Acute medical unit design – The impact of rearranged patient flows

Acute Medical Units (AMUs) are instigated in many hospitals across the world. An AMU admits acute patients, mainly arriving via the emergency department, for further assessment, care and treatment for a maximum designated period. Thereafter, patients who require additional care are transferred to regular wards that also admit elective patients. The literature reports several benefits (including reductions in in-patient mortality and in the length of stay), with these conclusions mostly based on empirical findings from studies focused on acute patient performance only. This paper sheds light on the potential hospital-wide impact of implementing a range of AMU designs in terms of length of the designated period, size and transfer policy. A simulation study is performed based on data from a large Dutch hospital. When establishing an AMU, hospitals usually transfer resources from existing wards to the new AMU. This seems logical since these wards receive fewer acute admissions once an AMU is in place. However, our research shows that this transfer of resources decreases the overall performance (of the AMU and the wards) for all the AMU designs investigated. We report on the scale of these negative effects and the required reduction in the length of acute patients' stays required to compensate for these effects.     

The temporal variation of cost-efficiency in Switzerland’s hospitals: an application of mixed models

This paper uses a mixed effects model to examine the temporal variation of cost efficiency in Switzerland’s general hospitals. The variations in total costs, the number of empty beds and the length of hospital stays are analyzed using financial data from a sample of 168 hospitals operating from 1998 to 2003, as well as hospitalization records disaggregated to Diagnosis Related Groups. Individual intercepts and random coefficients are used to account for the unobserved time-invariant heterogeneity and the differences in temporal patterns across hospitals and DRG categories. The analysis illustrates the usefulness of mixed models to account for unobserved factors such as quality, with a relatively weak assumption that their temporal variations, rather than their initial levels, be uncorrelated with efficiency changes. The results indicate that hospitals have adopted measures to curtail hospitalizations and reduce empty beds. The extent and effectiveness of these measures vary significantly across individual hospitals. However, there is no evidence in favor of a particular ownership type or subsidization regime. While the link between reduction rates of empty beds and gains in cost-efficiency is statistically significant, the expected association between shortening hospital stays and cost-efficiency cannot be clearly established in the data.

A bivariate count data model for household tourism demand

Households' choice of the number of leisure trips and the total number of overnight stays is empirically studied using Swedish tourism data. A bivariate hurdle approach separating the participation (to travel and stay the night or not) from the quantity (the number of trips and nights) decision is employed. The quantity decision is modelled with a bivariate mixed Poisson lognormal model allowing for both positive as well as negative correlation between count variables. The observed endogenous variables are drawn from a truncated density and estimation is pursued by simulated maximum likelihood. The estimation results indicate a negative correlation between the number of trips and nights. In most cases own price effects are as expected negative, while estimates of cross‐price effects vary between samples. Copyright © 2005 John Wiley & Sons, Ltd.     

Multiple imputation of incomplete zero‐inflated count data

Empirical count data are often zero‐inflated and overdispersed. Currently, there is no software package that allows adequate imputation of these data. We present multiple‐imputation routines for these kinds of count data based on a Bayesian regression approach or alternatively based on a bootstrap approach that work as add‐ons for the popular multiple imputation by chained equations (mice ) software in R (van Buuren and Groothuis‐Oudshoorn , Journal of Statistical Software, vol. 45, 2011, p. 1). We demonstrate in a Monte Carlo simulation that our procedures are superior to currently available count data procedures. It is emphasized that thorough modeling is essential to obtain plausible imputations and that model mis‐specifications can bias parameter estimates and standard errors quite noticeably. Finally, the strengths and limitations of our procedures are discussed, and fruitful avenues for future theory and software development are outlined.     

Expectation-based scan statistics for monitoring spatial time series data

We consider the simultaneous monitoring of a large number of spatially localized time series in order to detect emerging spatial patterns. For example, in disease surveillance, we detect emerging outbreaks by monitoring electronically available public health data, e.g. aggregate daily counts of Emergency Department visits. We propose a two-step approach based on the expectation-based scan statistic: we first compute the expected count for each recent day for each spatial location, then find spatial regions (groups of nearby locations) where the recent counts are significantly higher than expected. By aggregating information across multiple time series rather than monitoring each series separately, we can improve the timeliness, accuracy, and spatial resolution of detection. We evaluate several variants of the expectation-based scan statistic on the disease surveillance task (using synthetic outbreaks injected into real-world hospital Emergency Department data), and draw conclusions about which models and methods are most appropriate for which surveillance tasks.     

Dynamic prediction of mortality among patients in intensive care using the sequential organ failure assessment (SOFA) score: a joint competing risk survival and longitudinal modeling approach

In intensive care units (ICUs), besides routinely collected admission data, a daily monitoring of organ dysfunction using scoring systems such as the sequential organ failure assessment (SOFA) score has become practice. Such updated information is valuable in making accurate predictions of patients' survival. Few prediction models that incorporate this updated information have been reported. We used follow‐up data of ICU patients who either died or were discharged at the end of hospital stay, without censored cases. We propose a joint model comprising a linear mixed effects submodel for the development of longitudinal SOFA scores and a proportional subdistribution hazards submodel for death as end point with discharge as competing risk. The two parts are linked by shared latent terms. Because there was no censoring, it was straightforward to fit our joint model using available software. We compared predictive values, based on the Brier score and the area under the receiver operating characteristic curve, from our model with those obtained from an earlier modeling approach by Toma et al . [Journal of Biomedical Informatics 40, 649, (2007)] that relied on patterns discovered in the SOFA scores over a given period of time.     

Regional variations in hospital occupancy rates

This paper analyzes theoretically and empirically SMSA differences in occupancy rates in short-term general hospitals. Because of the randomness of shortrun demands for admission to hospitals, occupancy rates are greater, the greater the admission rate, the larger the population, and the fewer the hospitals in the SMSA. Occupancy rates are higher where a greater proportion of the population is black and where the winters are colder, both due to longer hospital stays. More beds per capita lowers the occupancy rate. The efficiency of bed use could be increased by greater coordination among hospitals.     

An extortionary guerrilla movement

This paper models an extortionary relationship between a pipeline operator and a guerrilla movement. Payment and attack decisions are modeled as an infinite-horizon Markov decision process, where each period the oil company chooses to pay or not pay an extortion demand and the movement decides to attack or not. Decisions depend on the level of single-period payoff and discounted expected future payoffs. We estimate the model with pipeline attack data and compare parameters when the discount factor is changed. We reject a zero discount factor hypothesis, demonstrating that the movement's observed attack pattern is compatible with extortionary behavior. Copyright © 2007 John Wiley & Sons, Ltd.     

Long-term interest rates,risk premia and unconventional monetary policy

We study two kinds of unconventional monetary policies: announcements about the future path of the short-term rate and long-term nominal interest rates as operating instruments of monetary policy. We do so in a model where the risk premium on long-term debt is, in part, endogenously determined. We find that both policies are consistent with unique equilibria, that, at the zero lower bound, announcements about the future path of the short-term rate can lower long-term interest rates through their impact both on expectations and on the risk premium and that long-term interest rate rules perform as well as, and at times better than, conventional Taylor rules. With simulations, we show that long-term interest rate rules generate sensible dynamics both when in operation and when expected to be applied.     

The effects of pension rights and retirement age on training participation: Evidence from a natural experiment

This paper uses a natural experiment approach to identify the effects of an exogenous change in future pension benefits on workers' training participation. We use unique matched survey and administrative data for male employees in the Dutch public sector who were born in 1949 or 1950. Only the latter were subjected to a major pension reform that diminished their pension rights. We find that this exogenous shock to pension rights postpones expected retirement and increases participation in training courses among older employees, although exclusively for those employed in large organizations.     

