs that agree on zero-probability events, and, therefore, with asymptotically homogeneous...
Persistent link: https://www.econbiz.de/10005042160