*Corresponding author: email@example.com
One of the most celebrated and feared concepts in the world today are risk which is the product of uncertainty. Many studies said, risk and uncertainty are often used interchangeably as they are the same thing, but it is not true. While risk can be measured and estimated but uncertainty cannot. Uncertainty regarding complete unawareness of the future and there is no amount of technical adjustment or mathematically delicacy that can change our basic ignorance of the future. However, risk and uncertainty cannot be separated because where there is uncertainty, there is risk. The probability of risk can be measured precisely, while that of the uncertainty can only be measured through the subjective likelihood depending on the marginal utility of an individual. Probably, no single model is the best at farm level, but the use of, MOTAD with compromise programming, marginal utility of money and Linear programming (LP) technique seems to offer a more powerful analytical instrument for agricultural systems modeling with respect to risk, uncertainty and decision-making, respectively.
This thesis aims to empirically test the validity of economic theories of the individual decisionmakingunderrisk and uncertainty with a laboratory experiment. The first chapter outlines this thesis. The second chapter experimentally tests Manski’s theory of satisficing (2017). He proposes solutions to two key questions: when should the decision- maker (DM) satisfice?; and how should the DM satisfice? The results show that some of Manski’s proposition (those relating to the “how”) appear to be empirically valid while others (those relating to the “when”) are less so. The third chapter extends the findings from the previous chapter, mainly relating to “how to satisfice”. I propose an alternative story with a different assumption of the subjects’ preference functional and of the payoff distribution. The results suggest that my alternative story appears to better-explain the subjects’ behaviour than that of Manski’s story. The fourth chapter explores the individual behaviour towards randomisation of the choice. I use the elicitation method that provides an additional option between two alternatives, namely “I am not sure what to choose” as an alternative of two standard options: "I choose A" or "I choose B". It gives a consequence where the subjects’ payoff is determined by a randomisation of two alternatives through the flipping a coin. I propose four stories to account for the choice of this option. The results show that the most of the subjects either have strictly convex preferences with random risk attitude or simply cannot distinguish the two alternatives.
Abstract: The costs functions are mentioned mostly in the relation to the Break-even Analysis where they are presented in the linear form. But there exist several different types and forms of cost functions. Fist of all, it is necessary to distinguish between the short-run and long-run cost function that are both very important tools of the managerial decisionmaking even if each one is used on a different level of management. Also several methods of estimation of the cost function’s para- meters are elaborated in the literature. But all these methods are based on the past data taken from the financial accounting while the financial accounting is not able to separate the fixed and variable costs and it is also strongly adjusted to taxation in the many companies. As a tool of the managerial decisionmaking support, the cost functions should provide a vision to the future where many factors of risk and uncertainty influence economic results. consequently, these random factors should be considered in the construction of cost functions, especially in the long-run. in order to quantify the influences of these risks and uncertainties, the authors submit the application of the Bayesian Theorem.
Abstract: Goal of the paper: proposal of a model for decision-making enhancement that includes qualitative and quantitative elements influencing managerial decision-making processes under geopolitical uncertainty.
Methods: primary: Analytic Hierarchy Process – for assessment of individual and collective utility of indexes describing the functioning of enterprises; secondary: Delphi questionnaires, Pareto-Lorenz diagram, stratified random sampling; AHP evaluations came from six professional managers Results: a mixed qualitative and quantitative instrument bringing geopolitical occurrences into managerial decision-makingunder turbulent environmental conditions; Practical implications: increased efficiency of managerial decision-making processes, with managerial decisions closer to the possible optimum, under given environmental conditions.
In light of all these evidences discussed above, we think it would be helpful to re-think about why people are often found to have inverse-S shaped probability weighting functions and to what extent this reflects an intrinsic decisional attitude towards objective probabilities. We try to answer these questions by looking into the decisionmaking process of choice underrisk and building a model that does not pre-impose any type of probability weighting function. We propose a theory featuring an attention-based state weighting mechanism and show how our theory accommodates the evidence. This theory highlights a potentially important reason for the observation probability weighting under CPT. Briefly speaking, people weight probabilities non-linearly because their perceptions about probabilities are affected by the salience of the outcomes associated with the corresponding states. In our theory, a state is said to be the most salient if choosing differently leads to the largest welfare difference under that state.
