Earticle

Purpose: This study explored how just culture, authentic leadership, safety climate, patient safety knowledge, and safety motivation all affect military nurses' reporting of patient safety events. Methods: This study adopted a cross-sectional and descriptive correlational design. Data were collected from 303 nurses working across eight military hospitals under the jurisdiction of the Armed Forces Medical Command in South Korea, from June 17 to July 25, 2020. The hypothesized model was then validated using structural equation modeling. Results: The participating military nurses did not show any proactive attitudes toward reporting near misses when compared with their responses to adverse or no-harm events. The final model exhibited goodness of fit. Herein, both safety climate (b ¼ 0.35, p ¼ .009) and patient safety knowledge (b ¼ 0.17, p ¼ .025) directly influence patient safety event reporting. Moreover, just culture indirectly influences patient safety event reporting (b ¼ 0.31, p ¼ .002). The discovered influencing factors account for 22.9% of the variance in explaining patient safety event reporting. Conclusions: Our findings indicate that just culture, safety climate, and patient safety knowledge either directly or indirectly affected patient safety event reporting among military nurses. These findings then serve to provide a theoretical basis for developing more effective strategies that would then improve military nurses' patient safety behaviors.

Purpose: This study explored the direct and indirect effects of risk factors of work-related musculoskeletaldisorders (WRMDs) in nurses working in intensive care units (ICUs). Methods: A cross-sectional study design was used. ICU nurses from 28 tertiary hospitals in the Hunanand Guangdong provinces participated in a survey conducted via a self-reported online questionnaire. Astructural equation model was used to fit the data and to evaluate associations among WRMDs and riskfactors. Results: Valid questionnaire samples were submitted by 984 ICU nurses. The prevalence of WRMDswithin the previous year among ICU nurses was 96.8%. A valid structural equation model was constructed,and a good fit was shown: Chi-square value/degrees of freedom ¼ 2.248; comparative fitindex ¼ .931; normal fit index ¼ .905; goodness-of-fit index ¼ .978; adjusted goodness-of-fit index ¼.966; and root mean square error of approximation ¼ .036. All regression coefficients for direct effectreached significant levels (critical ratio > 1.96 and p < .05). In the structural equation model, theoccurrence of WRMDs was directly affected by the following: physical factors, risk perception, and jobstress. Physical factors and a safe environment indirectly affected WRMDs through risk perception andjob stress. The strongest correlations with WRMDs were physical factors. Conclusion: The model provided a new perspective for understanding the associations among physicalfactors, workplace safety environment, risk perception, job stress, and WRMDs. To improve the practicesetting of the ICU, efforts should be made to help prevent WRMDs from physical, psychosocial, andenvironmental factors.

Purpose: Diabetes has the most detrimental impact on the dietary freedom of people with type 2diabetes (T2D), and it is important to facilitate dietary self-care behaviors in people with T2D withoutimpairing quality of life (QOL). Autonomous motivation to perform dietary self-care behaviors couldlessen their psychological burden and maintain their QOL. Therefore, the purpose of this study was toidentify the relationship between autonomous motivation for dietary self-care behaviors and QOL inpeople with T2D by establishing a hypothetical model using competence and implementation levels ofdietary self-care behaviors as mediating variables. Methods: This cross-sectional study recruited participants and collected data from August 2022 toJanuary 2023 using questionnaires assessing autonomous motivation for dietary self-care behaviors,competence and implementation levels of dietary self-care behaviors, and QOL directed toward peoplewith T2D at the outpatient diabetes department of a university hospital. The authors tested the hypotheticalmodel using structural equation modeling (SEM). Results: A total of 223 participants completed the questionnaires. The hypothetical model was modified based on testing the model using SEM. The final model showed a good fit, χ2(1) = 0.37 (p = .545);comparative fit index = 1.00; root mean square error of approximation = .00; standardized root meansquared residual = .01. The results showed that autonomous motivation for dietary self-care behaviorswas positively associated with overall QOL through competence and implementation levels of dietaryself-care behaviors, whereas it was not associated with diabetes-dependent QOL. Conclusion: Given that the final model was exploratory due to modifications from the hypotheticalmodel, further validation, including cross-validation using independent samples, should assess thereplicability and robustness of the model structure. Based on such validation, interventions to increaseautonomous motivation for dietary self-care behaviors in people with T2D may need to be developedand evaluated to improve their QOL.

