Pumped hydro energy storages commonly plan their operations on short-term forecasts of the upcoming electricity prices, meaning that errors in these forecasts would entail suboptimal operations of the energy storage. Despite the high investment costs of pumped hydro energy storages, few studies take a holistic approach to the uncertainties involved in such investment decisions. The aim of this study is to investigate how forecast errors in electricity prices affect the chosen size configuration in investment decisions for pumped hydro energy storages. Moreover, sizing decisions are made in the long-term and involve long-term uncertainties in electricity prices. A robust decision-making framework including long-term electricity price scenarios is therefore used to evaluate the effects of including forecast errors in the sizing decision. By simulating the day-to-day operation of the energy storage with short-term forecasts, the effects of including the errors are compared to using perfect information. Using this approach, the most robust capacity is shown to increase by 25 MW, from 2 375 MW to 2 400 MW, when including forecast errors instead of assuming perfect information in the simulations. This indicates that the deviations in short-term forecasts require the pumped hydro energy storage operator to be more flexible in their operations, thus requiring a higher capacity. In addition, the profitability of the energy storage decreased significantly when including forecast errors in the simulations, showing the importance of taking the short-term forecast errors into account in sizing and investment decisions of pumped hydro energy storage. / Driften av pumpkraftverk optimeras med hjälp av kortsiktiga prognoser av elpriser, vilket innebär att fel i dessa prognoser leder till suboptimal drift. Trots att investeringar i pumpkraftverk är kostsamma, har få studier ett holistisk synsätt kring osäkerheter i investeringsbeslutet. Målet med denna studie är att undersöka hur kortsiktiga prognosfel i elpriser påverkar den optimala dimensionering av pumpkraftverk. Investeringsbeslut i pumpkraftverk är långsiktiga och kräver estimat av framtida elpriser, vars karakteristik är osäker. Ett ramverk som bygger på robust beslutstagande, med scenarier över framtida elpriser, används därför för att bedöma effekten av att inkludera kortsiktiga prognosfel i investeringsbeslutet. Genom att simulera den dagliga driften av energilager, undersöks effekten av att inkludera prognosfel jämfört med perfekt information. Med detta tillvägagångsätt ökade den mest robusta kapaciteten med 25 MW, från 2 375 MW till 2 400 MW, när prognosfel inkluderades. Detta visar på att fel i kortsiktiga prognoser kräver pumpkraftverket av vara mer flexibelt, vilket ges av höjdkapacitet. Lönsamheten minskade också signifikant när prognosfel inkluderades, vilket visar på vikten av att ta hänsyn till kortsiktiga prognosfel i beslut kring dimensionering och investering av pumpkraftverk.