DECISION-MAKING, UNCERTAINTY AND RISK conditions for health or the environment? During these steps, the decision-maker also indicates how outcomes must be measured and what kinds of uncertainties should be considered in the analysis. After identifying the objectives and alternative solutions, the next step involves decomposition of the decision problem to understand its structure and measure uncertainty and values. This step involves the use of mathematical models that provide decision-makers with quantitative assessments of the decision problem and alternatives available. Such assessments include identification and quantification of the uncertainty and risk associated with the decision problem, as well as identification of the best alternative. After choosing the “best” alternative, sensitivity analysis is carried out to investigate how uncertainty in the input variables and criteria weights (preferences) affects the chosen alternative. If the chosen alternative is not robust to the uncertainties in the input variables, the decision-maker may determine whether further analysis is needed. This can result in either reconsidering the whole decision problem or making changes to the model structure or entering the implementation step. The arrows in Figure 2.3 show that the decision analysis process is an iterative one, indicating that the decision-maker may go through several iterations before the most preferred alternative is found.
If the positive impact of the DWH usage on the performance is recognized among the staff, people tend to embrace the new practice more willingly. Less efforts are required to use the system, the more efficient and satisfactory for an individual it is. That motivates people to use and develop the DWH, supplementing it with extra clear relevant data.
Application of simulation as fundamental toolkit in digital decision-making underlines the idea that digital approach does not conflict, but organically improves the analytical one. In other words, analytical approach is enhanced with the newest technological achievements of digital era. As an example of a practical use of the proposed approach a model for uncertainty reduction in construction projects decision-making was developed. The model is based on standard simulation modeling techniques and Monte Carlo simulations; the process of its building is presented in previous papers . As a result of the model run, a user obtains statistically justified probabilities of particular results, that is, decision- makingunderuncertainty is reduced to decision-makingunderrisk (figure 3). Notably, this transformation is more realistic in comparison with widely used Laplace criterion.
uncertainty. As a result, MARE has been further developed into a number of proprietory software tools as well as open-source libraries like the MCDA package for R (Bigaret, et al., 2017). MARE requires the decision-maker to provide a range in the form of a minimum, most likely and maximum value for each alternative with respect to each criterion. Using a range to capture preferences has become more common in medical applications (Peleg, et al., 2012), survey design (Schwarz, 1999; Bruine de Bruin, et al., 2012) and software development (Wagner, et al., 2017). Peleg et al. (2012) identified that some factors are difficult to be represented by a single value and that ranges can be relatively easy to agree upon by experts. This indicates that asking for ranges is beneficial for both single and group decision-making environments. Therefore it is important to investigate and incorporate the use of ranges in MCDM techniques. In this paper, we propose a new MCDM methodology, termed as Simulated Uncertainty Range Evaluations or SURE, which allows decision-makers to provide their preferences in ranges and the technique utilises triangular distributions to account for uncertain information. SURE offers a more theoretially sound methodology and an improved output for visualising the uncertainty associated with each decision alternative. The value of the proposed method is assessed using a real-life case study from a large pharmaceutical company where it is compared against other widely-used methods for decision-making. In the next section, we give a detailed overview of MARE and the issues associated with it in order to make the case for SURE discussed in the following section.
with large number of outcomes; the source of uncertainty is not distinguished.