Purpose: The project was to test a structural equation model in which self-efficacy, self-care health behaviors, and modifiable risk factors predict the quality of life (QOL) of individuals with coronary artery disease. Methods: The data set from the intervention study with 130 patients with coronary artery disease before the intervention was included in the secondary analysis for this study. The following parameters were measured: self-efficacy, self-care health behaviors with the subscales of health responsibility, exercise, consumption of a healthy diet, stress management, and smoking cessation; modifiable risk score; and QOL (assessed using the 36-item Short-Form Health Survey instrument). Results: The mean age of the participants was 66.1 years. The following evaluation parameters indicated that the proposed model provided a good fit to the data: comparative fit index at .87, goodness of fit index at .91, adjusted goodness of fit index at .84, standardized root mean square residual at .06, root mean square error of estimation at .09, and confidence interval at 0.06-0.13. Self-efficacy, self-care health behaviors, and modifiable risk factors had significant effects on QOL and explained 64.0% of the variance, with modifiable risk factors mediating between self-care health behaviors and QOL. Conclusions: The findings indicate that self-efficacy, self-care health behaviors, and modifiable risk factors play an important role in QOL in adults with coronary artery disease. Patients could be more confident in performing self-care health behaviors, leading to a better QOL, by more effectively managing their cardiovascular risk factors. Nursing strategies to improve QOL in this population should include motivating them to perform self-care health behaviors.

In a dynamic framework, our structural VAR approach shows determinants of mutual fund cash flows using the data of inflows and outflows obtained from Form N-SAR filings with the SEC in the EDGAR system. This approach allows us to understand how cash flows respond simultaneously to market volatilities, market returns, and fund returns. Empirical findings are as follows: First, market volatility (market return) shocks may have contemporaneous negative (positive) effects on net flows. We explain this result by the contemporaneous positive effect of market volatility (market return) shocks on outflows (inflows). Noteworthy is that outflows (inflows) are not affected by market return (market volatility) shocks. Second, fund return shocks have a statistically significant effect on net flows for more than 64% of sample funds in each fund style group, but this effect is somewhat mixed in terms of the sign or direction. Third, the logistic regression provides a partial explanation for the mixed effects of fund return shocks on cash flows. That is, such mixed effects may derive from diverse fund characteristics. The portfolio analysis provides similar conclusions. Finally, we find indirect evidence of the disposition effect for both growth funds and mid- and small-cap funds. Fund characteristics have important implications for the disposition effect.

We develop a log-linear structural VAR model to decompose unexpected excess market returns into permanent and temporary cash-flow news, discount-rate news, and nonfundamental news. We make some important findings. First, contrary to recent evidence for the United States, we find that discount-rate news plays a more important role than cash-flow news in global stock markets. Second, non-fundamental factor (i.e., investor sentiment) also plays a role in developed regional stock markets outside the United States. Finally, risk premiums are significantly higher in a down market than in an up market.

Mobile social shopping is a distinct subset of social shopping whereby users use mobile devices to participate in social shopping activities. This study aims to determine the antecedents of mobile social shopping intention. In this regard, we develop an integrated research model by incorporating the constructs from the theory of reasoned action, innovation diffusion theory, and self-determination theory. We collected the empirical data through an online survey of 312 respondents who are mobile social shoppers in Bangladesh. The structural equation model was used to assess the path relationships among constructs used in the research model. The findings of this study show that all predictors, except personal innovativeness, significantly influence the level of trust and electronic word of mouth, which, in turn, influences mobile social shopping intention. The importance performance map analysis outputs also depict that trust and electronic word of mouth are important factors, but they perform poorly compared to other constructs. The practical results strongly support the model integration, suggesting a comprehensive model can improve mobile social shopping intention. This can aid in the planning, evaluating, and implementing mobile social shopping, thereby improving the overall shopping experience for users.

One important individual characteristic exerting influence over the acquisition of pragmatic knowledge is pragmatic learning strategies. As it is in nascent stages of research interest, an attempt was made to investigate whether Iranian EFL learners’ comprehension of conversational implicature was predicted by memory, cognitive, metacognitive, social, compensation, and affective interlanguage pragmatic learning strategies. Totally, 376 upper-intermediate and advanced EFL learners, on the basis of their performance on a sample of Oxford Quick Placement Test, participated in this investigation. To carry out the present study, three data collection instruments were utilized including: Oxford Quick Placement Test, Interlanguage Pragmatic Learning Strategies Inventory, and Conversational Implicature Test. The hypothesized model was tested employing Amos 24 statistical package and revealed that Iranian EFL learners’ conversational implicature was predicted by cognitive, metacognitive and compensation interlanguage pragmatic learning strategies. Moreover, EFL learners’ cognitive IPLS was identified to be the strongest predictor (β= 0.45, p<.05) in predicting conversational implicature. This study concludes that the cognitive, metacognitive and compensation IPLS strategies can promote EFL learners’ comprehension of conversational implicature. The findings of the study can contribute to EFL teachers to implement more interlanguage pragmatic learning strategies in their classroom activities to develop better comprehension of conversational implicature and integrate this knowledge into the overall learning experiences.

