• The Korean Journal of Applied Statistics
• /
• v.22 no.5
• /
• pp.911-921
• /
• 2009

Receiver Operating Characteristic(ROC) and Cumulative Accuracy Profile(CAP) curves are two methods used to assess the discriminatory power of different credit-rating approaches. The points of optimal classification accuracy on an ROC curve and of maximal profit on a CAP curve can be found by using iso-performance tangent lines, which are based on the standard notion of accuracy. In this paper, we offer an alternative accuracy measure called the true rate. Using this rate, one can obtain alternative optimal threshold points on both ROC and CAP curves. For most real populations of borrowers, the number of the defaults is much less than that of the non-defaults, and in such cases the true rate may be more efficient than the accuracy rate in terms of cost functions. Moreover, it is shown that both alternative scores of optimal classification accuracy and maximal profit are the identical, and this single score coincides with the score corresponding to Kolmogorov-Smirnov statistic used to test the homogeneous distribution functions of the defaults and non-defaults.

• The Korean Journal of Applied Statistics
• /
• v.23 no.1
• /
• pp.13-28
• /
• 2010

Assuming a mixture distribution for credit evaluation studies, we discuss estimating threshold methods to minimize errors that default borrowers are predicted as non defaults or non defaults are regarded as defaults. A method by using statistical hypotheses tests, the most powerful test and generalized likelihood ratio test, for the probability density functions which are defined with the score random variable and the parameter space consisted of only two elements such as the default and non default states is proposed to estimate a threshold. And anther optimal thresholds to maximize classification accuracy measures of the accuracy and the true rate for ROC and CAP curves are estimated as equations related with these probability density functions. Three kinds of optimal thresholds in terms of the hypotheses testing, the accuracy and the true rate are obtained from normal random samples with various means and variances. The sums of the type I and type II errors corresponding to each optimal threshold are obtained and compared. Finally we discuss about their efficiency and derive conclusions.

• The Korean Journal of Applied Statistics
• /
• v.23 no.5
• /
• pp.943-953
• /
• 2010

From a mixture distribution of the score random variable for credit evaluation, there are many methods of estimating optimal thresholds. Most the research news is based on the assumption of normal distributions. In this paper, we extend non-normal distributions such as Weibull, Logistic and Gamma distributions to estimate an optimal threshold by using a hypotheses test method and other methods maximizing the total accuracy and the true rate. The type I and II errors are obtained and compared with their sums. Finally we discuss their e ciency and derive conclusions for non-normal distributions.

• Korean Journal of Culture and Social Issue
• /
• v.14 no.4
• /
• pp.1-18
• /
• 2008

The present study examined the accuracy of polygraph tests through two types of statistical methods with unknown ground truth. One method evaluated the accuracy based on the rates of agreements between polygraph test results of crime suspects and prosecutors' indictment decisions for them. Those crime suspects were tested with polygraph by the Prosecutors' Office of the Republic of Korea between 2000 and 2004. The other method estimated the accuracy by using the latent class analysis based on the frequency distributions of the polygraph results and indictments during 2006. Excluding cases that were 'inconclusive' on the polygraph test, the study showed that the accuracy of the polygraph tests is .914 (SE=.004) for the 2000-2004 data, and .885 (SE=.021) for the 2006 data. With the inclusion of 'inconclusive' cases in the 2006 data, the results from the latent class analysis showed the accuracy in the range between .707 and .734 (SE=.027~.031), with false positives between .078 and .087 (SE=.019~.023), and false negatives between .029 and .078 (SE=.010~.023). The probability that the polygraph test correctly classifies subjects appeared to be in the range between .912 and .925 (SE=.013-.016) for those who lie, and in the range between .867 to .955 (SE=.011-.040) for those who tell the truth.

• Communications for Statistical Applications and Methods
• /
• v.17 no.6
• /
• pp.755-765
• /
• 2010

For classification problems on mixture distribution, a threshold based on cost functions is optimal from the viewpoint of a minimum expected cost. Assuming that there is no cost information, we propose cost ratios in the expected cost corresponding to thresholds where the total accuracy and the true rate are maximized to explain the relation of these cost ratios minimizing the expected cost. Other cost ratios are also proposed by comparing the normalized expected costs when classification accuracy is maximized. The values of these cost ratios are located between two cost ratios for the expected costs based on classification accuracies, and converge to that of the minimum expected cost. This work suggests two cost ratios: one is minimized by the expected cost and the normalized expected cost, and the other in the expected cost and the normalized expected cost functions that are maximized classification accuracies. We discuss their compatibility based on the relation of these cost ratios.

• The Korean Journal of Applied Statistics
• /
• v.6 no.2
• /
• pp.311-318
• /
• 1993

In this paper, we consider the test based on using Forced question model instead of Warner model and compare the power of two randomized respose models. The estimator for the prportion of the individuals belonging to the sensitive group is obtained by using Forced question model and the conditions that the estimator by Forced question model will be more efficient than the estimators by Warner model are found when the respondents are truthrul in their answers.

