Publication:
A tool for functional data analysis and experimentation

dc.contributor.advisor González-Barreto, David
dc.contributor.author Rosario-Román, Dennis
dc.contributor.college College of Engineering en_US
dc.contributor.committee Artiles León, Noel
dc.contributor.committee Deliz Álvarez, José R.
dc.contributor.department Department of Industrial Engineering en_US
dc.contributor.representative Rodríguez Solís, Rafael
dc.date.accessioned 2018-11-28T17:10:52Z
dc.date.available 2018-11-28T17:10:52Z
dc.date.issued 2005
dc.description.abstract The objective of this research is to demonstrate the necessity of the industry of the use of functional data analysis techniques in order to analyze experiments. The type of experiment analyzed has the peculiarity that the response is measured repeatedly through time or through a specific signal factor. Two case studies are used in order to test the three methods proposed. The first method is a Point-Wise approach in which a classical ANOVA is performed in each level of the signal factor. The second uses a basis to represent the collection of all the response functions in order to relate the coefficients of the basis representation with the factors of the experiment. The third approach is a modification of the second method. The only difference is that regions are predetermined and the basis is applied and analyzed in each region separately. The three methods are proved in order to determine their effectiveness. en_US
dc.description.abstract El objetivo de esta investigación es el demostrar la necesidad de utilizar el análisis de datos funcionales en experimentos industriales. El tipo de experimentos analizados tiene la peculiaridad de que la respuesta se mide repetidamente a lo largo de un factor señal. Dos casos de estudio fueron utilizados para probar los tres métodos propuestos. El primer método se basa en conducir un análisis de varianza en cada nivel del factor señal. El segundo se utiliza una base para representar todas las funciones. Los coeficientes de la base están asociados a los factores del experimento. El tercer método es una modificación del segundo; la única diferencia es que se crean regiones con respecto al factor señal. En cada región se aplica la base y se analizan los coeficientes de la misma. Los tres métodos fueron probados con el propósito de determinar su efectividad. en_US
dc.description.graduationYear 2005 en_US
dc.identifier.uri https://hdl.handle.net/20.500.11801/1538
dc.language.iso English en_US
dc.rights.holder (c)2005 Dennis Rosario Román en_US
dc.rights.license All rights reserved en_US
dc.subject Functional data analysis techniques en
dc.subject Experiment analysis en
dc.title A tool for functional data analysis and experimentation en_US
dc.type Thesis en_US
dspace.entity.type Publication
thesis.degree.discipline Industrial Engineering en_US
thesis.degree.level M.S. en_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ININ_RosarioRomanD_2005.pdf
Size:
2.97 MB
Format:
Adobe Portable Document Format
Description: