L’intérêt des modèles non-linéaires réside, d’une part, dans une meilleure prise en compte des non-linéaritéscaractérisant les séries macroéconomiques et financières et, d’autre part, dans une prévision plus riche en information.A ce niveau, l’originalité des intervalles (asymétriques et/ou discontinus) et des densités de prévision (asymétriqueset/ou multimodales) offerts par cette nouvelle forme de modélisation suggère qu’une amélioration de la prévisionrelativement aux modèles linéaires est alors possible et qu’il faut disposer de tests d’évaluation assez puissants pourvérifier cette éventuelle amélioration. Ces tests reviennent généralement à vérifier des hypothèses distributionnellessur les processus des violations et des transformées probabilistes associés respectivement à chacune de ces formes deprévision. Dans cette thèse, nous avons adapté le cadre GMM fondé sur les polynômes orthonormaux conçu parBontemps et Meddahi (2005, 2012) pour tester l’adéquation à certaines lois de probabilité, une approche déjà initiéepar Candelon et al. (2011) dans le cadre de l’évaluation de la Value-at-Risk. Outre la simplicité et la robustesse de laméthode, les tests développés présentent de bonnes propriétés en termes de tailles et de puissances. L’utilisation denotre nouvelle approche dans la comparaison de modèles linéaires et de modèles non-linéaires lors d’une analyseempirique a confirmé l’idée selon laquelle les premiers sont préférés si l’objectif est le calcul de simples prévisionsponctuelles tandis que les derniers sont les plus appropriés pour rendre compte de l'incertitude autour de celles-ci. / The interest of non-linear models is, on the one hand, to better take into account non-linearities characterizing themacroeconomic and financial series and, on the other hand, to get richer information in forecast. At this level,originality intervals (asymmetric and / or discontinuous) and forecasts densities (asymmetric and / or multimodal)offered by this new modelling form suggests that improving forecasts according to linear models is possible and thatwe should have enough powerful tests of evaluation to check this possible improvement. Such tests usually meanchecking distributional assumptions on violations and probability integral transform processes respectively associatedto each of these forms of forecast. In this thesis, we have adapted the GMM framework based on orthonormalpolynomials designed by Bontemps and Meddahi (2005, 2012) to test for some probability distributions, an approachalready adopted by Candelon et al. (2011) in the context of backtesting Value-at-Risk. In addition to the simplicity androbustness of the method, the tests we have developed have good properties in terms of size and power. The use of ournew approach in comparison of linear and non-linear models in an empirical analysis confirmed the idea according towhich the former are preferred if the goal is the calculation of simple point forecasts while the latter are moreappropriated to report the uncertainty around them.