The co-occurrence of self-observed norm-conforming behavior,reduction of zero observations and remaining measurement quality

Norm-violating behavior is characterized by clear social norms which prescribe the non-occurrence of that behavior. From the theoretical framework of Allport it is derived that specifically norm-conformation is consistent, while violating norms is expected to be inconsistent and more circumstantial. This is in contrast to test-theoretic approaches of delinquent behavior that assume that various norm-violating responses form a consistent answer pattern that is scalable and reliable. In this study we study the inter-correlations, scalability and reliability of norm-violating responses and their relation with the reduction of zero observations. In concordance with Allport’s view it is expected that different norm-violating self-report items have limited interrelatedness and are limited in scalability and reliability in the norm-violating sub-population. The NLSY98 self-report data show that a large majority of respondents (69 %) conform systematically to all ten different norms, while only nine percent admits more than two different violations. The results show that in subsamples of norm-violating respondents, the correlations between items become closer to zero, dependent on the amount of zero reduction. Furthermore, both Loevinger’s H coefficient of scalability and scale reliability become unsatisfactorily low, when 35 % or more strict norm-conforming subjects are removed.     

The ties that bind: Buyer-supplier relations in the construction industry

This study considers the consequences of Inter Organisational relations at two levels: the micro level of the individual, and the macro level of the organisation. Merging Transaction Cost Economics with theories on the Social Embeddedness of relations, the paper tackles several hypotheses about problems in buyer–supplier relations. We amend the general hypothesis, as has been put forward by other researchers, that having a common past in combination with an expected common future in business will reduce the likelihood that problems and conflicts occur. Our focus lies on whether this shared past and future can preclude problems better when the organisational relations are at the micro level. Our analyses of survey data from 448 contractor–subcontractor relations from the contractor's perspective in the construction industry reveal mixed support for effects of a shared past or future. We hardly find any of the expected positive effects of a shared past on supplier performance. However, we do find support for the hypothesis that a larger likelihood of future business with the same business partner has a stronger (negative) effect on the occurrence of problems if the expected future business is at the level of individuals (instead of at the level of organisations).     

Motivation for alumni donations: a social identity perspective on the role of branding in higher education

• As a result of decreasing government funds and increasing competition, institutions of higher education have propelled themselves into business practices such as branding. Despite the growing literature on branding in higher education, there is little research on the relationship between alumni donor motivations and the university brand. This study explores donor motivations from social identity and self‐congruity theoretical perspectives. The authors used zero‐inflated negative binomial regression to assess the relationship between identification and count of donations. The results showed that if the level of identification with the university increased, the expected number of donations would also increase. The study further assessing the “zeros” (non‐donors), the results suggested that if an alumnus were to identify with the university, he would be 43% less likely to be “certain zero” (definitive non‐donor) and would find a way to give money. Additionally, the authors analyzed responses about why alumni donate and why they choose not to donate. The authors offered observations on the basis of respondent commentary and also raised the question of what happens when university branding efforts conflict with the perceptions of a large stakeholder group such as alumni.

Copyright © 2014 John Wiley & Sons, Ltd.     

Nowcasting growth using Google Trends data: A Bayesian Structural Time Series model

This paper investigates the benefits of internet search data in the form of Google Trends for nowcasting real U.S. GDP growth in real time through the lens of mixed frequency Bayesian Structural Time Series (BSTS) models. We augment and enhance both model and methodology to make these better amenable to nowcasting with large number of potential covariates. Specifically, we allow shrinking state variances towards zero to avoid overfitting, extend the SSVS (spike and slab variable selection) prior to the more flexible normal-inverse-gamma prior which stays agnostic about the underlying model size, as well as adapt the horseshoe prior to the BSTS. The application to nowcasting GDP growth as well as a simulation study demonstrate that the horseshoe prior BSTS improves markedly upon the SSVS and the original BSTS model with the largest gains in dense data-generating-processes. Our application also shows that a large dimensional set of search terms is able to improve nowcasts early in a specific quarter before other macroeconomic data become available. Search terms with high inclusion probability have good economic interpretation, reflecting leading signals of economic anxiety and wealth effects.     

Dynamic Equilibrium in the Hospital Industry

We present a dynamic model of the hospital industry in which nonprofit and for-profit hospitals coexist and compete and are differentiated by their objective functions, investment technologies, and taxation rates. In our model, patients differ by income and type of insurance coverage, and choose admission to their preferred hospital, while hospitals choose investment, entry, exit, and pricing strategies. We estimate the parameters of the model with aggregate data and a GMM procedure. We then use the model to examine the effects of changes in the Medicare reimbursement system, universal health-care coverage, and taxation of nonprofits.     

