Skewness into the Product of Two Normally Distributed Variables and the Risk Consequences
![Thumbnail](/dspace/bitstream/handle/2183/25706/Oliveira_O_2015_Skewness_distributed_variables.pdf.jpg?sequence=4&isAllowed=y)
Use este enlace para citar
http://hdl.handle.net/2183/25706Colecciones
- GI-C+D - Artigos [116]
Metadatos
Mostrar el registro completo del ítemTítulo
Skewness into the Product of Two Normally Distributed Variables and the Risk ConsequencesFecha
2016Resumen
[Abstract:]The analysis of skewness is an essential tool for decision-making since it can be used
as an indicator on risk assessment. It is well known that negative skewed distributions
lead to negative outcomes, while a positive skewness usually leads to good scenarios
and consequently minimizes risks. In this work the impact of skewness on risk analysis
will be explored, considering data obtained from the product of two normally
distributed variables. In fact, modelling this product using a normal distribution is
not a correct approach once skewness in many cases is di erent from zero. By ignoring
this, the researcher will obtain a model understating the risk of highly skewed
variables and moreover, for too skewed variables most of common tests in parametric
inference cannot be used. In practice, the behaviour of the skewness considering the
product of two normal variables is explored as a function of the distributions parameters:
mean, variance and inverse of the coe cient variation. Using a measurement
error model, the consequences of skewness presence on risk analysis are evaluated by
considering several simulations and visualization tools using software R([10])
Palabras clave
Inverse Coe
Product of normal variables
Inverse coefficient of variation
Probability risk analysis
Measurement error model
Product of normal variables
Inverse coefficient of variation
Probability risk analysis
Measurement error model
Versión del editor
ISSN
1645-6726