Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
80
result(s) for
"Insurance Statistical methods History."
Sort by:
Model migration and rough edges: British actuaries and the ontologies of modelling
The existing literature on modelling provides two main ways of viewing model migration: a modular view, which seeks to decompose models in their constitutive elements, and thus provides a view on what it is that migrates; and a practice-based view, which focuses on modelling as an activity, and understands a model as intricately entangled with its context of use. This article brings together these two sensitivities by focusing on ontologies of modelling. The paper presents a case study of the appropriation of modern finance theory’s ‘no-arbitrage’ models by British actuaries – a process that gradually unfolded at around the turn of the century and led to significant friction within the UK’s insurance industry. We can distinguish two main modelling ontologies: a ‘risk-neutral ontology’, which underpins no-arbitrage models and holds that the value of financial instruments is determined by ‘arbitrage’; and, a ‘real-world ontology’, which assumes that the economic world consists of real probabilities that may be approximated through a combination of archival-statistical methods and expert judgment. The appropriation of the risk-neutral modelling ontology was made possible by the declining legitimacy of actuarial expertise as ‘financial stewards’ of life insurance companies. The risk-neutral modelling ontology provided an ‘objective’ alternative to the traditional actuarial models, which explicitly required actuaries to make ‘prudent’ judgments. Despite the fact that the no-arbitrage modelling was considered an ‘objective’ affair, the valuation models that insurers use today are strongly shaped by political compromises, a result of the ‘rough edges’ of models.
Journal Article
Coming to Terms with Chance
The application of probability and statistics to an ever-widening number of life-decisions serves to reproduce, reinforce, and widen disparities in the quality of life that different groups of people can enjoy. As a critical technology assessment, the ways in which bad luck early in life increase the probability that hardship and loss will accumulate across the life course are illustrated. Analysis shows the ways in which individual decisions, informed by statistical models, shape the opportunities people face in both market and non-market environments. Ultimately, this book challenges the actuarial logic and instrumental rationalism that drives public policy and emphasizes the role that the mass media play in justifying its expanded use. Although its arguments and examples take as their primary emphasis the ways in which these decision systems affect the life chances of African-Americans, the findings are also applicable to a broad range of groups burdened by discrimination.
eBook
The Persistent Effects of Peru's Mining Mita
This study utilizes regression discontinuity to examine the long-run impacts of the mita, an extensive forced mining labor system in effect in Peru and Bolivia between 1573 and 1812. Results indicate that a mita effect lowers household consumption by around 25% and increases the prevalence of stunted growth in children by around 6 percentage points in subjected districts today. Using data from the Spanish Empire and Peruvian Republic to trace channels of institutional persistence, I show that the mita's influence has persisted through its impacts on land tenure and public goods provision. Mita districts historically had fewer large landowners and lower educational attainment. Today, they are less integrated into road networks and their residents are substantially more likely to be subsistence farmers.
Journal Article
The natural history of severe asthma and influences of early risk factors: a population-based cohort study
BackgroundSevere asthma is associated with disproportionately high morbidity, but little is known about its natural history and how risk factors at first year of diagnosis modify its subsequent development.MethodsUsing administrative health data, we retrospectively followed patients 14–55 years of age with newly diagnosed severe asthma in British Columbia, Canada. Based on intensity of resource use (drug therapy) and occurrence of exacerbations, each patient-year was classified into mild, moderate, or severe asthma. We estimated the probability of transition between severity levels or to death over the study period using a four-state Markov model, and used this to assess the 10-year trajectory of severe asthma and the influence of baseline risk factors.ResultsWe followed 13 467 patients. Ten years after incident severe asthma, 83% had transitioned to a less severe level (mild: 43%, moderate: 40%). Low socioeconomic status, high comorbidity burden, and high adherence (proportion of days covered (PDC) by asthma controller therapy) in the first year were independently associated with, respectively, 10%, 24% and 35% more time in severe asthma over the next 10 years. Sex was not associated with the clinical course.ConclusionsMost patients with incident severe asthma used fewer resources over time, indicating a long-term transition to milder asthma. Potentially modifiable risk factors for poor prognosis of severe asthma include low socioeconomic status and high comorbidity burden. The association between PDC and future asthma severity is likely due to residual confounding by disease severity.
Journal Article
Statistical Analysis of a Telephone Call Center
A call center is a service network in which agents provide telephone-based services. Customers who seek these services are delayed in tele-queues. This article summarizes an analysis of a unique record of call center operations. The data comprise a complete operational history of a small banking call center, call by call, over a full year. Taking the perspective of queueing theory, we decompose the service process into three fundamental components: arrivals, customer patience, and service durations. Each component involves different basic mathematical structures and requires a different style of statistical analysis. Some of the key empirical results are sketched, along with descriptions of the varied techniques required. Several statistical techniques are developed for analysis of the basic components. One of these techniques is a test that a point process is a Poisson process. Another involves estimation of the mean function in a nonparametric regression with lognormal errors. A new graphical technique is introduced for nonparametric hazard rate estimation with censored data. Models are developed and implemented for forecasting of Poisson arrival rates. Finally, the article surveys how the characteristics deduced from the statistical analyses form the building blocks for theoretically interesting and practically useful mathematical models for call center operations.
Journal Article
Health litigation and cancer survival in patients treated in the public health system in a large Brazilian city, 2014–2019
Background
Litigation for health care, also known as health judicialization, is frequent in Brazil. It involves recourse to the court system to access health services. The study aimed to evaluate whether cancer patients in Belo Horizonte, Minas Gerais, Brazil, increased their overall survival by increasing access to certain drugs or treatments through litigation, controlling for the effect of demographic and disease-related variables.