This thesis, which consists of four chapters, focuses on forecasting in a data-rich environment and related computational issues. Chapter 1, “An embarrassment of riches: Forecasting using large panels” explores the idea of combining forecasts from various indicator models by using Bayesian model averaging (BMA) and compares the predictive performance of BMA with predictive performance of factor models. The combination of these two methods is also implemented, together with a benchmark, a simple autoregressive model. The forecast comparison is conducted in a pseudo out-of-sample framework for three distinct datasets measured at different frequencies. These include monthly and quarterly US datasets consisting of more than 140 predictors, and a quarterly Swedish dataset with 77 possible predictors. The results show that none of the considered methods is uniformly superior and that no method consistently outperforms or underperforms a simple autoregressive process. Chapter 2. “Forecast combination using predictive measures” proposes using out-of-sample predictive likelihood as the basis for BMA and forecast combination. In addition to its intuitive appeal, the use of the predictive likelihood relaxes the need to specify proper priors for the parameters of each model. We show that the forecast weights based on the predictive likelihood have desirable asymptotic properties. And that these weights will have better small sample properties than the traditional in-sample marginal likelihood when uninformative priors are used. In order to calculate the weights for the combined forecast, a number of observations, a hold-out sample, is needed. There is a trade off involved in the size of the hold-out sample. The number of observations available for estimation is reduced, which might have a detrimental effect. On the other hand, as the hold-out sample size increases, the predictive measure becomes more stable and this should improve performance. When there is a true model in the model set, the predictive likelihood will select the true model asymptotically, but the convergence to the true model is slower than for the marginal likelihood. It is this slower convergence, coupled with protection against overfitting, which is the reason the predictive likelihood performs better when the true model is not in the model set. In Chapter 3. “Forecasting GDP with factor models and Bayesian forecast combination” the predictive likelihood approach developed in the previous chapter is applied to forecasting GDP growth. The analysis is performed on quarterly economic dataset from six countries: Canada, Germany, Great Britain, Italy, Japan and United States. The forecast combination technique based on both in-sample and out-of-sample weights is compared to forecasts based on factor models. The traditional point forecast analysis is extended by considering confidence intervals. The results indicate that forecast combinations based on the predictive likelihood weights have better forecasting performance compared with the factor models and forecast combinations based on the traditional in-sample weights. In contrast to common findings, the predictive likelihood does improve upon an autoregressive process for longer horizons. The largest improvement over the in-sample weights is for small values of hold-out sample sizes, which provides protection against structural breaks at the end of the sample period. The potential benefits of model averaging as a tool for extracting the relevant information from a large set of predictor variables come at the cost of considerable computational complexity. To avoid evaluating all the models, several approaches have been developed to simulate from the posterior distributions. Markov chain Monte Carlo methods can be used to directly draw from the model posterior distributions. It is desirable that the chain moves well through the model space and takes draws from regions with high probabilities. Several computationally efficient sampling schemes, either one at a time or in blocks, have been proposed for speeding up convergence. There is a trade-off between local moves, which make use of the current parameter values to propose plausible values for model parameters, and more global transitions, which potentially allow faster exploration of the distribution of interest, but may be much harder to implement efficiently. Local model moves enable use of fast updating schemes, where it is unnecessary to completely reestimate the new, slightly modified, model to obtain an updated solution. The last fourth chapter “Computational efficiency in Bayesian model and variable selection” investigates the possibility of increasing computational efficiency by using alternative algorithms to obtain estimates of model parameters as well as keeping track of their numerical accuracy. Also, various samplers that explore the model space are presented and compared based on the output of the Markov chain. / Diss. Stockholm : Handelshögskolan, 2006

Property market forecasts play a crucial role in modern real estate valuation methodologies and, consequently, flawed forecasts can have adverse impacts on the accuracy of valuations. This thesis identifies property industry inconsistencies in the formulation and application of office rent forecasts adopted in discounted cash flow (DCF) studies used to assess the value of commercial properties and the viability of proposed projects. Existing research on commercial property cycles and office property market modelling is examined in order to identify the dominant market drivers adopted by researchers. Forecasting techniques are also explored towards specifying space and rent models for the Brisbane CBD office market using the perceived dominant drivers as explanatory variables. Surveys of property valuers and developers are undertaken to underpin the selection of these variables. The implications of varying rent forecasts applied in DCF based valuation assessments are tested through the use of a case study involving four Brisbane office buildings. Innovative research is conducted through adopting geographic information system supported land use and historical valuation studies to delineate market precincts within the Brisbane CBD. The rent model is then re-estimated using precinct based office rent data to allow the generation of forecasts for the individual precincts. Out-of-sample accuracy test results for the precinct forecasts are compared with the results produced by the model specified using whole-of-city data. The literature reviews, surveys and model testing determine a relatively consistent range of dominant explanatory variables applicable to office markets. The case study, in a local context, confirms that varying forecasts do have a significant impact on property valuations. Tests of the forecast results generated by the Brisbane CBD model provide some evidence that more plausible office rent forecasts stem from the use of market models as compared with solely applying professional judgement based forecasts. Subject to data availability limitations, the precinct based rent model is found to produce rent forecasts superior to those generated by the whole-of-city model. Finally, the thesis makes a range of industry recommendations towards enhancing forecasts and recommendations are also made for potential future research projects.

In order to make informed decisions, we need to resort to various types of information and we need to know how uncertain this information is. A commonly used source for information and subsequent action is weather forecasts. The communication of uncertainty in weather forecasts has been widely studied for English speaking audiences, resulting in a number of guidelines that practitioners can follow. For forecasts aimed at Russian speaking audiences there are very few, if no, such studies. The aim of this study is to extend previous research on the communication of uncertainties in weather forecasts to the Russian-speaking domain. The underlying hypothesis for this study is that it should be possible to distinguish texts from different types of forecasts, with different inherent uncertainty, by analysing the linguistic uncertainty markers in the text-based section of these forecasts. If this is not the case, this could in a first step be solved by applying the recommendations in the available guidelines, in a second step the guidelines themselves might need to be extended to meet the needs of the practitioners. To test the hypothesis, I analyse the expressed linguistic uncertainty in two different sources of meteorological information: weather forecasts and seasonal outlooks. The analysis shows that the original hypothesis can be confirmed: the differences between these two sources of information can be detected by analysing linguistic uncertainty markers. Further, the recommendations from the guidelines were met to a large extent, but both type of forecasts, in particular the seasonal outlooks, would benefit from a more consolidated approach. The analysis also shows that these guidelines could be improved by placing an increased emphasis on text-based forecasts, highlighting which linguistic means should be used for what purpose. The guidelines could be extended with language-specific best-practise examples. This way the guidelines would cater for a much larger user-base than they do at present.