Costs related to inventory are usually a significant amount of the company’s total assets. Despite this, companies in general don’t pay a lot of interest in it, even if the benefits from effective inventory are obvious when it comes to less tied up capital, increased customer satisfaction and better working environment. Permobil AB, Timrå is in an intense period when it comes to revenue and growth. The production unit is aiming for an increased output of 30 % in the next two years. To make this possible the company has to improve their way to distribute and handle material,The purpose of the study is to provide useful information and concrete proposals for action, so that the company can build a strategy for an effective and sustainable solution when it comes to inventory management. Alternative methods for making forecasts are suggested, in order to reach a more nuanced perception of different articles, and how they should be managed. Analytic Hierarchy Process (AHP) was used in order to give specially selected persons the chance to decide criteria for how the article should be valued. The criteria they agreed about were annual volume value, lead time, frequency rate and purchase price. The other method that was proposed was a two-dimensional model where annual volume value and frequency was the criteria that specified in which class an article should be placed. Both methods resulted in significant changes in comparison to the current solution. For the spare part inventory different forecast methods were tested and compared with the current solution. It turned out that the current forecast method performed worse than both moving average and exponential smoothing with trend. The small sample of ten random articles is not big enough to reject the current solution, but still the result is a reason enough, for the company to control the quality of the forecasts. / Kostnader kopplade till lagerverksamheten är ofta en betydande del av företagets totala omsättning. Trots detta är generella intresset för effektiv lagerstyrning lågt, trots dokumenterade fördelar som mindre bundet kapital, ökad kundservice och bättre arbetsmiljö. Permobil AB, Timrå är inne i en tillväxtfas och siktar på att öka sin produktion med mer än 30 % inom två år. För att möjliggöra detta behöver företaget förbättra sin lagerstyrning och utveckla sitt sätt att distribuera material, dels till eftermarknad och dels till sin egen montering. Syftet med studien är att bistå företaget i dess önskan att skapa en effektivare lagerstyrning med avseende på kvalitet och kostnad. Alternativa metoder att klassificera artiklar föreslogs, för att skapa en mer nyanserad bild av en artikels karaktär och hur den ska styras. Analytic Hierarchy Process (AHP) användes för att ge utvalda nyckelpersoner en chans att bestämma kriterier för hur en artikel ska bedömas. Dessa kriterier var årligt volymvärde, ledtid, uttagsfrekvens och inköpspris. Den andra metoden som föreslogs var en tvådimensionell klassificering där årligt volymvärde och uttagsfrekvens delar in befintliga artiklar i nio klasser med olika prioritering. Båda metoder gav upphov till betydande förändringar i jämförelse med den nuvarande metoden. För reservdelslagret testades alternativa prognosmetoder, för att jämföra med den nuvarande. Det visade sig att de båda metoderna glidande medelvärde och exponentiell utjämning med trend presterade bättre än den befintliga metoden. Stickprovet på 10 slumpmässigt utvalda artiklar är för litet för att förkasta nuvarande sätt att prognosticera, men det finns skäl att upprätta rutiner för kvalitetskontroll för att säkra en hög nivå på framtida prognoser.

This dissertation examines the general research issue of whether the components of earnings are informative and specifically 1) how analysts consider earnings components when predicting future earnings and 2) whether the information content in, and analysts’ use of, earnings components have changed through time. Although earnings components have predictive value for future earnings based on each component’s persistence, extant research provides only a limited understanding of whether and how analysts consider this when forecasting. Using an integrated income statement and balance sheet framework to estimate the persistence of earnings components, I first establish that disaggregation based on the earnings components framework in this study is helpful to predict future earnings and helps explains contemporaneous returns. I then find evidence suggesting that although analysts consider the persistence of various earnings components, they do not fully integrate this information into their forecasts. Interestingly, analysts appear to be selective in their incorporation of the information in earnings components, seeming to ignore information from components indicating lower persistence, which results in higher forecast errors. Conversely, when a firm’s income is concentrated in high persistence items, analysts appear to incorporate the information into their forecasts, reducing their forecast errors. I also report that the usefulness of components relative to aggregate earnings has dramatically and continuously increased over the past several decades, and contemporaneous returns appear to be much better explained by earnings components than aggregate earnings (than historically). Finally, the relation between analyst forecast errors and the differential persistence of earnings components has also declined over time, indicating that analysts appear to recognize the increasing importance of earnings components through time. / text

This study seeks to expand the range of climates and conditions in which free cooling from an economizer can replace air conditioning power consumption in residential applications. To explore this issue, we first discretize a simple building model in space and in time. We then solve the associated energy and mass balances for the estimated hourly heating and cooling loads and humidity conditions with respect to an annual climate profile. We propose a forecast-based algorithm to control the rate of outdoor airflow brought in by an economizer, in response to the upcoming cooling load to be experienced by the interior airspace. The algorithm takes advantage of a range of acceptable temperatures for thermal comfort by precooling the envelope overnight to delay the onset of cooling demand during the day. In order to consider the highest potential benefit from such an algorithm, we bypass the considerable problem of forecast accuracy by basing the inputs on the upcoming cooling load according to an initial simulation of the full year. On the whole, even with the forecast-based control, the results of the study have much in common with previous findings in the literature. Precooling works better to reduce cooling load in cases of higher thermal and moisture mass, but a humid climate severely restricts when free cooling is beneficial. For the example house considered here with the Austin climate and other assumptions, the effect of the proposed forecast-based economizer control was to greatly reduce the indoor air cooling load while greatly increasing the number of annual hours of unacceptably high indoor humidity. When we adjusted the forecast-based algorithm to avoid the excess humidity, the remaining reduction in cooling load was not significant. To investigate further how a forecast-based economizer could reduce cooling load in humid climates, the prinicipal task should be to extend the control algorithm to forecast and manage upcoming indoor humidity levels in the same fashion as was done in this study for indoor air temperature. / text

