PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Conditional logit”

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 91 records · Page 5Linked to original sources

[Dependence of acute opiate poisoning lethal outcome on the gender, age, and duration of addiction].

The article presents toxicological characteristics of 198 cases of acute parenteral poisoning with morphine and heroin in the range of concentrations of their metabolites in the blood and urine which occur in practice. Risk of death is quantified in the range of possible morphine concentrations in the blood in acute opiates intoxication with reference to gender and age. Assessment of the criteria of quantitative opiates toxicity was made according to the method of logit regression and dose-effect curve suitable for analysis of correlations between probability of death and blood concentrations of opiates metabolites. Conditional lethal doses in respect to gender and age are calculated.

Adolescent↗

Income and employment among homeless people: the role of mental health, health and substance abuse.

BACKGROUND: The homeless population is among the poorest of the poor in the United States. Employment and government programs are potential sources of income, but many homeless people face potential barriers to work: many have serious mental and physical disabilities, and many more have alcohol and drug disorders. As a result, most homeless who work do so either for a few hours per day or only some days, which provides little income. General Assistance, a public program of last resort, also provides a low level of income support. More income might be gained through higher levels of work or participation in income support programs for people with disabilities. AIMS OF THE STUDY: To investigate the characteristics of homeless people that impede them in the labor market and in government program participation, paying particular attention to their mental and physical health, as well as their alcohol and drug problems. DATA: Data are from a survey of the homeless population in Alameda County, California, conducted from 1991 to 1993. Our sample is 471 homeless adults randomly selected from area shelters and meal providers, who were reinterviewed approximately 6 months later, regardless of domiciliary status. Mental health and substance use problems were assessed using the Diagnostic Interview Schedule, a structured, psychiatric interview that uses criteria based on the American Psychiatric Association's Diagnostic and Statistical Manual of Mental Disorders 3rd edn (revised). Employment between the first and second interview is categorized as none, low level (less than 6 hours a day or fewer than half the days between interviews) or higher level (at least 6 hours a day for at least half the days). ANALYTICAL PROCEDURES: The models of employment status and program participation are recursive in that homelessness at the first wave of the survey is treated as given. Thus we explore whether, given their initial homelessness, persons can gain or maintain access to income between the two interviews, conditional on the sample member's homelessness, health and disability at the first interview. Using maximum-likelihood methods, we estimate a generalized ordered logit model of whether the person works not at all, at a low level or at a higher level. Participation in disability programs and GA are estimated as probit models over the subsamples of potentially eligible participants. RESULTS: While a surprisingly large number of homeless people work, few homeless persons are able to generate significant earnings from employment alone. Physical health problems that limit work or daily activities, in particular, are barriers to employment. Drug and alcohol abuse and dependence are positively associated with lower work level but are negatively related to higher work level. Program participation is quite low relative to eligibility. Those with physical health problems are substantially more likely than those with mental health problems to be in the more generous disability programs. Substance use disorders are also a barrier to participation in disability programs. DISCUSSION: Mental health, health and disability play a large role in the employment and program participation of the homeless and persons at risk for homelessness. Physical disabilities are a barrier to employment, and those with substance use disorders are most likely to work at lower levels that provide less income. Rates of participation in government programs are low, and people with major mental disorders have especially low participation rate in disability programs. The low rates of participation, particularly in the disability programs, suggest the need for continued research in improving access to income support programs among eligible homeless populations.

Journal Article↗

Modelling transitional and joint marginal distributions in repeated categorical data.

When a repeated measures endpoint classifies people into several categories, marginal and transitional models provide two distinct approaches for data analysis. Marginal models estimate the probabilities of being in different categories over time. Transitional models estimate the probability of changing between any two given states during follow-up visits. This paper develops transitional and marginal models and applies them to a clinical trial of treatments of opiate addiction. The primary outcome was the presence or absence of opiates in a thrice weekly urine test, administered for 17 weeks. Subjects frequently miss visits, however, and in effect respond in one of three ways to a visit: missing, opiates present or opiates absent. Thus we have three possible states. Our transitional model conditions on the current state and models the transition from state k to one of the other (0, ..., K-1) states using a mutinomial logit model. This model generalizes previous work of Muenz and Rubinstein. Significant covariates in this model are predictive of state changes. Our marginal model views the state at each time point, rather than the transitions, as the primary response. Here we model the probability of being in state k with a multinomial logit model. Correlation within individuals over visits can be handled by applying the approach of Zeger and Liang or the bootstrap. Significant covariates in this model can include more 'global' summaries of a person such as extent of previous opiate use. Both marginal and transitional models are needed to provide a complete description of an individual's behaviour over time since global summaries might not affect transitions. Of particular substantive interest is how the opiate treatments affect both the marginal and transition probabilities.

