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 109 records · Page 6Linked to original sources

Logit-log calibration curves for EMIT assays.

The logit-log and four-parameter logistic procedures when appropriate for calculation of enzyme-multiplied immunoassay (EMIT) data have the advantage that they can be applied regardless of the kinetic analyzer or reaction conditions. To use these procedures correctly one must determine the change in absorbance at an infinite drug concentration (delta A infinity). The marked variation of delta A infinity with equipment and reaction conditions and the difficulty in determining this value have hindered broad use of these otherwise universally applicable procedures. We have evaluated two simple methods for determining delta A infinity, both based on its equivalence to delta A in the absence of specific antibody: (1) cross-kit reaction using antibody/substrate and enzyme-drug reagents from kits for different drugs, and (2) substitution of an antibody-free substrate reagent with composition based on direct analysis. The cross-kit procedure was tested with EMIT assays for phenobarbital, primidone, phenytoin, carbamazepine, ethosuximide, and theophylline. In some cases an unexpected type of cross-reaction occurred, giving an erroneously low value for delta A infinity. The antibody-free substrate reagent always permitted accurate determination of delta A infinity.

Anticonvulsants↗

Interrelations of the various mathematical approaches to radioimmunoassay.

Equations used for calculation of radioimmunoassay data are derived and compared. We show that the equation developed by Fernandez and Loeb is the most general of these. Those of Ekins et al., Hales and Randle, and Rodbard et al. are all derived here from this basic equation by neglecting certain of its terms. The logit-log plot of Rodbard et al. is a logarithmic transformation of the linear Hales-Randle equation. The basic equation, derived here solely from the mass-action law, approaches linearity under certain conditions without complex mathematical transformations of analyte concentrations or observable parameters. Applications are also presented.

Humans↗

Periparturient climatic, animal, and management factors influencing the incidence of milk Fever in grazing systems.

The objective of the present study was to quantify the climatic, animal, and management factors influencing incidence of milk fever (MF) in cows exposed to grazing systems. Data were extracted on 4,469 calvings of multiparous cows in a seasonal calving research herd between 1970 and 2000. Climatic data during the calving period also were extracted for these years. Poisson regression was used to investigate the effect of climate on frequency of MF within year; the offset variable was the number of cows at risk for MF at that time. Generalized estimating equations, with cow included as a repeated effect, were used to quantify the effect of parturition-associated cow and management factors on the logit of the probability of MF. Both univariate and multivariate analyses were performed. Explanatory variables investigated included time of calving relative to the herd-year calving period, parity, body weight, breed of cow, body condition score at calving, weight and gender of the calf, incidence of twin calves, calving inductions, and calving assistance. Odds of recurring MF within cow, as well as the timing of MF relative to day of calving, was quantified using generalized estimating equations with cow included as a repeated effect. Results show significant effects of evaporation, minimum grass temperature, difference between ambient maximum and minimum temperature, and rainfall on the odds of MF occurring, with a greater incidence at greater evaporation, larger diurnal variation in air temperature, greater rainfall, and lesser grass minimum temperature. Cow factors, such as age, excessive or poor body condition score, and requirement for calving assistance increased the odds of MF; a lesser odds ratio was observed in cows hormonally induced to calve and those that had twin births. Results indicate that herd managers may identify the day of greatest risk for MF and cows that are at greatest risk of MF based on climatic, cow, and management factors.

Animals↗

Differences in male and female injury severities in sport-utility vehicle, minivan, pickup and passenger car accidents.

This research explores differences in injury severity between male and female drivers in single and two-vehicle accidents involving passenger cars, pickups, sport-utility vehicles (SUVs), and minivans. Separate multivariate multinomial logit models of injury severity are estimated for male and female drivers. The models predict the probability of four injury severity outcomes: no injury (property damage only), possible injury, evident injury, and fatal/disabling injury. The models are conditioned on driver gender and the number and type of vehicles involved in the accident. The conditional structure avoids bias caused by men and women's different reporting rates, choices of vehicle type, and their different rates of participation as drivers, which would affect a joint model of all crashes. We found variables that have opposite effects for the genders, such as striking a barrier or a guardrail, and crashing while starting a vehicle. The results suggest there are important behavioral and physiological differences between male and female drivers that must be explored further and addressed in vehicle and roadway design.

