PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Event History Analysis”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2Linked to original sources
PubMed1996

Service utilization by schizophrenic patients in Groningen and South-Verona: an event-history analysis.

The question addressed to in this paper is whether severely mentally ill patients are treated differently in a community mental health service without the back-up of a mental hospital (south-Verona, Italy) compared with an institution-based system in which mental hospitals, although highly modernized, are still predominant (Groningen, The Netherlands). Using the psychiatric case-registers in both areas, the patterns of care in 2 years of follow-up of schizophrenic patients were constructed. Survival analysis was used to analyse in-, day- and out-patient episodes of care. Three-quarters of the Groningen and half of the south-Verona patients experienced at least one episode of hospitalization; 20% of the Groningen and 5% of the south-Verona patients were long-stay patients at the end of the observation period. The south-Verona patients had more episodes of in-patient and especially of day-patient and out-patient care. Cox's regression showed that the duration of episodes controlled for the history of events and sociodemographic characteristics, was significantly shorter in south-Verona. One of the main conclusion was that hospitalizations for the severely mental ill are also needed in a community-based system of care, supporting the assumption of a 'bed-rock' of mental illness. However, the south-Verona community mental health service seems to be able to reduce the duration of hospitalizations considerably.

Adolescent↗
PubMed1996

The effects of role socialization on the initiation of cocaine use: an event history analysis from adolescence into middle adulthood.

This research examines three relatively unexplored questions about the effects of role socialization on the initiation of cocaine use: (1) What are the effects of adult social roles on the initiation of cocaine use? (2) What are the effects of the life-course timing of entry into adult social roles on the initiation of cocaine use? and (3) What are the effects of life-course timing of the initiation of other drugs -- on the initiation of cocaine use? The data used in these analyses are from a national probability sample of men born between 1944 and 1954, inclusive (N = 1,933). Results indicate that the marital role was the only role which demonstrated a significant effect on the initiation of cocaine use. We find that either early or late entry into the marital role reduces its effect to nonsignificance. The timing of entry in the drug use roles indicates that the later the initiation of drug use the greater the odds of cocaine initiation. Results are discussed in light of the role socialization and developmental perspectives.

Adult↗
PubMed2002

Parental substance use disorder and the risk of adolescent drug abuse: an event history analysis.

A common observation in the research literature is that children of drug-dependent parents are at significantly heightened risk of adolescent drug use, abuse, and dependence. Recent research indicates that several psychological and interpersonal factors may affect the association between parents' psychoactive substance use disorder (PSUD) and drug use risks among adolescents, yet studies have failed to examine explicitly whether these factors moderate the association between PSUD and adolescent substance abuse. This paper explores these potential relationships using longitudinal data from a study that has followed three cohorts of adolescents and their families over a 7-year period. The cohorts are defined by parental diagnoses of PSUD, affective disorders, or no diagnosable disorder. The results indicate that PSUD is positively associated with adolescent drug abuse, yet this association is attenuated by strong family cohesion. Affective disorders among parents are associated with a higher risk of alcohol, but not drug, abuse. The associations are stronger in the presence of lower stress and higher self-esteem. PSUD is also associated more strongly with offspring drug and alcohol abuse when levels of use are lower. Hence, some unobserved mechanism that may involve physiological sensitivities to drugs and alcohol appears to put children of parents with drug problems at particular risk of drug and alcohol abuse. Limitations of the data and analysis are discussed.

Adolescent↗
PubMed1998

An event history analysis of age at last menstrual period: correlates of natural and surgical menopause among midlife Wisconsin women.

Population aging coupled with heightened consumerism among those using the health care system have increased public and research interest in menopause. Despite these trends, we know little about the process of menstrual cessation. This paper reviews previous claims regarding secular trends in menopausal age by considering how menstrual cessations differ by type: (1) that due to surgical intervention such as hysterectomy, and (2) that due to "natural" (non-surgical) menopause. Analyses of menopause that exclude hysterectomized women are flawed, because such women constitute a high proportion of American women at midlife. Competing risk survival analysis techniques are applied to model the shape of the underlying hazards for reproductive organ surgery versus "natural" menopause among 3506 midlife women from the Wisconsin Longitudinal Study. Weibull models are used to evaluate effects of a variety of possible correlates (including education, mental ability, occupation, family background, fertility experience, smoking behavior and hormone therapy). While socioeconomic parameters do contribute to observed differences in age at menstrual cessation, these factors operate through more proximate health-related behaviors (such as smoking in the case of natural menopause and fertility for surgical menopause).