Buprenorphine↗

[Delivery care in Chiapas, Mexico: who and where does provide it?].

OBJECTIVE: To identify the place and provider of delivery care; to analyse the relationship between the type of delivery care provider and prenatal care and sociodemographic factors; to identify groups with greater and lesser probability of receiving attention at health centers and to identify the reasons for not attending the health center nearest to the household. MATERIAL AND METHODS: Data on the delivery care of 297 women of La Fraylesca Region, Chiapas, were gathered using multivariate logit models to identify groups. RESULTS: From the total, 32% of childbirths occurred at health centers and 60% at home (mostly with poor sanitary conditions). Only 10% of women with less than 5 prenatal visits, school level under 3 years and whose household head was a peasant were attended by health care personnel. CONCLUSIONS: The accessibility and quality of health centers must be improved, and a programme aimed at increasing the number of deliveries that are attended by trained health care personnel should be implemented.

Adult↗

Enrollment choices in different types of HMOs: a multivariate analysis.

Enrollment decisions of a sample of an employed population choosing among open-panel and closed-panel HMOs and Blue Cross/Blue Shield are analyzed. This report, unlike previous ones, overcomes some of the difficulties of bivariate analysis by the use of the multivariate logistic probability model, logit. The results show that there are four consistent predictors of enrollment choice: previous source of care as the measure of access; family life stage and chronic conditions per family member as indicators of health risk; per capita income as the measure of economic vulnerability; and health concern. Having a private physician as the source of care is the best single predictor, its absence predicting a higher probability of enrollment in the closed, and its presence in the open-panel HMO. Higher risk life stage families, younger and with more children, are more likely to join the open-panel plan than the closed or retain BC/BS; higher incomes and larger numbers of chronic conditions appear to have the same effects. Higher levels of health concern, on the other hand, predict a greater probability of choosing the closed-panel plan. The probability of enrollment in any HMO is predicted with more than 50 per cent accuracy for 60 per cent of the sample. Choice between open and closed-panel plans is predicted with an accuracy in excess of 50 per cent for 80 per cent, and with an accuracy greater than 90 per cent for over 10 per cent of potential enrollees. The applicability of this approach to HMO feasibility analysis and planning is clearly indicated.

Analysis of Variance↗

Meta-analysis of binary data: which within study variance estimate to use?

We applied a mixed effects model to investigate between- and within-study variation in improvement rates of 180 schizophrenia outcome studies. The between-study variation was explained by the fixed study characteristics and an additional random study effect. Both rate difference and logit models were used. For a binary proportion outcome p(i) with sample size n(i) in the ith study, (circumflexp(i)(1-circumflexp(i))n)(-1) is the usual estimate of the within-study variance sigma(i)(2) in the logit model, where circumflexpi) is the sample mean of the binary outcome for subjects in study i. This estimate can be highly correlated with logit(circumflexp(i)). We used (macronp(i)(1-macronp)n(i))(-1) as an alternative estimate of sigma(i)(2), where macronp is the weighted mean of circumflexp(i)'s. We estimated regression coefficients (beta) of the fixed effects and the variance (tau(2)) of the random study effect using a quasi-likelihood estimating equations approach. Using the schizophrenia meta-analysis data, we demonstrated how the choice of the estimate of sigma(2)(i) affects the resulting estimates of beta and tau(2). We also conducted a simulation study to evaluate the performance of the two estimates of sigma(2)(i) in different conditions, where the conditions vary by number of studies and study size. Using the schizophrenia meta-analysis data, the estimates of beta and tau(2) were quite different when different estimates of sigma(2)(i) were used in the logit model. The simulation study showed that the estimates of beta and tau(2) were less biased, and the 95 per cent CI coverage was closer to 95 per cent when the estimate of sigma(2)(i) was (macronp(1-macronp)n(i))(-1) rather than (circumflexp(i)(1-circumflexp)n(i))(-1). Finally, we showed that a simple regression analysis is not appropriate unless tau(2) is much larger than sigma(2)(i), or a robust variance is used.

