• Title/Summary/Keyword: 콕스 회귀분석

Search Result 21, Processing Time 0.029 seconds

A Longitudinal Study on the Influential Factors for the Labor Market Entry of Disabled Women (여성장애인 노동시장 진입 영향요인에 관한 종단연구)

  • Park, Mi-Hee
    • The Journal of the Korea Contents Association
    • /
    • v.16 no.5
    • /
    • pp.783-801
    • /
    • 2016
  • The purpose of this research is to grasp the influencing factors on the labor market entry of disabled women, and to suggest policy alternatives to support the labor market entry of them. This article utilized the survey data of the 3rd to the 7th Panel Survey of Employment for the Disabled in 2010-2014(by PSED), which is a longitudinal survey for the disabled in Korea. I analyzed the pattern changes of the labor market entry of them with the passage of years, and the influencing factors on that by the event history analysis. The major findings are as follows: First, according to the life table analysis involved in change of the labor market entry, 90% of them continued to remain the longest period of unemployment for four years and the labor market entry rate was only 10% of them. Second, the result of Cox regression analysis shows that public benefit recipient or not, the degree of disability and discrimination experience at the job market were factors to affect the labor market entry. With these results, this study suggested the practical alternatives to improve the labor market entry of disabled women.

A Study on Firm Survival Factors : Focusing on Korean Software Firms (기업의 생존요인 연구 : 국내 소프트웨어 기업을 중심으로)

  • Park, Gangmin;Kim, Jun Youn
    • Journal of Technology Innovation
    • /
    • v.26 no.4
    • /
    • pp.98-121
    • /
    • 2018
  • This article analyzes the survival of Korean software firms from 1995 to 2015 by Cox regression model and product-limit method. The results show that survival rates are different for each sector: IT service, package software, game software and internet service. In addition, firm growth and investment in research and development positively affect software firm's survival, while slack resources negatively affect the software firm's survival. The implication of this study is that characteristics of the software industry and technologies should be taken into consideration in survival strategy of software firms and government policy. Previous research on survival analysis has been mainly conducted in the manufacturing industry or at the special circumstance such as the foreign exchange crisis of Korea in the late 1990s. The contribution of this study is that expanding the survival analysis to software firms in Korea which are becoming more important recently.

A Study on the Factors Affecting the Likelihood of the Asset Poor's Poverty Exit and Entry (자산빈곤이행 가능성에 영향을 미치는 요인에 관한 연구)

  • Kang, Sung-min;Yoo, Tae-kyun
    • Korean Journal of Social Welfare Studies
    • /
    • v.40 no.1
    • /
    • pp.115-138
    • /
    • 2009
  • The primary focus of this study is to examine the characteristics of the asset poor and to empirically investigate those factors affecting the likelihood of the asset poor's poverty exit and entry. The 2nd wave through 8th wave data from KLIPS were used for analysis. The asset poverty lined of 50% of the household net asset was set up so that households below 50% are classified as the asset poor. The characteristics of the asset poor were examined in a static manner by analyzing only the 8th wave KLIPS data. To investigate those factors affecting the likelihood of asset poor's poverty transferal with a dynamic perspective, the authors employed two survival analysis methods, the life table analysis and the Time-dependent Cox regression analysis. Based on the findings, some recommendations were made for future policy efforts to support the asset poor and for the current poverty policies as well. In specific, if the 'Individual Development Account' is to be initiated in the future, it would be essential to build a systematic model to utilize accumulated asset by enhancing job competencies and ability to gain a decent job.

Mortality Risk by Living Arrangements among Old Adults: Comparison between Living with Others and Living Alone (노인의 거주형태에 따른 사망 위험요인: 동거노인과 독거노인의 비교)

  • Lee, Si-Eun
    • Journal of Digital Convergence
    • /
    • v.18 no.9
    • /
    • pp.249-256
    • /
    • 2020
  • This study was to identify differences in mortality risk by living arrangements among older adults. We analyzed data from 3,827 older adults who took part in the 2014 Korean Longitudinal Study of Aging. Cox proportional hazards regression was used for data analysis. The significant factors associated with mortality risk in living with others were male, education level, self-rated health, limitation of instrumental activities of daily living, cognitive dysfunction, and depression. The significant factors associated with mortality risk in living alone were regular exercise, limitation of instrumental activities of daily living, and cognitive dysfunction. This study is significant in that it examined whether there are differences between mortality risk by living arrangements. According to the results of this study, nursing intervention should be developed to decrease mortality by living arrangements.

