Esther Hochsztain

Esther Hochsztain

Auto-generated profile, based on publicly available information

Esther Hochsztain

Dept. de Metodos Matematico Cuantitativos, Univ. de la Republica, Montevideo, Uruguay

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 December 2017 in Communications in Statistics - Theory and Methods
Verified
Journal Article
Closed access
CLCarlos López-Vázquez
Carlos López-Vázquez
EHEsther Hochsztain
Esther Hochsztain
The Friedman's test is used for assessing the independence of repeated experiments resulting in ranks, summarized as a table of integer entries ranging from 1 to k, with k columns and N rows. For its practical use, the hypothesis testing can be derived either from published tables with exact values for small k and N, or using an asymptotic analytical approximation valid for large N or large k. The quality of the approximation, measured as the relative difference of the true critical values with respect those arising from the asymptotic approximation is simply not known. The literature review shows cases where the wrong conclusion could have been drawn using it, although it may not be the only cause of opposite decisions. By Monte Carlo simulation we conclude that published tables do not cover a large enough set of (k, N) values to assure adequate accuracy. Our proposal is to systematically extend existing tables for k and N values, so that using the analytical approximation for values outside it will have less than a prescribed relative error. For illustration purposes some of the tables have been included in the paper, but the complete set is presented as a source code valid for Octave/Matlab/Scilab etc., and amenable to be ported to other programming languages.

24 April 2015 in TEC Empresarial
Verified
Journal Article
Closed access
PDF file
MMMaría Messina
María Messina
EHEsther Hochsztain
Esther Hochsztain
El Centro de Emprendedurismo CCEEmprende de- sarrolla, desde 2007, un programa de apoyo a emprende- dores. Para mejorar su gestión, resulta de gran importancia analizar, en forma preliminar, los emprendimientos en una de dos categorías: éxito o fracaso. En este artículo se identifican los principales factores asociados al éxito de un emprendimiento y cómo se vincu- lan para anticipar el futuro del emprendimiento. Se presenta un caso de estudio con base en los datos de una encuesta realizada a emprendedores participantes del programa, aplicando técnicas de clasificación. Las dos técnicas utilizadas de data mining son árbol de decisión y regresión logística, en ambas se obtuvieron resultados coincidentes. Los hallazgos muestran que los dos elementos más relevantes para anticipar el éxito de un emprendimiento son contar con financiamiento y que, anteriormente, la situa- ción laboral del emprendedor sea trabajador independiente. Estos primeros resultados obtenidos en el estudio de caso revelan información útil acerca de las mejores formas de apoyo al emprendedor, cómo generar incentivos al em- prendedor y la definición de herramientas o actividades que incidan favorablemente en el éxito de los emprendimientos. Si bien desde la teoría o para otras realidades existe infor- mación sobre los factores que colaboran en la determina- ción del éxito, para la realidad del Uruguay no se identifican estudios similares. Abstract Since 2007, the CCEE Entrepreneurship Centre has developed a supporting program for entrepreneurs. A preliminary analysis to determine if the venture was successful or a failure is made to improve the program’s management . In this article, the authors identify the main factors associated with entrepreneurship’s success, and how they can anticipate entrepreneurship’s performance. The case study is based on a survey data applied to the Entrepreneurship Program participants. The two data mining techniques are decision trees and logistic regression. The results were consistent across both tech- niques. The findings show that the two most important elements to predict entrepreneurship’s success are fun- ding and previous experience as self-employed. The results provided very useful insight about the best ways to support entrepreneurship, how to encoura- ge entrepreneurs, and define tools or activities to impact positively ventures success in Uruguay, since similar stu- dies have not been developed.

18 August 2016
Verified
Conference Paper
Closed access
EHEsther Hochsztain
Esther Hochsztain
A geoportal is a basic component of a spatial data infrastructure, used for searching, viewing, and downloading spatial data and services. It can be considered as a web application acting as an access point to the shared geographic information, being the place where distributed geographic data and services can be discovered. A geoportal offers the opportunity for different type of organizations to make their data and services accessible for the whole community of internet users and geoportals usability is considered a key concept. From the organizations point of view, usability is related to how the geoportal can support people to perform their tasks effectively and efficiently. From the end-users' point of view, usability concerns to how a geoportal is perceived, in a satisfying manner, to support users tasks. In this paper we present a mining approach to discover patterns related to geoportals usability evaluation. A framework is proposed based on several data sources in order to identify geoportals strengths and weaknesses affecting usability. The requirements emerging and its implications are analyzed. A geoportal evaluation case study is presented, performing web server logs analysis and System Usability Scale (SUS) questionnaire experimental data analysis applying factor analysis and association rules.

18 August 2016
Verified
Conference Paper
Closed access
EHEsther Hochsztain
Esther Hochsztain
ATAndromaca Tasistro
Andromaca Tasistro
MMMaria Messina
Maria Messina
Creative entrepreneurship is considered an important factor in economic development achievement, specially in the knowledge-based society. Universities play a fundamental role in the process of entrepreneurial development and the entrepreneurship ecosystem.CCEEmprende is a program to support entrepreneurs developed by Facultad de Ciencias Económicas y de Administración - Universidad de la República, Uruguay. In this paper we present the use of data mining to improve decision making in entrepreneurship management, based on CCEEmprende projects data. A case study using several data mining and statistical techniques (association rules, decision trees, logistic regression) is developed with two goals: anticipating project success and identifying the most important factors related to project success/failure.

20 September 2002 in Lecture Notes in Computer Science
Verified
Book Chapter
Closed access
PDF file
EHEsther Hochsztain
Esther Hochsztain
SMSocorro Millán
Socorro Millán
Ernestina MenasalvasErnestina Menasalvas
Ernestina Menasalvas

18 August 2016
Verified
Conference Paper
Closed access
EHEsther Hochsztain
Esther Hochsztain
ATAndromaca Tasistro
Andromaca Tasistro
Most data mining, business intelligence and data warehousing university courses are focused in techniques and modeling. But they fail in teaching business understanding, prototyping and how to involve business users from the first stages of a business intelligence project. In this paper we review research related to business intelligence teaching identifying strengths and weaknesses of most common ways of teaching and learning. Following we describe our experience teaching business intelligence in different areas. We continue proposing a method to test the project business applications and the return of investment study.