• 제목/요약/키워드: Hypothesis testing

검색결과 776건 처리시간 0.03초

비디오 객체 생성을 위한 자동 영상 분할 방법 (An Automatic Segmentation Method for Video Object Plane Generation)

  • 최재각;김문철;이명호;안치득;김성대
    • 방송공학회논문지
    • /
    • 제2권2호
    • /
    • pp.146-155
    • /
    • 1997
  • 본 논문은 MPEG-4와 같이 객체 및 내용 기반 영상 부호화에 필요한 동영상의 자동 영역 분할 알고리즘을 제안한다. 통계적 가설 검증(statistical hypothesis test)을 사용하여 영상 시퀀스내에 포함된 비디오 객체들(video objects)을 움직임 물체(moving objects)와 배경 (background)으로 자동 분할하는 새로운 영상 분할 알고리즘을 제안한다. 기존 방법들이 두 개의 연속된 영상을 사용하는 반면에, 제안된 방법은 3개의 연속된 영상을 사용하여, 2개의 차영상의 평균값을 비교하여 가설검증을 행함으로써 잡음에 강한 특성을 나타낸다. 그리고 제안된 방법은 기존 방법과는 달리 참분산(true variance)을 사전에 알고 있을 필요가 없는 장점을 갖고 있다[18]. 또한 시간정보만을 이용한 변화 검출 방법의 문제점인 불규칙하고 부정확한 영역의 경계를 공간정보를 이용하여 보정하는 새로운 방법을 제안한다. 시험 결과에서 주어진 것처럼 제안된 시공간정보를 이용한 영상 분할 알고리즘이 시각적으로 의미있는 분할 결과를 제공함을 알 수 있고, 정확한 영역 경계를 추출할 수 있기 때문에 MPEG-4와 같은 객체 기반 영상 부호화에 적용할 경우에 영역 경계에서 상당히 우수한 재생 화질을 얻을 수 있다.

  • PDF

기혼 맞벌이 여성의 일-가족양립에 관한 연구 - 일-가족양립의 긍정적 전이, 비대칭성, 차별적 기능 검증을 중심으로 - (A Study on the Work-Family Reconciliation of Married Women in Double Income Households - With a focus on testing the positive spillover, asymmetry, and differential functions of work-family reconciliation -)

  • 문영주
    • 가족자원경영과 정책
    • /
    • 제17권1호
    • /
    • pp.81-102
    • /
    • 2013
  • The purpose of this study was to investigate the work-family reconciliation level of married women in double-income households. Specifically, the study aimed to test the positive spillover effects, asymmetry, and differential functions of work-family reconciliation. The study thus analyzed 1,114 married women in double-income households in the third-year data of the Korean Longitudinal Survey of Women and Families (KLoWF) done by Korean Women's Development Institute (KWDI), with the exception of those who were separated, divorced, or widowed from their husbands. The data were put to descriptive statistics, frequency analysis, and exploratory factor analysis using SPSS 20.0 for Windows. AMOS 20.0 was used to test the hypothesis on positive spillover effects, asymmetry, and differential functions. The analysis results confirm that work-family conflict, family-work conflict, work-family facilitation, and family-work facilitation are different concepts, thus supporting the hypothesis on positive spillover effects. Secondly, the negative effects of family on work were greater than those of work on family, whereas the positive effects of family on work were greater than those of work on family, which finding partially supported the hypothesis on asymmetry among the components of work-family reconciliation. Finally, the married women in double-income households with preschool children experienced more work-family conflict and family-work conflict than those with no preschool children, which result supported the hypothesis on differential functions between the two groups of women. The findings were combined to provide implications for the utilization of family resources, policies for work-family reconciliation, and plans for institutional supports to promote the work-family reconciliation of married women in double-income households.

  • PDF

사출성형기의 제어방식에 따른 사출장치 정밀도 검사 (Injection Unit Precision Inspection according to Control Method of Injection Molding Machine)

  • 정현석;유중학
    • 한국산학기술학회논문지
    • /
    • 제17권4호
    • /
    • pp.414-419
    • /
    • 2016
  • 본 연구는 사출 성형기의 제어 방법에 따른 정밀 검사에 대한 연구를 수행하였다. 실험을 통하여, 유압사출 성형기와 전동식 사출성형기의 스크루 스트로크, 보압, 용융 수지온도에 대하여 정밀도에 미치는 영향을 조사하였다. 또한, 실험에서 얻어진 데이터 편차에 대한 가설 테스트를 수행 하였다. 연구를 통하여 스크루 스트로크, 용융 수지온도, 보압 순으로 편차가 크게 발생하는 것을 알 수 있었다. 유압식 사출성형기가 전동식 사출성형기에 비해 제품 간의 산포가 크게 발생하는 것을 확인하였다. 또한 통계프로그램인 미니탭을 활용하여 스크루 스트로크, 용융 수지온도, 보압에 대한 가설을 설립 한 후 P값을 확인하여 스크루 스트로크, 용융수지온도는 귀무가설($H_0$)을 채택하였으며, 보압은 상호차이가 발생한 대립가설($H_1$)을 채택하였다.

