Abstract not available

This dissertation is two essays in business decision-making. The first essay is motivated by recent field evidence suggesting significant reliance on conventional techniques (e.g. NPV and DCF) without assessment of the decision profile - its degree of uncertainty, ambiguity and knowledge distribution. However, without knowing the decision profile, the chosen decision might not be appropriate given the decision situation. Therefore, essay 1 develops a multi-faceted conceptualization of the decision profile and provides a prescriptive model for choosing appraisal methods based on this profile. Specifically, it prescribes the limited use of conventional methods to low ambiguity and uncertainty situations and using decision trees, real options, scenario planning and case-based methods as the level of uncertainty increases. In high ambiguity situations, however, the only viable approaches are case-based methods which do not have perfect information assumption that conventional alternative methods do. Case-based methods have been supported theoretically in case-based decisions and case-based reasoning literature but lags in its use in business decision-making. Possible reasons for this include a lack of concrete applications and developments of major concepts such as its case memory, similarity and prediction functions. Therefore, essay 2 proposes a model of case-based decisions called similarity-based forecasting (SBF) and applies it to a high uncertainty and ambiguity situation -- namely forecasting movie success. In doing so, it outlines operational definitions of the memory, similarity and prediction functions and, based on data from the entertainment industry, provides empirical support for the hypothesis that case-based methods can be more accurate than regression forecasting; both SBF and combined SBF-regression models were able to predict movie gross revenues with 40% and 50% greater accuracy than regression respectively. This essay concludes with a discussion of some possible directions for future research including applications using data from other domains and settings, testing the boundary conditions for which the SBF approach should be applied, experiments using SBF under uncertainty and complexity manipulations, and 'time stamped' comparisons with predictions made using information markets (e.g. Hollywood Stock Exchange).

Wind energy forecasting can facilitate wind energy integration into a power system. In particular, the management of power system security would benefit from forecast information on plausible large, rapid change in wind power generation. Numerical Weather Prediction (NWP) systems are presently the best available tools for wind energy forecasting for projection times between 3 and 48 hours. In this thesis, the types of weather phenomena that cause large, rapid changes in wind power in southeast Australia are classified using observations from three wind farms. The results show that the majority of events are due to horizontal propagation of spatial weather features. A study of NWP systems reveals that they are generally good at forecasting the broad large-scale weather phenomena but may misplace their location relative to the physical world. Errors may result from developing single time-series forecasts from a single NWP grid point, or from a single interpolation of proximate grid points. This thesis presents a new approach that displays NWP wind forecast information from a field of multiple grid points around the wind farm location. Displaying the NWP wind speeds at the multiple grid points directly would potentially be misleading as they each reflect the estimated local surface roughness and terrain at a particular grid point. Thus, a methodology was developed to convert the NWP wind speeds at the multiple grid points to values that reflect surface conditions at the wind farm site. The conversion method is evaluated with encouraging results by visual inspection and by comparing with an NWP ensemble. The multiple grid point information can also be used to improve downscaling results by filtering out data where there is a large chance of a discrepancy between an NWP time-series forecast and observations. The converted wind speeds at multiple grid points can be downscaled to site-equivalent wind speeds and transformed to wind farm power assuming unconstrained wind farm operation at one or more wind farm sites. This provides a visual decision support tool that can help a forecast user assess the possibility of large, rapid changes in wind power from one or more wind farms.

In recent years, there have been significant researches on holistic approaches to design flood estimation in Australia. The Monte Carlo Simulation technique, an approximate form of Joint Probability Approach, has been developed and tested to small gauged catchments. This thesis presents the extension of the Monte Carlo Simulation Technique to large catchments using runoff routing model URBS. The URBS-Monte Carlo Technique(UMCT),has been applied to the Johnstone River and Upper Mary River catchments in Queensland. The thesis shows that the UMCT can be applied to large catchments and be readily used by hydrologists and floodplain managers. Further the proposed technique provides deeper insight into the hydrologic behaviour of large catchments and allows assessment of the effects of errors in inputs variables on design flood estimates. The research also highlights the problems and potentials of the UMCT for application in practical situations. / Masters of Engineering (Hons.)