1.4 Cumulative Prospect Theory
Based on the earlier version of prospect theory, many authors have proposed more advanced and generalised models for decisionmakingunderuncertainty. For instance, the Anticipated Utility Model designed by Quiggin  and the Choquet Expected Utility model discovered by Wakker  managed to apply the cumulative utility to decisionmaking problem, hence explained some of the major behaviours observed in various paradoxes. However, in this project the idea of Cumulative Prospect Theory (CPT) developed by Tversky and Kahneman  is adapted and analysed. As an im- provement and variant of their earlier version of prospect theory, cumulative prospect theory incorporates many recent developments in this area. It is an adequate, de- scriptive and normative model for decisionmakingunderuncertainty. CPT model transforms probabilities of outcomes cumulatively rather than individually. It can be utilised to any uncertain prospects with even continuous probability distributions and unlimited number of outcomes. This model also enables to treat different probability weighting functions for gains and losses respectively. Thus it can accommodate some form of source dependence. More importantly, CPT model satisfies the stochastic dominance. Due to Daniel Kahneman’s contribution to behavioural economics and the development of CPT, he was awarded the Sveriges Riksbank Prize in Economic Sciences in Memory of Alfred Nobel in 2002, “for having integrated insights from psychological research into economic science, especially concerning human judgment and decision-makingunderuncertainty” .
Water resources management decisionmaking process is subject to many challenges from risk and uncertainty. In the past, imprecise safety factors were used to address uncertainty and risk. There is a need for providing water resources decision makers with formal decision support tools that accurately incorporate risk and uncertainty. The goal of this report is to demonstrate how information provided to decision makers can be improved through the use of probabilistic and fuzzy set approaches for quantifying risk and uncertainty in water resources management. Probabilistic and fuzzy set approaches are used to expand on existing decisionmaking procedures and toolsets to account for uncertainty and risk. Toolsets like simplex linear programming optimization, multi-objective analysis, and simulation of mathematical models can modified for use in the probabilistic and fuzzy domains. The methodologies for simulation, optimization, and multi-objective analysis underuncertainty are detailed in this report. In order to demonstrate how uncertainty and risk may be quantified using the probabilistic and fuzzy toolsets a set of generic problems is presented in the report. It should be noted that the tools detailed in the report may find wide application beyond the problems discussed here.
The role of immediate emotions in individual decisionmaking has been overlooked in the economics literature, whereas it has played a prominent role in psychology. For example, the risk-as-feelings hypothesis (Loewenstein et al., 2001 [ 19 ]) interprets immediate emotions that may be aroused by outcomes as heuristics that motivate and determine choice directly. Building on evidence in psychology showing that the strength of immediate emotions is determined largely by both the vividness of the mental images of an outcome and by its temporal proximity to the moment of choice rather than by the likelihood of the outcome, the risk-as-feelings hypothesis posits that immediate emotions have an “all-or-none characteristic: they may be sensitive to the possibility rather than the probability” of the outcome. Therefore, one would expect that subjects dealing with affect-rich outcomes underrisk would be very sensitive to probability variations at the endpoints of the probability scale but relatively insensitive at intermediate probability values. Rottenstreich and Hsee’s (2001 [ 23 ] (p. 187)) experimental evidence supports these predictions. In the gain domain, they found both more pronounced overweighting of low probabilities and more pronounced underweighting of high probabilities for risky lotteries associated with an affect-rich outcome (i.e., a coupon for a romantic trip) rather than with an affect-poor outcome (i.e., cash), other things being equal. Moreover, probability variations between 1% and 99% had a very limited impact on choice in the affect-rich case, but a big impact on choice in the affect-poor case. To explain their findings, Rottenstreich and Hsee (2001) [ 23 ] (p. 186, 189) argued that the affect-rich outcome elicited a more pronounced curvature of the decision weighting function (i.e., more likelihood insensitivity) than the affect-poor outcome, as long as it elicited hope of winning when the probability of winning was low and fear of losing when it was high. Alternatively, they argued that greater immediate emotions of savouring associated with the emotionally powerful positive outcome increased the elevation of the weighting function at each probability level, which, in their experiments, was exhibited as more overweighting of low probabilities. Ditto et al. (2006) [ 24 ] (p. 104) offered experimental evidence of the elevation effect at high probabilities for an
3.2 Analysis and Exploration of Alternatives at Different Levels of Detail
