• 제목/요약/키워드: Categorical Factor

검색결과 51건 처리시간 0.02초

집락표본자료에 대한 적합도검정과 독립성검정 (Goodness of Fit and Independence Tests for Clustered Sample Data)

  • 南宮 坪;崔秉洙;李柱祿
    • 응용통계연구
    • /
    • 제2권2호
    • /
    • pp.79-89
    • /
    • 1989
  • 일단집락표본추출에서 Pearson $X^2$과 Wald통계량, 표본설계효과에 의한 수정통계량 그리고 축소인자에 의한 수정통계량을 비교하였다. 적합도 검정과 독립성검정의 경우 시뮬레이션에 의한 결과, Wald 통계량은 Pearson $X^2$통계량과는 유의한 차이를 나타냈으나 두 개의 수정통계량는 큰 차이가 없게 나타났다.

  • PDF

부등 제한 조건하에서의 베이지안 추론 (Bayesian Inference with Inequality Constraints)

  • 오만숙
    • 응용통계연구
    • /
    • 제27권6호
    • /
    • pp.909-922
    • /
    • 2014
  • 부등제한 조건 (>,<,=)과 관련된 베이지안 추론에서 다음의 세 가지 주제에 대하여 기존의 연구와 최근의 연구동향 그리고 추후 연구주제에 대하여 살펴보았다 : ⅰ) 모수에 대한 여러 부등제한 조건들의 비교, ⅱ) 모수에 부등제한 조건을 부여하는 것이 타당하다고 할 때 모수의 동등성에 관한 동시 다중 검정, ⅲ) 순서적 범주형 변수에 대한 분할표에서 스코어 모수에 순서적 부등제한 조건을 가정 할 때 스코어 모수의 동등성에 대한 다중 검정.

Sales Forecasting Model Considering the Local Environment

  • Kim, Chul Soo;Oh, Su Min;Park, So Yeon
    • Communications for Statistical Applications and Methods
    • /
    • 제19권6호
    • /
    • pp.849-858
    • /
    • 2012
  • Today, local environmental factors has an influence on our society. Local environmental factors, as well as weather-related natural phenomena, social phenomena are also included. In this paper, numeric factors and categorical factors were analyzed, looking for a local environmental factors affecting the company's sales.Sales model by performing a regression analysis based on this was implemented.Sales model considering the local environment had an accuracy of 88.89%.

Autoregressive Cholesky Factor Modeling for Marginalized Random Effects Models

  • Lee, Keunbaik;Sung, Sunah
    • Communications for Statistical Applications and Methods
    • /
    • 제21권2호
    • /
    • pp.169-181
    • /
    • 2014
  • Marginalized random effects models (MREM) are commonly used to analyze longitudinal categorical data when the population-averaged effects is of interest. In these models, random effects are used to explain both subject and time variations. The estimation of the random effects covariance matrix is not simple in MREM because of the high dimension and the positive definiteness. A relatively simple structure for the correlation is assumed such as a homogeneous AR(1) structure; however, it is too strong of an assumption. In consequence, the estimates of the fixed effects can be biased. To avoid this problem, we introduce one approach to explain a heterogenous random effects covariance matrix using a modified Cholesky decomposition. The approach results in parameters that can be easily modeled without concern that the resulting estimator will not be positive definite. The interpretation of the parameters is sensible. We analyze metabolic syndrome data from a Korean Genomic Epidemiology Study using this method.

어촌체험마을 방문객 유형화에 관한 연구 - 충남 태안군 어촌체험마을을 중심으로 - (A Study on the Types of Visitors to Experiential Fishing Villages - Focused on the Case of Tae An-Gun in Chung Nam Province -)

  • 김종화;조은정
    • 농촌계획
    • /
    • 제20권3호
    • /
    • pp.45-53
    • /
    • 2014
  • This study classifies the types of visitors to experiential fishing villages and analyses the features and target marketing strategies by categorical groups. Seven factors are extracted by Factor Analysis and the results of Cluster Analysis indicate the classification of five groups. The first group puts emphasis on the family connection, so family centered facilities and programs are necessary. The second group is composed of surrounding area residents whose purpose of visit is unclear. So environmentally friendly village development programs to encourage local patriotism are necessary. The third group puts emphasis on the necessary facilities and programs for experiencing the fishing village and traditional play, etc. The fourth group emphasizes programs related with the region and the means to satisfy visitor's aesthetic desires. Finally, the fifth group aims at various desires that are generally felt in experiential fishing villages. So this group requires marketing strategies from the public point of view. The existing research mostly surveys rural tourism villages, but this study highlights the difference in dealing with fishing villages as opposed to rural villages, from the perspective of industry and settlement.