世界各國目前均積極努力於加速或維持其本國經濟成長率。“開發中國家”都竭盡所能，力求提高生活水準。已開發國家則極力避免經濟衰退，企求更大的財富與繁榮。欲提高生活水準，惟有在“經濟成長”高於“人口增加率”時始有可能。而欲使經濟成長達到預期目標，良好的經濟預測實為不可或缺的一環，近年來西歐（尤以荷蘭為首）及美日諸國對於經濟預測十分重視，計量經濟學的發展也正方興未艾。台灣地區之經濟屬於海島經濟類型，如何利用有限的經濟資源，從事經濟建設，加速邁向現代化，乃是全國上下一致努力的目標。對於未來經濟發展的動向之觀測，固未可忽視。台灣區之經濟預測，目前已有中央研究院、經合會、行政院國民總供需預測小組進行研究，建立計量模型。本文係參考中央研究院于宗先博士所作之“台灣經濟計量模型與經濟預測”，針對凱因斯所倡有效需求理論中之民間消費與民間投資兩部門，作更深入之分析。至於政府消費與公營事業及政府資本形成，其決定本諸政府政策，非依據市場行為，須單獨處理，故不包括在模型之內，亦即不由本文模型來決定。模型之各方程式均採線性式(Linear form)，分別用普通最小二乘法(Ordinary Least Squares; OLS)及兩段最小二乘法(Two Stage Least Squares, TSLS)求解，再自此二法所得之解選出較佳者建立“台灣區民間消費與投資計量模型”，總計20個方程式，計消費函數十一，投資函數九，並據之以預測未來三年（民國60-62年）有關之經濟變數之數值。所需資料大部份取自行政院主計處編印之中華民國國民所得黃皮書，而所有資料之計算則大部份應用本校電腦館之IBM1130型電子計算機進行處理。 本文的討論將分為以下六部份：(1)經濟模型與預測。(2)普通、一般化及兩段最小二乘法之理論。(3)台灣區民間消費與投資計量模型。(4)線性重合(Multi-colinearity)與序列自行相關(Serial autocorrelation)之處理方法。(5)模型之預測能力。(6)結論。

No description available.

<p>In this paper, the forecast performance of an unrestricted Vector Autoregressive (VAR) model was compared against the forecast accuracy of a Vector error correction (VECM) model when computing out-of-sample forecasts for Swedish exports. The co-integrating relation used to estimate the error correction specification was based upon an economic theory for international trade suggesting that a long run equilibrium relation among the variables included in an export demand equation should exist. The results obtained provide evidence of a long run equilibrium relationship between the Swedish export volume and its main determinants. The models were estimated for manufactured goods using quarterly data for the period 1975-1999 and once estimated, the models were used to compute out-of-sample forecasts up to four-, eight- and twelve-quarters ahead for the Swedish export volume using both multi-step and one-step ahead forecast techniques. The main results suggest that the differences in forecasting ability between the two models are small, however according to the relevant evaluation criteria the unrestricted VAR model in general yields somewhat better forecast than the VECM model when forecasting Swedish exports over the chosen forecast horizons.</p>

Paradoxically, pepole avoid being totally the same with others to keep their uniquness but follow the fads to avoid isolation. We construct a simple model under this concept to explain the empirical findings of forecasters’ behavior such as old forecasters are more radical and late forecasters tend to anti-herd. We show that forecasters' forecasts are not necessarilly unbiased when they consider the benefit of making correct forecasts and the cost of being wrong. Furthermore, we extended our model and show that when uninformed agent cannot differentiate which informed agents is better, she chooses mean of the two experts' opinions when the difference of the opinions is small but choose randomly from the two experts' opinions when the difference is big.