In addition to the aforementioned information, decision- makers need to be able to explore and compare alternatives at different levels of detail. The presence of uncertainty in the values of input variables implies that there are many possible realisations (or values) for each input variable. This gives rise to the presence of many possible scenarios, where each scenario represents a possible combination of all values of input variables, one for each variable (Marco et al., 2008). In this situation, the visualisation tool should allow the generation of all possible scenarios. This requires facilities for enabling decision-makers to provide their own estimates of the values for each uncertain variable and its distribution. In addition, it requires computational facilities for propagating all uncertainties through models and criteria used in decision-making. Once all uncertainties are propagated through the models, the visualisation tool should then provide decision-makers with a complete picture of all generated scenarios and the distribution of uncertainties and risks anticipated to exist in these scenarios. At the same time, it should allow decision- makers to interact with the decision model to allow experimentation with different possible “what-if”
Distilling the common principles of the many risk tribes and dialects into serviceable definitions and narratives, the book provides a foundation for the practice of risk analysis and decisionmakingunderuncertainty for professionals from all walks of life. In the first part of the book, readers learn the language, models, and concepts of risk analysis and its three component tasks—risk management, assessment, and communication. The second part of the book supplies the tools, techniques, and methodologies to help readers apply the principles. From problem identification and brainstorming to model building and choosing a probability distribution, the author walks readers through the how-to of risk assessment. Addressing the critical task of risk communication, he explains how to present the results of assessments and how to develop effective messages.
The main purpose of this research is developing methods and models of decision-making to assess the stock market state, and predict the possible changes in the RTS index value. This article shows that the analytical models for assessing the stock market state do not give reliable results. The absence of the reliable estimates associated with the high degree of uncertainty, random, nonlinear and non-stationary process with a significant degree of aftereffect. In this paper, to formalize the securities market parameters it’s proposed the fuzzy sets method. To assess the stock market current state and make decisions the fuzzy situational analysis model (situational model) is applied. The analytical prediction results of the stock market and graph of the RTS index expected return changes in 2014-2016 are showed. The model of calculating the fuzzy inference rules truth degree to predict the RTS index is developed. The market parameters linguistic definition is given and the expert’s rules construction to predict the RTS index growth is shown. The program in Matlab environment is designed to perform research. The study result showed that the model allows for the RTS index prediction in the condition of incomplete initial data with a confidence level about 90%.
choices where participants need to judge or predict outcomes [ 22 ]. In these experiments, small performance-based payments are awarded for each correct decision. In summary, offering performance-related incentives is important from the perspective of engaging both the deliberative system of an individual and in making the environment more salient for our subjects. By including incentives, the data is more representative of the types of decisions that users of the visualization platform are likely to face the data is likely to be superior to a situa- tion where there were no task-related monetary incentives. Although incentive experiments are widely used in experimental economics to assist with understanding human judgments of risk, they have not yet been widely applied to spatial decision-making and geovisualization.
The work is of significance as the effects of EPU on commercial property investment activity have largely been ignored until now, despite the recognised potential of volatile property prices and returns to contribute to a destabilised economy. Hence, exploring and understanding the complexities of causation across and between uncertainty, behaviour and pricing is essential, to illuminate practices and thus enable the optimisation of market and policy responses. This paper is novel in that it combines macro- and micro-level approaches to investigate the investment decision- making process, drawing on the real estate pricing framework proposed by Crosby et al. (2016) which explicitly identifies these two levels of factors as important. Firstly, the paper, based on the aggregate level approaches in other work, tests the complexities of causation between changes in economic policy uncertainty and changes in asset returns. The tests are undertaken over time and across sectors, and reveal that two-way Granger-Causality exists between commercial property returns and EPU, although the relationships are complex and subject to differences in the occupier and investor markets across sectors. Data characteristics are also important. Subsequently, the second stage, at a highly granular micro-level, uses unique primary behavioural data to explore individual real estate investment decisions and, specifically, whether investors seek the same asset characteristics in different EPU contexts. This reveals that some attributes remain critical to investors, regardless of uncertainty, with income security prioritised regardless of EPU changes. It also highlights some differences between distinct EPU regimes, indicating not just that investor behaviour responds to uncertainty, but the results reveal what those differences are. Furthermore, the findings show that behaviours vary across decision-makers operating within the same time period, but who have different economic outlooks.
