• 제목/요약/키워드: Hypothesis Decision

검색결과 245건 처리시간 0.022초

RR 접근방법과 P-Value 접근방법을 이용한 가설판정의 적용방안 (Implementation Strategy of Hypothesis Decision Using Rejection Region Approach and P-Value Approach)

  • 최성운
    • 대한안전경영과학회:학술대회논문집
    • /
    • 대한안전경영과학회 2012년 추계학술대회
    • /
    • pp.431-434
    • /
    • 2012
  • The paper reviews properties of hypothesis decision approaches using rejection region and significance probability. The study also presents the guidelines for quality practioners to implement most useful hypothesis testing techniques such as RR(Rejection Region) approach and P-Value approach.

  • PDF

구매유형에 따른 산업재 구매의사결정에 미치는 영향요인 (Influence Factors of Purchasing Decision Making of Industrial Buyer According to Purchasing Style)

  • 이승희;이영하;김혜경;조영준
    • 디지털융복합연구
    • /
    • 제6권3호
    • /
    • pp.121-129
    • /
    • 2008
  • This paper aimed to exam the influence factor of purchasing decision making of industrial buyer and analyzed their effects on success. From the previous studies, we extracted influence factor which are buying center, character of Industrial goods provider. The result showed the difference in the purchasing decision-making process in accordance with the type of buying task(Hypothesis 1). And a test was made the difference in the mode of purchase decision-making(Hypothesis 2). A test was made the difference in supplier's evaluative criterion in accordance with the type of buying task(Hypothesis 3).

  • PDF

Does Happiness Always Lead to Reliance on Feelings in Decision Making?

  • Moon-Yong Kim
    • International journal of advanced smart convergence
    • /
    • 제12권4호
    • /
    • pp.370-377
    • /
    • 2023
  • Previous research has demonstrated that happy moods are known to promote feeling-based processing, whereas sad moods promote reason-based processing. The current research investigates a boundary condition for the effects of a happy mood on feeling-based decision making. This research proposes that the level of control (low vs. high) one exercises in a happy situation can promote a greater reliance on feelings (vs. reasons) in making judgments and decisions. Specifically, we hypothesize that (1) a happy individual in a situation where control level is low (vs. high) will be more likely to choose a cognitively (vs. affectively) superior option (hypothesis 1), and (2) a happy individual in a situation where control level is low (vs. high) will exert reason- (vs. feeling-) based processing (hypothesis 2). Consistent with the hypothesis 1, the results of two experiments show that happy individuals are more likely to choose cognitively versus affectively superior options in a situation where control level is low (vs. high). Moreover, the mediation analysis confirms that happy individuals are more likely to rely on cognitive, reason-based decision making when their control level is low, which supports the hypothesis 2.

라이프스타일 유형이 외식 구매 의사 결정 과정에 미치는 영향 (The Effect of Lifestyle Patterns on Decision Making Process for Foodservice Purchase)

  • 김기영;배현수;허준
    • 한국조리학회지
    • /
    • 제14권4호
    • /
    • pp.257-268
    • /
    • 2008
  • The purpose of this study was to conduct factor analysis on Foodservice consumers' lifestyle patterns in dietary life, classify lifestyle patterns, and identify how lifestyle patterns influence the 5 stages of decision making process for purchase. Among 300 copies of the distributed questionnaire, 259 copies were collected for this study. It used a total of 283 copies as the effective samples for empirical analysis except 12 copies with false entries among them. For data analysis, it conducted frequency analysis, validity and reliability analysis, factor analysis, and multiple regression analysis using SPSS 12.0. As a result, Hypothesis 1 was significant while Hypothesis 2, 3, and 5 were partially significant. On the contrary, Hypothesis 4 was not significant. Therefore, lifestyle patterns had partially significant effects on decision making process for dining-out purchase. This study subdivided dining-out consumers' lifestyles which were limited to dietary life, and also subdivided decision making process for dining-out consumers' dining-out purchase into five stages. It is significant and very suggestive that this study identified what lifestyle patterns concretely had significant effects on the specific decision making stage. In the future, the researches on adolescent class and silver class should be executed continuously.

  • PDF

결정에서 반응 조화설의 재검증 (Re-examination of Response Compatability Hypothesis in Decision-Making)

  • 안상지;이영애
    • 인지과학
    • /
    • 제20권2호
    • /
    • pp.197-223
    • /
    • 2009
  • 반응 조화설 (Shafir, 1993)은 결정에서 두 대안 중 한 대안의 특징들이 선택이나 거부의 반응과 조화될수록 사람들이 그 대안을 더 택한다고 주장한다. 장단점을 많이 가진 풍부한 대안이 그렇지 않은 보통의 대안보다 더 많이 선택되고 더 많이 거부되어야 한다. 유승민과 이영애(2001)는 이 가설의 예측과 일치하지 않은 결과를 얻었다. 본 연구는 두 대안의 특징들의 제시 방식 그리고 질문 순서를 변화시켜 반응 조화설을 검토하였다. 특징들을 나열하지 않고 문장으로 제시하고 선택 또는 거부 질문을 먼저 제시하였을 때 반응 조화설과의 예측과 상당히 일치하는 결과를 얻었다. 본 연구는 반응 조화설을 검토할 때 선호의 구성 방식이 중요함을 밝혔다. 본 연구의 결과를 최근 연구들과 비교하였다.