از آنجایی کھ اینگونھ پژوھش ھا در مرحلھ ابتدایی پژوھشی قرار دارند، در این مقالھ تلاش شد تا بھ بررسی این موضوع پرداختھ شود کھ آیا درک زبان آموزان ایرانی از معانی ضمنی توسط استراتژی ھای حافظھ ای، شناختی، فراشناختی، اجتماعی، جبرانی، و عاطفی پیش بینی می شود؟ در مجموع 376 زبان آموز زبان انگلیسی سطح متوسط و پیشرفتھ بر اساس عملکردشان درنمونھ آزمون تعیین سطح برای انجام پژوھش انتخاب شدند. ھمچنین از سھ ابزار جم عآوری داده از جملھ آزمون تعیین سطح آکسفورد، پرسشنامھ استراتژی یادگیری بین زبانی منظور شناسی و آزمون درک معانی ضمنی استفاده شد. نتایج معادلات ساختاری پژوھش حاضر نشان داد کھ استراتژی ھای یادگیری شناختی، فراشناختی و جبرانی، درک معانی ضمنی مکالمھ زبان آموزان ایرانی را پیش بینی می کنند. ھمچنین،استراتژی یادگیری شناختی فراگیران زبان در پیشبینی درک مفاھیم ضمنی مکالمھ نقش بسیار مھمی را ایفا می کند. یافتھھای این مطالعھ میتواند بھ معلمان زبان انگلیسی کمک کند تا استراتژی ھای یادگیری شناختی،فراشناختی و جبرانی را در فعالی تھای کلاسی خود پیادهسازی کنند تا بدین وسیلھ بھ درک بھتری از مفاھیم ضمنی مکالمھ دست یابند واز این دانش در تجربیات یادگیری کلی استفاده نمایند.

구조방정식모형의 안정적인 추정을 위해서는 정확한 모형과 적절한 자료가 요구되나, 실제 연구에서는 이러한 조건을 모두 충족하는 데 한계가 있어 추정이 불안정해지는 경우가 빈번하다. 최근 정규화 기법이 구조방정식 분야에서 추정의 안정성을 향상시킬 수 있는 방법으로 도입되면서 관련 연구가 활발히 이루어지고 있다. 그러나 대부분의 연구자에게 정규화 기법은 여전히 생소하며, 이를 활용하여 추정 불안정 문제를 해결하는 것은 익숙지 않다. 따라서, 본 연구에서는 정규화 기법의 개념을 전반적으로 소개하고, 구조방정식모형에서의 적용 방안을 빈도주의 추정법에 따라 정규화된 최대우도 추정 및 정규화된 최소제곱 추정으로 구분하여 제시한다. 또한, 구조방정식에서 발생할 수 있는 추정 불안정 문제의 원인을 정리하고, 특정한 추정 불안정 상황에서 정규화 기법의 적용 가능성을 탐색하여 상황별 적용 가이드라인을 정리한다. 마지막으로, 실제 자료를 활용하여 정규화된 구조방정식모형의 분석 과정을 구체적으로 제시하고, 특정한 추정 불안정 상황에서 일반적인 최대우도 추정 결과와 비교함으로써 정규화 기법의 효용성을 확인한다.

Structural equation modeling (SEM) relies on accurate model specification and appropriate data to ensure stable parameter estimation. However, in practice, these ideal conditions are often difficult to satisfy, leading to frequent issues with estimation instability. In recent years, regularization techniques have emerged as a promising solution to enhance estimation stability in SEM, drawing increasing attention in the field. Despite their potential, regularization methods remain unfamiliar to many researchers, and applying them effectively to address estimation challenges is not yet commonplace. This study aims to bridge this gap by providing a comprehensive overview of regularization techniques and proposing practical approaches for their application in the context of frequentist SEM. Specifically, we distinguish between regularized maximum likelihood estimation and regularized least squares estimation, outlining how each can be utilized to mitigate instability. We also identify key sources of estimation instability in SEM and explore how regularization can be applied in response to specific instability scenarios, offering corresponding guidelines for implementation. Finally, an empirical example using real data is presented to illustrate the full analytical procedure of regularized SEM. Through a comparative analysis with conventional maximum likelihood estimation under a condition of instability, we demonstrate the practical advantages and effectiveness of regularization approaches.

