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 19 recordsLinked to original sources

Multinomial and conditional logit discrete-choice models in demography.

Although discrete-choice statistical techniques have been used with increasing regularity in demographic analyses, McFadden's conditional logit model is less well known and seldom used. Conditional logit models are appropriate when the choice among alternatives is modeled as a function of the characteristics of the alternatives, rather than (or in addition to) the characteristics of the individual making the choice. We argue that this feature of conditional logit makes it more appropriate for estimating behavioral models. In this article, the conditional logit model is presented and compared with the more familiar multinomial logit model. The difference between the two techniques is illustrated with an analysis of the choice of marital and welfare status by divorced or separated women.

Adult↗

Reconsidering the use of rankings in the valuation of health states: a model for estimating cardinal values from ordinal data.

BACKGROUND: In survey studies on health-state valuations, ordinal ranking exercises often are used as precursors to other elicitation methods such as the time trade-off (TTO) or standard gamble, but the ranking data have not been used in deriving cardinal valuations. This study reconsiders the role of ordinal ranks in valuing health and introduces a new approach to estimate interval-scaled valuations based on aggregate ranking data. METHODS: Analyses were undertaken on data from a previously published general population survey study in the United Kingdom that included rankings and TTO values for hypothetical states described using the EQ-5D classification system. The EQ-5D includes five domains (mobility, self-care, usual activities, pain/discomfort and anxiety/depression) with three possible levels on each. Rank data were analysed using a random utility model, operationalized through conditional logit regression. In the statistical model, probabilities of observed rankings were related to the latent utilities of different health states, modeled as a linear function of EQ-5D domain scores, as in previously reported EQ-5D valuation functions. Predicted valuations based on the conditional logit model were compared to observed TTO values for the 42 states in the study and to predictions based on a model estimated directly from the TTO values. Models were evaluated using the intraclass correlation coefficient (ICC) between predictions and mean observations, and the root mean squared error of predictions at the individual level. RESULTS: Agreement between predicted valuations from the rank model and observed TTO values was very high, with an ICC of 0.97, only marginally lower than for predictions based on the model estimated directly from TTO values (ICC = 0.99). Individual-level errors were also comparable in the two models, with root mean squared errors of 0.503 and 0.496 for the rank-based and TTO-based predictions, respectively. CONCLUSIONS: Modeling health-state valuations based on ordinal ranks can provide results that are similar to those obtained from more widely analyzed valuation techniques such as the TTO. The information content in aggregate ranking data is not currently exploited to full advantage. The possibility of estimating cardinal valuations from ordinal ranks could also simplify future data collection dramatically and facilitate wider empirical study of health-state valuations in diverse settings and population groups.

Journal Article↗

Robust error-minimization in the genetic code across physicochemical metrics and variant codes: A graph-theoretic analysis in GF(2)6.

The standard genetic code reduces the impact of point mutations, but the robustness of this property across physicochemical metrics, naturally occurring variant codes, and codon-reassignment mechanisms remains incompletely quantified. Embedding the 64 codons in GF(2)6 represents the hypercube Q6 as a coordinate-dependent subgraph of the encoding-independent single-nucleotide mutation graph H(3,4), and enables continuous &#x3c1;-interpolation between the two. Under a quartet-pattern shuffle null (n=10,000), the standard code is significantly low-cost across four established, code-independent physicochemical distance metrics with partially overlapping content (Grant ham p=0.0062; Miyata p<0.001; Woese polar requirement p=0.003; Kyte-Doolittle hydropathy p=0.001), and the signal strengthens monotonically as &#x3c1; moves Q6&#x2192;H(3,4). A structure-aware sensitivity analysis under the alignment-derived ProtSub matrix (Jia & Jernigan 2021) yields the most extreme percentile of any measure tested (p=0.0004; all five p-values pass Bonferroni at &#x3b1;=0.05). Across the 27 NCBI translation tables, near-optimality is preserved: 11 of 12 informative-distance variants retain top-5% placement after BH-FDR correction. Natural codon reassignments avoid disrupting codon-family connectivity: under the encoding-independent H(3,4) adjacency, observed events are topology-breaking at relative risk 0.32 versus the candidate landscape (permutation p&#x2264;10-4). The H(3,4) result is stable by construction; the Q6 decomposition is representation-specific and fails to show depletion under 8 of 24 base-to-bit encodings, so we report H(3,4) as the primary test and Q6 as a sensitivity. Event-level conditional-logit modelling shows that topology avoidance and local physicochemical cost provide complementary, only weakly correlated signal (rs=0.15), and that topology adds explanatory value beyond physicochemistry under both Q6 and encoding-independent H(3,4) adjacency. Retrospective reanalysis of nine genome-recoding datasets is consistent with codon-family topology operating as an evolutionary-trajectory constraint distinct from acute engineering fitness. The contribution is the second axis: code evolution is jointly constrained by physicochemical smoothness and codon-family topological integrity, and these two constraints are partly independent.

