• 응용통계연구
• /
• 제29권2호
• /
• pp.389-398
• /
• 2016

본 연구에서는 신용보증기금으로부터 보증받은 기업의 미시적 성과를 분석하기 위해 비보증기업과 비교 분석하였다. t-test나 회귀모형과 같은 단순모형으로 비교하게 되면 선택편의에 의해 실제 보증성과를 나타낼 수 없다. 이러한 문제점을 해결하기 위해서, 선택편의를 보정한 회귀모형을 제안하였고 실제 자료에 적용하였다. 분석결과 비보증기업에 비하여 보증기업의 미시적 성과를 확인할 수 있었다.

• 가정과삶의질연구
• /
• 제25권4호
• /
• pp.31-41
• /
• 2007

This study aimed to develop a cognitive-behavioral group counseling program for depression and aggressiveness in adolescents with delinquent propensity and to examine its efficacy through pre- and post-tests. The program included cognitive restructuring, exposure training, social skills training and relaxation training. Juvenile Delinquency Scale, BDI, K-YSR, and BDHI were administered to 520 3rd grade middle-school female students to assess their levels of delinquency, depression and aggressiveness. Initially 41 students who met all the following criteria were selected: 1) top 15% scores on Juvenile Delinquency Scale, 2) top 30% scores on BDI, K-YSR and BDHI respectively. Individuals currently receiving clinical treatment were excluded. Finally 39 students were selected and randomly assigned to either a treatment group(n=20) or a control group(n=19). Then the students in the treatment group were divided into 4 subgroups. The program consisted of 12 weekly sessions, approximately $1.5{\sim}2$ hours in duration. Pre- and post-tests administered to both groups included Juvenile Delinquency Scale, BDI, K-YSR, BDHI, and CLAB. Additionally, MESSY for teachers was added at pre- and post-tests. The collected data were statistically analyzed through independent t-test and paired t-test. The results of the study were as follows: 1) The students in the treatment group showed a significant reduction in the level of depression and aggressiveness in comparison with those in the control group. 2) Teachers reported a significant reduction in internalizing/externalizing behaviors of the students in the treatment group.

• 응용통계연구
• /
• 제30권1호
• /
• pp.69-82
• /
• 2017

R-지수(representativeness indicator)는 무응답이 발생했을 때 표본의 대표성을 나타내주는 지표이다. 표본의 대표성은 모수 추정의 정확성(accuracy)과 관계가 있으며 정확성은 편향(bias)와 관계가 있다. 따라서 표본의 대표성을 나타내는 R-지수가 높으면 대표성이 높아 편향이 없고 정확성이 높은 결과를 얻을 수 있다. R-지수는 일반화선형모형의 로짓 또는 프로빗 모형을 적합한 후 얻어진 경향 점수(propensity score)에 의해 계산된다. 본 논문에서는 R-지수와 이질적인 층별 응답률과의 관련성을 연구하였으며 편향, 제곱근 RMSE 등과 같은 비교통계량이 무응답에 얼마나 민감한지 등을 모의실험을 통하여 살펴보았다. 또한 변형된 2010년 경제총조사 자료를 이용하여 실제 자료분석도 실시하였다.

• 대한간호학회지
• /
• 제37권3호
• /
• pp.414-421
• /
• 2007

Background: Nursing intervention studies often suffer from a selection bias introduced by failure of random assignment. Evaluation with selection bias could under or over-estimate any intervention's effects. PS matching (PSM) can reduce a selection bias through matching similar Propensity Scores (PS). PS is defined as the conditional probability of being treated given the individual's covariates and it can be reused to balance the covariates of two groups. Purpose: This study was done to assess the significance of PSM as an alternative evaluation method of nursing interventions. Method: An intervention study for patients with some baseline individual characteristic differences between two groups was used for this demonstration. The result of a t-test with PSM was compared with a t-test without matching. Results: The level of HbA1c at 12 months after baseline was different between the two groups in terms of matching or not. Conclusion: This study demonstrated the effects of a quasi-random assignment. Evaluation using PSM can reduce a selection bias impact that affects the result of the nursing intervention. Analyzing nursing research more objectively to reduce selection bias using PSM is needed.

