• 가정과삶의질연구
• /
• 제8권1호
• /
• pp.15-30
• /
• 1990

The purpose of this study was to provide basic data for consumer complaining behavior. For this purpose, questionaire was given to 600 individuals who have resided in Seoul as the housewife consumer and possessed the experience to use the purchased refrigerators within the period of 5 years. 437 data were analyzed by the statistical methods like frequency, percentage, ANOVA, Duncan's Multiple Range Test, X2-test, Pearson's correlation and multiple regression analysis. The results of this study were described as follows; 1) Complaining behavior have shown significant differences according to housewife's age, degree of perceived housewife's consumer education, husband's job and housewife's job. 2) The type of attribution of dissatisfaction have shown significant differences according to husband's job, housewife's job and family income. 3) There was significant difference in the complaining behavior according to the type of causal attribution and responsibility attribution. 4) The complaining behavior was influenced by causal attribution of dissatisfaction, responsibility attribution of dissatisfaction, family income, degree of perceived housewife's consumer education, husband's job and housewife's age. And the relative contribution of each variable explaining the complaining behavior was decreased according to the order of variables that were described.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.247-251
• /
• 1997

FCM(Fuzzy Cognitive Map) is a fuzzy signed directed graph for representing causal reasoning which has fuzziness between causal concepts. Authors have already proposed FCM-based fault diagnostic scheme and verified its usefulness. However, the previously proposed scheme has the problem of lower diagnostic resolution as in the case of other qualitative approaches. In order to improve the diagnostic resolution, a concept of fuzzy number is introduced into the basic FCM-based fault diagnostic algorithm. By incorporation the fuzzy number into fault FCM models, quantitative information such as the transfer gain between the state variables can be effectively utilized for better diagnostic resolution. Furthermore, an enhanced TAM(Temporal Associative Memory) recall procedure and modified and modified pattern matching scheme are also proposed.

• 통상정보연구
• /
• 제10권1호
• /
• pp.329-347
• /
• 2008

The purpose of this study is to examine the causal relationship between the exchange rate and economic growth, and to induce policy implications. In order to test whether time series data is stationary and the model is fitness or not, we put in operation unit root test, cointegration test. And we apply Granger causality based on an error correction model. The results indicate that uni-dierctional causality between exchange rate and economic growth is detected. Exchange rate impacts on economic growth, but economic growth don't impact on exchange rate. The analysis of impulse reaction function shows that the impulse of exchange rate impacts on Korean economic growth in negative direction. We can infer policy suggestion as follows: The fluctuation of exchange rate much affects economic growth, thus we must make a stable policy of exchange rate to continue economic growth.

• Communications for Statistical Applications and Methods
• /
• 제7권1호
• /
• pp.65-86
• /
• 2000

The estimates from an EM when it is applied to a large causal model of 10 or more categorical variables are often subject to the initial values for the estimates. This phenomenon becomes more serious as the model structure becomes more serious as the model structure becomes more complicated involving more variables. In this regard Wu(1983) recommends among others that EMs are implemented several times with different sets of initial values to obtain more appropriate estimates. in this paper a new approach for initial values is proposed. The main idea is that we use initials that are calibrated to data. A simulation result strongly indicates that the calibrated initials give rise to the estimates that are far closer to the true values than the initials that are not calibrated.

• 아동학회지
• /
• 제27권3호
• /
• pp.271-284
• /
• 2006

In order to define their relative influence, this study analyzed causal relationships between academic achievement of elementary school students and such related variables as self-esteem and the psychological and economic environment of the home, including clarification of other significant variables affecting academic achievement. Participants were a sample of 485 5th grade students from 8 elementary schools in Busan. Correlation, analysis of covariance structure modeling, and model-fitness tests were applied to the data. Results indicated that the psychological environment of the home has the most significant influence on the academic achievement of children, and the economic environment of the home and self-esteem have relatively low or indirect influence.