Codon reassignment↗

Destination choice of interstate family migrants to selected areas in California.

"In this study an attempt has been made to construct a destination choice model for those families who migrated to California from other states between the years 1965 and 1970. "The empirical work is based on a Public Use Sample of Basic Records from the 1970 Census; the technique of estimation used in this study is McFadden's maximum likelihood (multinomial logit technique which often is referred to as conditional logit). "[The] findings confirm the hypothesis that various groups of migrants respond somewhat differently to the geographic and economic stimuli in selecting their destinations in California. While white family migrants pay attention to the level of expected earnings in selecting their destinations, black family migrants are more concerned with the expansion of economic opportunities (i.e., growth rates of income and employment)."

Black or African American↗

Hospital choice of rural Medicare beneficiaries: patient, hospital attributes, and the patient-physician relationship.

OBJECTIVE: To examine how patient and hospital attributes and the patient-physician relationship influence hospital choice of rural Medicare beneficiaries. DATA SOURCES: Medicare Current Beneficiary Survey (MCBS), Health Care Financing Administration (HCFA) Provider of Services (POS) file, American Hospital Association (AHA) Annual Survey, and Medicare Hospital Service Area (HSA) files for 1994 and 1995. STUDY DESIGN: The study sample consisted of 1,702 hospitalizations of rural Medicare beneficiaries. McFadden's conditional logit model was used to analyze hospital choices of rural Medicare beneficiaries. The model included independent variables to control for patients' and hospitals' attributes and the distance to hospital alternatives. PRINCIPAL FINDINGS: The empirical results show strong preferences of aged patients for closer hospitals and those of greater scale and service capacity. Patients with complex acute medical conditions and those with more resources were more likely to bypass their closest rural hospitals. Beneficiaries were more likely to bypass their closest rural hospital if they had no regular physician, had a shorter patient-physician tie, were dissatisfied with the availability of health care, and had a longer travel time to their physician's office. CONCLUSIONS: The significant influences of patients' socioeconomic, health, and functional status, their satisfaction with and access to primary care, and their strong preferences for certain hospital attributes should inform federal program initiatives about the likely impacts of policy changes on hospital bypassing behavior.

Aged↗

Mixed effects logistic regression models for longitudinal binary response data with informative drop-out.

A shared parameter model with logistic link is presented for longitudinal binary response data to accommodate informative drop-out. The model consists of observed longitudinal and missing response components that share random effects parameters. To our knowledge, this is the first presentation of such a model for longitudinal binary response data. Comparisons are made to an approximate conditional logit model in terms of a clinical trial dataset and simulations. The naive mixed effects logit model that does not account for informative drop-out is also compared. The simulation-based differences among the models with respect to coverage of confidence intervals, bias, and mean squared error (MSE) depend on at least two factors: whether an effect is a between- or within-subject effect and the amount of between-subject variation as exhibited by variance components of the random effects distributions. When the shared parameter model holds, the approximate conditional model provides confidence intervals with good coverage for within-cluster factors but not for between-cluster factors. The converse is true for the naive model. Under a different drop-out mechanism, when the probability of drop-out is dependent only on the current unobserved observation, all three models behave similarly by providing between-subject confidence intervals with good coverage and comparable MSE and bias but poor within-subject confidence intervals, MSE, and bias. The naive model does more poorly with respect to the within-subject effects than do the shared parameter and approximate conditional models. The data analysis, which entails a comparison of two pain relievers and a placebo with respect to pain relief, conforms to the simulation results based on the shared parameter model but not on the simulation based on the outcome-driven drop-out process. This comparison between the data analysis and simulation results may provide evidence that the shared parameter model holds for the pain data.