  • PDF

스케일러블 비디오 부호화에서 통계적 가설 검증 기법을 이용한 고속 화면간 모드 결정 (Fast Intermode Decision for Scalable Video Coding using Statistical Hypothesis Testing)

  • 이범식;함상진;김병선;이근식;박근수;김문철
    • 방송공학회논문지
    • /
    • 제12권3호
    • /
    • pp.250-265
    • /
    • 2007
  • 본 논문에서는 가변 움직임 블록을 이용한 움직임 예측과 계층적 B-화면 구조가 결합되어 많은 연산량이 요구되고 있는 SVC 구조에서 통계적 가설 검증 방법을 적용하여 화면간 움직임 모드 결정을 효율적으로 수행함으로써 부호화 과정의 연산량을 크게 줄일 수 있는 화면간 모드 고속 결정 알고리듬을 소개한다. 제안된 방법은 $16{\times}16$ 매크로 블록과 $8{\times}8$ 하위 매크로 블록에 통계적 가설 검증 기법을 적용하여 실행되며, 현재 블록과 복원된 참조 블록간의 화소값을 비교하여 율-왜곡 최적화 (RDO: Rate Distortion Optimization) 기반 움직임 모드 결정을 고속으로 수행함으로써 SVC의 부호화 과정에서 소요되는 부호화 시간을 전체 연산량 대비 최대 69%까지 감소시킨다. 그러나 연산량 감소에 따른 비트율의 증가나 화질의 열화는 무시할 수 있을 정도로 적음을 실험을 통해 확인하였다.

조세와 자금조달결정의 관계에 관한 실증연구 (An Empirical Study on the Relationship Between Tax and Financing Decision)

  • 신용재;김형규
    • 산업융합연구
    • /
    • 제2권1호
    • /
    • pp.23-46
    • /
    • 2004
  • Tax exhaustion effect hypothesis says that firms with low expected marginal tax rates on their interest deductions employ less debt in their capital structure. We use logit analysis to study how financing decision is related to tax after controlling non tax effects. We treat non debt tax shields as proxy of marginal corporate tax rates which affect the probability of using the deductibility of debt tax shields and empirically test the tax effect on financing decision in Korea. In conclusion, we provide evidence that debt financing is positively related to tax in the former sub-period. This results partially support for tax exhaustion effect hypothesis and low tax rate firms have lower debt levels than high tax rate firms.

  • PDF

대학생의 통제위치가 진로의사결정유형에 미치는 영향 (The Influence of student career decision-making on the type of locus of control)

  • 이길환;서정민;이일우
    • 대한안전경영과학회지
    • /
    • 제14권3호
    • /
    • pp.299-314
    • /
    • 2012
  • In this study, college students, the nature of the locus of control type determines that they affect about career decision making. For this purpose I a systematic and comprehensive study to literature research and empirical research. This research topics and research model based on the hypothesis set and set the hypothesis verified results to the following conclusions were able to elicit. Internals types influence that they showed a positive impact in reasonable career decision making type. Externals types influence that they showed a positive impact in intuitive, dependent career decision making type. The summarized facts, as above, may be empirical analysis results that may be advised during the career decision making of college students, and will be data which will propose a new direction in the career decision making of college students also.

Consumer Analysis for Increasing Occupancy Rates of Tourism Hotel

  • Gozaly, Jimmy
    • Industrial Engineering and Management Systems
    • /
    • 제16권1호
    • /
    • pp.103-108
    • /
    • 2017
  • Tourism is a sector that plays an important role in the economic growth of Indonesia. Bandung as the capital of West Java province is known as the city with diverse tourism potential, both in the attractiveness of the city and surrounding natural beauty. DHR is a three stars resort hotel in the city with a strategic location. As a three stars resort hotel, DHR has been experiencing occupancy rate problems, consequently, it cannot often reach the set targets, both during high season and low season. The purpose of this study is to identify the factors of hotel performance that influences consumer staying back decision in the future. Questionnaires have been distributed to hotel guests to gather information regarding their interest and the performance assessment of the hotel services and facilities, and staying back decision in the future. Discriminant Analysis and Hypothesis Testing are used to determine which hotel performance variables will directly affect consumer staying back decision. The result of this study provide marketing strategy that should be implemented by the hotel management in order to increase its occupancy rate.

Weighted Finite State Transducer-Based Endpoint Detection Using Probabilistic Decision Logic

  • Chung, Hoon;Lee, Sung Joo;Lee, Yun Keun
    • ETRI Journal
    • /
    • 제36권5호
    • /
    • pp.714-720
    • /
    • 2014
  • In this paper, we propose the use of data-driven probabilistic utterance-level decision logic to improve Weighted Finite State Transducer (WFST)-based endpoint detection. In general, endpoint detection is dealt with using two cascaded decision processes. The first process is frame-level speech/non-speech classification based on statistical hypothesis testing, and the second process is a heuristic-knowledge-based utterance-level speech boundary decision. To handle these two processes within a unified framework, we propose a WFST-based approach. However, a WFST-based approach has the same limitations as conventional approaches in that the utterance-level decision is based on heuristic knowledge and the decision parameters are tuned sequentially. Therefore, to obtain decision knowledge from a speech corpus and optimize the parameters at the same time, we propose the use of data-driven probabilistic utterance-level decision logic. The proposed method reduces the average detection failure rate by about 14% for various noisy-speech corpora collected for an endpoint detection evaluation.