A Dynamic Analysis of the Women's Labor Market Transition: With a Focus on the Relationship between Productive and Reproductive Labor (여성의 생산노동과 재생산노동의 상호연관성이 취업에 미치는 영향에 관한 경험적 연구)

  • 이재열
    • Korea journal of population studies
    • /
    • v.19 no.1
    • /
    • pp.5-44
    • /
    • 1996
  • Wornen's lahor market participation as well as the policy concern for wider utilization of married women, have continuously grown up. However, research efforts on the determinants of women's labor market participation, in the context of the relationship hetween life courses and active entry into lahor market, has been far behind the growing interest in this field. This study has conducted an event histoiry analysis of women's labor market transition utilizing personal occupational history data collected by the Korea Institute for Women's Development in 1991. The analysis is divided into tow parts: First part introduces logit regression to analyze the determinants of women's labor market participation and exit. The second part employs Cox regression to see the variation of transition rate between employment and non-employment. The result shows that there is a wide variation in women's labor market participation according to age, cohort, and family formation. Special note is needed for the significantly negative effect of marriage and child birth on labor market participation. The transition pattern of lower class women with less education fits well to the prediction of neo-classical economics; but the tendency of highly educated women's regression to non-employment reveals the strong influence of the unfavorable labor market structure, which can be better explained by the neo-structuralist perspective. There is a strong trade-off between productive and reproductive labor of women, which can only be corrected by strong policy implementation, such as extended child care facilities, abolition of discriminatory employment practices, and expansion of flexible part-time employment.

  • PDF

Variable Selection in Frailty Models using FrailtyHL R Package: Breast Cancer Survival Data (frailtyHL 통계패키지를 이용한 프레일티 모형의 변수선택: 유방암 생존자료)

  • Kim, Bohyeon;Ha, Il Do;Noh, Maengseok;Na, Myung Hwan;Song, Ho-Chun;Kim, Jahae
    • The Korean Journal of Applied Statistics
    • /
    • v.28 no.5
    • /
    • pp.965-976
    • /
    • 2015
  • Determining relevant variables for a regression model is important in regression analysis. Recently, a variable selection methods using a penalized likelihood with various penalty functions (e.g. LASSO and SCAD) have been widely studied in simple statistical models such as linear models and generalized linear models. The advantage of these methods is that they select important variables and estimate regression coefficients, simultaneously; therefore, they delete insignificant variables by estimating their coefficients as zero. We study how to select proper variables based on penalized hierarchical likelihood (HL) in semi-parametric frailty models that allow three penalty functions, LASSO, SCAD and HL. For the variable selection we develop a new function in the "frailtyHL" R package. Our methods are illustrated with breast cancer survival data from the Medical Center at Chonnam National University in Korea. We compare the results from three variable-selection methods and discuss advantages and disadvantages.

Effects of Nutrition Related Factors on Mortality Risk among Community-residing Older Adults in Korea (한국 지역사회 거주 노인의 영양관련 요인이 사망위험에 미치는 영향)

  • Lee, Si-Eun;Lee, Eliza
    • Journal of Digital Convergence
    • /
    • v.16 no.10
    • /
    • pp.343-350
    • /
    • 2018
  • The purpose of this study was to identify the effect of nutrition related factors on mortality risk among community-residing older adults in Korea. We analyzed data from 8,532 older adults who took part in the 2008 living profiles of older people survey and 2011 death mortality data. According to Cox regression analysis, male (Hazard Ratio [HR], 2.03; 95% Confidence Interval [CI], 1.74~2.37), diabetes mellitus (HR, 1.35; 95% CI, 1.12~1.64), underweighted (HR, 2.68; 95% CI, 2.16~3.31), dysphagia (HR, 1.23; 95% CI, 1.02~1.47), chewing ability (HR, 1.33; 95% CI, 1.11~1.59), and undernutrition (HR, 1.47; 95% CI, 1.23~1.75) significantly affected mortality risk. Systematic nutrition support programs should be developed to decrease the mortality among Korean older adults.