Analgesics↗

Choice of hospital for delivery: a comparison of high-risk and low-risk women.

OBJECTIVE: This article tests whether or not the factors that affect hospital choice differ for selected subgroups of the population. DATA SOURCES: 1985 California Office of Statewide Health Planning and Development (OSHPD) discharge abstracts and hospital financial data were used. STUDY DESIGN: Models for hospital choice were estimated using McFadden's conditional logit model. Separate models were estimated for high-risk and low-risk patients, and for high-risk and low-risk women covered either by private insurance or by California Medicaid. The model included independent variables to control for quality, price, ownership, and distance to the hospital. DATA EXTRACTION: Data covered all maternal deliveries in the San Francisco Bay Area in 1985 (N = 61,436). ICD-9 codes were used to classify patients as high-risk or low-risk. The expected payment code on the discharge abstract was used to identify insurance status. PRINCIPAL FINDINGS: The results strongly reject the hypothesis that high-risk and low-risk women have the same choice process. Hospital quality tended to be more important for high-risk than low-risk women. These results also reject the hypothesis that factors influencing choice of hospital are the same for women covered by private insurance as for those covered by Medicaid. Further, high-risk women covered by Medicaid were less likely than high-risk women covered by private insurance to deliver in hospitals with newborn intensive care units. CONCLUSIONS: The results show that the choice factors vary across several broadly defined subgroups of patients with a specific condition. Thus, estimates aggregating all patients may be misleading. Specifically, such estimates will understate actual patient response to quality of care indicators, since patient sensitivity to quality of care varies with the patients' risk status.

Choice Behavior↗

Social exclusion in clients with comorbid mental health and substance misuse problems.

BACKGROUND: The concept of comorbid mental health problems and substance misuse has gained prominence in the last two decades, due in part to the closure of large psychiatric hospitals and to the increasing prevalence of drug use in the community. This client group has a dual requirement for both medical and social care needs and is at risk for social exclusion. METHODS: A retrospective matched case-control study to examine aspects of social exclusion between service users who have comorbid diagnoses and those with a single diagnosis. Samples were drawn from the service users of a mental health Trust in the South-East of England, from both Adult Mental Health (n = 400) and Drug and Alcohol services (n = 190). Data were collected from Care Programme Approach assessment forms and medical records. McNemar's chi(2) and odds ratios via a conditional logit regression model are used to test for differences in the social exclusion indicators. RESULTS: There were significant differences in social exclusion between the comorbid and singly diagnosed clients of the Adult Mental Health service, but differences were less pronounced between the comorbid and singly diagnosed clients of the specialist Drug and Alcohol service. CONCLUSIONS: Recent Government policy advocates treating comorbid clients within mainstream mental health services. Health care workers need to recognise the likelihood of high levels of social exclusion among clients with comorbid problems.

Adolescent↗

Interprovincial migration of physicians in Canada: where are they moving and why?

This paper analyzes the provincial characteristics contributing to physician's decision in his/her choice of province of residence. It (1) attempts to determine if, and the extent to which, expected income in a province plays a role in physician's decision; (2) predicts yearly probabilities of physician's choice of province of residence; (3) examines marginal effect of expected income in a province on response (choice of province of residence) probability for physicians residing in each province. We estimated McFadden's conditional logit discrete-choice model with yearly probability of choosing a province of residence as a dependent variable for physicians residing in each province separately. The results show: (1) the effect of expected income in a province on the choice of province of residence is positive and statistically significant for physicians residing in Ontario and Saskatchewan. There are other provincial characteristics besides income that affect physician's choice of province of residence; (2) most physicians choose the province they are currently residing. However, those who choose a province other than the current province of residence, the preference for a certain province varies across physicians residing in different provinces; (3) the marginal effect of expected income in a province on response probability varies across provinces for physicians residing in the same province. It also varies across physicians residing in different provinces for the same amount of change in income in the same province.

