Dynamic Programming Approaches for Estimating and Applying Large-scale Discrete Choice Models

People go through their life making all kinds of decisions, and some of these decisions affect their demand for transportation, for example, their choices of where to live and where to work, how and when to travel and which route to take. Transport related choices are typically time dependent and characterized by large number of alternatives that can be spatially correlated. This thesis deals with models that can be used to analyze and predict discrete choices in large-scale networks. The proposed models and methods are highly relevant for, but not limited to, transport applications. We model decisions as sequences of choices within the dynamic discrete choice framework, also known as parametric Markov decision processes. Such models are known to be difficult to estimate and to apply to make predictions because dynamic programming problems need to be solved in order to compute choice probabilities. In this thesis we show that it is possible to explore the network structure and the flexibility of dynamic programming so that the dynamic discrete choice modeling approach is not only useful to model time dependent choices, but also makes it easier to model large-scale static choices. The thesis consists of seven articles containing a number of models and methods for estimating, applying and testing large-scale discrete choice models. In the following we group the contributions under three themes: route choice modeling, large-scale multivariate extreme value (MEV) model estimation and nonlinear optimization algorithms. Five articles are related to route choice modeling. We propose different dynamic discrete choice models that allow paths to be correlated based on the MEV and mixed logit models. The resulting route choice models become expensive to estimate and we deal with this challenge by proposing innovative methods that allow to reduce the estimation cost. For example, we propose a decomposition method that not only opens up for possibility of mixing, but also speeds up the estimation for simple logit models, which has implications also for traffic simulation. Moreover, we compare the utility maximization and regret minimization decision rules, and we propose a misspecification test for logit-based route choice models. The second theme is related to the estimation of static discrete choice models with large choice sets. We establish that a class of MEV models can be reformulated as dynamic discrete choice models on the networks of correlation structures. These dynamic models can then be estimated quickly using dynamic programming techniques and an efficient nonlinear optimization algorithm. Finally, the third theme focuses on structured quasi-Newton techniques for estimating discrete choice models by maximum likelihood. We examine and adapt switching methods that can be easily integrated into usual optimization algorithms (line search and trust region) to accelerate the estimation process. The proposed dynamic discrete choice models and estimation methods can be used in various discrete choice applications. In the area of big data analytics, models that can deal with large choice sets and sequential choices are important. Our research can therefore be of interest in various demand analysis applications (predictive analytics) or can be integrated with optimization models (prescriptive analytics). Furthermore, our studies indicate the potential of dynamic programming techniques in this context, even for static models, which opens up a variety of future research directions.

Impact of PL 94-566 on agricultural employers and UI trust funds in selected states.

"Prepared by G. Joachim [i.e. Joachim G.] Elterich and Linda Graham"--Prelim. p.

Vulnerabilities, impacts and adaptations to climate change in the agricultural sector and agricultural soils.

2009

Raising concerns and reporting poor care in practice

This article considers the issue of poor care and how nurses should respond when they encounter it. Several reports and inquiries into failings in care have called into question the standards of care provided by nurses. Of equal concern is the observation that in some instances, poor care is unreported. While there may be underlying structural and organisational reasons for this, it is contended that nurses have a legal, moral and professional obligation to report poor care when they become aware of it.

A review of Australian approaches for monitoring, assessing and reporting estuarine condition: II. State and Territory programs

In contrast to Europe, the USA and South Africa, Australia has no specific, overarching federal legislation to underpin a nationally-coordinated framework for monitoring, assessing and reporting estuarine condition. This has resulted in a complex mosaic of diverse approaches and governance structures, hindering the ability to make inter-State comparisons. In this second part of a comprehensive three-part review, we present a systematic appraisal of current and impending approaches for measuring and reporting estuarine condition in each of Australia's States and Territories. A concise summary is provided in each case, supported by extensive appendices containing detailed accounts of relevant monitoring and reporting programs. We synthesise and evaluate this output at the State/Territory level, highlighting areas of improvement and major gaps.