Computer Simulation↗

Power and sample size calculations for discrete bounded outcome scores.

We consider power and sample size calculations for randomized trials with a bounded outcome score (BOS) as primary response adjusted for a priori chosen covariates. We define BOS to be a random variable restricted to a finite interval. Typically, a BOS has a J- or U-shaped distribution hindering traditional parametric methods of analysis. When no adjustment for covariates is needed, a non-parametric test could be chosen. However, there is still a problem with calculating the power since the common location-shift alternative does not hold in general for a BOS. In this paper, we consider a parametric approach and assume that the observed BOS is a coarsened version of a true BOS, which has a logit-normal distribution in each treatment group allowing correction for covariates. A two-step procedure is used to calculate the power. Firstly, the power function is defined conditionally on the covariate values. Secondly, the marginal power is obtained by averaging the conditional power with respect to an assumed distribution for the covariates using Monte Carlo integration. A simulation study evaluates the performance of our method which is also applied to the ECASS-1 stroke study.

Computer Simulation↗

Length of stay, conditional length of stay, and prolonged stay in pediatric asthma.

OBJECTIVE: To understand differences in length of stay for asthma patients between New York State and Pennsylvania across children's and general hospitals in order to better guide policy. DATA SOURCES/STUDY SETTING: All pediatric admissions for asthma in the states of Pennsylvania and New York using claims data obtained from each state for the years 1996-1998, n = 38,310. STUDY DESIGN: A retrospective cohort design to model length of stay (LOS), the probability of prolonged stay, conditional length of stay (CLOS or the LOS after stay is prolonged), and the probability of readmission, controlling for patient factors, state, location and hospital type. ANALYTIC METHODS: Logit models were used to estimate the probability of prolonged stay and readmission. The LOS and the CLOS were estimated with Cox regression. Model variables included comorbidities, income, race, distance from hospital, and insurance type. Prolonged stay was based on a Hollander-Proschan "New-Worse-Than-Used" test, corresponding to a three-day stay. PRINCIPAL FINDINGS: The LOS was longer in New York than Pennsylvania, and the probabilities of prolonged stay and readmission were much higher in New York than Pennsylvania. However, once an admission was prolonged, there were no differences in CLOS between states (when readmissions were not added to the LOS calculation). In both states, children's hospitals and general hospitals had similar adjusted LOS. CONCLUSIONS: Management of asthma appears more efficient in Pennsylvania than New York: Less severe patients are discharged faster in Pennsylvania than New York; once discharged, patients are less likely to be readmitted in Pennsylvania than New York. However, once a stay is prolonged, there is little difference between New York and Pennsylvania, suggesting medical care for severely ill patients is similar across states. Differences between children's and general hospitals were small as compared to differences between states. We conclude that policy initiatives in New York, and other states, should focus their efforts on improving the care provided to less severe patients in order to help reduce overall length of stay.

Adolescent↗

Radioimmunoassay of measles virus hemagglutinin protein G.

Guinea pig and rabbit antisera from animals immunized with purified measles virus hemagglutinin (G) protein were used to establish a solid-phase four-layer radioimmunoassay for quantitative measurement of the G protein. The sensitive of the assay was 2 ng of purified G protein, and 200 micrograms of protein from uninfected Vero cells neither decreased the sensitivity nor reacted non-specifically in the assay. Radioimmunoassay standard dose-response curves were established and unknown values interpolated from these using the logit program of a desktop computer. Using this procedure, a measles virus growth curve in infected Vero cells was determined by measurement of G protein production. Under these same conditions, hemagglutination was not sensitive enough to detect early hemagglutinin production. Viral antigens in canine distemper virus, Newcastle disease virus, parainfluenza viruses 1-4, simian virus 5, and respiratory syncytial virus-infected cell lysates did not cross-react in the radioimmunoassay. A small degree of cross-reactivity was detected with mumps viral antigens, both with Vero cell-derived (wild-type strain) and egg-derived (Enders strain) purified virus preparations and with a cell lysate antigen prepared from wild-type mumps virus-infected Vero cells.

