• 응용통계연구
• /
• 제24권6호
• /
• pp.1271-1284
• /
• 2011

본 논문에서는 위치와 척도모수가 모두 알려지지 않은 역가우스분포에 대한 적합도 검정으로 기존에 개발된 엔트로피 기반 검정을 확장한 쿨백-라이블러 정보 기반 적합도 검정을 소개한다. 역가우스분포에 대한 단순 또는 복합 영가설을 검정하기 위한 4가지 형태의 검정통계량을 제시하고 검정통계량의 계산에 사용할 표본크기에 따른 윈도크기와 기각값을 모의실험을 통해 결정하여 표의 형태로 제공한다. 검정력 분석을 위해 수행한 모의실험의 결과에서 위치와 척도모수가 모두 알려진 역가우스분포에 대한 쿨백-라이블러 정보 기반 적합도 검정은 모든 대립분포와 표본크기에서 EDF 검정들보다 좋은 검정력을 가지는 것으로 나타난다. 위치모수 또는 척도모수만 알려진 역가우스분포에 대한 쿨백-라이블러 정보 기반 적합도 검정은 모든 대립분포에 대해서 표본크기가 커짐에 따라 검정력이 증가하는 경향을 보인다. 위치와 척도모수가 모두 알려지지 않은 역가우스분포에 대한 쿨백-라이블러 정보 기반 적합도 검정은 대체적으로 엔트로피 기반 검정과 비슷한 수준의 검정력을 보이는 것으로 나타나고 이 결과를 통해서 두 검정은 동일함을 확인할 수 있다.

• Journal of the Korean Data and Information Science Society
• /
• 제24권4호
• /
• pp.847-856
• /
• 2013

본 논문에서는 모수적과 비모수적 엔트로피 추정량들에 기초한 정규분포에 대한 적합도 검정을 다룬다. 정규분포의 엔트로피에 대한 모수적 추정량으로 사용할 최소분산비편향추정량을 유도한다. 이 추정량과 대립가설 하에서의 자료생성분포에 대한 비모수적 엔트로피 추정량으로 표본엔트로피와 이것의 변형된 추정량들을 이용하여 검정통계량들을 구축했고 이 검정통계량들을 사용하는 새로운 엔트로피 기반 적합도 검정들을 제시한다. 제안한 검정들의 기각값들을 모의실험을 통해 추정해서 표의 형태로 제시한다. 성능의 조사를 위해 수행한 모의실험에서 제안한 검정들이 기존의 Vasicek (1976) 검정보다는 더 좋은 검정력을 가지는 것으로 나타난다. 응용에서 새로운 검정들이 정규성 검정을 위한 경쟁적인 도구로 시용될 수 있을 것으로 기대된다.

• Journal of the Korean Data and Information Science Society
• /
• 제25권5호
• /
• pp.1039-1055
• /
• 2014

검정통계량의 영가설 분포는 모집단 분포에 의존하는데 모집단의 분포를 모를 때 영가설 분포를 검정통계량의 조건부 분포로 대체하여 검정하는 방법을 순열 검정이라고 한다. Strasser와 Weber (1999)는 순열 검정을 통합하는 이론을 마련하였고, Hothorn 등 (2006, 2008)은 그 이론을 R에 내장된 coin 패키지에 구현하였다. coin 패키지에서 조건부 독립성 검정은 총괄적인 형태의 함수인 independence test를 통해서 할 수 있지만 대표적인 독립성 검정은 사용자가 편리하도록 간편한 함수를 별도로 제공하고 있다. 본 논문에서는 Strasser와 Weber (1999)의 순열 검정 방법에 대해 소개하고, coin 패키지에 내장된 15개의 간편 함수에 대해 independence test 함수로 변환하는 절차를 설명하고자 한다. 또한, 정의한 independence test 함수를 써서 실제 자료의 점근 분포와 순열 검정, 정확 검정에 기초한 p-값을 서로 비교하고자 한다.