• 응용통계연구
• /
• 제36권5호
• /
• pp.415-445
• /
• 2023

생존 자료에서 Hade 등 (2020) 은 시간-의존 교란 변수가 환자의 처치 시점에 영향을 미칠 때, 해당 효과를 보정하여 treatment delay effect를 올바르게 추정하기 위해 성향 점수 매칭 방법을 이용하였다. 이 때, treatment delay effect란 환자가 관심 있는 지연 시점만큼 늦게 처치를 받는 경우 제 때 받는 경우에 비해 사건 발생 위험에 미치는 영향을 의미한다. 본 연구에서는 또 다른 성향 점수 기반 모형인 Cox-MSM 모형 또한 해당 효과를 올바르게 추정할 수 있는지 모의 실험을 통해 확인 및 기존 매칭 모형과 비교하였다. 모의실험 결과, 세 가지 모형 모두 다양한 시나리오 내에서 treatment delay effect를 올바르게 추정함을 확인하였다. 특히 모든 시나리오 내에서 Cox-MSM의 제곱근평균제곱오차의 값이 가장 낮았으며, restricted Cox matching 모형에서 가장 큰 값을 가지는 것으로 나타났다. 결론적으로, 성향 점수에 기반하나 매칭이 아닌 방법 또한 treatment delay effect 적용이 가능하다는 결과를 제공한다. 추후 G-formula과 같이 성향 점수 기반이 아닌 모형에서도 적용이 가능한지에 대한 상세 연구가 필요하다고 사료된다.

• 응용통계연구
• /
• 제36권5호
• /
• pp.381-397
• /
• 2023

대부분의 임상시험에서 가장 대표적으로 사용되는 실험설계는 무작위화로, 치료 효과를 정확하게 추정하기 위해 이용된다. 그러나 무작위화가 이루어지지 않은 관찰연구의 경우 치료군과 대조군의 비교로 얻는 치료효과에는 환자 간의 특성 등 여러 조정되지 않은 차이로 인해 편향이 발생한다. 성향 점수 가중치는 이러한 문제점을 해결하기 위해 널리쓰이는 방법으로 치료 효과를 추정하는데에 있어 교란요인을 조정하여 편향을 최소화하도록 하는 방법이다. 성향 점수를 이용한 가중치 방법 중 가장 널리 알려진 역확률 가중치는 관찰된 공변량이 주어졌을 때 특정 치료에 할당될 조건부 확률의 역에 비례하는 가중치를 할당한다. 그러나 이 방법은 극단적인 성향 점수에 의해 종종 방해 받아 편향된 추정치와 과도한 분산을 초래한다는 점이 알려져있어 이러한 문제를 완화하기 위해 절사 역확률 가중치, 중복 가중치, 일치 가중치를 포함한 여러 가지 대안 방법이 제안되었다. 본 논문에서는 제한된 중복, 잘못 지정된 성향 점수 모델 및 예측과 반대되는 치료 등 다양한 문제상황에서 여러 성향 점수 가중치 방법의 성능을 비교하는 시뮬레이션 비교연구를 수행하였다. 비교연구의 결과 중복 가중치와 일치 가중치는 편향, 제곱근평균제곱오차 및 포함 확률 측면에서 역확률 가중치와 절사역확률 가중치에 비에 우월한 성능을 보임을 확인하였다.

• 노동경제논집
• /
• 제32권3호
• /
• pp.61-89
• /
• 2009

본 논문은 CECD의 PISA 2006 자료를 사용하여 전 세계의 상이한 국가들에서 사교육에 대한 지출(private education expenditures)이 학업성적 향상에 어떤 영향을 미치는지를 추정하였다. 사교육비 지출의 내생성을 통제하기 위하여 성향점수 매칭법을 사용하였다. 실증 결과에 의하면, PISA 2006 자료에 조사된 15개 국가들 각각에서 사교육비 지출의 효과는 그리 크지 않다. 사교육비 지출을 10% 증가시킬 때 성적은 평균 0.6% 정도 또는 그 이하로 증가한다.