Accidents, Traffic↗

A better lemon squeezer? Maximum-likelihood regression with beta-distributed dependent variables.

Uncorrectable skew and heteroscedasticity are among the "lemons" of psychological data, yet many important variables naturally exhibit these properties. For scales with a lower and upper bound, a suitable candidate for models is the beta distribution, which is very flexible and models skew quite well. The authors present maximum-likelihood regression models assuming that the dependent variable is conditionally beta distributed rather than Gaussian. The approach models both means (location) and variances (dispersion) with their own distinct sets of predictors (continuous and/or categorical), thereby modeling heteroscedasticity. The location sub-model link function is the logit and thereby analogous to logistic regression, whereas the dispersion sub-model is log linear. Real examples show that these models handle the independent observations case readily. The article discusses comparisons between beta regression and alternative techniques, model selection and interpretation, practical estimation, and software.

Analysis of Variance↗

Uptake of aluminum, cadmium, copper, lead, and zinc by human scalp hair and elution of the adsorbed metals.

Uptake of aluminum (Al), cadmium (Cd), copper (Cu), lead (Pb), and zinc (Zn) from aqueous solutions by human scalp hair (water/hair = 100:1) has been studied in the concentration range 0-50 mg/L. Hair metal levels were determined by a wet digestion procedure and atomic absorption spectrometry. Under conditions used, uptake followed a sigmoid concentration-response relationship. The order of binding capacity of hair to the metals was as follows: Al greater than Cd greater than Cu greater than Pb greater than Zn. Using logit transformation 50% saturation was evaluated at the following metal concentrations (hair metal concentration of saturation is given in parenthesis): 0.34 mg/L for Al (0.154 mg/g); 1.82 mg/L for Cd (0.363 mg/g); 2.21 mg/L for Cu (0.651 mg/g); 2.52 mg/L for Pb (0.986 mg/g); 23.84 mg/L for Zn (1.616 mg/g). Percentage elution of trace metals from hair after treatment with metal-enriched solutions by five different procedures ranged from 14.5 to 46.5% for Al, from 11.1 to 28.9% for Zn, from 11.5 to 28.4% for Pb, from 8.9 to 13.6% for Cd, and from 0.1 to 11.8% for Cu. In addition, trace element concentrations were measured in tap water samples and shampoos.

Acetone↗

Drug use practices among MDMA/ecstasy users in Ohio: a latent class analysis.

This study describes the drug use practices among 402 recent MDMA (3,4-methelyenedioxymethamphetamine) users recruited in Ohio using respondent-driven sampling. About 64% of the participants were men, 81.6% were white, and the mean age was 20.9 years. Latent class analysis was used to identify subgroups of MDMA users. Use of cocaine, opioids, amphetamines, tranquilizers, inhalants, marijuana, and hallucinogens during the previous 6 months, and days of "drunkenness" in the past 30, were used for classification. A three-class model was preferable and reflected "Limited range," "Moderate range," and "Wide range" drug use patterns. For example, the conditional probability of using opioids during the previous 6 months was .07 in Class 1, .59 in Class 2, and .88 in Class 3. Other substances followed similar patterns. Predictors of class membership were examined in a multinomial logit model in which the "Limited range" Class was treated as the reference group. Participants who were white, younger, and who reported more than 10 occasions of MDMA use were more likely to be in the "Wide range" drug use Class. Latent class analysis is a useful method to help describe and understand variability in polydrug use patterns.

Adolescent↗

Frequency of traumatic cow injuries in relation to housing systems in Swiss organic dairy herds.