5. STRATEGIC DIRECTIONS FOR FUTURE DEVELOPMENTS
Some of the deficiencies of currently available industrial tool condition monitoring systems have been highlighted in section 2 above, as has the gap between the industrial practice and the academic research. Reliability and robustness are key requirements for the further transition of the fundamental research into commercial application. In order to effect these improvements, operators will need to have increased confidence in the decisionmaking capabilities of TCM systems. Demonstrably the ‘black box’ approach to tool breakage recognition (and associated reaction by the machine controller) has not worked. It has been widely recognised that effective human judgment relies on both objective and subjective judgement. The mushrooming field of fuzzy logic and its applications to decisionmaking, since Zadeh’s seminal paper , is testament to the human requirement to incorporate degrees of uncertainty into their decisionmaking processes. In the light of this, it is somewhat puzzling that dichotomous forecasting dominates the TCM system market. Intuitively, notwithstanding the possibly increased complexity of designing such a system, a system which gives probabilistic predictions of tool breakage would be of more value to (and therefore less likely to be misused by) machine operatives.
When analyzing the presented scheme, it should be noted that the decision-making process is cyclical, in addition, this scheme is an idealized model, since real decision-making processes, due to the variety of situations and problems requiring solutions, usually differ from it, i.e. in fact, the structure of the managerial decision-making process is largely determined by the situation and the problem is solved. At the same time, decisions made in the field of strategic forecasting should essentially rely on data from future periods, of course, that it is physically impossible to do this, which is why it is most often necessary to operate on data from past periods, as well as information about the current situation, extrapolating them over time. It turns out that the predicted data already contains a significant share of uncertainty due to their very nature.
IPO (Initial Public Oﬀ ering) is a complex decisionmaking task which is always associated with diﬀ erent types of uncertainty. Poor accuracies of available probabilities of lotteries e.g. quantiﬁ cation of investor interest is studied in the ﬁ rst part of this paper (Meluzín, Doubravský, Dohnal, 2012).
However, IPO is o en prohibitively ill-known. This paper takes into consideration the fact that decision makers cannot specify the structure/topology of the relevant decision tree. It means that one IPO task is speciﬁ ed by several (partially) diﬀ erent decision trees which comes from diﬀ erent sources e.g. from diﬀ erent teams of decision makers/experts. A ﬂ exible integration of those trees is based on fuzzy logic using the reconciliation (Meluzín, Doubravský, Dohnal, 2012). The developed algorithm is demonstrated by a case study which is presented in details. The IPO case integrates two partially diﬀ erent decision trees.
This first stage of the study has provided insights into the complexities of the relationships between commercial investment property returns and EPU. At the highest level of aggregation, for all property, as set out in Table 2, total returns are seen to change in response to changing uncertainty and this is most strongly confirmed in the office sector. The retail and industrial sectors, however, perhaps surprisingly, appear different. Over the longer term, consumer spending, the holy grail in the investor market of the retail sector (and the expanding logistics sector of the industrial market), has been comparatively resilient. Rising vacancy rates in the retail sector in more recent years are linked to business factors and consumer behaviour, rather than economic policy uncertainty; yet those vacancies themselves are highly visible in the news and shown to trigger policy debates and uncertainty. Finally, and interestingly, the results shown for comparison in the appendices suggest that transaction-linked capital returns are more sensitive to EPU than the appraisal data in Table 2 suggest. These results add valuable knowledge to this area, which has largely been overlooked in previous studies. However, a disaggregated approach is needed to truly explore the drivers underlying the results and, thus, provide new insights into the effects of uncertainty on the actual decision-making of investors. Therefore, to do this, the second stage of the study focuses on investigating investment decision-making at the micro-level to see if, and how, behaviour and, specifically, the purchase preferences underlying pricing decisions differ across contrasting period of EPU.