Models, Theoretical↗

The effect of treatment completion and length of stay on employment and crime in outpatient drug-free treatment.

Length of stay in treatment has been found to be a significant predictor of positive post-treatment outcomes, such as decreases in unemployment and crime. However, length of stay may be an incomplete predictor of successful treatment. Surprisingly, few studies have examined whether completing treatment in addition to length of stay is an important factor in explaining positive treatment outcomes. The objective of our study is to examine the effect that treatment completion and length of stay have on post-treatment employment and crime for patients in outpatient drug-free treatment, the largest treatment modality in the United States. We use conditional logit and multiple regression models with program-level indicator variables (fixed effects) to estimate the effect of treatment completion and length of stay on employment and crime controlling for drug use severity, previous treatment history, and other patient demographics. Data are from the National Treatment Improvement Evaluation Study and include 986 adults enrolled in outpatient drug-free programs across the United States. We find that treatment completion and length of stay are significantly related to post-treatment employment. Holding length of stay constant, the occurrence of employment at follow-up among patients who complete their planned treatment is almost 2 times that of patients who do not complete treatment. However, treatment completion did not have a statistically significant effect on the probability of post-treatment crime. Although our results are mixed, these findings suggest that greater attention should be placed on evaluating the importance of both length of stay and treatment completion in treatment outcome studies.

Adult↗

Job matching in pharmacy labor markets: a study in four states.

PURPOSE: Reports from various pharmacy labor market sectors suggest that the United States may be experiencing a shortage of pharmacists. To guide policy making and planning with respect to this shortage, it is necessary to develop a better understanding of the process by which pharmacists choose jobs. Using the economic theory of job matching, this study sought to understand how (a) attributes of the practice setting, (b) characteristics of pharmacists, and (c) regional and urbanization variables are associated with pharmacy practice setting choices. METHODS: A secondary database containing information about employment characteristics and work histories of 541 pharmacists in four states was used. The data were augmented with information on the relative number of employment opportunities in each of three practice settings (large chain, institutional, and independent) in the year the respondent's most recent employment change occurred. Practice setting choices were modeled using multinomial conditional logit regression. RESULTS: A total of 477 pharmacists represented in the database met the inclusion criteria for the study. Multivariate analyses showed that the impact of search costs and wage differentials varied with the practice setting chosen. Pharmacists choosing independent settings over large chain settings were more likely to be white and to have worked in an independent setting in their prior job. Pharmacists living in Oregon were less likely to choose institutional settings compared to those living in Massachusetts, whereas those living in areas with populations greater than 50,000 were more likely to choose institutional settings. CONCLUSIONS: Pharmacist job matching appears to be a complex process in which diverse factors interact to produce a final match. Our results suggest that the pharmacy labor market may actually be composed of two distinct labor markets: an ambulatory market and an institutional market.

Adult↗

Initial practice locations of international medical graduates.

OBJECTIVE: To examine the influence of place of graduate medical education (GME), state licensure requirements, presence of established international medical graduates (IMGs), and ethnic communities on the initial practice location choices of new IMGs. DATA SOURCES: The annual Graduate Medical Education (GME) Survey of the American Medical Association (AMA) and the AMA Physician Masterfile. STUDY DESIGN: We identified 19,940 IMGs who completed GME in the United States between 1989 and 1994 and who were in patient care practice 4.5 years later. We used conditional logit regression analysis to assess the effect of market area characteristics on the choice of practice location. The key explanatory variables in the regression models were whether the market area was in the state of GME, the years of GME required for state licensure, the proportion of IMGs among established physicians, and the ethnic composition of the market area. PRINCIPAL FINDINGS: The IMGs tended to locate in the same state as their GME training. Foreign-born IMGs were less likely to locate in markets with more stringent licensure requirements, and were more likely to locate in markets with higher proportions of established IMG physicians. The IMGs born in Hispanic or Asian countries were more likely to locate in markets with higher proportions of the corresponding ethnic group. CONCLUSIONS: Policymakers may influence the flow of new IMGs into states by changing the availability of GME positions. IMGs tend to favor the same markets over time, suggesting that networks among established IMGs play a role in attracting new IMGs. Further, IMGs choose their practice locations based on ethnic matching.