Prognostic Value of Serum Ferritin in Terminally Ill Cancer Patients (말기암환자에서 예후인자로서 혈청 Ferritin의 유용성)

  • Lee, Soo Hee;Choi, Youn Seon;Hwang, In Cheol;Yeom, Chang Hwan;Lee, June Yeong
    • Journal of Hospice and Palliative Care
    • /
    • v.18 no.1
    • /
    • pp.51-59
    • /
    • 2015
  • Purpose: Predicting life expectancy of terminally ill cancer patients is very important. In many studies, ferritin is detected at higher levels in the sera of cancer patients, and higher ferritin level correlates with aggressiveness of disease and poor outcomes of patients. This study evaluated a prognostic role of serum ferritin levels in terminally ill cancer patients. Methods: This study enrolled 65 terminally ill cancer patients from March through June 2012. We assessed routine laboratory findings including serum ferritin levels as well as demographic and clinical characteristics of the patients. To examine the association between serum ferritin levels and patient's characteristics, we used Spearman's correlation analysis, Wilcoxon's rank sum test or Kruskal-Wallis test, as appropriately. For multivariate analysis, Cox's proportional hazard regression model was used to evaluate significance of serum ferritin levels as a prognostic factor. Results: A negative correlation between serum ferritin levels and survival time was found. After adjusting for sex, age, performance status, creatinine levels and white blood cell counts, serum ferritin levels were significantly associated with survival time. Conclusion: Even at the very end of life of terminal cancer patients, serum ferritin levels were an independent prognostic factor for survival.

How Do Research Capabilities and Financial Resources Affect Professors' Entrepreneurship?: Using the Speed of University Spin-off Formations (교수의 연구역량과 연구비 수혜가 대학스핀오프 기업 형성 속도에 미치는 영향)

  • Cho, Sul-Ah;Kang, Ki-H.;Kang, Jin-A
    • Journal of Technology Innovation
    • /
    • v.19 no.2
    • /
    • pp.99-128
    • /
    • 2011
  • University-to-industry technology transfer has become an increasingly important issue in recent years. Studies on technology transfer and commercialization evolved to diverse knowledge transfer channels. Among them, university spin-off is not only known as the most direct and tangible method but also suitable for effectively transferring tacit knowledge. Much of the studies on university spin-offs are mostly focused on macro-level but studies using the individual professors as their unit of analysis need better understanding as well. This paper investigates why the speed of university spin-off formations differ among individual professors drawing on the resource-based view. Utilizing data of 149 professors in 25 universities who formed spin-offs, Cox regression results suggest that professors' technological research capabilities, academic research capabilities and financial resources promote university spin-off formations.

  • PDF

Impact of Gender Differences in Elderly Patients with Acute Myocardial Infarction (고령의 급성 심근경색증 환자에서 성별에 따른 영향)

  • Seol, Soo Young;Jeong, Myung Ho;Lee, Seung Hun;Sohn, Seok-Joon;Cho, Jae Yeong;Kim, Min Chul;Sim, Doo Sun;Hong, Young Joon;Park, Hyung Wook;Kim, Ju Han;Ahn, Youngkeun;Cho, Jeong Gwan;Park, Jong Chun
    • The Korean Journal of Medicine
    • /
    • v.94 no.1
    • /
    • pp.96-106
    • /
    • 2019
  • Background/Aims: It is well known that gender differences are associated with clinical outcomes in patients with acute myocardial infarction (AMI). However, it is not clear whether gender differences affect the prognosis of elderly patients with AMI. Methods: We analyzed the incidence of in-hospital complications and mortality in the Korea Acute Myocardial Infarction Registry-National Institutes of Health from November 2011 to June 2015. This study included elderly patients (≥ 75 years) diagnosed with AMI. Results: A total of 2,953 patients were eligible for this study. Among them, 1,529 (51.8%) patients were female, and the mean age of the female group was older than that of the male group (80.7 ± 4.4 vs. 79.6 ± 4.0 years, respectively, p < 0.001). Elderly females utilized emergency medical services less frequently compared with elderly males (11.5 vs. 15.4%, respectively, p < 0.001). Elderly female AMI patients had a similar rate of in-hospital mortality compared with elderly males (7.1 vs. 8.4%, respectively, p = 0.196). The rate of major cardiac adverse events (MACEs) was lower in elderly females than males during a 12-month follow-up (hazard ratio [HR] 1.19, 95% confidence interval [CI] 1.00-1.41, p = 0.045). According to multivariate analysis, the male gender is an independent factor for predicting 1-year MACEs (HR 1.37, 95% CI 1.14-1.65, p < 0.001). Conclusions: No significant differences in peri-procedural complications or in-hospital mortality were observed between male and female elderly patients with AMI. However, elderly female patients had a more favorable prognosis than male patients during a 1-year clinical follow-up.