Term structure models and the zero bound: An empirical investigation of Japanese yields

When Japanese short-term bond yields were near their zero bound, yields on long-term bonds showed substantial fluctuation, and there was a strong positive relationship between the level of interest rates and yield volatilities/risk premiums. We explore whether several families of dynamic term structure models that enforce a zero lower bound on short rates imply conditional distributions of Japanese bond yields consistent with these patterns. Multi-factor “shadow-rate” and quadratic-Gaussian models, evaluated at their maximum likelihood estimates, capture many features of the data. Furthermore, model-implied risk premiums track realized excess returns during extended periods of near-zero short rates. In contrast, the conditional distributions implied by non-negative affine models do not match their sample counterparts, and standard Gaussian affine models generate implausibly large negative risk premiums.     

Factors affecting development of crisis management mechanisms in hospitals

The growing competition among hospitals has almost dissolved hospitals’ absolute dominance over the physician–patient relationship. Many existing systems or regulations governing public organizations are so rigid that outstanding physicians in public hospitals may easily depart or be head hunted by competitors. Therefore, there will be more and starker challenges ahead of public hospitals. Through collection and analysis of a large sample, we attempt to apply a unique data validation method—nonlinear fuzzy neural network model to investigate the research issue. The questionnaire was administered to chairmen or physicians taking administrative positions in Taiwan’s public hospitals. The empirical results are as follows: Uncertainty of the hospital business environment is positively correlated with development of crisis management mechanisms; Operation of crisis management mechanisms is positively correlated with establishment of a medical risk management system; Organizational culture in public hospitals is disadvantageous to operation of crisis management mechanisms.     

Accounting for length of hospital stay in regression models in clinical epidemiology

In hospital epidemiology, logistic regression is a popular model to study risk factors of hospital-acquired infections. One key issue in this analysis is how to incorporate the time dependency of acquiring an infection during the hospital stay. In the applied literature, researchers often simply adjust for the entire length of hospital stay, which also includes the time after infection. A further issue is that discharge and death are competing events for hospital-acquired infections. After discussing the limitations of logistic regression adjusted for length of stay in this setting, we compare this approach with appropriate analyses incorporating competing risks and with an illness–death model with hospital-acquired infection as an intermediate event. The cumulative incidence function, cause-specific hazard ratios, and subdistribution hazard ratios are considered as reference measures. Real-life and simulated data are used to demonstrate biases and limitations associated with logistic regression adjusted for length of stay. We conclude that logistic regression adjusted for length of stay should not be used when investigating hospital-acquired infections and that appropriate methods involving the use of multistate models should be used to capture the time dependency in time-to-event settings, especially in the presence of competing events.     

Incentive effects in the demand for health care: a bivariate panel count data estimation

This paper contributes in three dimensions to the literature on health care demand. First, it features the first application of a bivariate random effects estimator in a count data setting, to permit the efficient estimation of this type of model with panel data. Second, it provides an innovative test of adverse selection and confirms that high‐risk individuals are more likely to acquire supplemental add‐on insurance. Third, the estimations yield that in accordance with the theory of moral hazard, we observe a much lower frequency of doctor visits among the self‐employed, and among mothers of small children. Copyright © 2002 John Wiley & Sons, Ltd.     

Ellsberg’s two-color experiment,portfolio inertia and ambiguity

Results in this paper relate the observation of an interval of prices at which a decision maker (DM) strictly prefers to hold a zero position on an asset (termed “portfolio inertia”) to the DM’s perception of the underlying payoff relevant events as ambiguous, as the term is defined in [Econometrica 69 (2001) 265]. The connection between portfolio inertia and ambiguity is established without invoking a parametric preference form, such as the Choquet expected utility or the max–min multiple priors model. This allows us to draw an observable distinction between portfolio inertia that may arise purely due to first-order risk aversion type effects, such as those which could arise even if preferences were probabilistically sophisticated, and portfolio inertia that involves ambiguity perceptions.