이 연구는 선행연구에서 밝혀진 요인들을 중심으로 음주운전자 174명과 일반운전자 166명을 대상으로 성격요인, 인지요인 및 음주운전 행동 간의 구조관계를 알아보고 두 집단 간 구조모형에 유의미한 차이가 존재하는지 살펴보았다. 음주운전 관련 인지요인의 측정 문항 개발을 위해 선행연구에서 사용된 음주운전 인지관련 문항을 참고로 예비문항을 만들고 내용타당화 과정을 거쳐 최종적으로 12개의 문항을 선정하였다. 확인적 요인분석을 통해 내적 통제력과 외적귀인을 음주운전 인지요인 척도로, 음주운전 관련 성격 요인으로 공격성, 충동성, 감각추구성, 새로운 경험추구성을 선정하였다. 연구 결과, 일반운전자 집단과 음주운전자 집단 간에 구조모형의 차이는 존재하지 않았고, 두 집단 모두 완전매개 모형이 타당한 것으로 나타나, 일반적으로 음주운전과 성격과의 관계에서 인지요인의 매개 요인으로 작용함을 검증하였다. 이러한 결과는 음주운전 성격, 음주운전 인지, 음주운전 행동 세 요인들의 관계에 대해 보다 구조적인 정보를 제공해 주며, 사회문제로 부각되고 있는 음주운전 예방 및 재발방지 프로그램 개발의 기초 자료로 활용할 수 있다. 또한 음주운전 관련 성격, 인지요인들 간의 구조적 관계를 이해함으로써 운전자의 인지요인 및 성격 요인의 특성에 근거하여 차별적인 개입전략이 이루어져야함을 시사한다

Previous research has explored the domain of legal and educational prevention in regard of phenomena of accidents and injuries caused by drinking and driving. Most investigation of psychological factors attempt to distinguish characteristics of drunk drivers relative to the general driving populations. This study examined cognitive factors as a mediator between personality and drunk driving. Survey data from 174 convicted drunk drivers(single and multiple offenders) and 166 general drivers were analyzed using structural equation modeling. Two comparative models were proposed: full mediating model and partial mediating model. Result indicated that cognitive factors relevant to drunk driving fully mediated the relationship between personality and drunk driving and there is no significant difference between drunk drivers and general driving populations on supported structural model. The implications of these findings are discussed in the context of cognitions and personality to improve short term cognitive interventions and long term counseling interventions.

본 연구에서는 조직몰입 3요소 모형(Allen & Meyer, 1990)의 내적구조를 탐색적 구조방정식 모형(ESEM: Exploratory Structural Equation Modeling)을 적용하여 검토하였다. 그동안 많은 선행 연구들에서는 3요소 모형에 대한 확인적 요인분석의 결과로 정서적, 지속적, 규범적 몰입의 각 척도가 서로 구별되는 구성개념을 측정하는 것으로 보고되었다. 이에 본 연구는 기존의 문항분석 방식과 다른 개방적 문항분석 방식인 ‘척도 내’ 그리고 ‘척도 간’ ESEM을 적용하여, 한국의 사회복지기관에서 일하는 사회복지사를 대상으로 수집된 자료에서 문항들 간에 측정오차간 상관이 통제된 가운데 3요소 척도의 내적구조를 보다 정밀히 검토하였다. 이를 위해, 전통적 방식의 EFA 결과와 CFA결과를 개방적 방식의 ‘척도 내’ ESEM 결과와 비교하여 제시하고, 다른 유사 개념 또는 선행변수로 자주 연구되는 척도들과 함께 ‘척도 간’ ESEM을 실시한 결과를 제시하였다. 그 결과 ‘척도 내’ ESEM 모형에서 EFA 및 CFA 보다 더 높은 합치도와 요인 변별도가 제시되어, 실제 자료를 보다 잘 반영한 3요소 모형의 내적구조를 확인할 수 있었다. ‘척도 간’ ESEM 분석 결과에서는 방법요인에 의한 상관값이 비교적 크게 나타나, 방법효과가 여러 개념들이 함께 측정되는 경험 자료에서 얼마나 심각하게 본래의 척도 구조를 왜곡시킬 수 있는지를 실증적으로 보여주었다. 이는 부정적 표현의 역문항들과 번역 과정에서 본래 의도와 다르게 해석될 수 있는 표현으로 인해 문항들간 발생가능한 방법효과를, 측정오차간 상관으로 추정하면서 확인된 부분이다. 3요소 모형의 내적구조를 검토하기 위해 본 연구에서 시도한 ESEM 방법론을 통해, 척도 내 문항들에서 발생할 수 있는 동일방법 효과를 통제하고서 내적 구조를 추정함은 물론, 각 문항들이 복수의 유사 개념을 측정할 수 있는 가능성을 충분히 허용함으로서 실제 척도의 양상을 보다 개방적으로 검토할 수가 있었다. 이러한 분석 결과는 서구에서 개발된 3요소의 선언척도가 문화권이 다른 한국의 경험 자료에서 나타나는 실제척도와 얼마나 다를 수 있는지를 확인하는 기회가 되면서, 동시에 한국의 문화를 반영한 조직몰입의 개념화와 타당화의 필요성을 제기한다. 한국 직장인들이 생각하는 조직몰입의 구성개념과 이론의 논리적 구조가 확립되어, 경험연구에서 지지될 수 있는 탄탄한 내적구조를 가진 조직몰입 척도의 개발이 요구된다.