Dans cette thèse, nous nous intéressons à la représentation et à la prise en compte des incertitudes dans les systèmes de prévision hydrologique probabilistes à moyen-terme. Ces incertitudes proviennent principalement de deux sources : (1) de l’imperfection des prévisions météorologiques (utilisées en intrant de ces systèmes) et (2) de l’imperfection de la représentation du processus hydrologique par le simulateur pluie-débit (SPQ) (au coeur de ces systèmes).La performance d’un système de prévision probabiliste s’évalue par la précision de ses prévisions conditionnellement à sa fiabilité. L’approche statistique que nous suivons procure une garantie de fiabilité à condition que les hypothèses qu’elle implique soient réalistes. Nous cherchons de plus à gagner en précision en incorporant des informations auxiliaires.Nous proposons, pour chacune des sources d’incertitudes, une méthode permettant cette incorporation : (1) un post-traitement des prévisions météorologiques s’appuyant sur la propriété statistique d’échangeabilité et permettant la prise en compte de plusieurs sources de prévisions, ensemblistes ou déterministes ; (2) un post-traitement hydrologique utilisant les variables d’état des SPQ par le biais d’un modèle Probit arbitrant entre deux régimes hydrologiques interprétables et permettant ainsi de représenter une incertitude à variance hétérogène.Ces deux méthodes montrent de bonnes capacités d’adaptation aux cas d’application variés fournis par EDF et Hydro-Québec, partenaires et financeurs du projet. Elles présentent de plus un gain en simplicité et en formalisme par rapport aux méthodes opérationnelles tout en montrant des performances similaires. / In this thesis, we are interested in representing and taking into account uncertainties in medium term probabilistic hydrological prediction systems.These uncertainties mainly come from two sources: (1) from the imperfection of meteorological forecasts (used as inputs to these systems) and (2) from the imperfection of the representation of the hydrological process by the rainfall-runoff simulator (RRS) (at the heart of these systems).The performance of a probabilistic forecasting system is assessed by the sharpness of its predictions conditional on its reliability. The statistical approach we follow provides a guarantee of reliability if the assumptions it implies are complied with. We are also seeking to incorporate auxilary information to get sharper.We propose, for each source of uncertainty, a method enabling this incorporation: (1) a meteorological post-processor based on the statistical property of exchangeability and enabling to take into account several (ensemble or determistic) forecasts; (2) a hydrological post-processor using the RRS state variables through a Probit model arbitrating between two interpretable hydrological regimes and thus representing an uncertainty with heterogeneous variance.These two methods demonstrate adaptability on the various application cases provided by EDF and Hydro-Québec, which are partners and funders of the project. Those methods are moreover simpler and more formal than the operational methods while demonstrating similar performances.

Thesis is aimed on creation of prediction model for releasing medium-term water stream flow forecasts. Created model create forecasts based on principal of finding most similar historical case. Usefulness of forecasting model is demonstrated for operation of one isolated reservoir in gauge profile Oslavany on river Oslava.

No description available.

