Published

2010-01-01

BONDAD DE AJUSTE EMPLEANDO LA FUNCIÓN GENERADORA DE MOMENTOS

GOODNESS-OF-FIT EMPLOYING THE MOMENT GENERATING FUNCTION

Keywords:

bondad de ajuste, función generadora de momentos, simulación (es)
Goodness-of-fit, Moment generating function, Simulation (en)

Authors

  • Luis Alfonso Muñoz Institución Educativa Técnico San Juan Bautista
  • Jorge Humberto Mayorga Universidad Nacional de Colombia
Proponemos una estadística para evaluar la bondad de ajuste, donde se emplearon las funciones generatrices de momentos muestral y poblacional; a partir de la información considerada se encontró que la estadística Gn tuvo un comportamiento diferente de acuerdo con el modelo usado para el ajuste. Su desempeño fue superior o igual a la estadística de Pearson, pero fue superada por la estadística de K-S; además, para la estadística evaluada no fue influyente el tamaño de la muestra.
We propose a statistic to evaluate the goodness-of-fit where we used the empirical moment generating function and the moment generating function, from the considered information it found that the Gn statistic was different behavior according to the used model for the fitting. Its behavior was great or similar to the Pearson statistics, but it was exceeded for the K-S statistic, also for the evaluated statistic was not influential to the sample size.

Downloads

Download data is not yet available.

References

Cabaña, A. & Quiroz, J. (2005), `Using the Empirical Moment Generating Function in Testing for the Weibull an the Type I Extreme Distributions', Test 12(2), 417-431.

Collander, R. & Chalfant, J. (1985), An alternative Approach to Decisions under Uncertainty: The Empirical Moment Generating Function, Work Paper, Universiy of California, Department of Agricultural and Resources Economics.

Conover, W. (1999), Practicad Nonparametric Statistics, third edn, John Wiley, United States of America.

Csorgo, S. (1981), `Multivariate Empirical Characteristic Function. Zeitschrift für Wahrscheintichkeits-Theoric und Verwandte Gabiete', Annals of Probabidity (55), 203-229.

Csorgo, S. (1986), `Testing for Normality in Arbitrary Dimension', Annals of Sta-tistics 14(2), 708-723.

Csorgo, S. & Heathcote, C. (1987), Testing for Symetry', Biometrika 1(74), 177-184.

Epps, T. Sc Pulley, L. (1985), l'wo Test of fit Based on the Sample Characteristic Function with Applications to Exponentiality, Paper presented at the annual meeting of the American Statistical Association, Las Vegas, NE.

Feuerverger, A. & Mureika, A. (1977), 'The Empirical Characteristic Function and its Applications', Annals of Statistics (5), 88-97.

Heathcote, C. (1977), 'The Integrated Squared Error Estimation of Parameters', Biometrika 2(64), 255-264.

Koutrouvelis, I. (1980), 'A goodness-of-fit Test of Simple Hypotheses Based on the Empirical Characteristic Function', Biometrika 1(67), 238-240.

Koutrouvelis, I. Sc Kellermeier, J. (1981), 'A goodness-of-fit Test Based on the Empirical Characteristic Function when Parameters must be Estimated', Journal of the American Statistical Association 2(43), 173-176.

Meintanis, S. (2007), 'A Kolmogorov-Smirnov Type Test for Skew Normal Dis-tributions Based on the Empirical Moment Generating Function', Journal of Statistical Planning and Inference 137(8), 2681-2688.

Mood, A., Graybill, F. & Boes, D. (1974), Introduction to the Theory of Statistics, third edn, McGraw-Hill, Singapore.

Muñoz, L. (1998), Bondad de ajuste empleando la función generadora de momentos, Tesis de maestría, Departamento de Estadística, Universidad Nacional de Colombia, Bogotá, Colombia.

Quand, R. & Ramsey, J. (1978), Tstimating Mixtures of Normal Distributions and Switching Regressions', Journal of the American Statistical Association (73), 730-741.