Allen and Meyer's(1990) 3-component model of organizational commitment(OC) was investigated using exploratory structural equation modeling(ESEM) with samples of full-time social workers at social welfare organizations in South Korea. Confirmatory factor analysis(CFA) has been at the heart of testing factor structure of the 3-component model in organizational commitment research wherein each scale of the affective, continuance, and normative commitment is reported to measure conceptually and empirically separable construct. The present study applied ESEM, specifically ‘intra-scale’ and ‘inter-scale’ ESEM, to scrutinize factor structure of the 3-component scales. ESEM methodology uses exploratory approach in that all cross-loadings are estimated between each measure and factors, with uniqueness correlated according to the researcher's hypotheses as in CFA. In this respect, ESEM can be viewed as an open approach to item analysis distinguished from the conventional (closed) approach, such as EFA and CFA. This study provided detailed assessment of the 3-component model through comparisons of factor structures estimated by EFA, CFA and ‘intra’ ESEM, followed by the ‘inter’ ESEM conducted on all other variables(assumed to be similar constructs with or antecedents of OC). As a result, the ‘intra-scale’ ESEM showed a substantially better fit and yielded more discriminated factors(less correlated) than did EFA and CFA that are models for planned scale. The ‘inter-scale’ ESEM revealed how seriously method effect can distort an original factor structure in empirical data measured together with multiple scales of other constructs. Using ESEM has advantages of estimating common factor structures, controlling for common method effect that are typically included in measures in applied research. Also, it allows for much more possibilities that each item can measure multiple constructs so as to reveal more realistic factor structures. Taken together, the present results suggest a need to conceptualize and validate a new scale for organizational commitment reflecting Korean culture.

Purpose: This study aimed to identify the factors explaining the performance of health behaviors among adults withmetabolic syndrome based on the theory of planned behavior. Methods: A total of 218 adults with metabolic syndromewere recruited for the study from September to December, 2017. Data were analyzed using SPSS/WIN 22.0and AMOS 24.0. Results: The hypothetical model appeared to fit the data with x2/df=2.65, SRMR (StandardizedRoot Mean Residual)=.07, PNFI (Parsimonious Normed Fit Index)=.67. Attitude toward health behavior, subjectivenorm and perceived behavioral control explained 32.3% of variance in intention toward health behavior. Perceivedbehavioral control showed significant direct effects and mediating effect through intention on health behavior (γ=.57,t=5.85). Family support also had significant direct effects on health behavior (γ=.38, t=4.75). Attitude toward healthbehavior, subjective norm, perceived behavioral control, and family support were the significant factors explaining56.3% of variance in the performance of health behaviors among patients with metabolic syndrome. Conclusion:Health promotion programs for behavioral modification in this population should focus on these factors to lead tobetter health outcomes. Further studies are warranted to test the health promotion strategies based on theory ofplanned behavior for long-term change toward a healthy lifestyle among individuals with metabolic syndrome.

Purpose: The purpose of this study was to determine the relationship among concepts of the salutogenic model - sense of coherence, occupational stress, and health status in clinical nurses. Methods: Participants were recruited from a hospital in Seoul using a stratified random sampling. A total of 349 nurses participated in the study and data were collected using a self-administered questionnaire. The structural equation model was used to assess the relationships among the variables. Results: The results of the study showed that occupational stress and health behavior were significant factors, directly explaining the health status of nurses. Factors explaining occupational stress were: sense of coherence, and social support. Sense of coherence showed higher effects on occupational stress than those of social support. Sense of coherence and the work conditions (work experience and shift work) of nurses had a significant and direct effect on health behavior. Sense of coherence and social support had a significant and indirect effect on health status through occupational stress and health behavior. Conclusion: Strategies to enhance sense of coherence and social support are necessary for successful health promotion programs for nurses.

