Working Papers 2014 by Andres Ramirez Hassan
The gravity model is a workhorse tool that has been widely used in international trade. However, ... more The gravity model is a workhorse tool that has been widely used in international trade. However, one empirical question that frequently arises is related to the conceptualization and measurement of distance. To overcome this limitation, our study proposes an index of distance based on multivariate statistical analysis. Specifically, we build our index using Factorial Analysis for Mixed Data. For robustness check, we use Principal Component Analysis. Both techniques summarize in one factor information related to geographical, cultural, political and economic variables that might affect international trade between countries. We use this index as proxy of distance, and Gross Domestic Product as proxy of mass, and we run some panel data exercises between 1995 and 2000 for 10 Latin American economies. Estimations indicate that the sign of the load factors in Factor Analysis for Mixed Data are intuitively plausible, and that panel data exercises give sensible robust outcomes.
In this paper we analyze the effect of four possible alternatives regarding the prior distributio... more In this paper we analyze the effect of four possible alternatives regarding the prior distributions in a linear model with autoregressive errors to predict piped water consumption: Normal-Gamma, Normal-Scaled Beta two, Studentized-Gamma and Student's t-Scaled Beta two. We show the effects of these prior distributions on the posterior distributions under different assumptions associated with the coefficient of variation of prior hyperparameters in a context where there is a conflict between the sample information and the elicited hyperparameters. We show that the posterior parameters are less affected by the prior hyperparameters when the Studentized-Gamma and Student's t-Scaled Beta two models are used. We show that the Normal-Gamma model obtains sensible outcomes in predictions when there is a small sample size. However, this property is lost when the experts overestimate the certainty of their knowledge. In the case that the experts greatly trust their beliefs, it is a good idea to use Student's t distribution as the prior distribution, because we obtain small posterior predictive errors. In addition, we find that the posterior predictive distributions using one of the versions of Student's t as prior are robust to the coefficient of variation of the prior parameters. Finally, it is shown that the Normal-Gamma model has a posterior distribution of the variance concentrated near zero when there is a high level of confidence in the experts' knowledge: this implies a narrow posterior predictive credibility interval, especially using small sample sizes.
Papers by Andres Ramirez Hassan
SSRN Electronic Journal, 2022
SSRN Electronic Journal, 2008
Una función de producción agregada para la economía colombiana: características e interacción ent... more Una función de producción agregada para la economía colombiana: características e interacción entre el trabajo calificado, el trabajo no calificado y el capital, 1994-2005.
SSRN Electronic Journal, 2008
Consequences of omitting relevant inputs on the quality of the data envelopment analysis under di... more Consequences of omitting relevant inputs on the quality of the data envelopment analysis under different input correlation structures
Ecos De Economia Issn 1657 4206, Apr 12, 2011
El presente artículo hace una comparación entre dos maneras de estimar el spread de los rendimien... more El presente artículo hace una comparación entre dos maneras de estimar el spread de los rendimientos de los bonos del gobierno colombiano, como son: la metodología de Nelson & Siegel y una metodología basada en el cálculo del spread a través de la Tasa Interna de Retorno de títulos transados en el mercado; para así estudiar si existe XQD UHODFLyQ VLJQLÀFDWLYD HQWUH GLFKR VSUHDG \ OD SUREDELOLGDG GH TXH HQ XQ SHULRGR GH DQiOLVLV HVSHFtÀFR OD FXUYD GH UHQGLPLHQWRV VLUYD FRPR SUHGLFWRU GH OD DFWLYLGDG HFRQyPLFD \ HVSHFtÀFDPHQWH VL HVWH LQVWUXPHQWR HVWi HQ FDSDFLGDG GH GHWHFWDU episodios de recesión. Para tal efecto, se construyen varios modelos binomiales bajo enfoques frecuentistas y bayesianos. Los resultados encontrados sugieren que la FXUYD GH UHQGLPLHQWRV SRU Vt VROD QR EULQGD OD LQIRUPDFLyQ VXÀFLHQWH D ORV KDFHGRUHV de política para tomar las decisiones que afectarán el comportamiento de la economía futura; ya que el spread esconde expectativas de diferentes tipos, como expectativas GH LQÁDFLyQ GH SROtWLFD ÀVFDO \R GH JDVWR S~EOLFR SRU OR FXDO HV GLItFLO DUJXPHQWDU TXp comportamientos del spread obedecen a cada una de estas expectativas, pues aunque éstas se encuentran relacionadas, dicha relación no es perfecta.