Guidelines for developing and reporting machine learning predictive models in biomedical research : a multidisciplinary view

BACKGROUND: As more and more researchers are turning to big data for new opportunities of biomedical discoveries, machine learning models, as the backbone of big data analysis, are mentioned more often in biomedical journals. However, owing to the inherent complexity of machine learning methods, they are prone to misuse. Because of the flexibility in specifying machine learning models, the results are often insufficiently reported in research articles, hindering reliable assessment of model validity and consistent interpretation of model outputs.

OBJECTIVE: To attain a set of guidelines on the use of machine learning predictive models within clinical settings to make sure the models are correctly applied and sufficiently reported so that true discoveries can be distinguished from random coincidence.

METHODS: A multidisciplinary panel of machine learning experts, clinicians, and traditional statisticians were interviewed, using an iterative process in accordance with the Delphi method.

RESULTS: The process produced a set of guidelines that consists of (1) a list of reporting items to be included in a research article and (2) a set of practical sequential steps for developing predictive models.

CONCLUSIONS: A set of guidelines was generated to enable correct application of machine learning models and consistent reporting of model specifications and results in biomedical research. We believe that such guidelines will accelerate the adoption of big data analysis, particularly with machine learning methods, in the biomedical research community.

The census of Iowa, as returned in the year 1873 : showing, in detail, the population, agricultural statistics, and other items of interest / published under direction of the Executive Council, 1874

This is the Census of Iowa as returned in the year 1873, showing in detail, the population, agricultural statistics, and other items of interest

Determinants of environmental accounting and reporting practices in portuguese local entities

Purpose – The purpose of this paper is to develop environmental accounting and reporting practices (EARPs) by Portuguese local entities and their determining factors. Design/methodology/approach – Data were obtained through a postal survey. In order to measure the degree of development of environmental accounting and reporting practices index was developed, which reflects the extent to which a set of eight EARPs have been implemented by the 69 Portuguese local entities included in the sample. Three variables are considered in this study as possible factors that drive the development of environmental management practices (EMPs) by local entities, namely, size of entity, accounting framework, degree of development of EMPs. Findings – Results indicate the degree of development of EARPs in Portuguese local entities is low. Additionally, accounting regulation and the degree of development of EMPs are explaining factors of the degree of development of environmental accounting practices in Portuguese local entities. Originality/value – This study adds to the international research on environmental accounting in public sector by providing empirical data from a country, Portugal, where empirical evidence is still relatively limited.

Global research alliance modelling platform (GRAMP): an open web platform for modelling greenhouse gas emissions from agro-ecosystems

Carbon (C) and nitrogen (N) process-based models are important tools for estimating and reporting greenhouse gas emissions and changes in soil C stocks. There is a need for continuous evaluation, development and adaptation of these models to improve scientific understanding, national inventories and assessment of mitigation options across the world. To date, much of the information needed to describe different processes like transpiration, photosynthesis, plant growth and maintenance, above and below ground carbon dynamics, decomposition and nitrogen mineralization. In ecosystem models remains inaccessible to the wider community, being stored within model computer source code, or held internally by modelling teams. Here we describe the Global Research Alliance Modelling Platform (GRAMP), a web-based modelling platform to link researchers with appropriate datasets, models and training material. It will provide access to model source code and an interactive platform for researchers to form a consensus on existing methods, and to synthesize new ideas, which will help to advance progress in this area. The platform will eventually support a variety of models, but to trial the platform and test the architecture and functionality, it was piloted with variants of the DNDC model. The intention is to form a worldwide collaborative network (a virtual laboratory) via an interactive website with access to models and best practice guidelines; appropriate datasets for testing, calibrating and evaluating models; on-line tutorials and links to modelling and data provider research groups, and their associated publications. A graphical user interface has been designed to view the model development tree and access all of the above functions.