Educational Status↗
PubMed2005

Leaving nursing: an event-history analysis of nurses' careers.

OBJECTIVES: The current shortage of nurses is a major problem for health care systems around the world and has revitalized interest in the dynamics of nurses' careers. This paper investigates the factors associated with qualified nurses in Britain moving to different employment statuses, including jobs outside nursing, unemployment, maternity leave and family care over time. METHODS: British Household Panel Survey (BHPS) data collected between 1991 and 2001 were used to estimate the effects of covariates on transition rates between different employment statuses. RESULTS: Individual characteristics associated with shorter tenure in the profession include being male, being younger, having a degree, and having been born in the UK. Many nurses leave to care for their families, which suggests the possibility of returning to the profession at a later date. A number of job characteristics are also related to leaving, including low pay, managerial responsibility, full-time work and lack of opportunities to use initiative. Nurses seem to be particularly vulnerable to leaving early in their careers, but those who survive the first few years are likely to remain in the profession for the rest of their working lives. CONCLUSIONS: It is particularly important in policy terms that ability to use initiative is related to leaving nursing for another form of full-time employment and, in particular, to leaving for a better job. This finding is consistent with results from studies of the Magnet hospitals in the US. Taken together, these results suggest that strategies to improve nurse retention must attend to nurses' status, authority and position in the hierarchy if they are to be successful. The results also provide strong support for those who argue that better rates of pay are necessary in order to improve nurse retention.

Adult↗
PubMed2002

Are all grandmothers equal? A review and a preliminary test of the "grandmother hypothesis" in Tokugawa Japan.

An unresolved question arising from human evolutionary research relates to the function of the postreproductive period in human females. If menopause is not merely an artifact resulting from the benefits of civilization, there must be an adaptive mechanism favoring the offspring of women who continue to thrive well past the time of their last ovulation. The "grandmother hypothesis" was developed on the basis of the original suggestion by Williams (1957 Evolution 11:32-39) that "stopping early" would benefit already-born children. This idea, combined with the concepts of kin selection (Hamilton 1964 J Theor Biol 7:1-52) and parental investment (Trivers 1972 Sexual Selection and the Descent of Man, Chicago: Aldine, p. 136-179), was expanded to suggest that postreproductive women (in contrast to males) contribute to their inclusive fitness by extending support to their grandchildren. We used discrete time event history analysis (Allison [1984] Event History Analysis, Newbury Park: Sage; Allison [1995] Survival Analysis, Cary, NC: SAS Institute) and logistic regression on data provided in population registers (Shūmon Aratame Chō, or SAC) from a village in central Japan, covering the period from 1671-1871, in a preliminary investigation of the effects of household grandparental presence on the probability of a child's death. We found that after accounting for the presence of other household members, the only grandparent whose presence exerted a consistent negative effect on the likelihood of a child's death was the mother's mother. Due to the small sample size of households that contained maternal grandmothers, these results failed to achieve statistical significance. Their importance, however, is in what they suggest about future research, i.e., census data from preindustrial societies can provide a basis for testing evolutionary proposals, including the "grandmother hypothesis."

Adaptation, Physiological↗
PubMed1988

The analysis of event history data: a review of progress and outstanding problems.

This paper reviews methods for the analysis of event history data by both parametric (exponential/Poisson) and semi-parametric methods. It identifies a need for software for handling the data structures of complex event histories and shows that, with such software, most Markov and semi-Markov models of event history data may be dealt with in the framework of generalized linear models. Finally, the emergent 'frailty' models for associated risks are discussed together with their implications for statistical software.

Data Interpretation, Statistical↗
PubMed2004

A SAS macro for estimating transition probabilities in semiparametric models for recurrent events.

In many clinical studies involving event history analysis, the event of interest is non-fatal and may occur more than once for each subject. Models based on the theory of counting processes have been developed to deal with such data, the recurrences being considered as transitions in a Markovian process. Under this setting, the experimental units can move between states over time, and it is possible to estimate the corresponding transition probabilities employing regression models that incorporate the influence of covariates. Despite of this, most of the softwares are concerned only in the estimation of regression parameters and do not provide transition probabilities estimates. The aim of this paper is to present a SAS macro developed to estimate the transition probabilities, considering three approaches for the regression modeling. The macro is flexible enough to allow the user to select the model to be fit providing, for a given set of covariates, plots of the estimates for the predicted transition probabilities as a function of time.