• Radiation Oncology Journal
• /
• v.8 no.2
• /
• pp.183-188
• /
• 1990

Between January 197l and December 1987, 113 patients with nasopharyngeal cancer (NPC) were treated by radiation therapy with or without chemotherapy in the department of Radiation Oncology, Yonsei University Hospital. There were 19 patients under thirty years of age. The histology was undifferentiated carcinoma in $68\%$ of the younger patients as compared to $47\%$ of the older patients. Sex, stage, initial symptoms and treatment modalities differed little from those of older patients. In younger patients, the initial complete response rate was $79\%$ as compared to older patients with $54\%$, distant metastases were more common and the overall five year survival rate was not significantly different between the two age groups ($33.7\%$ for the young vs. $37.4\%$ for the old). The five year survival rates for stage III and IV were $60.0\%$ and $24.5\%$, respectively. Histologic subtype was not correlated with survival. The best survival was found only in patients who obtained a complete clearance of disease after radiation therapy.

• Radiation Oncology Journal
• /
• v.4 no.1
• /
• pp.29-34
• /
• 1986

Thirty-six patients with carcinoma of the tonsillar region treated with radical radiotherapy at Yonsei Cancer Center between Jan. 1971 and Dec. 1980 were retrospectively reviewed. The purpose of this study is to evaluate the clinical characteristics and the treatment results. Seventy-five per cent of patients were in advanced stage when they were first seen. Incidence of nodal involvement at the time of initial presentation was $64\%$. Bilateral nodal involvement was found in $19\%$ of cases. Three-year local control rates for T1, T2, T3, and T4 were $88\%,\;46\%,\;25\%,\;and\;11\%$, respectively. Advanced neck nodes were poorly controlled $(N1\;70\%,\;N2\;20\%,\;N3\;12\%)$. The prognosis is mainly affected by the status of the primary and neck nodes Overall three-year local control rate was $42\%$.

• Radiation Oncology Journal
• /
• v.15 no.4
• /
• pp.339-348
• /
• 1997

Purpose : To evaluate the role of postoperative radiation therapy after curative resection of sigmoid colon cancer Materials and Methods : From 1988 to 1993, a total of 93 Patients with curative resectable sigmoid colon cancer of modified Astler-Coiler (MAC) stage B2, B3, C2, C3 was divided into two groups on the basis of those who received radiation treatment and those who did not. Forty-three patients who treated by surgery alone were classified as postop RT (-) group The remaining 50 patients who underwent postoperative radiotherapy were classified as postop RT (+) group. In all patients in Postop RT (+) group. radiation therapy was delivered using 4 or 10 MV linear accelerators to treat the tumor bed with approximately 5cm margin to a total dose 50.4-61Gy(median 54Gy) in 1.8Gy per fraction. Thirty-two patients were treated. with 5-Fluorouracil based adjuvant chemotherapy at least 3 cycles. but these was no significant difference between two groups. Treatment failure Pattern, 5-year local failure-free survival rates (LFFS), and 5-year disease-free survival rates (DFS) were compared between two groups. Result : Five year LFFS and DFS were $85.1\%,\;68.5\%$, respectively, In Postop RT (-) group, LFFS was $76.2\%$ compared with $91.7\%$ in Postop RT (+) group. Improved LFFS and DFS were seen for patients with stage C3 sigmoid colon carcinoma with postoperative radiation therapy compared with postop RT (-) group (P=0.01, p=0.06 respectively), in stage B3, LFFS washigher in postop RT (+) group than that in Postop RT (-) group. although itwas not significant. Especially, local control was higher in stage 74 inpostop RT (+) group than that in postop RT (-) group, Conclusion : This studv showed significantly improved LFFS and DFS in MAC Stage C3 and improved tendency of LFFS and DFS in MAC Stage B3 disease. Large scale prospective study is required to verify the role of adjuvant radiation therapy in resectable sigmoid colon cancer.

• Journal of Astronomy and Space Sciences
• /
• v.19 no.1
• /
• pp.47-56
• /
• 2002

Observations of times of minimum lights of the eclipsing binary V65l Cas were carried out on the three nights from November 21-23, 2000. From our observations a total of seven new times of minimum lights was obtained. Through the analysis of photoelectric and CCD times of minima of V65l Cas including ours, the light time orbit due to a third body, which was propose by Kim ＆ Lee (2000), was confirmed and improved. The resultant values for the period, semi-amplitude, and eccentricity of the light-time orbit were $6.^{y}3,\;0.^{d}0013$, and 0.78, respectively. The deduced marts range of the third body is . If the third body is $0.09M_{\odot}\;{\leq}\;M_3\;{\leq}\;0.20M_{\odot}\;for\;i_3\;{\geq}\;30^{\circ}$. If the third body suggested in V65l Cas system exists really and is a main-sequence star, it is located at the end of the main-sequence.