• 대한간호학회지
• /
• 제12권1호
• /
• pp.25-38
• /
• 1982

As technological civilization and medical science has developed, standards of living have imp-roved and human life expectancy has been extended. But the incidence and mortality rate of cancer have been gradually increasing due to the pollution of the environment. Even though cancer is still a great threat to human beings, the etiology and appropriate cure forcancerhavenotyetbeendiscovered. The early detection and treatment of cancer is urgently needed. This study concentrates on the health behavior of woman regarding the papanicolau smear for early detection of cervical cancer. It was done in order to provide a direction for scientific health education materials by investigating predictors of preventive health behavior. The subjects for this study were made up of 54 woman, who comply with preventive health practices(compliant) who attended the Cervical Cancer Center of Y University Hospital in order to have tests for early detection of cervical cancer and 54 woman who did not comply with preventive health practices (noncompliant) selected from 100 housewives of I apartment, Kang Nam Ku, Seoul. The study method used, was a questionnaire for the compliance group and an interview for the noncompliance group. The period for data collection was from October 13th to October 24th. 1981. Analysis of the data was done using percentages, T-test, Pearson Correlation and Stepwise Multiple Regression. The results of study were as follows: 1. The hypotheses tested were based on the health belief model; 1) The first hypothesis,“The compliant may have more knowledge of the cervical cancer than the noncompliant”was rejected(T=-1.86, p>.05) 2) The second hypothesis,“The compliant may have a higher severity of cervical cancer than the noncompliant”was accepted (T=5.41, p<.001) 3) The third hypothesis, “The compliant may have a higher susceptability to cervical cancer than the noncompliant”was accepted(T=3.51, p<.01). 4) The fourth hypothesis,“The compliant may have more beneHt than cost'from the cervical cancer tests than the noncompliant" was accepted(T=7.46, p<.001). 5) The fifth hypothesis,“The compliant may have more health concern than the noncompliant”. was accepted(T=3.39, p<.01). These results show that severity, susceptability, benefit(over cost) and health concern influence the preventive health behavior in this Study. 2. In the correlation among variables, it was found that the knowledge of cervical cancer and the benefit(over cost) of preventive health behavior were negatively correlated(r=-2.75, p<.01), Severity of cervical cancer and benefit (over cost) of preventive health behavior were positively correlated(r=.280, p＜.01), severity and susceptability of cervical cancer were positively correlated(r= .238, p<.01), benefit(over cost) and health concern were positively correlated(r= .299, p<.01). The benefit(over cost) may be raised by increasing the severity and health concern. Therefore the compliance rate of woman may be raised through health education by increasing the benefit(over cost) of the individual. 3. The Stepwise Multiple Regression between health behavior and predictors. 1) The factor“Benefit(over cost)”could account for preventive health behavior in 34.4％ of the sample(F=55.6204 P<.01). 2) When the factor“Severity”is added to this, it accounts for 44.3% of preventive health behavior(F=41.679, p<.01). 3) When the factor“Susceptability”is also included, it accounts for 46.7% of preventive health behavior(F=30.373, p<.01). 4) When the factor “Health concern”is included, it accounts for 48.1% of preventive health behavior(F=23859, p<.05). This means that other factors appear to influence preventive health behavior, since the combination of variables explains only 48.1％ of the Preventive health behavior. Therefore further study to investigate the predictors of preventive health behavior is necessary.

• Communications for Statistical Applications and Methods
• /
• 제24권5호
• /
• pp.519-531
• /
• 2017

We consider goodness-of-fit test statistics for Weibull distributions when data are randomly censored and the parameters are unknown. Koziol and Green (Biometrika, 63, 465-474, 1976) proposed the $Cram\acute{e}r$-von Mises statistic's randomly censored version for a simple hypothesis based on the Kaplan-Meier product limit of the distribution function. We apply their idea to the other statistics based on the empirical distribution function such as the Kolmogorov-Smirnov and Liao and Shimokawa (Journal of Statistical Computation and Simulation, 64, 23-48, 1999) statistics. The latter is a hybrid of the Kolmogorov-Smirnov, $Cram\acute{e}r$-von Mises, and Anderson-Darling statistics. These statistics as well as the Koziol-Green statistic are considered as test statistics for randomly censored Weibull distributions with estimated parameters. The null distributions depend on the estimation method since the test statistics are not distribution free when the parameters are estimated. Maximum likelihood estimation and the graphical plotting method with the least squares are considered for parameter estimation. A simulation study enables the Liao-Shimokawa statistic to show a relatively high power in many alternatives; however, the null distribution heavily depends on the parameter estimation. Meanwhile, the Koziol-Green statistic provides moderate power and the null distribution does not significantly change upon the parameter estimation.

• Journal of the Korean Statistical Society
• /
• 제30권1호
• /
• pp.41-61
• /
• 2001

The minimum negative exponential disparity estimator(MNEDE), introduced by Lindsay(1994), is an excellenet competitor to the minimum Hellinger distance estimator(Beran 1977) as a robust and yet efficient alternative to the maximum likelihood estimator in parametric models. In this paper we define the negative exponential deviance test(NEDT) as an analog of the likelihood ratio test(LRT), and show that the NEDT is asymptotically equivalent to he LRT at the model and under a sequence of contiguous alternatives. We establish that the asymptotic strong breakdown point for a class of minimum disparity estimators, containing the MNEDE, is at least 1/2 in continuous models. This result leads us to anticipate robustness of the NEDT under data contamination, and we demonstrate it empirically. In fact, in the simulation settings considered here the empirical level of the NEDT show more stability than the Hellinger deviance test(Simpson 1989). The NEDT is illustrated through an example data set. We also define a goodness-of-fit statistic to assess adequacy of a specified parametric model, and establish its asymptotic normality under the null hypothesis.