Methods
A retrospective cohort study was conducted. Patients with breast, prostate, brain, lung, or colon cancers from 2014 to 2019 were included. Survival analysis was performed using the Cox proportional hazards model.
Results
In the multivariate analysis, litigation was significantly associated with increased survival in cancers of breast (HR = 0.51, 95%CI 0.33–0.80), prostate (HR = 0.50, 95%CI 0.30–0.85), colon (HR = 0.59, 95%CI 0.38–0.93), and lung (HR = 0.36, 95%CI 0.22–0.60). Five-year survival rates of patients who sued for treatment were 97.8%, 88.7%, 59.3%, and 26.0%, compared to median survival of 95.7%, 78.7%, 41.2%, and 2.4%, respectively, among patient that did not resort to court action. The study suggests that litigation for access to cancer treatment may represent a step forward in obtaining more effective treatment. This study´s main limitations are the lack of patients´ clinical information for use as control variables and the lack of variables to assess patients´ quality of life. The study also found that many cases involved claims that could have been solved by administrative rather than legal action. Some claims thus reflect the lack of adequate administrative procedures.
Conclusion
When based on scientific evidence, access to new therapies, combined with other technologies already available, can favor patient survival. Access to new therapies through litigation may increase health inequalities since low-income patients have limited access to legal recourse against the State to meet their needs. The timely approval of new effective therapies can mitigate the judicialization of cancer treatment.
Journal Article
Is Gibrat’s “Economic Inequality” lognormal?
In the seminal book “Les Inégalités Économiques,” Gibrat (Les Inégalités Économiques, Librairie du Recueil Sirey, Paris, 2013) proposed the law of proportional effect and claimed that a variety of empirical size distributions—such as income, wealth, firm size, and city size—obey the lognormal distribution. Gibrat’s law went on to become a stylized result stimulating a voluminous subsequent research that has contributed to our understanding of stochastic growth processes and a statistical regularity of the size distribution. However, many of the motivating examples used by Gibrat in his original work were subject to various data issues, and Gibrat’s reasoning of lognormal fit was based solely on graphical analysis. In this paper, we revisit the original 24 data sets considered by Gibrat (Les Inégalités Économiques, Librairie du Recueil Sirey, Paris, 2013) and show that in the majority of cases, the Pareto-type distribution actually provides a better fit to the data than lognormal. We show that Gibrat’s erroneous conclusion is partly due to data binning, truncation, and failure to weight data points properly.
Journal Article
Dealing with trend uncertainty in empirical estimates of European rainfall climate for insurance risk management
The insurance industry uses mathematical models to estimate the risks due to future natural catastrophes. For climate‐related risks, historical climate data are a key ingredient used in making the models. Historical data for temperature and sea level often show clear and readily quantified climate change driven trends, and these trends would typically be accounted for when building risk models by adjusting earlier values to render the earlier data relevant to the future climate. For other climate variables, such as rainfall in many parts of the world, the questions of whether there are climate change driven trends in the historical data, and how to quantify them if there are, are less simple to answer. We investigate these questions in the context of European rainfall with a specific focus on how to deal with the uncertainty around trend estimates. We compare 10 empirical methodologies that one might use to model and predict trends, including traditional statistical testing and alternatives to statistical testing based on standard methods from model selection and model averaging. We emphasize prediction and risk assessment, rather than detection of trends, as our goal. Viewed in terms of this goal, the methods we consider each have qualitative and quantitative advantages and disadvantages. Understanding these advantages and disadvantages can help risk modellers make a choice as to which method to use, and based on the results we present, we believe that in many common situations model averaging methods, as opposed to statistical testing or model selection, are the most appropriate. Flood risk modelling often involves estimating trends in historical rainfall, but uncertainties make that very difficult. We compare 10 different methods that can be used to model trends, including nine methods that adjust the trends to compensate for uncertainty. The different methods have various advantages and disadvantages, but model averaging methods, in particular, turn out to have a number of properties that may make them more suitable for risk modelling than ordinary least squares or ordinary least squares combined with statistical testing.
Journal Article
Digital rectal examination and its associated factors in the early detection of prostate cancer: a cross-sectional population-based study
Background
Digital rectal examination (DRE) is one of the most common strategies for prostate cancer early detection. However, the use for screening purposes has a controversial benefit and potential harms can occur due to false-positive results, overdiagnosis and overtreatment. The objective of this study is to calculate the prevalence and identify factors associated with the receipt of DRE in Brazilian men.
Methods
We selected men older than 40 from a nationwide population-based survey (13,625 individuals) excluding those with prostate cancer diagnosis. Information was extracted from the most recent database of the Brazilian National Health Survey (PNS 2013). Statistical analysis was carried out to calculate incidence rate ratios, with 95% confidence intervals and
p
values, through multivariate analysis with Poisson regression and robust variance.
Results
Men having private health insurance (63.3%; CI = 60.5–66.0) presented higher prevalence of DRE than those in the public health system (41.6%; CI = 39.8–43.4). The results show a positive association between DRE and men having private health insurance, aged 60–69, living with a spouse, never smokers, and living in urban areas. Among public health services users, this positive association was observed among men aged 70–79, living with a spouse, having bad/very bad health self-perception, abstainers, ex-smokers, with undergraduate studies, presenting four or more comorbidities, and residing in urban areas.
Conclusions
Prostate cancer screening with DRE is quite frequent in Brazil, specially among men with private health plans and better access to health services, healthier lifestyle and at more advanced ages, characteristics which increase the risk of overdiagnosis and overtreatment.
Journal Article