• Journal of the Korean Data and Information Science Society
• /
• v.24 no.6
• /
• pp.1465-1475
• /
• 2013

The chi-square type test statistic is the most commonly used test in terms of measuring testing goodness-of-fit for multinomial logistic regression model, which has its grouped data (binomial data) and ungrouped (binary) data classified by a covariate pattern. Chi-square type statistic is not a satisfactory gauge, however, because the ungrouped Pearson chi-square statistic does not adhere well to the chi-square statistic and the ungrouped Pearson chi-square statistic is also not a satisfactory form of measurement in itself. Currently, goodness-of-fit in the ordinal setting is often assessed using the Pearson chi-square statistic and deviance tests. These tests involve creating a contingency table in which rows consist of all possible cross-classifications of the model covariates, and columns consist of the levels of the ordinal response. I examined goodness-of-fit tests for a proportional odds logistic regression model-the most commonly used regression model for an ordinal response variable. Using a simulation study, I investigated the distribution and power properties of this test and compared these with those of three other goodness-of-fit tests. The new test had lower power than the existing tests; however, it was able to detect a greater number of the different types of lack of fit considered in this study. I illustrated the ability of the tests to detect lack of fit using a study of aftercare decisions for psychiatrically hospitalized adolescents.

• Communications for Statistical Applications and Methods
• /
• v.26 no.2
• /
• pp.191-203
• /
• 2019

The problem of examining how well an assumed distribution fits the data of a sample is of significant and must be examined prior to any inferential process. The observed failure time data of items are often not wholly available in reliability and life-testing studies. Lowering the expense and period associated with tests is important in statistical tests with censored data. Goodness-of-fit tests for perfect data can no longer be used when the observed failure time data are progressive Type II censored (PC) data. Therefore, we propose goodness-of-fit test statistics and a graphical method based on generalized Lorenz curve for PC data from a location-scale distribution. The power of the proposed tests is then assessed through Monte Carlo simulations. Finally, we analyzed two real data set for illustrative purposes.

• Journal of applied mathematics & informatics
• /
• v.26 no.1_2
• /
• pp.177-189
• /
• 2008

In this paper, we have considered an investigation on goodness of fit tests based on divergence measures. In the case of categorical data, under certain regularity conditions, we obtained asymptotic distribution of these tests. Also, we have proposed a modified test that improves the rate of convergence. In continuous case, we used our modified entropy estimator [10], for Kullback-Leibler information estimation. A comparative study based on simulation results is discussed also.

• Communications for Statistical Applications and Methods
• /
• v.6 no.3
• /
• pp.967-976
• /
• 1999

In this paper we study the Hellinger distance based goodness-of-fit tests that are analogs of likelihood ratio tests. The minimum Hellinger distance estimator (MHDE) in normal models provides an excellent robust alternative to the usual maximum likelihood estimator. Our simulation results show that the Hellinger deviance test (Simpson 1989) based goodness-of-fit test is robust when data contain outliers. The proposed hellinger deviance test(Simpson 1989) is a more direcct method for obtaining robust inferences than an automated outlier screen method used before the likelihood ratio test data analysis.

• Journal of the Korean Statistical Society
• /
• v.23 no.2
• /
• pp.379-402
• /
• 1994

Graphical and numerical methods for checking the assumption of proportional hazards of Cox model for censored survival data are discussed. The strenths and weaknessess of several goodness of fit tests for the propotional hazards for the two-sample problem are evaluated with Monte Carlo simulations, and the tests of Schoenfeld (1980), Andersen (1982), Wei (1984), and Gill and Schumacher (1987) are considered. The goodness of fit methods are illustrated with the survival data of patients who had chronic liver disease and had been treated with the endoscopy injection sclerotheraphy. Two other examples of data known to have nonpropotional hazards are also used in the illustration.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.233-238
• /
• 2003

Goodness of fit test statistics based on the information discrepancy have been shown to perform very well (Vasicek 1976, Dudewicz and van der Meulen 1981, Chandra et al 1982, Gohkale 1983, Arizona and Ohta 1989, Ebrahimi et al 1992, etc). Although the test is well defined for the non-censored case, censored case has not been discussed in the literature. Therefore we consider a goodness of fit test based on the partial Kullback-Leibler(KL) information with the type II censored data. We derive the partial KL information of the null distribution function and a nonparametric distribution function, and establish a goodness of fit test statistic. We consider the exponential and normal distributions and made Monte Calro simulations to compare the test statistics with some existing tests.

• Communications for Statistical Applications and Methods
• /
• v.8 no.2
• /
• pp.483-497
• /
• 2001

When one fits a parametric density function to a data set, it is usually advisable to test the goodness of the postulated model. In this paper we study the nonparametric tests for testing the null hypothesis against general alternatives, when the null hypothesis specifies the density function up to unknown parameters. We modify the test statistic which was proposed by the first author and his colleagues. Asymptotic distribution of the modified statistic is derived and its performance is compared with some other tests through simulation.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.889-902
• /
• 2013

Several goodness-of-fit test statistics have been proposed for a multinomial logit regression model; however, the properties of the proposed tests were not adequately studied. This paper evaluates three different goodness-of-fit tests using grouping strategies, proposed by Fagerland et al. (2008), Bull (1994), and Pigeon and Heyse (1999). In addition, Pearson (1900)'s method is also examined as a reference. Simulation studies were conducted to evaluate the four methods in terms of null distribution and power. A real data example is presented to illustrate the methods.

• International Journal of Reliability and Applications
• /
• v.8 no.1
• /
• pp.41-51
• /
• 2007

In this paper, we use the moments of order statistics derived by Lieblein (1955) to develop the correlation goodness-of-fit test for the Rayleigh distribution. In such we simulate the percentage points of the test statistics for the one-parameter and two-parameter cases. In addition, we calculate the power of the proposed tests based on some alterative distributions. Finally, we apply the procedures developed in the paper to some real data.

• Journal of the Korean Data and Information Science Society
• /
• v.6 no.1
• /
• pp.31-37
• /
• 1995

We consider density estimates of the usual type generated by a kernel function. By using the limit theorems for the maximum of normalized deviation of the estimate from its expected value, we propose to use data dependent bandwidth in the tests of goodness of fit based on these statistics. Also a small sample Monte Carlo simulation is conducted and proposed method is compared with Kolmogorov-Smirnov test.