A pooled Bayes test of independence using restricted pooling model for contingency tables from small areas

  • Jo, Aejeong;Kim, Dal Ho
    • Communications for Statistical Applications and Methods
    • /
    • 제29권5호
    • /
    • pp.547-559
    • /
    • 2022
  • For a chi-squared test, which is a statistical method used to test the independence of a contingency table of two factors, the expected frequency of each cell must be greater than 5. The percentage of cells with an expected frequency below 5 must be less than 20% of all cells. However, there are many cases in which the regional expected frequency is below 5 in general small area studies. Even in large-scale surveys, it is difficult to forecast the expected frequency to be greater than 5 when there is small area estimation with subgroup analysis. Another statistical method to test independence is to use the Bayes factor, but since there is a high ratio of data dependency due to the nature of the Bayesian approach, the low expected frequency tends to decrease the precision of the test results. To overcome these limitations, we will borrow information from areas with similar characteristics and pool the data statistically to propose a pooled Bayes test of independence in target areas. Jo et al. (2021) suggested hierarchical Bayesian pooling models for small area estimation of categorical data, and we will introduce the pooled Bayes factors calculated by expanding their restricted pooling model. We applied the pooled Bayes factors using bone mineral density and body mass index data from the Third National Health and Nutrition Examination Survey conducted in the United States and compared them with chi-squared tests often used in tests of independence.

한국 의류산업의 국제경쟁력 향상을 위한 결정요인 (The Determinants of International Competitiveness for the Korean Apparel Industry)

  • 백영하;박재옥
    • 한국의류학회지
    • /
    • 제32권3호
    • /
    • pp.474-485
    • /
    • 2008
  • The purpose of this study is to examine the determinants and elements to enhance Korean international competitiveness, employing Porter's(1998) Diamond Model. Half of the 500 leading apparel exporters that were members of the Korea Apparel Industry Association in 2003 were selected as the target of this research. From May to June of 2003, survey questionnaires were sent to executives of these 250 companies in person or by telephone, e-mail, or fax. Seventy questionnaires were used for the final data anlysis. The items used were Reliability, Categorical Regression, and Frequency, using SPSS 11.5. The results were as follows: First, as a result of analyzing the influence of international competitiveness in Korean apparel industry, the firm's strategy, structure, and rivalry was the most influential factor. Others were related and supporting industries, government, chance, demand conditions, and factor conditions. Also, the elements that affect Korean international competitiveness were listed as the level of price competition in foreign markets, the level of labor cost, export marketing capacity, and exchange fluctuation. The most important element to improve the international competitiveness of the Korean apparel industry was a demand growth rate of the overseas markets(Demand Conditions), followed by the level of the labor costs(Factor Conditions), the capability of internationalization(Firm Strategy, Structure, and Rivalry), the change of currency(Chance), the quality and management of products(Demand Conditions), the capability of planning products(Firm Strategy, Structure, and Rivalry), free trade from 2005(Chance), and global sourcing strategy(Firm Strategy, Structure, and Rivalry). Korea's main rival country in apparel related and supporting industry factors is China. However, Korea has a higher level of technology development, quality, and price level than China.

소아에서 발생한 장중첩증에서 수술적 치료의 필요와 관련된 위험인자 (Risk Factors Associated with the Need for Operative Treatment of Intussusception in Children)

  • 하헌탁;조자윤;박진영
    • Advances in pediatric surgery
    • /
    • 제20권1호
    • /
    • pp.17-22
    • /
    • 2014
  • The aim of this study was to identify the risk factor related to the need for operative treatment and avoid unnecessary non-operative management for intussusception in children. We retrospectively reviewed medical records of patient treated for intussusception at our institution between January 2006 and January 2013. Clinical features such as gender, age, seasonal variation, symptoms and signs, treatment results were analyzed. Univariate and multivariate analyses including a chi-square test for categorical variables and logistic regression analysis were performed. During the study period, 356 patients were treated for intussusception. 328 (92.1%) was treated successfully by the non-operative pneumoreduction, and 28 (7.9%) required operative management. On univariate analysis, risk factors which were related to the need for operative treatment were age, vomiting, bloody stool, lethargy, and symptoms duration. A logistic regression analysis in order to assess for independent predictors of operative treatment was performed. Age (<6 vs ${\geq}12$ months) (OR 4.713, 95% CI 1.198~18.539, p=0.027) and symptoms duration longer than 48 hours (OR 4.534, 95% CI 1.846~11.137, p=0.001) were significantly associated with a requirement for operative treatment. We conclude that younger age and a longer duration of symptoms (${\geq}48$ hours) are the independent risk factor related to the need for operative treatment for intussusception. Early surgical intervention or transfer to a hospital with pediatric surgical capabilities should be considered for patients with these findings.