SSRN Electronic Journal, 2014
In this paper we analyze the effect of four possible alternatives regarding the prior distributio... more In this paper we analyze the effect of four possible alternatives regarding the prior distributions in a linear model with autoregressive errors to predict piped water consumption: Normal-Gamma, Normal-Scaled Beta two, Studentized-Gamma and Student's t-Scaled Beta two. We show the effects of these prior distributions on the posterior distributions under different assumptions associated with the coefficient of variation of prior hyperparameters in a context where there is a conflict between the sample information and the elicited hyperparameters. We show that the posterior parameters are less affected by the prior hyperparameters when the Studentized-Gamma and Student's t-Scaled Beta two models are used. We show that the Normal-Gamma model obtains sensible outcomes in predictions when there is a small sample size. However, this property is lost when the experts overestimate the certainty of their knowledge. In the case that the experts greatly trust their beliefs, it is a good idea to use Student's t distribution as the prior distribution, because we obtain small posterior predictive errors. In addition, we find that the posterior predictive distributions using one of the versions of Student's t as prior are robust to the coefficient of variation of the prior parameters. Finally, it is shown that the Normal-Gamma model has a posterior distribution of the variance concentrated near zero when there is a high level of confidence in the experts' knowledge: this implies a narrow posterior predictive credibility interval, especially using small sample sizes.
In this paper is analyzed the macroeconomic effects associated with increases in the capital tax ... more In this paper is analyzed the macroeconomic effects associated with increases in the capital tax rate and labor tax rate under a Neoclassical model with elastic labor supply and positive externalities due to government's spending. It is found that these policies reduce the production, the investment and the labor supply; however, the effects over the consumption are different. It is concluded that tax reforms based on labor income is more contractive that tax reforms based on capital income.
Este estudio pretende analizar empíricamente la condición Marshall-Lerner en la economía Colombia... more Este estudio pretende analizar empíricamente la condición Marshall-Lerner en la economía Colombiana tomando como marco de referencia el período 1980-2001. El efecto de una depreciación de la tasa de cambio real sobre la balanza comercial en el largo plazo es analizado utilizando el procedimiento de cointegración de Johansen, bajo un modelo cuya especificación seguirá los desarrollos recientes de macroeconomía abierta basados en agente representativo y optimización dinámica. Luego del análisis econométrico se realizará una revisión sobre las implicaciones de política económica.
elac.uca.edu.ni
This paper shows an academic exercise in order to understand the bases of economic growth theory.... more This paper shows an academic exercise in order to understand the bases of economic growth theory. First of all, we develop some fundamental ideas about the economic growth theory. Second, we take specifically the Harrod (1939)-Domar (1946) model, and we develop the mathematical structure implicitly in that model, and finally we do a simulation exercise, this one shows the restrictions inside the model's equilibrium.
SSRN Electronic Journal, 2020
Model uncertainty remains a persistent concern when exploring the drivers of civil conflict and c... more Model uncertainty remains a persistent concern when exploring the drivers of civil conflict and civil war. Considering a comprehensive set of 34 potential determinants in 175 post-Cold-War countries (covering 98.2% of the world population), we employ stochastic search variable selection (SSVS) to sort through all 234 possible models. Looking across both cross-sectional and panel data, three robust results emerge. First, past conflict constitutes the most powerful predictor of current conflict: path dependency matters. Second, larger shares of Jewish, Muslim, or Christian citizens are associated with increased chances of conflict incidence and onset - a result that is independent of religious fractionalization, polarization, and dominance. Third, economic and political factors remain less relevant than colonial origin and religion. These results lend credence to several existing schools of thought on civil conflict and provide new avenues for future research.
Documentos De Trabajo Cief, 2011
Maquinaria y equipo Equipo de transporte Construcciones y edificaciones Año Maquinaria y equipo E... more Maquinaria y equipo Equipo de transporte Construcciones y edificaciones Año Maquinaria y equipo Equipo de transporte Construcciones y edificaciones * Los intervalos se encuentran estipulados al 95% de confianza. Fuente. Cálculos propios. Como se puede evidenciar el modelo replica relativamente bien la dinámica observada en la economía colombiana en el período 2000-2006, lo cual está asociado a que el coeficiente de ajuste de la ecuación del capital en el modelo de corrección de errores es superior al 90%. Como se puede evidenciar en los gráficos 5, 6 y 7, aunque la inversión en edificaciones que captura el sistema es bastante cercana a la observada, esta característica no se transfiere tajantemente a la inversión en maquinaria y equipo de transporte, lo cual obedece a que la bondad de ajuste de las ecuaciones derivadas del modelo translogarítmico en general son inferiores al 50%. Gráfico 14. Series de inversión real en edificaciones y de inversión simulada por el sistema (a pesos constantes del 2000). Colombia, 1970-2006 * * Desviaciones estándar entre paréntesis Fuente. Cálculos propios.
Social Science Research Network, 2014
SSRN Electronic Journal
Food price elasticities (PE) are essential for evaluating impacts of food pricing interventions. ... more Food price elasticities (PE) are essential for evaluating impacts of food pricing interventions. Existing econometric estimates of food PEs are often poor, being based on single observational data sets without much variation in prices and failing to utilise prior information. In order to provide better PE estimates for policy analysis, this paper innovates the use of experimental purchasing data from a recent virtual supermarket experiment to estimate the PE matrix for a large set of foods via a Linear Almost Ideal Demand System (AIDS) and proposes an approach to incorporate PE results from observational data studies in the empirical results within a Bayesian estimation framework. We combine a multi-stage Bayesian approach to estimate a set of demand systems using the Edgerton approach to aggregate elasticities to obtain Marshallian and Hicksian PE matrices for a total of 23 food groups.
Econometrics: Single Equation Models eJournal, 2013
Spanish Abstract: El objetivo de este articulo es identificar determinantes que llevan a los indi... more Spanish Abstract: El objetivo de este articulo es identificar determinantes que llevan a los individuos a tomar la decision de ser empresarios en Medellin AM en 2009. Mediante modelos Logit y Probit Multinomial, y Logit Binario secuencial, se estima la probabilidad de que una persona tome la decision ocupacional de ser empresario, independiente formal, empleado o independiente informal, siendo el primer estado aquel que genera mayor efecto en el desarrollo de la region. Los resultados permiten observar que la educacion, el uso de tecnologias de informacion y telecomunicaciones, y el capital financiero son las variables que mas contribuyen en la probabilidad de ser empresario. Estos resultados sugieren nuevos elementos a la discusion de politica publica relacionada con el emprendimiento y fortalecimiento empresarial. English Abstract: The main objective of this paper is to identify key factors that determine the decision of an individual to become an entrepreneur in the Medellin Metr...
arXiv: Econometrics, 2018
Central to many inferential situations is the estimation of rational functions of parameters. The... more Central to many inferential situations is the estimation of rational functions of parameters. The mainstream in statistics and econometrics estimates these quantities based on the plug-in approach without consideration of the main objective of the inferential situation. We propose the Bayesian Minimum Expected Loss (MELO) approach focusing explicitly on the function of interest, and calculating its frequentist variability. Asymptotic properties of the MELO estimator are similar to the plug-in approach. Nevertheless, simulation exercises show that our proposal is better in situations characterized by small sample sizes and noisy models. In addition, we observe in the applications that our approach gives lower standard errors than frequently used alternatives when datasets are not very informative.
Revista Ingenierias Universidad De Medellin, 2007
In this paper, we analyze different methodologies that are used to handle short term interest rat... more In this paper, we analyze different methodologies that are used to handle short term interest rate volatility. Specifically, we shall analyze the outcomes that are obtained through three specifications: CKLS, Conditional Heteroscedastic and BHK. The evidence shows that the best specification is reached through the EGARCH model. It is found that positive shocks in the short term interest rate cause a volatility 22.3% higher than negative shock of the same size. Also, the process converges to an unconditioned mean of 7.11% with a correction factor of 1.2% daily. It is found that the model offers good forecast in a period of three months.
Documentos De Trabajo Cief, 2011
Uploads
Working Papers 2014 by Andres Ramirez Hassan
Papers by Andres Ramirez Hassan
short-term elasticities estimates of the beef demand in Colombia using
quarterly data since 1998 until 2007. However, complexity on the decision
process of consumption should be taken into account, since expenditure
on a particular good is sequential. In the case of beef demand in Colom-
bia, a Multi-Stage process is proposed based on an Almost Ideal Demand
System (AIDS). The econometric novelty in this paper is to estimate si-
multaneously all the stages by the Generalized Method of Moments to
obtain a joint covariance matrix of parameters estimates in order to use
the Delta Method for calculating the standard deviation of the long-term
elasticities estimates. Additionally, this approach allows us to get elastic-
ities estimates in each stage, but also, total elasticities which incorporates
interaction between stages. On the other hand, the short-term dynamic is
handled by a simultaneous estimation of the Error Correction version of
the model; therefore, Monte Carlo simulation exercises are performed to
analyse the impact on beef demand because of shocks at di erent levels
of the decision making process of consumers. The results indicate that,
although the total expenditure elasticity estimate of demand for beef is
1.78 in the long-term and the expenditure elasticity estimate within the
meat group is 1.07, the total short-term expenditure elasticity is merely
0.03. The smaller short-term reaction of consumers is also evidenced on
price shocks; while the total own price elasticity of beef is -0.24 in the
short-term, the total and within meat group long-term elasticities are -
1.95 and -1.17, respectively.