Adult↗

Computerized health information and the demand for medical care.

OBJECTIVE: Consumer health information, once the domain of books and booklets, has become increasingly digitized and available on the Internet. This study assessed the effect of using computerized health information on consumers' demand for medical care. METHODS: The dependent variable was self-reported number of visits to the doctor in the past year. The key independent variable was the use of computerized health information, which was treated as endogenous. We tested the effect of using computerized health information on physician visits using ordinary least squares, instrumental variables, fixed effects, and fixed-effects instrumental variables models. The instrumental variables included exposure to the Healthwise Communities Project, a community-wide health information intervention; computer ownership; and Internet access. Random households in three cities were mailed questionnaires before and after the Healthwise Communities Project. In total, 5909 surveys were collected for a response rate of 54%. RESULTS: In both the bivariate and the multivariate analyses, the use of computerized health information was not associated with self-reported entry into care or number of visits. The instrumental variables models also found no differences, with the exception that the probability of entering care was significantly greater with the two-stage conditional logit model (P <.05). CONCLUSIONS: Although providing people with health information is intuitively appealing, we found little evidence of an association between using a computer for health information and self-reported medical visits in the past year. This study used overall self-reported utilizations as the dependent variable, and more research is needed to determine whether health information affects the health production function in other important ways, such as the location of care, the timing of getting care, or the intensity of treatment.

Adolescent↗

Selection of a cardiac surgery provider in the managed care era.

OBJECTIVE: Many health planners promote the use of competition to contain cost and improve quality of care. Using a standard econometric model, we examined the evidence for "value-based" cardiac surgery provider selection in eastern Massachusetts, where there is significant competition and managed care penetration. METHODS: McFadden's conditional logit model was used to study cardiac surgery provider selection among 6952 patients and eight metropolitan Boston hospitals in 1997. Hospital predictor variables included beds, cardiac surgery case volume, objective clinical and financial performance, reputation (percent out-of-state referrals, cardiac residency program), distance from patient's home to hospital, and historical referral patterns. Subgroup analyses were performed for each major payer category. RESULTS: Distance from patient's home to hospital (odds ratio 0.90; P =.000) and the historical referral pattern from each patient's hometown (z = 45.305; P =.000) were important predictors in all models. A cardiac surgery residency enhanced the probability of selection (odds ratio 5.25; P =.000), as did percent out-of-state referrals (odds ratio 1.10; P =.001). Higher mortality rates were associated with decreased probability of selection (odds ratio 0.51; P =.027), but higher length of stay was paradoxically associated with greater probability (odds ratio 1.72; P =.000). Total hospital costs were irrelevant (odds ratio 1.00; P =.179). When analyzed by payer subgroup, Medicare patients appeared to select hospitals with both low mortality (odds ratio 0.43; P =.176) and short length of stay (odds ratio 0.76; P =.213), although the results did not achieve statistical significance. The commercial managed care subgroup exhibited the least "value-based" behavior. The odds ratio for length of stay was the highest of any group (odds ratio = 2.589; P =.000) and there was a subset of hospitals for which higher mortality was actually associated with greater likelihood of selection. CONCLUSIONS: The observable determinants of cardiac surgery provider selection are related to hospital reputation, historical referral patterns, and patient proximity, not objective clinical or cost performance. The paradoxic behavior of commercial managed care probably results from unobserved choice factors that are not primarily based on objective provider performance.

Cardiovascular Diseases↗

Selection of children to provide care: the effect of earlier parental transfers.