Estimating mineralisation of organic nitrogen from biosolids and other organic wastes applied to soils in subtropical Australia

One major benefit of land application of biosolids is to supply nitrogen (N) for agricultural crops, and understanding mineralisation processes is the key for better N-management strategies. Field studies were conducted to investigate the process of mineralisation of three biosolids products (aerobic, anaerobic, and thermally dried biosolids) incorporated into four different soils at rates of 7-90 wet t/ha in subtropical Queensland. Two of these studies also examined mineralisation rates of commonly used organic amendments (composts, manures, and sugarcane mill muds). Organic N in all biosolids products mineralised very rapidly under ambient conditions in subtropical Queensland, with rates much faster than from other common amendments. Biosolids mineralisation rates ranged from 30 to 80% of applied N during periods ranging from 3.5 to 18 months after biosolids application; these rates were much higher than those suggested in the biosolids land application guidelines established by the NSW EPA (15% for anaerobic and 25% for aerobic biosolids). There was no consistently significant difference in mineralisation rate between aerobic and anaerobic biosolids in our studies. When applied at similar rates of N addition, other organic amendments supplied much less N to the soil mineral N and plant N pools during the crop season. A significant proportion of the applied biosolids total N (up to 60%) was unaccounted for at the end of the observation period. High rates of N addition in calculated Nitrogen Limited Biosolids Application Rates (850-1250 kg N/ha) resulted in excessive accumulation of mineral N in the soil profile, which increases the environmental risks due to leaching, runoff, or gaseous N losses. Moreover, the rapid mineralisation of the biosolids organic N in these subtropical environments suggests that biosolids should be applied at lower rates than in temperate areas, and that care must be taken with the timing to maximise plant uptake and minimise possible leaching, runoff, or denitrification losses of mineralised N.

Incorporating fishery observer data into an integrated catch-at-age and multiyear tagging model for estimating mortality rates and abundance

Tagging experiments are a useful tool in fisheries for estimating mortality rates and abundance of fish. Unfortunately, nonreporting of recovered tags is a common problem in commercial fisheries which, if unaccounted for, can render these estimates meaningless. Observers are often employed to monitor a portion of the catches as a means of estimating reporting rates. In our study, observer data were incorporated into an integrated model for multiyear tagging and catch data to provide joint estimates of mortality rates (natural and f ishing), abundance, and reporting rates. Simulations were used to explore model performance under a range of scenarios (e.g., different parameter values, parameter constraints, and numbers of release and recapture years). Overall, results indicated that all parameters can be estimated with reasonable accuracy, but that fishing mortality, reporting rates, and abundance can be estimated with much higher precision than natural mortality. An example of how the model can be applied to provide guidance on experimental design for a large-scale tagging study is presented. Such guidance can contribute to the successful and cost-effective management of tagging programs for commercial fisheries.

Illinois agricultural statistics : livestock and poultry by counties, ten years ending January 1, 1975 /

Chiefly tables.

Didiman: Australian agricultural extension officers in the territory of Papua and New Guinea, 1945-1975

Historically, the development philosophy for the two Territories of Papua and New Guinea (known as TPNG, formerly two territories, Papua and New Guinea) was equated with economic development, with a focus on agricultural development. To achieve the modification or complete change in indigenous farming systems the Australian Government’s Department of External Territories adopted and utilised a programme based on agricultural extension. Prior to World War II, under Australian administration, the economic development of these two territories, as in many colonies of the time, was based on the institution of the plantation. Little was initiated in agriculture development for indigenous people. This changed after World War II to a rationale based on the promotion and advancement of primary industry, but also came to include indigenous farmers. To develop agriculture within a colony it was thought that a modification to, or in some cases the complete transformation of, existing farming systems was necessary to improve the material welfare of the population. It was also seen to be a guarantee for the future national interest of the sovereign state after independence was granted. The Didiman and Didimisis became the frontline, field operatives of this theoretical model of development. This thesis examines the Didiman’s field operations, the structural organisation of agricultural administration and the application of policy in the two territories.