la tasa de interés a corto plazo. Específicamente se analizarán los resultados que se
obtienen a través de la especificación CKLS, Heterocedasticidad Condicionada y
Mixta. Los hechos estilizados enseñan que la mejor especificación para describir el
proceso generador de la tasa de interés interbancaria en la economía colombiana
para el período 2001–2006 es el modelo EGARCH. Se encuentra que las
innovaciones positivas en la tasa de interés ocasionan una volatilidad 22,3% mayor
que innovaciones negativas de la misma magnitud. Además, el proceso converge a
una media no condicionada de 7,11% con una corrección diaria del 1,2%. Se
encuentra que el modelo ofrece pronósticos relativamente sensatos a un plazo de tres
meses.
trabajo calificado, el trabajo no calificado y el capital que se obtienen asumiendo una
función de producción agregada translogarítmica para la economía colombiana. En general se encuentra que el trabajo calificado ha ganado participación al interior del proceso
productivo en detrimento del trabajo no calificado y el capital. En general, los factores productivos son bienes normales, pero el trabajo calificado es el que reacciona más
fuertemente ante expansión en el producto. Por otra parte, el trabajo no calificado es el factor productivo que presenta el mayor valor absoluto de la elasticidad precio de la
demanda. Finalmente, se evidencia una relación de complementariedad entre el trabajo calificado y los otros dos factores, pero se presenta una relación de sustitubilidad entre el capital y el trabajo no calificado. Este acontecimiento microeconómico, unido al
abaratamiento del costo de uso del capital y el encarecimiento del trabajo no calificado
explican el poco descenso que ha experimentado la tasa de desempleo en la economía colombiana, pese al buen desempeño macroeconómico reciente.
of the data envelopment analysis. Specifically, the case of omitting a relevant variable in
the input oriented problem is analyzed when there are different correlation structures
between the inputs. It is established that the correlation matrix gives relevant information
about the homogeneity of the decision making units and the intensity of inputs used in the
production process. The methodology is based on a series of Monte Carlo simulations and
the quality of the data envelopment analysis is measured as the difference between the true
efficiency and the efficiency calculated. It is found that omitting relevant inputs causes
inconsistency, and this problem is worse when there is a negative correlation structure.
mientras que el ranking universitario está inversamente relacionado con dicha probabilidad. Por otra parte, se encuentra que la posición socioeconómica, medida a través del estrato, es una variable bastante explicativa de la elección universitaria; específicamente, los bachilleres provenientes de
estratos bajos y medios tienden a optar por universidades públicas, mientras que los bachilleres de estratos altos seleccionan universidades privadas.
evolución tarifaria si no se hubiese presentado la reforma de los 90’s. Así mismo, estima las elasticidades precio y gasto para dichos servicios mediante el Sistema Casi Ideal de
Demanda (AIDS) y con el cálculo de la variación equivalente establece si la regulación generó una mejora en el bienestar de los consumidores.
lograr la transformación social y económica de Colombia. Muestra de esta
hipótesis, son el creciente número de trabajos académicos y políticas
encaminadas a fomentar la actividad emprendedora en el país y sus regiones. Por
tanto, se quiere contrastar lo observado en la literatura aplicado al caso de
Medellín Área Metropolitana para el año 2009, con el fin de aportar a la discusión
sobre los determinantes y políticas de creación y fortalecimiento de empresas. De
esta forma, dadas unas características socioeconómicas de los individuos y la
región se quiere conocer cuál es probabilidad de que una persona sea empresaria,
independiente formal, empleada o independiente informal, siendo el primer
estado aquel que genera mayor efecto en el crecimiento y desarrollo de la región.
Para ello, se utilizan tres modelo de elección discreta, tales como logit y probit
multinomial, y logit binario secuencial, que permiten observar que la educación,
uso de tecnologías de información y telecomunicaciones, y el capital financiero
son variables que más contribuyen en la probabilidad de ser empresario.