We use the first wave of data from the Asset and Health Dynamics Among the Oldest Old (AHEAD) study to examine the effects of past parent-to-child financial transfers on selection of a child to provide assistance with basic personal care for unmarried parents. We estimate a fixed-effects conditional logit model and find a positive and significant association between past financial transfers and a child's current helping behavior. The coefficient of past financial transfers is in the direction hypothesized, and its magnitude is 80% as large as that of gender, a well-documented powerful predictor of parental caregiving. There appears to be substantial evidence that earlier parent-to-child financial gifts play a role in determining which child in the family will provide assistance.

Aged↗

Health maintenance organization penetration and the practice location choices of new physicians: a study of large metropolitan areas in the United States.

OBJECTIVES: The rapid growth of health maintenance organizations is reshaping the practice opportunities available to physicians. The practice location decisions of new physicians provide a sensitive bellwether of these changes. This study assessed the effect of health maintenance organization penetration on practice location for physicians completing graduate medical education (GME). METHODS: Conditional logit regression analysis was used to determine the effect of health maintenance organization penetration on practice location, controlling for other market characteristics. Subjects were physicians who finished GME between 1989 and 1994 and who located in one of the 98 US metropolitan areas with more than 500,000 population. The outcome measure was the particular metropolitan area chosen by each new physician. RESULTS: Early in the study period, new generalists were significantly more likely to locate in metropolitan areas with high health maintenance organization penetration than in low penetration areas, whereas new specialists' practice location choices were not associated with health maintenance organization penetration. The likelihood of choosing a high penetration relative to a low penetration area declined with time, however, for both generalists and specialists. Consequently, by the end of the study period, health maintenance organization penetration had a weak but significant negative effect on practice location for generalists and a strong negative influence on practice location for specialists. CONCLUSIONS: New generalists who completed graduate medical education between 1989 and 1994 were more likely than new specialists to locate in market areas with high health maintenance organization penetration; however, the proportions of both generalists and specialists who chose high penetration areas decreased during the study period. This finding may reflect reduced practice opportunities in high penetration areas relative to low penetration areas as health maintenance organizations' systems for controlling utilization began to yield results. Alternatively, new physicians may have become more hesitant to accept available positions in high penetration areas.

Adult↗

Can high quality overcome consumer resistance to restricted provider access? Evidence from a health plan choice experiment.

OBJECTIVE: To investigate the impact of quality information on the willingness of consumers to enroll in health plans that restrict provider access. DATA SOURCES AND SETTING: A survey administered to respondents between the ages of 25 and 64 in the West Los Angeles area with private health insurance. STUDY DESIGN: An experimental approach is used to measure the effect of variation in provider network features and information about the quality of network physicians on hypothetical plan choices. Conditional logit models are used to analyze the experimental choice data. Next, choice model parameter estimates are used to simulate the impact of changes in plan features on the market shares of competing health plans and to calculate the quality level required to make consumers indifferent to changes in provider access. PRINCIPAL FINDINGS: The presence of quality information reduced the importance of provider network features in plan choices as hypothesized. However, there were not statistically meaningful differences by type of quality measure (i.e., consumer assessed versus expert assessed). The results imply that large quality differences are required to make consumers indifferent to changes in provider access. The impact of quality on plan choices depended more on the particular measure and less on the type of measure. Quality ratings based on the proportion of survey respondents "extremely satisfied with results of care" had the greatest impact on plan choice while the proportion of network doctors "affiliated with university medical centers" had the least. Other consumer and expert assessed measures had more comparable effects. CONCLUSIONS: Overall the results provide empirical evidence that consumers are willing to trade high quality for restrictions on provider access. This willingness to trade implies that relatively small plans that place restrictions on provider access can successfully compete against less restrictive plans when they can demonstrate high quality. However, the results of this study suggest that in many cases, the level of quality required for consumers to accept access restrictions may be so high as to be unattainable. The results provide empirical support for the current focus of decision support efforts on consumer assessed quality measures. At the same time, however, the results suggest that consumers would also value quality measures based on expert assessments. This finding is relevant given the lack of comparative quality information based on expert judgment and research suggesting that consumers have apprehensions about their ability to meaningfully interpret performance-based quality measures.

Adult↗