Perineural Invasion Independent Prognostic Factors in Patients with Gastric Cancer Undergoing Curative Resection

  • Selcukbiricik, Fatih;Tural, Deniz;Buyukunal, Evin;Serdengecti, Suheyla
    • Asian Pacific Journal of Cancer Prevention
    • /
    • 제13권7호
    • /
    • pp.3149-3152
    • /
    • 2012
  • Objective: The prognostic significance of perineural invasion (PNI) in gastric cancer has been previously investigated but not clearly clarified. The objective of our study was to investigate the role of PNI as prognostic factor in patients undergoing curative surgical resection and without distant metastasis in comparison with other clinicopathological factors. Methods: Between 2001 and 2010, 287 cases of gastric adenocarcinoma underwent radical gastrectomy recorded in hospital based registries. PNI was assessed as positive when cancer cells were seen in the perinerium or neural fascicles intramurally. Categorical and continuous variables were summarized using descriptive statistics and compared using chi-square and Mann-Whitney U tests, respectively. Cancer related survival rates were estimated by the Kaplan-Meier method. Results: PNI was positive in 211 of 287 cancers (73%), with a positive relation to lymph node metastases and advanced stage (p=0.0001, p=0.0001, respectively), mural invasion, and lymphatic and blood vessel invasion (p=0.0001, p=0.0001, respectively). The median survival of the PNI positive patients was significantly shorter than that of their PNI negative counterparts (24.1 versus 38.2 months, p=0.008). In the multivariate analysis, we detected PNI was an independent prognostic factor (p=0.025, HR=1.21, 95% CL 1.08-2.3) along with classical clinicopathological variables such as lymph node involvement (p=0.001), pT stage (p=0.03), and LVI (p=0.017), but not age, gender, tumour localization, stage, histologic type, and surgery procedure. Conclusions: PNI positivity in gastric cancers was related mural invasion, lymph node involvement, advanced stage and lymphatic and venous blood vessels. The presence of PNI appeared as an independent prognostic factor on survival on multivariate analysis, not influenced by tumor stage, lymph node metastases and other classical factors.

현장 소방활동 안전사고 원인에 대한 4M 분석 (4M Analysis of the factors affecting firefighters' on-site safety)

  • 김태범;변혜정;강태선
    • 한국산업보건학회지
    • /
    • 제27권3호
    • /
    • pp.231-237
    • /
    • 2017
  • Objectives: This study was conducted to determine firefighters' work-related accident rate and investigate the factors affecting their on-site safety. Methods: We developed a web-based self-reported questionnaire designed to inquire into firefighters' work-related accident experience and the factors (4M; Man, Machine, Media, Management) affecting firefighters' on-site safety. We distributed questionnaires to all members of firefighting organizations in South Korea by e-mail and 9,149 were returned, resulting in a response rate of 23.1%. Results: Fifteen point seven percent of the respondents reported work-related injuries within the past one year, and 35.1% answered that current accident investigation reports are not helpful for preventing the same accident from recurring. Among the 4M factors, the one most affecting firefighters' on-site safety in the order of priority is the Man factor, followed by Machine, Media, and Management. However, the results from detailed sub-categorical factors showed some differences. 'Lack of human resources', one of the Management factors, was the most influential (70.3%), followed by 'worn-out equipment' under the Machine factor (67.2%). The viewpoint of elements of the Man factor including 'forgetting instructions' and 'fatigue and illness' were significantly different according to firefighters' rank. The higher the firefighter's rank, the more they answered 'forgetting instructions,' while the opposite was the case for 'fatigue and disease'. Conclusions: The present firefighters' accident investigation report needs to be improved, and the 4M method could prove very useful. In addition, it is necessary to set up a proper firefighters' accident investigation and prevention system.