본 연구는 한국주택금융공사 보금자리론 풀을 대상으로 합리적 조기상환을 가정하는 이론모형을 통해 조기상환율을 추정하고 분석하는 것을 목적으로 한다. 연구대상 풀은 2010년 12월 기준 최소 관측치가 30개가 넘는 34개 풀이며 조기상환 관측치는 1,877개 관측치를 활용하였다. 이론모형은 금리요인 외에 주택가격을 상태변수로 도입하며, 모기지 차입자의 이질성을 명시적으로 고려하는 Downing, Stanton, and Wallace(2005) 모형을 적용하되 주택가격이 하락하는 경우 뿐 아니라 상승하는 경우에도 조기상환율에 영향을 미칠 수 있도록 조기상환 위태율 구조를 변형하여 조기상환율을 추정하였다. 조기상환율 추정 시 금리요인 외에 주택가격을 상태변수로 포함하는 경우와 포함하지 않는 경우를 구분하여 분석하였다. 실증분석결과 모기지론의 조기상환율을 설명하는 요인으로서 금리변수와 함께 주택가격변수 역시 통계적으로 유의하게 추정되었다. 위태율 모수구조에 있어 Downing et al.(2005)과 같이 주택가격을 가격하락에 따른 부도요인에만 영향을 미치는 방식으로 설정하는 경우에는 조기상환율을 설명하기 어려웠으며 주택가격 상승도 조기상환율에 영향을 미칠 수 있도록 설정된 변형된 위태율 모수구조에서는 추정 결과가 우수하였다. 국내의 경우 부도요인 효과가 유의하지 않은 이유는 연구 대상기간(2004년~2010년)동안 주택가격이 큰 폭으로 하락한 경험이 없고 모기지론 대출시장에서 보수적인 LTV(Loan-To-Value)가 적용되어 온 것에 기인하는 것으로 판단된다.

We estimate a two-factor structural mortgage valuation model using data on pool-level termination rates for fixed-rate mortgage loans issued by the Korea Housing Finance Corporation (KHFC) between 2004 and 2008. Our model is a modified version of that proposed by Downing, Stanton, and Wallace (DSW, 2005), in which borrowers rationally decide when to prepay and default in response to changes in house prices as well as interest rates. DSW (2005) find that incorporating house price movements into the model significantly improves its ability to match historical prepayment data over Stanton’s (1995) one-factor (interest rate only) model. In DSW (2005), house price changes are modeled to affect borrowers’ termination behavior only when prices decline by increasing the value of default option, but this particular specification does not bode well for our Korean sample period, during which house prices did not experience substantial or sharp declines. Consequently, we modify DSW’s (2005) two-factor model so that house price movements influence termination behavior when prices increase as well as when prices decline. In contrast to the structural model used in this paper, previous empirical research on mortgage prepayment in Korea has mostly used statistical models, in which termination behavior is modeled as a function of a set of exogenous variables such as interest rates and house prices that represent the factors affecting prepayment and default. While such statistical approach may produce estimated prepayment rates that are closer to the historical data, its out-of-sample forecasting power is likely to be low, and the model is not suitable for pricing mortgage-backed securities. The structural approach taken in this study, on the other hand, models prepayment and default as a rational borrower’s optimal responses to the changes in interest rates and house prices that represent the model’s state variables. Such structural models should perform better out of sample than statistical models, and they can be used in the valuation of mortgage-backed securities. The mortgage prepayment data used in this study are from 34 pools of fixed-rate mortgage loans (called Bogeumjari loans) issued by the KHFC. The sample period is from June 2004 to December 2010, and the prepayment rates at the pool-level, as published monthly by the KHFC, are used. The empirical results show that both interest rates and house price changes significantly affect prepayment rates. In particular, house prices and prepayment rates have a positive association, consistent with Park and Bang (2011) and Choi and Kim (2011), who use statistical models. In addition, incorporating house price movements into the model improves its performance in matching historical prepayment rates, compared to the model in which only interest rate movements are considered. The results of Davidson and MacKinnon’s (1981) J-test selecting between non-nested models show that the two-factor specification that includes house prices and interest rates is better for estimating prepayment rates than the one-factor (interest rate) specification. Moreover, we find that the two-factor model produces prepayment forecasts that are closer to the historical data than the one-factor model in an out-of-sample test. In a structural model, mortgage terminations (prepayment or default) are the result of borrowers’ optimizing behavior, and house price movements can affect the borrowers’ termination behavior as follows. When house prices fall, the value of the default option implicitly held by the borrower increases. And the movements in the value of the default option significantly affect the value of the borrower’s prepayment option and therefore, the likelihood of prepayment. However, we find that prepayment rates decrease with declining house prices. The house prices in Korea experienced some declines during our sample period, but not by any substantial degree. Our finding of lower prepayment rates in times of declining house prices is similar to Mattey and Wallace (2001), who find that weak house prices tend to depress refinancing and prepayments. When house prices increase, so does the collateral value of the houses and the value of the borrower’s equity, which influences the likelihood of prepayment if, for example, the borrower wants to cash out some of the increase in equity. This argument is consistent with the higher prepayment rates during times of increasing house prices found in this paper. More specifically, the period of increasing house prices in our sample is from late 2006 to early 2007, which coincides with rising interest rates. Despite the rising interest rates and penalties for prepayment, prepayment rates during that period increased in close association with rising house prices, suggesting that both interest rates and changes in house prices significantly affect mortgage prepayment rates in Korea.

