• Communications for Statistical Applications and Methods
• /
• 제9권3호
• /
• pp.765-774
• /
• 2002

Suppose one is given a vector X of a finite set of quantities $X_i$ which are independent Poisson random variables. A null hypothesis $H_0$ about E(X) is to be tested against an alternative hypothesis $H_1$. A quantity $\sum\limits_{i}w_ix_i$ is to be computed and used for the test. The optimal values of $W_i$ are calculated for three cases: (1) signal to noise ratio is used in the test, (2) normal approximations with unequal variances to the Poisson distributions are used in the test, and (3) the Poisson distribution itself is used. The above three cases are considered to the situations that are without background noise and with background noise. A comparison is made of the optimal values of $W_i$ in the three cases for both situations.

• 대한가정학회지
• /
• 제35권1호
• /
• pp.319-338
• /
• 1997

This study examined the time allocation pattern of husbands and wives. This study investigated i)the pattern of time allocation in the light of the extent of time spent in housework child care and leisure among husbands and wives living in urban area ii) the differences in extent of time spent in such activities between wives and husbands and iii) the determinants of time spent in such activities. A system of time allocation equations based on household production theory and several hypotheses explaining the distribution of domestic work among couples were employed. According to the results the pattern of time allocation was different between wives and husbands. Regardless of women's employment status wives were more likely to have dual responsibilities than were husbands. The time equation employed in this study had more explanatory power in the pattern of time allocation of wives than of husbands and of employed wives than of non-employed wives. The sex-role ideology hypothesis was supported for non-employed wives but not for employed wives. The time availability hypothesis was supported for the time allocation of employed wives and husbands. The economic efficiency hypothesis was supported for employed wives' time allocation.

• Journal of the Korean Data and Information Science Society
• /
• 제13권2호
• /
• pp.307-315
• /
• 2002

Suppose one is given a vector X of a finite set of quantities $X_i$ which are independent Poisson signals. A null hypothesis $H_0$ about E(X) is to be tested against an alternative hypothesis $H_1$. A quantity $$\sum\limits_{i}\omega_ix_i$$ is to be computed and used for the test. The optimal values of $\omega_i$ are calculated for three cases : (1) signal to noise ratio is used in the test, (2) normal approximations with unequal variances to the Poisson distributions are used in the test, and (3) the Poisson distribution it self is used. A comparison is made of the optimal values of $\omega_i$ in the three cases as parameter goes to infinity.

• 인지과학
• /
• 제27권4호
• /
• pp.541-572
• /
• 2016

인과 추론은 심리학에서는 물론 최근 베이스 접근법을 취하는 인지과학자들에 의해서도 활발히 연구되고 있다. 본 연구는 인과추론에 대한 대표적 심리학 이론인 힘-확률대비이론(a power probabilistic contrast theory of causality)을 중심으로 인과 추론의 최근 동향을 개관하고자 한다. 힘-확률대비이론에서는, 원인은 결과를 일으키거나 억제하는 힘(power)인데, 이 힘은 특정한 조건하에서 통계적 상관을 통해 파악될 수 있다고 가정한다. 본 논문에서는 이 이론에 대한 초기의 경험적 지지 증거를 먼저 살펴본 다음, 베이스 접근에 기반을 둔 이론과의 쟁점을 명확히 하고, 원인은 맥락에 무관하게 동일하게 작동한다는 인과적 불변성 가정(causal invariance hypothesis)을 중심으로 한 보다 최근의 연구 결과를 소개하고자 한다. 이 연구들은 종래의 통계적 접근법으로는 잘 설명되지 않는 결과를 제시함으로써, 철학, 통계학, 그리고 인공 지능 등과 같은 인접 분야에 인과성에 대한 힘 이론을 진지하게 고려할 것을 촉구하고 있다.