Denna studie kartlägger om det är möjligt att med hjälp av svenska insynspersoners värde-pappershandel prognostisera den svenska aktiemarknaden. Individuella insynspersoner har tidigare visats ha mer information kring enskilda företag än övriga aktörer på en aktiemarknad och har vistats skapa överavkastning gentemot marknaden. Aggregerad insynshandel har tidi-gare visat sig ha ett positivt samband med framtida avkastning på aktiemarknader. För att undersöka sambandet mellan svensk insynshandel och den svenska aktiemarknaden använder vi finansinspektionens insynslista som innefattar över 209 000 transaktioner av svensk insynshandel för perioden 1991-2013. Detta material undersöks tillsammans med hi-storiska indexvärden över tidsperioden och sambandet kartläggs med hjälp av OLS-regressioner. Vi undersöker även vad som driver sambandet mellan insynshandel och framtida avkastning, och vilket ekonomiskt värde det finns i insynshandel som prognosinstrument. Resultaten visar på att det finns ett statistiskt signifikant positivt samband mellan insynshan-del och framtida avkastning på den svenska aktiemarknaden. Detta samband blir starkare på lång sikt. Vi ser även att köptransaktioner är en starkare indikator för framtida marknadsrörel-ser än säljtransaktioner. Detta bekräftar tidigare studier där de menar att insynspersoner ofta säljer innehav på grund av andra anledningar än vinstsyfte. Vi finner även att sambandet drivs av ett informationsövertag men även av en Contrarian-strategi samt en genomlysningseffekt. Slutligen skapar vi prognosmodeller grundade i historisk insynshandel och genomför backtest på dessa under 22 år. Resultaten pekar på att insynshandel fungerar bra för att prognostisera framtida uppgångar på den svenska aktiemarknaden och är användbara för att skapa invester-ingsstrategier. / This study investigates if it possible to forecast the Swedish stock market using insider trading data. Individual insiders have been shown to have more information concerning a company than other investors. Additionally, insiders have been shown to be able to outperform the market in earnings from trading in company stock. Aggregate insider trading has, in previous studies, been shown to have a positive relationship with future returns on stock markets. To map the relationship between Swedish insider trading and the Swedish stock market we use the insider trading records from Finansinspektionen containing over 209 000 transactions over the course of 22 years. These records are examined together with a historic stock price index from the same time period. The relationship between the two is examined using OLS-regressions. We examine what factors drive the predictive power of insider trading and what economic value insider trading has as a forecasting instrument. Our results show that there is a statistically significant positive relationship between insider trading and future returns on the Swedish stock market, the significance increases with time. We also find indications that insider purchases have a stronger relationship with future index movements than insider sales have. This is consistent with earlier studies that find that insid-ers sell stock for many other reasons than profit. We conclude that the predictive power of insider trading derive from an information advantage, although our results indicates that some of the predictive power can be explained by a contrarian-strategy and a transparency effect. Finally we construct forecast-models based on historical insider trading and back-test these on the 22 year period. Results from these tests indicate that aggregate insider trading is effective in predicting future rises in the stock market and can function as a basis for successful invest-ment strategies.

This dissertation presents a new measure of U.S. inflation persistence from the point of view of a professional forecaster. In chapter 2 I explore two different measures that give insight into the views of professional forecasters and link their views with U.S. inflation data. One of these measures, given by the persistence implied by forecast revisions, appears to have similarities with actual inflation persistence over the 1981–2008 sample period. Chapter 3 explores forecast revisions in a more general setting allowing forecasters to have their own views on inflation persistence as well as a unique information set. This chapter builds a measure of perceived inflation persistence via the implied autocorrelation function that follows from the estimates obtained using a forecaster-specific state-space model. When compared to the autocorrelation function for actual inflation, forecasters tend to react less to shocks that hit inflation than the actual inflation data would suggest. This could be due to increased credibility of the Federal Reserve, but it could also be a result of a bias in the underlying inflation forecasts. Chapter 4 focuses on this issue and finds that the reluctance of forecasters to make revisions to their previously announced forecasts causes their estimates of perceived inflation persistence to be understated as their announced inflation forecasts differ from their true inflation expectations. This chapter also presents a method to undo this bias by retrieving their true inflation expectations series. / Thesis (Ph.D, Economics) -- Queen's University, 2012-12-21 15:39:23.616