통계 모형을 이용한 데이터 분석에서 적절한 결측치 처리가 최종적인 통계적 결론 도출에 결정적인 영향을 미칠 수 있다는 것은 이미 잘 알려져 있다. 따라서 현재까지 다양한 결측치 처리 기법이 제안되어왔고, 그 중 최근 활발히 연구되고 있는 기법으로서 완전정보최대우도(full information maximum likelihood), 다중대체(multiple imputation), 그리고 베이지안(Bayesian) 접근법이 있다. 이 중 완전정보최대우도법은 사회과학 통계에서 가장 많이 사용되는 방법으로서 많은 심리학 연구자들에게도 이미 알려져 있는 방법이나, 다른 두 방법, 즉 다중대체 및 베이지안 접근법은 아직은 많은 심리학 연구자들에게 생소한 방법이다. 따라서 본 논문에서는 이 세 가지 방법을 공분산 구조모형의 맥락에서 소개하고 주요 특징을 비교함으로써 심리학 연구자들의 결측치 처리에 관한 이해를 돕고자 하였다. 공분산구조모형의 적용 과정은 다른 통계모형과 달리 자료와 모형간의 적합도 지수를 계산하고 이를 바탕으로 모형의 적절성을 판단하는 과정을 포함한다. 최대우도법에서는 카이자승 통계량을 기준으로 다양한 적합도 지수가 파생되어 제안되었으며, 다중대체법은 D2와 D3 통계량이, 그리고 베이지안 접근법에서는 사후예측모형검증(posterior predictive model checking) 기법이 사용된다. 최대우도법의 카이자승 통계량은 다양한 맥락에서 독립적으로 연구된 결과가 있으나, 다중대체법 및 베이지안 접근법에서 제안된 방법은 공분산 구조모형의 맥락에서 그 성능이 평가된 적이 없으며 서로 비교된 적도 없다. 따라서, 본 논문에서는 동일한 구조방정식모형의 자료-모형간 적합성 판단에 있어서 세 가지 다른 결측치 처리 방법이 어떤 영향을 미치는지 비교 분석하였다. 구체적으로, 본 논문에서는 모의실험(simulation) 기법을 사용하여, 모집단에서 데이터가 종단적 측정 불변성을 지지하지 않는 경우(longitudinal measurement non-invariance)를 가정하고, 옳은 모형을 사용한 경우의 제 1 종 오류율과 부분측정불변성(partial measurement invariance)을 가정한 모형을 적용한 경우의 검정력을 최대우도, 다중대체, 그리고 베이지안 접근법 별로 추정/비교하였다. 본 연구의 결과는 결측치가 존재하는 데이터를 공분산 구조모형을 이용하여 분석하고자 하는 연구자들에게 결측치 처리 기법의 특성을 이해하고 최종 모형의 적합성을 판단하는데 적절한 지침을 제공할 것으로 기대된다.

In practical applications of any statistical modeling, including structural equation modeling(SEM), virtually every data set contains missing values. It is a well known fact that improper handling of missing data can exert harmful impact on subsequent statistical inferences in a variety of ways to varying degrees. In the context of SEM, the full information maximum likelihood(FIML) has been arguably the most popular method for addressing missing data. Despite of being yet less widely known to majority of applied researchers as flexible alternatives to FIML, multiple imputation (MI) procedures and Bayesian approaches have recently begun to emerge as viable solutions among many applied researchers. An important objective of this article is to introduce these methods to applied researchers in an accessible manner using SEM as the context. Structural equation modeling actually involves the process of proposing, estimating, and evaluating the researcher’s hypothesis that is believed to be underlying and purported in generating the observed data. Therefore, it is essential to evaluate the overall goodness-of-fit of the posited model in any given application. FIML, MI and Bayesian approaches, respectively, yield the chi-square, , , and the posterior predictive modeling checking (PPMC) p-value as statistical tools for the assessment of data-model fit. Another important objective of this article is to study performance of these model evaluation tools in the context of SEM. Further, relative performance of these data-model fit assessment tools is to be evaluated with respect to their Type I error rates and power. The performance of these assessment tools, except the chi-square statistics, has never been evaluated nor been compared within the context of SEM. The initial results provided in the present article is believed to not only enhance the knowledge base regarding the characteristics of these assessment tools under missing data, but also provide an initial guideline for the proper use of these assessment tools in the real-world data analysis especially in the application of SEM with missing data.

