Browsing by Autor "Darwin Ugarte Ontiveros"

Now showing 1 - 6 of 6

Cognitive bias in insurance: Evidence from a health scheme in India
(Elsevier BV, 2021) Jean‐Philippe Platteau; Darwin Ugarte Ontiveros
Cognitive Bias in Insurance: Evidence from India
(Federal Reserve Bank of St. Louis, 2017) Darwin Ugarte Ontiveros; Jean‐Philippe Platteau
This paper is an attempt to understand the factors behind low contract renewal rates frequently observed in insurance programs in poor countries. This is done on the basis of the experience of a micro-insurance health program in India. We show that poor understanding of the insurance concept, compounded by a serious supply-side information failure, is a major cause of low contract renewal among households which had previously enrolled into the program. Controlling for the level of their information about how to collect the insurance payout, households that did not experience a health shock during the first year tended to pull out of the scheme when they are subject to a cognitive bias reflected in short-term framing. When they are classic expected utility maximizers, however, the absence of a health shock did not affect their contract renewal decision. The policy implication of our findings is considerable since they provide a strong justification for mandatory universal health insurance.
Explaining the Gender Gap Dilemma in Microfinance
(RELX Group (Netherlands), 2023) Evelin Mamani Huayta; Darwin Ugarte Ontiveros
Outliers in Semi-Parametric Estimation of Treatment Effects
(RELX Group (Netherlands), 2017) Darwin Ugarte Ontiveros; Gustavo Canavire‐Bacarreza; Luis Castro Peñarrieta
Outliers in Semi-Parametric Estimation of Treatment Effects
(Multidisciplinary Digital Publishing Institute, 2021) Gustavo Canavire‐Bacarreza; Luis Castro Peñarrieta; Darwin Ugarte Ontiveros
Outliers can be particularly hard to detect, creating bias and inconsistency in the semi-parametric estimates. In this paper, we use Monte Carlo simulations to demonstrate that semi-parametric methods, such as matching, are biased in the presence of outliers. Bad and good leverage point outliers are considered. Bias arises in the case of bad leverage points because they completely change the distribution of the metrics used to define counterfactuals; good leverage points, on the other hand, increase the chance of breaking the common support condition and distort the balance of the covariates, which may push practitioners to misspecify the propensity score or the distance measures. We provide some clues to identify and correct for the effects of outliers following a reweighting strategy in the spirit of the Stahel-Donoho (SD) multivariate estimator of scale and location, and the S-estimator of multivariate location (Smultiv). An application of this strategy to experimental data is also implemented.
TÉCNICAS ROBUSTAS Y NO ROBUSTAS PARA IDENTIFICAR OUTLIERS EN EL ANÁLISIS DE REGRESIÓN
(2021) Darwin Ugarte Ontiveros; R. Guzmán
Verificar si los resultados de un modelo de regresión reflejan el patrón de los datos, o si los mismos se deben a unas cuantas observaciones atípicas (outliers) es un paso importante en el proceso de investigación empírica. Para este propósito resulta aún común apoyarse en procedimientos (estándares) que no son eficaces para este propósito, al sufrir del denominado “masking effect”, algunos de ellos sugeridos incluso en los libros tradicionales de econometría. El presente trabajo pretende alertar a la comunidad académica sobre el peligro de implementar estas técnicas estándares, mostrando el pésimo desempeño de las mismas. Asimismo, se sugiere aplicar otras técnicas más idóneas sugeridas en la literatura sobre “estadística robusta” para identificar outliers en el análisis multivariado. Para facilitar la aplicación de las mismas, el trabajo pone a disposición de la comunidad académica un programa en Stata del tipo do-file para identificar y categorizar outliers basado en el trabajo de [1]. Simulaciones de Monte Carlo dan evidencia de la aplicabilidad de la misma.