A study was performed to estimate the extent of cow injuries as an indicator of animal welfare in organic dairy farms in Switzerland. The study was conducted during the winter feeding period of 1997/98 and was part of a larger project on animal health, nutrition and production in certified organic dairy herds in Switzerland. Potential predictors of injuries related to animal housing were quantified and relations between occurrence of injuries and nutritional status and production were evaluated. The investigation was designed as a cross-sectional study and included a representative sample of 152 farms and 1856 cows. Every farm was visited once and each cow was scored for claw-, skin- and joint-lesions and body condition. Statistical analyses were performed appropriate for a stratified and one-stage cluster sample weighted for the entire population of organic dairy farms in Switzerland. Possible individual and environmental predictors of cow injuries were analysed using multinomial logit models for ordinal outcomes. The overall frequencies of injuries were 10.4% for joint lesions, 12.8% for soft-tissue injuries and 3.6% for claw lesions. Most joint injuries (84.9%) were observed at the hock joint, 9.4% at the carpus and 3.1% at the knee joint. The analysis of the association between frequency of injuries and potential predictors revealed heterogeneous results and the risk profiles were different between the categories of injuries measured in the study. These observations support the assumption that variations in type and severity of injuries are due to specific differences of animal management, housing design and due to different characteristics of individual cows.

Animal Welfare↗

Welfare reform and female headship.

While much of the focus of recent welfare reforms has been on moving recipients from welfare to work, many reforms were also directed at decisions regarding living arrangements, pregnancy, marriage, and cohabitation. This article assesses the impact of welfare reform waivers and Temporary Assistance for Needy Families (TANF) programs on women's decisions to become unmarried heads of families, controlling for confounding influences from local economic and social conditions. We pooled data from the 1990, 1992, 1993, and 1996 panels of the Survey of Income and Program Participation, which span the period when many states began to adopt welfare waivers and to implement TANF, and estimated logit models of the incidence of female headship and state-stratified, Cox proportional hazard models of the rates of entry into and exit from headship. We found little consistent evidence that waivers affected female headship of families.

Adolescent↗

What percentage of workers with work-related illnesses receive workers' compensation benefits?

This study estimates the rate at which workers suffering from occupational illnesses file for workers' compensation lost wage benefits and identifies some of the factors that affect the probability that a worker with an occupational illness will file. A database of reports of known or suspected cases of occupational illness is matched with workers' compensation claims data. Overall, between 9% and 45% of reported workers file for benefits. Data limitations prevent a more precise estimate of this rate, but a large proportion of workers with occupational illnesses clearly does not utilize the worker's compensation system. Logit analysis of a choice-based sample shows that women and employees of small firms are more likely than others to file for worker's compensation and that filing rates vary considerably across industries and diagnostic categories. Acute conditions related to the current job are no more likely to lead to claims than chronic conditions with long latency periods between exposure and development of disease.

Adult↗

The association between processes, structures and outcomes of secondary prevention care among VA ischemic heart disease patients.

BACKGROUND: Hyperlipidemia and hypertension are well-established risk factors for recurrent cardiovascular events among patients with ischemic heart disease (IHD). Despite national recommendations, concordance with guidelines for LDL cholesterol and blood pressure remains inadequate. The objectives of this study were to 1) determine concordance rates with LDL cholesterol and BP recommendations; and 2) identify patient factors, processes and structures of care associated with guideline concordance among VA IHD patients. METHODS: This was a cross sectional study of veterans with IHD from 8 VA hospitals. Outcomes were concordance with LDL guideline recommendations (LDL<100 mg/dl), and BP recommendations (<140/90 mm Hg). Cumulative logit and hierarchical logistic regression analyses were performed to identify patient factors, processes, and structures of care independently associated with guideline concordance. RESULTS: Of 14,114 veterans with IHD, 55.7% had hypertension, 71.5% had hyperlipidemia, and 41.6% had both conditions. Guideline concordance for LDL and BP were 38.9% and 53.4%, respectively. However, only 21.9% of the patients achieved both LDL <100 mg/dl and BP <140/90 mm Hg. In multivariable analyses, patient factors including older age and the presence of vascular disease were associated with worse guideline concordance. In contrast, diabetes was associated with better guideline concordance. Several process of care variables, including higher number of outpatient visits, higher number of prescribed medications, and a recent cardiac hospitalization were associated with better guideline concordance. Among structures of care, having on-site cardiology was associated with a trend towards better guideline concordance. CONCLUSION: Guideline concordance with secondary prevention measures among IHD patients remains suboptimal. It is hoped that the findings of this study can serve as an impetus for quality improvement efforts to improve upon secondary prevention measures and reduce the morbidity and mortality of patients with known IHD.