Brazil↗
PubMed1989

Analysis of behavioral durations in observational studies of social interaction.

Many social science disciplines investigate dyadic or triadic social interaction by recording the interactive behaviors as qualitative codes. This article introduces a method for analyzing and interpreting variation in the durations of coded behaviors obtained during such interactions. Using survival analysis and event history analysis as its basis, this article discusses the use of regression techniques that enable the researcher to assess how the distributions of behavioral durations depend on covariate observations. An analysis of conflicts between mothers and children illustrates the discussion, using the proportional hazards model. Behavioral and attitudinal differences among the mother-son dyad predicted variation in the durations of mothers' negative statements to their sons.

Child↗
PubMed2000

Predictors of medical events in patients enrolled in the cardiac insufficiency bisoprolol study (CIBIS): a study of the interactions between beta-blocker therapy and occurrence of critical events using analysis of competitive risks.

BACKGROUND: The risk of occurrence of medical events in a clinical trial is competitive in nature; that is, in a given patient the risk of having a critical event depends on the amount of time elapsed since random assignment and on the previous events that may have occurred in the patient. The purpose of this study was to examine the relations between baseline variables, the interactions between treatment, bisoprolol, or placebo, and the occurrence of critical events during the CIBIS trial, a mortality and morbidity trial of beta-blockade in patients with heart failure. METHODS AND RESULTS: A Cox model for censored data was used to analyze the relations between baseline variables, total deaths, permanent treatment withdrawals, nonlethal cardiovascular events, and their interactions with bisoprolol or placebo. We examined the influence of treatment on the occurrence of deaths, permanent treatment withdrawals, and nonlethal cardiovascular events by using the technique of event history analysis, which takes into account competitive risks between events. Compared with placebo, bisoprolol reduced mortality rates in patients with a left ventricular ejection fraction < or =20% (relative risk [RR] 0.49; 95% confidence interval [CI] 0.27 to 0.88; P =.02). In patients whose baseline heart rate was in the upper tertile of distribution, permanent treatment withdrawals were less frequent in patients randomly assigned to bisoprolol than in patients randomly assigned to placebo (RR 0.50; 95% CI 0.28 to 0.88; P =.02). Bisoprolol reduced the incidence of nonlethal cardiac events in patients in whom heart failure was present for at least 4 years (RR 0.44; 95% CI 0.27 to 0.71; P <.01). Event history analysis revealed that among patients who died under treatment after having at least 1 nonlethal cardiovascular event, 20 patients were treated with placebo but only 7 patients were treated with bisoprolol (RR 0.41; 95% CI 0.17 to 0.98; P <.05). CONCLUSIONS: Some patients with heart failure derive more benefit from beta-blocker therapy than others. In the CIBIS trial, they are those patients with the lower left ventricular ejection fractions and those who have nonlethal cardiovascular events but in whom beta-blocker therapy is not permanently discontinued.

Adrenergic beta-Antagonists↗
PubMed2005

The effect of hospitalization with medical illnesses on the suicide risk in the oldest old: a population-based register study.

OBJECTIVES: To compare the effect of hospitalization with medical illnesses on the suicide risk in the oldest old (> or = 80) with that in the old (65-79) and middle-aged (52-64) using nationwide data. DESIGN: Event-history analysis using time-varying covariates based on prospective individual-level register data. SETTING: Population-based record linkage. PARTICIPANTS: All persons aged 52 and older living in Denmark during 1996 to 1998 (N=1,684,205). MEASUREMENTS: The studied event is completed suicide. The following time-varying variables are included in the analysis: current age, hospitalization with medical illnesses within previous 2 years, and number of different medical diagnoses given at hospitalizations within previous 2 years. Relative suicide risks were calculated using event-history analysis. The proportional attributable risk was calculated to assess to which extent hospitalization can explain the increased suicide risk in the oldest old. RESULTS: During the 3-year study period, 1,184 persons committed suicide. Hospitalization with medical illnesses was associated with an increased suicide risk in the study population. The highest suicide rates were found in the oldest-old men who had been hospitalized during the previous 2 years: 113 per 100,000 versus 80 per 100,000 in the general population of men aged 80 and older. Also, the oldest-old women with a history of hospitalization had a higher suicide rate than their peer group. Nevertheless, the oldest old experienced a lower increase in risk after hospitalization than the middle-aged. Experiencing three or more different diagnoses increased the risk further. Almost two-thirds of the oldest old who committed suicide had experienced a medical hospitalization during a 2-year period preceding the suicide. A substantial part of the greater suicide rate in the oldest old than in the middle-aged can be attributed to the increased prevalence of medical hospitalization. CONCLUSION: The oldest old who have been hospitalized with medical illnesses have a significantly higher suicide risk than people in the same age range with no hospitalization, although they experience a lower increase in risk after hospitalization than the middle-aged. The increased prevalence of medical illnesses explains a part of the greater suicide risk with age, especially for the oldest old women. Considering that hospitalization with medical illness often precedes suicide in the oldest old, hospitalization may play an important role in identification of suicidal ideation in older people.