• Hip & pelvis
• /
• 제34권2호
• /
• pp.96-105
• /
• 2022

Purpose: Use of dual mobility (DM) articulations can reduce the risk of instability in both primary and revision total hip arthroplasty (THA). Knowledge regarding the impact of this design on patient-reported outcome measures (PROMs) is limited. This study aims to compare clinical outcomes between DM and fixed bearing (FB) prostheses following primary THA. Materials and Methods: All patients who underwent primary THA between 2011-2021 were reviewed retrospectively. Patients were separated into three cohorts: FB vs monoblock-D vs modular-DM. An evaluation of PROMs including HOOS, JR, and FJS-12, as well as discharge-disposition, 90-day readmissions, and revisions rates was performed. Propensity-score matching was performed to limit significant demographic differences, while ANOVA and chi-squared test were used for comparison of outcomes. Results: Of the 15,184 patients identified, 14,652 patients (96.5%) had a FB, 185 patients (1.2%) had a monoblock-DM, and 347 patients (2.3%) had a modular-DM prosthesis. After propensity-score matching, a total of 447 patients were matched comparison. There was no statistical difference in the 90-day readmission (P=0.584), revision rate (P=0.265), and 90-day readmission (P=0.365) and revision rate due to dislocation (P=0.365) between the cohorts. Discharge disposition was also non-significant (P=0.124). There was no statistical difference in FJS-12 scores at 3-months (P=0.820), 1-year (P=0.982), and 2-years (P=0.608) between the groups. Conclusion: DM bearings yield PROMs similar to those of FB implants in patients undergoing primary THA. Although DM implants are utilized more often in patients at higher-risk for instability, we suggest that similar patient satisfaction may be attained while achieving similar dislocation rates.

• 기술경영경제학회:학술대회논문집
• /
• 기술경영경제학회 1997년도 제11회 하계학술발표회 논문집
• /
• pp.57-82
• /
• 1997

This paper empirically examines various personal characteristics and preferences of HRM (Human Resorce Mamagement) systems using data from 968 R&D professionals in 9 private R&D organizations. It identifies different patterns of reward and career development needs associated with 4 types of R&D professionals, who are categorized by personal characteristics: personality and attitude. A productive leader type shows active personal traits (which encompass high scores of need for achievement, risk-taking propensity, tolerance for ambiguity, and self-efficacy) and positive attitudes (which include high scores of job satisfaction, organizational commitment, and low scores of turnover intention), while a cynical bystander type exhibits passive personal traits and negative attitudes toward a job. A passive adapter, who has passive personal characteristics but positive attitudes, and a frustrated champion, who is active in personality but negative in current job attitude, lie in between them. The results reveal that: 1) These four different types of R&D professionals show differences in their education, age and tenure level, and technical performance. 2) They have different career orientations and problem solving styles. 3) They also exhibit different preferences in performance appraisal criteria and rater, and reward structures. Based on these findings, this study suggests a contingent type of human resource management in terms of selection and staffing of R&D professionals, performance appraisal, incentive systems, and career development plans.

• 지역사회간호학회지
• /
• 제26권2호
• /
• pp.89-99
• /
• 2015

Purpose: The purpose of this study was to demonstrate the effects of visiting nursing services in long-term care (LTC) insurance on changes in health status and physical functions among the elderly. Methods: We analyzed survey data on the living status and welfare needs of the elderly from 2008 and 2011 using the difference-in-difference method with propensity score matching. Results: The subjects were 76 elders including 38 visiting nursing service users(intervention group) and 38 home-based LTC service users (control group). Results from DID analysis confirmed that the subjective health status level of the intervention group was 2.2 points higher (p=.044) and the depression level was 0.3 point lower (p=.039) than the control group. In addition, the intervention group's ADL score was 1.9 (p=.027) and IADL 3.9 (p=.030), showing that their health was deteriorated less. Conclusion: Visiting nursing service in LTC insurance was associated with delayed deterioration of subjective health status, depression, ADL and IADL. These findings suggest the need of rebuilding visiting nursing service programs focusing on prevention services, which will be more contributive to elderly health care and the reduction of social costs.