본 연구에서는 해외생산량 및 교역조건의 변화가 한국경제에 미치는 영향을 구조적 VAR모형을 이용하여 추정한다. 특히 이들 교란의 파급경로인 수출과 수입함수를 모형에 직접 포함하여 소규모개방경제의 특성을 반영하며 분석의 정확도 향상을 시도한다. 구조적 교란항은 공적분, 해외생산량의 외생성 그리고 장기제약조건을 이용하여 식별한다. 실증분석 결과 해외생산량 교란과 교역조건 교란은 수출 및 수입에 지대한 영향을 미쳤다. 또한 국내생산량 변동에도 결정적인 요인으로 단기에서의 영향력이 특히 크게 나타났으며 장기에서는 국내생산량 교란의 기여도와 동등하게 나타났다. 이러한 결과는 한국경제의 대외여건 변화에 대한 민감도를 다시 한번 입증한다.

This paper examines the effects of changes in foreign output and the terms of trade on the Korean economy using a structural VAR approach. Unlike previous studies, the model includes exports and imports so that the direct linkage of foreign activity to the domestic economy is explicitly taken account. The underlying structural shocks are recovered by imposing exogeneity of foreign output and long-run identifying restrictions together with cointegration relations. Empirical analysis shows that both foreign output and terms of trade shocks are the major determinants of movements in exports and imports. These shocks also contribute significantly to the variations of domestic output. The evidence is particularly strong in the short run while their total contribution in the long run is the same level as the domestic output shock. These results attest to the importance of external shocks in the Korean economy.

본 연구는 환변동보험의 결정 요인에 대한 연구를 동적 시계열분석을 통해 확장함으로써 환변동보험 수요 결정요인에 대한 보다 다양한 형태의 실증분석을 실시하고 그로부터 시사점을 도출하고자 한다. 이러한 연구목적을 위해 본 연구는 구조적 자기벡터회귀모형을 적용하고 그로부터 환변동보험 수요의 결정요인들에 대한 충격이 환변동보험 수요에 미치는 동태적 영향을 분석한다. 본 연구에서는 환변동보험 수요의 결정요인을 고찰하기 위하여 구조적 자기벡터회귀모형을 활용한다. 본 연구는 환변동보험 수요에 영향을 주는 요인으로 환변동보험금, 원-달러 환율, 환율변동성이 중요한 반면 수출규모는 유의한 영향을 주지 못함을 발견하였다. 이러한 결과는 환변동보험 수요를 설명하는데 있어서 외환시장의 추이와 환변동보험의 수출기업에 대한 보상 규모가 수출규모보다 더 중요하다는 시사점을 제시한다. 한편, 구조적 자기벡터회귀모형의 추정으로부터 도출된 결과는 사전적으로 주어진 이론적 가정에 의존하기 때문에, 추후 환변동보험 수요 관련 이론의 발전을 통해 보다 확장된 연구가 가능할 것이다.

This paper provides empirical evidence for the determinants of demand for foreign exchange risk insurance. In doing so, this paper adapts the structural VAR (SVAR) approach and explores dynamic response of foreign exchange risk insurance to the structural innovations of Won-Dollar exchange rate, exchange rate volatility, export, and foreign exchange risk insurance money. Using the SVAR approach, we impose several restrictions to the reduced-form VAR and implement economic structures to dynamic response of demand for foreign exchange risk insurance to the relevant shocks. The results show that the insurance money has a strong impact on the insurance demand while the Won-Dollar exchange rate and its volatility have moderate effects. In addition, the size of export has no significant effect on the insurance demand. Our empirical evidences imply that foreign exchange market and the insurance money play more crucial role than the size of export in explaining demand for foreign exchange insurance. The estimation results from SVAR, however, are subject to the ex ante assumptions on the insurance demand. Given the limitations of SVAR, more theoretical works are required to provide more foundations for related empirical studies.

This study examines the effect of reading strategy, self-efficacy, motivation, and previously acquired knowledge on English reading comprehension. The casual relationships among those variables were hypothesized. Data from a sample of 240 middle school students were collected to empirically test the proposed hypotheses in the research model. The structural equation modeling (SEM) approach was used to analyze the casual relationships between variables. The results indicate that four learners variables have a positive impact on English reading comprehension. In particular, reading strategy has a strongest impact on English reading comprehension followed by previously acquired knowledge. Finally, academic and practical implications are discussed based on the study results.