• 수면정신생리
• /
• 제9권2호
• /
• pp.100-105
• /
• 2002

Personality traits in insomniac patients have been a subject of many studies. A number of these studies have used the MMPI and have demonstrated elevated scores on several clinical scales reflecting somatic concerns, somatization, depression, anxiety, worry and social alienation. And it was suggested that insomnia was due to a process of internalization of psychological distress. Another hypothesis about psychological mechanisms has focused upon worry. Excessive and uncontrollable cognitive activity seem to be a characteristic feature of many insomniacs. One author emphasized the role of the dependency need and found a characteristic pattern among insomniacs. The central feature of this pattern is frustration of dependency need. The purpose of this paper was to review possible personality variable that may be predisposing causal factors of insomnia. Several factors are suggested by many studies, but in order to explore their causal importance other experimental and longitudinal studies are needed.

• Journal of Korea Trade
• /
• 제25권2호
• /
• pp.178-195
• /
• 2021

Purpose - This study aims to analyze consumer in the multidimensional aspect of a combination of corporate image and brand personality in order to identify the structural causal relationship between consumer choice and corporate image and brand personality. Design/methodology - This study combined theoretical literature studies with empirical field studies using questionnaire survey methods. To achieve this objective, a hypothetical causal model consisting of three potential variables and nine measurement variables was created based on prior research, and a structural equation model was used to identify the suitability of the model. Findings - The hypothetical model established by this study was judged to be generally appropriate. In particular, corporate image was shown to have significant static direct effects on consumer choice and brand personality. It was also shown that brand personality had a direct static effect on consumer choice, and that corporate image has an indirect significant impact on consumer choice by moderating brand personality. Originality/value - Previous papers have mainly focused on one-dimensional studies of various images, such as companies and brands. However, this paper used a model that analyzed consumer choice through multi-clue information rather than corporate images as the only clue to consumer choice.

• 한국간호교육학회지
• /
• 제10권1호
• /
• pp.54-63
• /
• 2004

The purpose of this study is to identify the factors that influence stress experienced by nursing students and to provide a perceived causal structure model among these variables. The ultimate goal of this study is to develop efficient guidance to clinical nursing education in this population. This study intends to apply perceived causal structure: network analysis method which was developed by Kelly(1983), and has been applied in nursing research. This method is selected to show dynamic relationship of stressor using network method. Data was collected from convenient sample of 186 junior college nursing students who had the clinical practice experience during 10 weeks. Data collection and analysis was conducted in 2 steps from December, 9, 2002 to February, 8, 2003. Step 1.: Data was collected using literature review(10 articles) to identify the causes of stress. Nine causes of stress were extracted. Step 2.: As perceived casual structure network study, data was collected using questionnaires which included 9 extracted cause and stress. The questionnaire contained a 10 X 10 grid table with 10 causes and effects printed. In network analysis, 'Yes' was scored as 1, 'No' was scored as 0, and the mean(maximum 1, minimum 0) was calculated. Construction of the network under inductive eliminative analysis which stopped the construction of the network when the consensual agreement level dropped near 50% was proceeded by adding causes in order of the mean rating level. In this study, construction of the final network was stopped by consensual agreement level of 52% of the total subjects. The results are summarized as follows : Step 1: Investigation of the causes of stress ; The extracted causes of stress from quality data was identified 9 categories ; negative nurse, lack of clinical practice opportunity, ambiguous role, negative patient, lack of nursing knowledge and skill, difficult of personal relations, inefficient clinical practice guidance, gap of theory and practice, lack of support. Step 2 : Construction of the perceived causal structure model ; 1) The most central cause of stress is ambiguous role in the systems of causation. 2) The distal cause of stress is inefficient clinical practice guidance 3) The causes that have a number of outgoing link are negative nurse, ambiguous role. 4) The causes that have a number of incoming link are ambiguous role, gap of theory- practice, lack of clinical practice opportunity, lack of nursing knowledge- skill. 5) There is a mutual relationship between stress and difficult of personal relations, stress and ambiguous role, ambiguous role and negative nurse, ambiguous role and lack of clinical practice opportunity, ambiguous role and lack of nursing knowledge-skill, lack of nursing knowledge-skill and gap of theory- practice. In conclusion, the network suggests that the first centre cause is related on ambiguous role and the second on negative nurse, inefficient clinical practice guidance in the systems of causation