• Journal of the Korean Data and Information Science Society
• /
• 제25권2호
• /
• pp.385-392
• /
• 2014

랜덤워크 가설은 금융시장의 예측 어려움을 이론적으로 설명하는 가설이다. 현재까지 다양한 랜덤워크 검정방법들이 개발되어 왔으나 낮은 검정력과 유의수준 왜곡 등의 문제를 보이는 것으로 알려져 있다. 본 논문에서는 이러한 문제점들을 개선하기 위해 부호검정에 기초한 랜덤워크 검정방법을 제안하였다. 랜덤워크와 관련하여 흔히 사용되고 있는 Dickey와 Fuller (1979) 검정과 모의실험을 통해 성능을 비교하였다.

• 응용통계연구
• /
• 제26권4호
• /
• pp.611-622
• /
• 2013

Mudholkar와 Tian (2002)이 제시한 엔트로피 기반 검정은 위치모수와 척도모수가 모두 알려져 있지 않거나 척도 모수만 알려져 있는 역가우스분포의 적합을 알아보고자 하는 경우에만 사용이 가능하다. 본 논문에서는 위치모수와 척도모수가 모두 알려져 있거나 위치모수만 알려져 있는 역가우스분포의 적합에도 적용할 수 있는 엔트로피 기반 적합도 검정을 소개한다. 이 검정은 확률적분변환에 기초를 두고 있다. 모의실험을 통해서 추정한 표본크기와 윈도크기에 따른 검정통계량의 기각값과 근사기각값을 얻기 위한 계산공식을 제시한다. 제안한 검정과 Mudholkar와 Tian (2002)의 검정을 검정력 측면에서의 성능을 비교하고자 모의실험을 수행한다. 모의실험 결과에서 제안한 검정은 기존의 엔트로피 기반 검정보다 더 좋은 검정력을 가지는 것으로 나타난다.

• 한국국방경영분석학회지
• /
• 제27권2호
• /
• pp.124-133
• /
• 2001

The purpose of this study is investigate the differences among parametric and nonparametric test statistics for the tree alternative hypothesis in the randomized block design. As the results, it was found that there was no large differences among parametric and nonparametric test statistics in power when the block sizes were larger, and Hollander's statistic had better power than other nonparametric test statistics. It is recommended that Hollander's test statistic is more useful method when we have no information about the distribution of population.

• 한국보건간호학회지
• /
• 제5권2호
• /
• pp.37-44
• /
• 1991

This paper follows the Walker of Avant approach to concept analysis of the concept of power. For the purposes of the paper, power was defined as the actural or potential ability or capacity to achieve objectives through an interpersonal process in which the goals and means to achieve the goals are mutually established and worked toward. The distinction between the view of power as 'power to' versus 'power over' are addressed in the literature review. King's conceptual framework was used as a guide. The defining attributes of power are: 1. The actual or potential ablity or capacity to achieve objectives or attain goals. 2. An Interpersonal process, 3. Mutual establishment of goals and the means to achieve the goals and 4. Mutually working toward the goals. The antecedents for power were idntified in the literature review: 1. the presence of two or more people 2. acquisition of power skill 3. possession of the power sources 4. an orientation of power as good and 5. self-confidence. The concequences of power are the achievement of objectives or goal attainment. Finally Assumptions and testable hypothesis are proposed.

• Communications for Statistical Applications and Methods
• /
• 제16권4호
• /
• pp.707-711
• /
• 2009

We propose new cointegration tests using signs of the regressors as instrumental variable. Our tests have the asymptotic standard normal distribution and are free from the dimension of regressors under the null hypothesis of no cointegration. A Monte-Carlo simulation shows that the proposed tests have a stable size and an improved power. Particulary, the tests have better power for small numbers of observations.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2004년도 추계학술대회
• /
• pp.17-23
• /
• 2004

At the conclusion from the hypothesis testing, there is a possibility of making Type I error and Type II error. The purpose of this article is to use this program in statistics teaching through developing the program for studying on the concept about these two errors, two kinds of the probability of errors by the variation of rejection region, two kinds of the probability of errors by the variation of sample size, the relations of the probability $\alpha$ and $\beta$ by these two errors, and power function, power curve.