TESTING FOR SMOOTH TRANSITION NONLINEARITY IN PARTIALLY NONSTATIONARY VECTOR AUTOREGRESSIONS

  • Seo, Byeong-Seon
    • Journal of the Korean Statistical Society
    • /
    • 제36권2호
    • /
    • pp.257-274
    • /
    • 2007
  • This paper considers the tests for the presence of smooth transition non-linearity in the partially nonstationary vector autoregressive model. The transition parameters cannot be identified under the null hypothesis of linearity, and therefore this paper develops the tests for smooth transition nonlinearity, the associated asymptotic theory and the bootstrap inference. The Monte Carlo simulation evidence shows that the bootstrap inference generates moderate size and power performances.

A Study on Bayesian p-values

  • Hwnag, Hyungtae;Oh, Heejung
    • Communications for Statistical Applications and Methods
    • /
    • 제9권3호
    • /
    • pp.725-732
    • /
    • 2002
  • P-values are often perceived as measurements of degree of compatibility between the current data and the hypothesized model. In this paper, a new concept of Bayesian p-values is proposed and studied under the non-informative prior distributions, which can be thought as the Bayesian counterparts of the classical p-values in the sense of using the concept of significance level. The performances of the proposed Bayesian p-values are compared with those of the classical p-values through several examples.

A Nonparametric Bootstrap Test and Estimation for Change

  • Kim, Jae-Hee
    • Communications for Statistical Applications and Methods
    • /
    • 제14권2호
    • /
    • pp.443-457
    • /
    • 2007
  • This paper deals with the problem of testing the existence of change in mean and estimating the change-point using nonparametric bootstrap technique. A test statistic using Gombay and Horvath (1990)'s functional form is applied to derive a test statistic and nonparametric change-point estimator with bootstrapping idea. Achieved significance level of the test is calculated for the proposed test to show the evidence against the null hypothesis. MSE and percentiles of the bootstrap change-point estimators are given to show the distribution of the proposed estimator in simulation.

An Adaptive Test for Ordered Interqartile Ranges among Several Distributions

  • Park, Chul-Gyu
    • Journal of the Korean Statistical Society
    • /
    • 제30권1호
    • /
    • pp.63-76
    • /
    • 2001
  • An adaptive estimation and testing method is proposed for comparing dispersions among several ordered groups. Based upon the large sampling theory for nonparametric quartile estimators, we derive the order restricted estimators and construct a simple test statistic. This test statistic has a mixture of several chi-square distributions as its asymptotic null distribution. The proposed test is illustratively applied to survival time data for the patients with carcinoma of the oropharynx.

  • PDF

Locating the Change Point of Mean Residual Life of Certain Life Distributions

  • Li, Xiaohu
    • International Journal of Reliability and Applications
    • /
    • 제3권2호
    • /
    • pp.91-98
    • /
    • 2002
  • A class of life distributions, whose mean residual life keeps stable at its earlier phase and then starts to decrease in time, is proposed to model the life of an element haying survived its burn-in. A strongly consistent estimator and a nonparametric testing procedure are developed to locate the occurrence of the change-point of the mean residual life. Finally, some numerical simulations are employed to be an illustration as well.

  • PDF

k-Sample Rank Procedures for Ordered Location-Scale Alternatives

  • Park, Hee-Moon
    • 품질경영학회지
    • /
    • 제22권2호
    • /
    • pp.166-176
    • /
    • 1994
  • Some rank score tests are proposed for testing the equality of all sampling distribution functions against ordered location-scale alternatives in k-sample problem. Under the null hypothesis and a contiguous sequence of ordered location-scale alternatives, the asymptotic properties of the proposed test statistics are investigated. Also, the asymptotic local powers are compared with each others. The results show that the proposed tests based on the Hettmansperger-Norton type statistic are more powerful than others for the general ordered location-scale alternatives. However, the Shiraishi's tests based on the sum of two Bartholomew's rank analogue statistics are robust.

  • PDF

The Program for Teaching on Type I error and Type II error

  • 최현석
    • 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.

  • PDF