• 한국콘텐츠학회논문지
• /
• 제21권10호
• /
• pp.576-593
• /
• 2021

본 연구에서는 토익 시험의 정답률과 변별도에 영향을 미치는 구조적인 요인이 무엇인지 분석하기 위하여 문항 분석에서 도출된 각 파트별 코퍼스 지표들을 분석하였다. 이를 위하여 모의 토익 시험의 정답률과 변별도에 대한 코퍼스 요인들의 회귀 분석을 실시하였고, 분석 결과는 다음과 같다. 정답률에 대해서는 기초산출치중에서 word_length, no_word_sentence1, sentence_length, 정합성 지표들 중에서는 LSA_overlap_adjacent_sentences, 어휘 다양성 지표들 중에서는 MTLD_VOCD, 접속사 지표들 중에서는 All_logical_causal_connectives_incidence, 상황모형 지표들 중에서는 casual_particles_causal_verbs_Ratio, 통사적복잡성 지표들 중에서는 Minimal_Edit_Distance1, Left_embeddedness, 통사적 패턴밀도 지표들 중에서는 Infinitive_density, Preposition_phrase_density 등이 음의 영향을 미치는 것으로 나타났다. 이러한 코퍼스 요인들은 토익의 정답률을 낮추는 효과가 있기 때문에 하위 레벨의 학습자들이 단기적인 학습효과를 향상시킬 수 있는 중요한 정보들을 제공해 줄 수 있을 것이다. 변별도에 대해서는 어휘 다양성 지표들 중에서 MTLD_VOCD, 접속사 지표들 중에서는 All_logical_causal_connectives_incidence, Additive_connectives_incidence, 통사적 패턴밀도 지표들 중에서는 Infinitive_density, 어휘정보 지표들 중에서는 person1_2_pronoun_incidence 등이 정의 영향을 미치는 것으로 나타났다. 이러한 코퍼스 요인들은 변별도 증가에 영향을 주기 때문에 영어 능력 하위 그룹에 필요한 학습 프로그램을 개발하는 데 있어서 활용될 수 있을 것이다.

• 디지털융복합연구
• /
• 제19권3호
• /
• pp.167-176
• /
• 2021

최근 빅데이터 분석 기술이 발전하면서 사회 이슈를 분석하기 위해 그 동안 많은 텍스트 마이닝 기법을 활용한 연구들이 진행되어왔다. 사회이슈를 도출하기 위한 기존의 연구들을 살펴보면 다량의 텍스트 데이터를 뉴스, SNS 등으로부터 수집하여 토픽 모델링, 네트워크 분석 등의 기법을 이용하여 데이터로부터 이슈를 추출하고 분석하는 방식으로 연구들이 이루어져왔다. 사회 이슈는 다양한 사회현상들이 누적되어 나타나는 결과물이다. 하지만 기존 연구들이 가지는 한계점은 사회적으로 나타나는 이슈, 즉 결과에 대한 분석에 초점이 맞춰져 있어 해당 이슈의 발생 원인을 밝히는 것에는 한계를 가진다는 것이다. 사회이슈에 적절하게 대응하기 위해서는 어떠한 사회이슈가 존재하는지를 확인하는 것뿐만 아니라 사회이슈의 발생 원인을 파악하는 것이 필요하다. 이러한 한계점을 극복하기 위해서 본 연구에서는 사회 이슈와 관련한 텍스트로부터 사회이슈의 원인이 되는 요인을 도출하는 방법을 국어학의 품사이론을 기반으로 제안하였다. 이를 위해서 2017년 1월부터 2019년 12월까지의 3년 동안의 사회이슈와 관련한 뉴스데이터를 수집하여 수집된 텍스트 내 단어들의 인과관계를 인과문형을 찾아 분석한 후 기존 텍스트마이닝 기법 접목하여 사회이슈의 원인 단어들을 찾는 방법론을 제안하였다.