Aged↗
PubMed2002

Racial/ethnic and gender differences in the incidence and onset age of DSM-IV alcohol use disorder symptoms among adolescents.

OBJECTIVE: Several investigators have questioned the validity of the DSM-IV Alcohol Use Disorders criteria for diagnosing alcohol use problems among teenagers, with specific concerns about their utility across different subgroups. In the current study, we examined whether particular racial/ethnic or gender subgroups varied in the incidence and onset age of Alcohol Use Disorder symptoms. METHOD: Members of a sample composed of 1,045 community-dwelling "drinkers" (59.4% male; 13.8% black, 21.2% foreign-born Hispanic, 30.7% U.S.-born Hispanic and 33.6% non-Hispanic white) were interviewed retrospectively using the Composite International Diagnostic Interview. The first occurrence of each DSM-IV symptom in a participant was examined by race/ethnicity and gender. Discrete-time event history analysis compared onset patterns from ages 14 through 20 years. RESULTS: The cumulative incidence of Alcohol Abuse and Alcohol Dependence diagnoses, as well as one alcohol abuse symptom and four dependence symptoms, varied by race/ethnicity. The incidence of both diagnoses, as well as two alcohol abuse symptoms, varied by gender. Event history analysis revealed no significant subgroup variation in first onset patterns for only three of the eleven symptoms. Racial/ethnic variation, but not gender variation, was significant for three symptoms, and both racial/ethnic variation and gender variation was significant for the remaining five symptoms. CONCLUSIONS: Our findings indicate that most of the DSM-IV Alcohol Use Disorder symptoms, when applied to adolescents, demonstrate significant subgroup variation in incidence and onset age patterns. These results speak to the urgent need for additional research concerning the nosology and diagnosis of alcohol use problems among younger drinkers, especially among specific racial/ethnic and gender subgroups.

Adolescent↗
PubMed2005

Homelessness and drug abuse among young men who have sex with men in New York city: a preliminary epidemiological trajectory.

The objective of this paper is to profile the role of homelessness in drug and sexual risk in a population of young men who have sex with men (YMSM). Data are from a cross-sectional survey collected between 2000 and 2001 in New York City (N = 569). With the goal of examining the import of homelessness in increased risk for the onset of drug and sexual risk, we compare and contrast three subgroups: (1) YMSM with no history of homelessness, (2) YMSM with a past history of homelessness but who were not homeless at the time of the interview, and (3) YMSM who were currently homeless. For each group, we describe the prevalence of a broad range of stressful life events (including foster care and runaway episodes, involvement in the criminal justice system, etc.), as well as selected mental health problems (including past suicide attempts, current depression, and selected help-seeking variables). Additionally, we examine the prevalence of selected drug and sexual risk, including exposure to a broad range of illegal substances, current use of illegal drugs, and prevalence of lifetime exposure to sex work. Finally, we use an event history analysis approach (time-event displays and paired t-test analysis) to examine the timing of negative life experiences and homelessness relative to the onset of drug and sexual risk. High levels of background negative life experiences and manifest mental health distress are seen in all three groups. Both a prior experience of homelessness and currently being homeless are both strongly associated with both higher levels of lifetime exposure to drug and sexual risk as well as higher levels of current drug and sexual risk. Onset of these risks occur earlier in both groups that have had an experience of housing instability (e.g., runaway, foster care, etc.) but are delayed or not present among YMSM with no history of housing instability. Few YMSM had used drug prior to becoming homeless. While causal inferences are subject to the limitations of a cross-sectional design, the findings pose an empirical challenge to the prevailing assumption that prior drug use is a dominant causal factor in YMSM becoming homeless. More broadly, the data illustrate the complexity of factors that must be accounted for, both in advancing our epidemiological understanding of the complexity of homelessness and its relationship to the onset of drug and sexual risk among high risk youth populations.