本研究探討分析師盈餘預測偏差程度是否受到景氣循環的影響。首先以美國股市大盤指數的漲跌趨勢判定景氣循環的高峰時點，並藉此區分景氣循環由上往下反轉與否之依據。其次，探討當景氣由上往下反轉時，分析師盈餘預測的偏差程度是否有明顯增加的現象。最後，探討預測該公司之分析師人數、公司盈餘變動程度、公司發生損失及分析師盈餘預測的分散程度與分析師盈餘預測偏差程度之相關性，於景氣由上往下反轉時期與景氣穩定成長時期是否會有顯著差異。 實證結果顯示：(1)分析師盈餘預測偏差程度的確會受到景氣循環的影響。當景氣由上往下反轉時，分析師未能掌握景氣循環的脈動，立即修正其盈餘預測，而是傾向發佈具樂觀性偏差的盈餘預測。(2)處於景氣由上往下反轉時期，預測該公司之分析師人數、公司發生損失及分析師預測盈餘分散程度對分析師盈餘預測的偏差程度之影響會產生強化效果。然而，本研究並無充足證據顯示，公司盈餘變動程度與分析師盈餘預測偏差程度之相關性會受到景氣由上往下反轉而有所不同。 / This study investigates whether business cycle affects bias in analysts’ earnings forecasts. Based on NASDAQ market index, an economic sudden slump is selected for examining whether the bias in analysts’ earnings forecasts is more obvious during the period of the economic slump. On top of this, the association between the bias in analysts’ earnings forecasts and some economic factors including number of analysts following, change in earnings, firm loss and forecast dispersion in the economic sudden slump is also explored. The empirical results show that business cycle in analysts’ earnings forecasts indeed influences bias. When the economic sudden slump happens, analysts are not aware of business cycle’s fluctuation in time to revise their earnings forecasts; instead they trend to issue optimistic bias in earnings forecasts. In the economic sudden slump, the number of analysts following, firm loss and forecast dispersion deeply affect bias in analysts’ earnings forecasts. However, this study does not find sufficient evidence that the association between change in earnings and bias in analysts’ earnings forecasts is more obvious during the period of economic sudden slump.

This two part analysis looks at forecasting models in the United States' 2016 presidential election and breaks down the elections fundamental and contingency factors. This paper argues that political science forecasting models could be improved through a more localized approach and by utilizing additional contingency factors. The psychology study of this analysis explores the already established relationship between political conservatism and favorability ratings, as well as the relationship between perceived similarity between voter personality and candidate personality, referred to as personality mirroring, and favorability ratings. The study uses past research to suggest that these relationships for the 2016 presidential candidates, Hillary Clinton and Donald Trump, can be explained through mediating variables: leader effectiveness and trust. The study used participants recruited through Amazon’s Mechanical Turk for data, all adults who voted in the 2016 US presidential election. The study found that there was a full mediation of leadership effectiveness for Donald Trump and significant partial mediation for the other three explored relationships.

Aujourd'hui, La Poste se trouve dans une situation particulièrement délicate au regard des mutations de son environnement économique. Pour répondre à ses nouveaux enjeux, elle doit développer sa planification stratégique, dans laquelle la prévision de son chiffre d'affaires joue un rôle particulièrement crucial. Or, à l'heure actuelle, les méthodes utilisées par la Direction Stratégique, notamment pour traiter la question de l'effet jours ouvrables, ne sont pas optimales et l'entreprise cherche à les améliorer. Notre thèse, réalisée en convention CIFRE avec la Direction Marketing Stratégique de La Poste, s'inscrit dans ce questionnement. Notre recherche vise plus spécifiquement à déterminer quels sont les meilleurs modèles économétriques pour la prévision du chiffre d'affaires du courrier. On se penche dans un premier temps sur la question de l'effet jours ouvrables que l'on traite à l'aide de méthodes de prévision, afin d'en obtenir une analyse approfondie. Puis on cherche à déterminer des modèles de prévisions adaptés à chaque type de clientèle et, enfin, au chiffre d'affaires totales. Pour l'entreprise, cette recherche vise à élaborer un outil fiable de prévision et d'aide à la décision. Au point de vue théorique, le principal apport de notre travail réside dans l'utilisation de modèles de prévision pour analyser l'effet jours ouvrables, à la place de l'utilisation d'outils de détection automatique. / Nowadays, La Poste is facing a particularly complex situation, related to the many changes of its economic environment. In order to respond to the new issues, it must develop strategic planning, in which income prediction plays a crucial part. Yet, to this day, the methods used by the Strategy Department are not optimal and the company is working at their improvement. Our research,conducted in the framework of a CIFRE partnership with the Strategic Marketing Department in La Poste, is anchored in this questioning. Our work is specifically aimed at determining the best econometric models to predict income of the Mail activity. We first focus on the issue of the "Trading days effect", that we examine using prediction methods, in order to get an in-depth view of it. Then we engage in determining prediction models adapted to each type of customers and, finally, a model for total income. For the company, this research is aimed at elaborating a reliable prediction and decision-making tool. From the theoretical point of view, the main contribution of our work lies in our using prediction models to analyze "Trading days effect", instead of automatic detection tools.