Animals↗

Modeling rear-end collisions including the role of driver's visibility and light truck vehicles using a nested logit structure.

This paper presents an analysis of the effect of the geometric incompatibility of light truck vehicles (LTV)--light-duty trucks, vans, and sport utility vehicles--on drivers' visibility of other passenger cars involved in rear-end collisions. The geometric incompatibility arises from the fact that most LTVs ride higher and are wider than regular passenger cars. The objective of this paper is to explore the effect of the lead vehicle's size on the rear-end crash configuration. Four rear-end crash configurations are defined based on the type of the two involved vehicles (lead and following vehicles). Nested logit models were calibrated to estimate the probabilities of the four rear-end crash configurations as a function of driver's age, gender, vehicle type, vehicle maneuver, light conditions, driver's visibility and speed. Results showed that driver's visibility and inattention in the following (striker) vehicle have the largest effect on being involved in a rear-end collision of configuration CarTrk (a regular passenger car striking an LTV). Possibly, indicating a sight distance problem. A driver of a smaller car following an LTV, have a problem seeing the roadway beyond the LTV, and therefore would not be able to adjust his/her speed accordingly, increasing the probability of a rear-end collision. Also, the probability of a CarTrk rear-end crash increases in the case that the lead vehicle stops suddenly.

Accidents, Traffic↗

Selection in context: patterns of natural selection in the glycoprotein 120 region of human immunodeficiency virus 1 within infected individuals.

Evolution of the HIV-1 V3 loop was monitored in 15 subjects over a period of 5 years at approximately 6-month intervals. Putative recombination was detected in many of the sequences. Evolutionary trees were estimated from the nonrecombinant viral sequences found in each individual. Selection and altered demographic regimes were detected with logit and other contingency analyses in a highly context-dependent fashion. Mutations leading to amino acid substitutions are subject to positive selection over a broad range of clinical conditions in the nonsyncytium-inducing (NSI) form, and the growth rates of the NSI strains and their level of genetic subdivision change little in going from a healthy immune system to a severely compromised immune system. In contrast, the SI form has a significant increase in growth rate as the immune system goes from healthy to compromised, particularly in those subjects who did not receive any antiviral drug therapy. This increase in SI growth rate results in a significant growth advantage of SI over NSI when the immune system is compromised. The SI strains also show more demographic subdivision when the immune system is healthy than when the immune system is compromised, and the SI form has greater demographic subdivision than NSI in subjects with healthy immune systems who also are not receiving antiviral drug therapy. Positive selection on amino-acid-changing mutations weakens and then intensifies again in the SI strains in going from healthy to compromised immune systems. These patterns are consistent with other studies that suggest that NSI strains inhibit replication of SI strains, that the V3 loop is more hidden from the immune system in the NSI form, that evolution in the V3 loop influences cell tropism and coreceptor usage, that substrate for replication of SI forms increases as the disease progresses, and that death of CD8 cells is influenced by the type of coreceptor usage typically found in SI but not in NSI strains. Finally, the transition between NSI and SI forms is associated with a burst of evolutionary change due to strong positive selection at sites other than those that define the NSI/SI phenotypes.

Acquired Immunodeficiency Syndrome↗

[Age at menarche among schoolgirls from a rural community in Southeast Brazil].

The purpose of this study was to determine the 3rd percentile (P3), 50th percentile (P50 = median age at menarche = MAM), and amplitude between the extremes (P97 and P3) of age at menarche among schoolgirls in the county of Barrinha, São Paulo, Brazil. Values were correlated with socioeconomic conditions such as social class, number of siblings, and father's employment status. This was a cross-sectional study based on the use of status quo adjusted by logit for calculation of percentiles. A questionnaire was applied to 1,602 schoolgirls aged 8 to 17 years (incomplete). MAM was 12 years (y) and 6 months (m), with a P97 of 10 y and 2 m and a P3 of 14 y and 10 m. Girls from lower-income families and those with unemployed fathers showed later MAM. No difference in MAM was observed with respect to number of siblings. Amplitude between P97 ad P3 was great in the overall sample. We conclude that Barrinha presented a MAM similar to and even lower than regional values for Brazil and for some developed countries. The study of the interval between extreme percentiles proved to be a better indicator of biological diversity and socioeconomic inequality than MAM alone.