Adolescent↗
PubMed1996

The spatial mobility of two generations of young adults in Norway.

"This article presents results from a longitudinal study using data from the Norwegian population register, combined with data from the 1970 and 1980 censuses. For two generations, those born in 1948 and 1958, successive migrations are considered and the effects of various sociodemographic characteristics on migratory behaviour are explored....Event-history analysis is used to examine the duration of stay at the place reached at age 22, and the effects of individual characteristics on this duration. Since a distinction is made between intra- and inter-regional migration, it has been possible to show that these effects vary significantly depending on whether we are dealing with short- or long-distance migration."

Demography↗
PubMed1999

Recurrence of maltreatment: an application of the National Child Abuse and Neglect Data System (NCANDS).

OBJECTIVE: The research describes and compares patterns of maltreatment recurrence across multiple states using large samples, confirms the patterns of recurrence found in the literature, and explores unreported patterns of recurrence. METHOD: A recurrence data set for calendar years 1994 and 1995 was constructed from the multi-state case level data from the National Child Abuse and Neglect Data System. These data were available for 10 states and included a range from 2,419 to 99,288 substantiated or indicated report-child pairs per state. A common set of data constructs lent consistency to data construction and analysis, while preserving differences in policy. Event History Analysis (survival) techniques were used. RESULTS: Single site studies were confirmed across the 10 states. These include the pattern where neglect is most likely to recur, followed by physical abuse and then sexual abuse. Similarly, younger children are more likely to recur. A finding of the analysis is that the likelihood of recurrence increases in a systematic and consistent fashion based upon the sequential ordering of recurrent maltreatment events. Also, the likelihood of recurrence is associated with the provision of postinvestigative services. CONCLUSION: Highly consistent patterns of recurrence were observed across states. Children experiencing multiple recurrences compared to no recurrence or one recurrence may represent a special at risk population requiring additional research. Adequate baselines and an understanding of recurrence is needed when considering recurrence as an outcome indicator or in developing risk assessment tools. Important recurrence patterns may be difficult to detect reliably with relatively small samples.

Adolescent↗
PubMed2006

Ecstasy and gateway drugs: initiating the use of ecstasy and other drugs.

PURPOSE: The main purposes of this study are to examine whether and to what extent ecstasy use serves as a gateway to the use of such hard drugs as cocaine, heroin, and methamphetamine and compare ages of onset of alcohol and marijuana use and subsequent use of cocaine, heroin, and methamphetamine among young adult ecstasy users. METHODS: Face-to-face surveys were conducted with 268 young adult ecstasy users in Atlanta, GA. Subjects were solicited by using the community identification process, including targeted sampling and guided recruitment. Data analysis involved discrete-time event-history analysis. RESULTS: Results suggest that age of onset of ecstasy use influences the initiation of cocaine and methamphetamine use for our sample of active ecstasy users. In addition, alcohol and marijuana use precedes the initiation of cocaine and methamphetamine use, but only marijuana use influences the initiation of heroin use. CONCLUSIONS: The sequential progression of drug use proposed in the gateway literature is not immutable. Researchers must take into account the changing popularity of drugs over time, such as the emergence of ecstasy use, when identifying patterns of drug-use onset.

Adolescent↗
PubMed2006

Dynamic path analysis-a new approach to analyzing time-dependent covariates.

In this article we introduce a general approach to dynamic path analysis. This is an extension of classical path analysis to the situation where variables may be time-dependent and where the outcome of main interest is a stochastic process. In particular we will focus on the survival and event history analysis setting where the main outcome is a counting process. Our approach will be especially fruitful for analyzing event history data with internal time-dependent covariates, where an ordinary regression analysis may fail. The approach enables us to describe how the effect of a fixed covariate partly is working directly and partly indirectly through internal time-dependent covariates. For the sequence of times of event, we define a sequence of path analysis models. At each time of an event, ordinary linear regression is used to estimate the relation between the covariates, while the additive hazard model is used for the regression of the counting process on the covariates. The methodology is illustrated using data from a randomized trial on survival for patients with liver cirrhosis.

Aged↗