Design flood estimation is often required in hydrologic practice. For catchments with sufficient streamflow data, design floods can be obtained using flood frequency analysis. For catchments with no or little streamflow data (ungauged catchments), design flood estimation is a difficult task. The currently recommended method in Australia for design flood estimation in ungauged catchments is known as the Probabilistic Rational Method. There are alternatives to this method such as Quantile Regression Technique or Index Flood Method. All these methods give the flood peak estimate but the full streamflow hydrograph is required for many applications. The currently recommended rainfall based flood estimation method in Australia that can estimate full streamflow hydrograph is known as the Design Event Approach. This considers the probabilistic nature of rainfall depth but ignores the probabilistic behavior of other flood producing variables such as rainfall temporal pattern and initial loss, and thus this is likely to produce probability bias in final flood estimates. Joint Probability Approach is a superior method of design flood estimation which considers the probabilistic nature of the input variables (such as rainfall temporal pattern and initial loss) in the rainfall-runoff modelling. Rahman et al. (2002) developed a simple Monte Carlo Simulation technique based on the principles of joint probability, which is applicable to gauged catchments. This thesis extends the Monte Carlo Simulation technique to ungauged catchments. The Joint Probability Approach/ Monte Carlo Simulation Technique requires identification of the distributions of the input variables to the rainfall-runoff model e.g. rainfall duration, rainfall intensity, rainfall temporal pattern, and initial loss. For gauged catchments, these probability distributions are identified from observed rainfall and/or streamflow data. For application of the Joint Probability Approach to ungauged catchments, the distributions of the input variables need to be regionalised. This thesis, in particular, investigates the regionalisation of the distribution of rainfall duration and intensity. In this thesis, it is hypothesised that the distribution of storm duration can be described by Exponential distribution. The developed new technique of design flood estimation can provide the full hydrograph rather than only peak value as with the Probabilistic Rational Method and Quantile Regression Technique. The developed new technique can further be improved by addition of new and improved regional estimation equations for the initial loss, continuing loss and storage delay parameter (k) as and when these are available. / (M. Eng.) (Hons)

Thesis (M.S.)--University of Nevada, Reno, 2005. / "December 2005." Includes bibliographical references (leaves 77-78). Online version available on the World Wide Web.

<p>The purpose of this paper is to investigate the predictive power of the variables advanced notice of dismissal (layoffs) and vacancies for the unemployment rate. Based on the Box Jenkins Methodology, the paper makes use of Granger causality and out-of-sample tests to compare the forecast performance of a naïve reference model and the two models extended to include either lagged values of layoffs or vacancies. It is shown that layoffs make up a significant leading variable, exhibiting particularly strong predictive power at forecast horizons of 2-6 months. It is also shown that the predictive power of vacancies is more ambiguous. Vacancies constitute a valuable explanatory variable for the unemployment rate, but does not possess the same leading, predictive qualities as layoffs.</p>

<p>This is an empirical study which goal is to determine what causes changes in housing prices. It is done by using data for Stockholm and Sydney to create a model to forecast the change of house prices in the two cities. The findings suggest that the main determinants are nominal interest, household income, and the supply of new dwellings.</p><p>This is in line with previous studies. It is also investigated whether the use of financial indicators such as the development of the stock market has an impact on the house prices.</p><p>The findings regarding the implication of the financial indicators are dubious. Lastly, an investigation is made to see whether the so-called “ripple effect” can be applied to an international level. The inclusion of the ripple effect seems to be positive to the forecasting models used in this paper.</p>

The thesis contains two chapters which address questions important both for the economic theory and applications. In Chapter I we show that inequalities are an important tool in the theory of production functions. Various notions of internal economies of scale can be equivalently expressed in terms of upper or lower bounds on production functions. In the problem of aggregation of efficiently allocated goods, if one is concerned with two-sided bounds as opposed to exact expressions, the aggregate production function can be derived from some general assumptions about production units subject to aggregation. The approach used does not require smoothness or convexity properties. In Chapter II we introduce a new forecasting techniques essential parts of which include using average high-order polynomial estimators for in-sample fit and low-order polynomial extension for out-of-sample fit. We provide some statements following the Gauss-Markov theorem format. The empirical part shows that algebraic polynomials treated in a proper way can perform very well in one-step-ahead prediction, especially in prediction of the direction of exchange rate movements. / Graduation date: 1995

River ice breakup and associated flooding are realities for many northern communities. This is certainly the case in Hay River, NWT, which is located at the junction of the Hay River and Great Slave Lake. Hay River experiences a wide range of spring river ice scenarios; from docile thermal melt outs, to severe ice jams resulting in life-threatening, disastrous flooding. This study involved the analysis of five seasons of aerial and time-lapse photographs, water level measurements and hydrometeorologic data. This work also compiled an extended historical record of breakup in the Hay River delta, which was compared against the field data gathered for this study; combining local, experiential knowledge with scientific observation into a cohesive description of breakup. This will be used to advise the non-technical flood watch community on the patterns of timing and sequencing of breakup, which is critical for evacuation planning. / Water Resources Engineering