Adult↗

Infant mortality by cause of death: main and interaction effects.

We examine infant mortality among the 1980-1982 live birth cohorts in the state of Florida, specific to five categories of underlying cause of death: infections, perinatal conditions, delivery complications, congenital malformations, and sudden infant death syndrome. The gross and net effects of eight categorical and continuous independent variables, along with 11 first-order interactions, are examined with microlevel data through the use of multinomial logit regression. Findings suggest the complexity of variable effects by cause of death and indicate the simultaneous importance of biological and social factors. It is important that the pattern of interactions suggests an overall dependence of infant life chances on social circumstances. It also suggests that these effects are attenuated for some variables and causes of death at lower birth weights, probably due to advances in health care organization, access, and technology.

Birth Weight↗

Quality of care and the demand for health services in Bamako, Mali: the specific roles of structural, process, and outcome components.

The public finance and foreign exchange crisis of the 1980s aggravated the unfavourable economic trends in many developing countries and resulted in budget cuts in the health sector. Policymakers, following the suggestions of World Bank experts, introduced user fees. Economic analysis of the demand for health care in these countries focused on the impact of price and income on health service utilisation. But the lesson to date from experiences in cost recovery is that without visible and fairly immediate improvements in the quality of care, the implementation of user fees will cause service utilisation to drop. For this reason, the role of quality of health care has been recently a subject of investigation in a number of health care demand studies. In spite of using the data from both households and facilities, recent studies are quite limited because they measure quality only by structural attributes (availability of drugs, equipment, number and qualifications of staff, and so on). Structural attributes of quality are necessary but not sufficient conditions for demand. A unique feature of this study is that it also considers the processes followed by practitioners and the outcome of care, to determine simultaneously the respective influence of price and quality on decision making. A nested multinomial logit was used to examine the choice between six alternatives (self-treatment, modern treatment at home, public hospital, public dispensary, for-profit facility and non-profit facility). The estimations are based on data from a statistically representative sample of 1104 patients from 1191 households and the data from a stratified random sample of 42 out of 84 facilities identified. The results indicate that omitting the process quality variables from the demand model produces a bias not only in the estimated coefficient of the "price" variable but also in coefficients of some structural attributes of the quality. The simulations suggest that price has a minor effect on utilisation of health services, and that health authorities can simultaneously double user fees and increase utilisation by emphasising improvement of both the structural and process quality of care in public health facilities.

Decision Making↗

Alternative regression approaches to the analysis of medical care survey data.

In a multivariate analysis of ambulatory care utilization of a subsample of the 1970 National Health Interview Survey (NHIS) data the dependent variables representing utilization, acute conditions and chronic conditions were found to have discrete variable properties violating normality assumptions of standard regression analysis. Focusing on the utilization variable, alternative multivariate approaches were compared with results obtained from standard least squares analysis. These were Poisson-based multivariate regression, logit analysis, and discriminant analysis. While the fixed interval measure of utlization had an L-shaped frequency distribution with considerable departure from normality, it was found that more theoretically appropriate alternatives provided only marginal gains over the standard least squares techniques.

Acute Disease↗

Transitions in living arrangements among elders in Japan: does health make a difference?

OBJECTIVE: This research evaluates the hypothesis that poor health triggers a change in living arrangements among elderly adults in Japan. METHODS: Data came from a national probability sample of 2,200 Japanese people aged 60 or older. Four surveys of this sample were conducted over a period of 9 years, from 1987 to 1996. Multinomial logit regression analyses were used to analyze the effects of demographic characteristics, socioeconomic status, and health on changes in living arrangements. RESULTS: Living arrangements among the Japanese elderly people remained quite stable over the 9-year period. Physical and mental health conditions were found to exert both direct and indirect effects on transitions in living arrangements. DISCUSSION: Poor health does trigger changes in living arrangement. Both physical (i.e., chronic conditions and functional status) and mental (i.e., depressed affect) health conditions play a role in such transitions. Because health conditions are correlated with competing risks of mortality, attrition, and proxy interview, health effects on changes in living arrangement are likely underestimated.