Adolescent↗

The choice of dental care sector by young adults before and after subsidization reform in Finland.

This work is a part of a project, which aims at studying the utilization of dental care by young adults and the effects of subsidization reform (SR) on it. SR was introduced in 1986 for the Finnish population born after 1960 and comprised a decrease of about 50% in the out-of-pocket price for dental care both in the public and private sector. The copayments are paid by the National Health Insurance in the private and municipalities through taxation in the public sector. In this work, the choice of dental care sector (private or public) before and after the reform and the effect of the reform on the choice are examined. The choice was measured by revealed preference; i.e. by actual choice in a period of two years before and after the reform. A random sample was drawn at the end of 1985 (before) and 1987 (after) from the population of 19-26/27 years of age in four towns, in which the conditions of supply of dental services differed essentially (n = 2250 at both occasions). The data were gathered by using a self-administered questionnaire. The method of analysis was discrete logit analysis and applied Chow-test. The changes in choices between 1985 and 1987 were counted by estimated model by using means of independent variables. The change in the choice of sector caused by the subsidization reform was marginal. The probability of choosing public sector increased 3%-points in the target group of the reform (19-25 aged), but the relative importance of different factors explaining the choice did not change. However, changes in the relative importance of explanatory factors took place in the first age group left outside the reform, but no clear picture was obtained about a possible change in the probability of choosing public sector in this group.

Adult↗

Predicting place of death in the program of all-inclusive care for the elderly (PACE): participant versus program characteristics.

OBJECTIVES: To assess the relationship between participant-specific and program-specific characteristics and the place of death in the Program of All-Inclusive Care for the Elderly (PACE). DESIGN: A retrospective, population-based, cross-sectional study. SETTING: PACE is a community-based managed care model serving a frail, nursing home-eligible population of Medicare beneficiaries. PARTICIPANTS: Two thousand two hundred sixty-three PACE decedents from 12 sites that were fully capitated for Medicare and Medicaid by mid-1997. MEASUREMENTS: Participant-specific characteristics include the range of demographic, functional, and cognitive status; skilled care needs; medical conditions; and advance care directives measures. The PACE site-specific indicator was also included to assess the effect of program sites on place of death. Bivariate, logistic, and multinomial logit models were employed. RESULTS: The probability of death at home is twice as great (45%) for PACE program participants as for the general population of older Americans. Twenty-one percent of PACE participants die in hospitals, compared with 53% of Medicare beneficiaries. Participants who are older and live in the community have a significantly greater (P< .05) probability of dying at home than does an average PACE enrollee. Those with a do-not-resuscitate order are 7.4% less likely to die in the hospital than are those without. PACE participants with a live-in informal caregiver are 10.3% (P< .05) less likely to die at home than those without a caregiver. When all participant characteristics were accounted for, there remained significant variation in the place of death by PACE plan. We found the least amount of site-specific variation in deaths occurring at home and the most variation in deaths occurring in hospitals. CONCLUSION: Nationally, the low rate of home death has prompted some to conclude that it is unlikely that we will, as a society, decide to take our dying older people back into our homes. The PACE experience suggests that it is possible to modify this trend. The results indicate that patient and program characteristics are both important in predicting the place of death. The variation across PACE sites suggests that an opportunity for narrowing these gaps, and reducing the proportion of hospital deaths, exists. The PACE end-of-life practice style could potentially be applied to other populations and may have important public policy implications.

Aged↗

Conditional switching: a new variety of regression with many potential environmental applications.