• Genomics & Informatics
• /
• 제5권2호
• /
• pp.61-67
• /
• 2007

The allele frequencies of markers as well as linkage disequilibrium (LD) can be changed in cases due to the LD between markers and the disease allele, exhibiting spurious associations of markers. To identify the true association, classical statistical tests for dealing with confounders have been applied to draw a conclusion as to whether the association of variants comes from LD with the known disease allele. However, a more direct test considering LD using estimated haplotype frequencies may be more efficient. The null hypothesis is that the different allele frequencies of a variant between cases and controls come solely from the increased disease allele frequency and the LD relationship with the disease allele. The haplotype frequencies of controls are estimated using the expectation maximization (EM) algorithm from the genotype data. The estimated frequencies are applied to calculate the expected haplotype frequencies in cases corresponding to the increase or decrease of the causative or protective alleles. The suggested method was applied to previously published data, and several APOE variants showed association with Alzheimer's disease independent from the APOE ${\varepsilon}4$ variant, rs429358, regardless of LD showing significant simulated p-values. The test results support the possibility that there may be more than one common disease variant in a locus.

• International Journal of Oral Biology
• /
• 제34권3호
• /
• pp.137-142
• /
• 2009

Whole-body $\gamma$-irradiation(WBI), which produces an oxidative stress, is reported to attenuate the acute antinociceptive action of morphine (a $\mu$-opioid receptor agonist), but not DPLPE (a $\delta$-opioid receptor agonist), in mice. Recently, we also reported that antinociceptive effect of morphine, but not $\beta$-endorphin (a novel $\varepsilon$-opioid receptor agonist), was attenuated by oxidative stress. These findings prompted us to investigate the effect of WBI on the antinociception of morphine and $\beta$-endorphin in mice. Mice were exposed to WBI (5 Gy) from a $^{60}Co$ gamma-source and tested 2 hours later for antinociception produced by intracerebroventricular administration of morphine or $\beta$-endorphin using the hot water tail-immersion and the writhing tests. WBI significantly attenuated the antinociception produced by morphine only in the hot water tail-immersion test, whereas the antinociception of $\beta$-endorphin was significantly potentiated by WBI in both tests. These results demonstrate a differential sensitivity of $\mu$- and $\varepsilon$-opioid receptors to WBI, and support the hypothesis that morphine and $\beta$-endorphin administered supraspinally produce antinociception by different neuronal mechanisms.

• 응용통계연구
• /
• 제26권3호
• /
• pp.401-411
• /
• 2013

변수들 간 인과관계는 시차 회귀방정식을 사용한 초기의 검정법 이후 새로운 통계적 기법이 계속 개발되면서 더욱 다양하고 효율적인 분석이 가능하게 되었지만 오랜 논쟁의 대상인 닭과 달걀 간 선행관계에 대한 검정은 의외로 간과되어왔다. 본 연구에서는 현대적 관점에서 두 변수 간 인과관계를 학문적으로 조명해보기 위해 사용가능한 자료를 이용하여 통계적 검정을 실시해 보았다. 두 변수 간 관계에는 구조적 변화가 발생하지 않았음이 입증되면서 사용한 검정법 모두 수준변수 및 정상변수에서 일관된 검정결과를 보이는 것으로 나타났다.

• 대한인간공학회지
• /
• 제28권1호
• /
• pp.1-7
• /
• 2009

As products are getting more diverse and new products are entering the market faster, customers have trouble learning how to use them. User-oriented menu structures may solve this problem. In order to design user-oriented menu structures, spreading activation theory has been studied. The spreading activation test shows that the strong associative relationship between words has shorter response times. Based on the spreading activation test, asymmetric spreading activation was introduced and a hypothesis that in a well-designed menu structure, association between upper-low menu pairs is not affected by an activation direction was tested for this study. In this study the menu of a cellular phone (Model: SPH-w2900) was extracted, and underwent 1st spreading activation tests. Then, on each menu pair, response time differences (asymmetric transition) by accuracy and directions were analyzed to find out problems in labels and improve menu structures and vocabulary. Second spreading activation tests were conducted to check whether asymmetric transitions decreased. The results showed that response time differences (asymmetric transition) for activation directions were found to be dropped significantly. Asymmetric transitions in spreading activation presented in this study will be helpful to define user-oriented menu structures.