Aged↗

Independent and linked migrants: determinants of African American interstate migration.

"Through kinship and other links to destinations, many African American interstate migrants in the United States join other people in destination households. These ¿linked' migrants contrast to ¿independent migrants' who move as individuals or intact groups and set up their own households at the destination. Using U.S. Census Public Use Micro Sample data, this paper first shows that, in the 1985-90 period, about 45 percent of all Black interstate migrants were independent, compared to 38 percent who were linked to housing at the destination and 17 percent who moved into group quarters. Second, a multinomial logit model, incorporating individual and state-level variables, is specified that contrasts the determinants of independent and linked migration.... It is concluded that the understanding of Black migration must take into account a variety of factors beyond traditional labor market conditions, including links to the destination and individual housing circumstances."

Black or African American↗

Intertrial sources of stimulus control and delayed matching-to-sample performance in humans.

Two experiments compared delayed matching-to-sample (DMTS) accuracy under 2 procedures in adults with mental retardation. In the trial-unique procedure, every trial in a session contained different stimuli. Thus, comparison stimuli that were correct on one trial were never incorrect on other trials in that session (or vice versa). In the 2-sample DMTS procedure, the same 2 comparison stimuli were presented on each trial, and their function changed quasi-randomly across trials conditional upon the sample stimulus. Across 2 experiments, 7 of 8 subjects showed the highest overall accuracy under the trial-unique procedure, and no subject showed consistently higher accuracy under the 2-sample procedure. Negative, exponential decay functions fit to logit p values showed that this difference was due largely to the steeper delay-mediated decline in sample control for the 2-sample procedure. Stimulus-control analyses indicated that, under the 2-sample procedure, the selection of the comparison stimulus on Trial N was often controlled by the comparison stimulus selection on Trial N-1 rather than the Trial-N sample stimulus. This source of competing stimulus control is not present in trial-unique procedures. Experiment 2 manipulated intertrial interval duration. There was a small but consistent increase in accuracy as a function of intertrial interval duration under the 2-sample procedure, but not under the trial-unique procedure.

Adult↗

Work characteristics and lifestyle as predictors in the development of chronic non-specific lung disease among elderly municipal employees.

OBJECTIVES: This study prospectively evaluated factors of working conditions and lifestyle in the development of chronic non-specific lung disease (CNSLD). METHODS: Baseline data were collected in 1981 from 5386 municipal employees born in 1923-35 who had no diagnosed CNSLD. The subjects were studied again in 1985 with a postal questionnaire. The predictors of CNSLD were selected by multivariate logistic regression analysis. RESULTS: 159 (3%) reported the development of CNSLD confirmed by a physician. During the 4.6 year follow up period the average annual incidence was 6.5/1000 subjects. In men the logit model followed was: smoking (odds ratio (OR) 1.17, 95% confidence interval (95% CI) 1.06-1.29), tight work schedule (OR 1.31, 95% CI 1.03-1.65), loss of a close friend (OR 2.21, 95% CI 1.13-4.31), and retirement of a spouse (OR 3.31, 95% CI 1.35-8.11). In women the selected risk factors were: smoking (OR 1.22, 95% CI 1.01-1.38), atopy (OR 1.99, 95% CI 1.12-3.53), physically heavy work (OR 1.65, 95% CI 1.09-2.29), poor physical working conditions such as heat, cold, changing temperature (OR 1.41, 95% CI 1.13-1.75), and infrequent communication with other people at work (OR 1.25, 95% CI 1.05-1.49). CONCLUSION: The differences in the predictors of the incidence of CNSLD between men and women were partly explained by different smoking habits, frequency of atopy, and working conditions. In men the significance of life events (loss of close friend and retirement of wife) need further investigation.

Adult↗