We introduce a new form of regression that has many applications to environmental studies. For a sequence composed of key variates with prototypic value chi, this form differs from the estimation of a location parameter-based curve, mu(chi), a scale parameter-based curve, sigma(chi), or other currently used types of regression. Instead of estimating a curve location, scale, or alpha-quantile parameter, it assumes that there are two or more population subgroups; for example, consisting of unsensitized and sensitized individuals, respectively. Although within each subgroup the relationships mu(chi) or sigma(chi) may or may not be horizontal, these relationships are not deemed to be of primary importance. Instead, the mixing parameter P that indexes the proportions of the two subgroups is treated as being related to the key variate value chi. In the sense that its goal is the estimation of a proportion, the new procedure resembles logit regression. But, in terms of the continuous spectrum of values attained by the response variate, the means used to attain its goal are dissimilar from those of logit regression. Specifically, group membership is not known directly but is determined from a proxy continuous variate whose values overlap between groups. Examples are given with simulated and natural data where this new form of regression is applied. We believe that conditional switching regression is a particularly valuable research tool when chemical level chi of an induced asthma attack or birthweight chi measured in a study of the biomarker cotinine's effect on pregnancy outcomes determines whether an attack or a negative outcome occurs.(ABSTRACT TRUNCATED AT 250 WORDS)

Birth Weight↗

Exploring the demand for a voluntary Medicare prescription drug benefit.

The purposes of this study were (1) to assess the utility of the economic theory of demand for insurance for modeling voluntary Medicare drug benefit enrollment decisions and (2) to explore the degree of adverse selection and crowd-out that might occur under a voluntary enrollment Medicare prescription benefit. Data were collected using a cross-sectional, mail survey of 2,100 community-dwelling adults aged 65 and older in Wisconsin. Respondents were asked to evaluate their likelihood of enrollment in any of 4 hypothetical drug benefit plans under the assumption that they could enroll in one of the hypothetical plans or maintain their current coverage. Data analyses included bivariate comparisons across enrollment likelihood categories and logit analysis of enrollment likelihood as a function of respondent characteristics. 1041 usable survey forms were returned for an adjusted response rate of 51.5%. Older adults with 4 or more chronic conditions were most likely to report that they were "very likely" to enroll in one of the hypothetical drug plans, as were those with the highest out-of-pocket drug spending in the previous 30 days. Respondents with no or self-purchased drug benefits were more likely than those with employer-based plans to express a higher likelihood of enrollment in one of the hypothetical plans. Adverse selection may be problematic for a voluntary enrollment Medicare drug benefit. Given that high out-of-pocket drug spending (secondary to drug coverage source) was a consistent predictor of enrollment likelihood, demand-side factors affecting the crowding out of employer-based drug coverage sources by a voluntary enrollment drug benefit appear minimal. However, the availability of a Medicare prescription benefit may still lead to crowd-out through employer incentives.

Aged↗

Health effects of managed care among the near-elderly.

OBJECTIVE: The authors evaluate whether enrolling in a health maintenance organization (HMO) or preferred provider organization (PPO) affects the health of adults ages 55 to 64, relative to fee-for-service plans. METHODS: A nationwide random sample of 4,044 adults with employer-sponsored health insurance is drawn from the 1994 to 2000 waves of the Health and Retirement Study. Multinomial logit regressions are estimated for self-reported general health status, first using a sample of all near-elders, then using subsamples of near-elders with and without longstanding chronic health conditions. The possibility of selection bias into managed care plans is considered and explicitly addressed in model estimation. RESULTS: We find no ill effects of HMOs on health status, and older adults with a history of chronic health conditions actually fare better upon enrolling in these plans. DISCUSSION: More research is needed to understand the reasons for the observed beneficial effects of managed care.

Fee-for-Service Plans↗

Environmental effects on neonatal mortality of beef calves.

Calving records from 1969 to 1989 from the Roman L. Hruska U.S. Meat Animal Research Center were used to investigate how climatic conditions, in addition to dystocia, age of dam, size of calf, and sex affect calf survival from birth to 1 wk of age. Data were analyzed separately for cows calving with (n = 11,094) or without (n = 72,187) dystocia. Neonatal mortality was described by a logit model and parameters were estimated by maximum-likelihood procedures. Calves born to cows with dystocia were five times as likely to die neonatally than calves born without assistance. Of all calves that died, 43.6% were born with difficulty. Of these calves, survival was lowest for those that were small relative to their genetic group, sex, and age of dam. Large calves had markedly increased mortality only when born to 2-yr-old dams. Average ambient temperature and precipitation on day of calving affected survival nonlinearly and the magnitude of the effect depended on age of dam, sex and size of calf, and dystocia incidence. Calves born to 2-yr-old cows were more susceptible to severe weather conditions than calves born to older cows. The negative effect of precipitation on survival increased with decreasing temperature.

Age Factors↗