No description available.

No description available.

No description available.

Thesis (M.B.A.)--Boston University / PLEASE NOTE: Boston University Libraries did not receive an Authorization To Manage form for this thesis or dissertation. It is therefore not openly accessible, though it may be available by request. If you are the author or principal advisor of this work and would like to request open access for it, please contact us at open-help@bu.edu. Thank you. / 2031-01-01

I investigate the way in which Australian managers issue their earnings forecasts, and the impact this has on the reaction of equity investors and security analysts. Using a sample of 233 management earnings forecasts issued from 1994 to 2001, I find that managers are more likely to issue earnings forecasts when they have bad earnings news than good earnings news. I find that a vast majority of forecasts are ???framed??? by the use of an accompanying earnings benchmark. Forecasts are issued with varying degrees of specificity (or precision) and also with variation in additional accompanying disclosures. Forecasts issued with negative framing (forecast earnings less than benchmark earnings) are more likely to be accompanied by statements about factors external to the firm in explaining performance, while forecasts issued with positive framing (forecast earnings greater than benchmark earnings) are more likely to be accompanied by additional verifiable forecasts of components of earnings. I find the market reaction to earnings forecasts released with positive framing is higher than for forecasts released with negative framing, after controlling for forecast news and other forecast properties. I also examine security analysts??? forecasts around the release of management earnings forecasts and find that after the release of a management earnings forecast, analyst activity increases, but that analysts??? forecasts become less accurate and more biased. Neither the extent of analyst activity nor changes in analysts??? forecast accuracy or bias is related to forecast framing.

Stochastic weather generators create multiple series of synthetic daily weather (precipitation, maximum temperature, etc.), and ideally these series will have statistical properties similar to those of the input historical data. The synthetic output has many applications and for example, can be used in sectors such as agriculture and hydrology. This work used a ?hybrid? weather generator which consists of a parametric Markov chain for generating precipitation occurrence and a nonparametric k-nearest neighbor method for generating values of maximum temperature, minimum temperature, and precipitation. The hybrid weather generator was implemented and validated for use at 11 different locations in the Southeastern United States. A total of 36 graphic diagnostics were used to assess the model?s performance. These diagnostics revealed that the weather generator successfully created synthetic series with most statistical properties of the historical data including extreme wet and dry spell lengths and days of first and last freeze. Climate forecasts are typically provided for seasons or months. Alternatively, process models used for risk assessment often operate at daily time scales. If climate forecasts were incorporated into the daily weather input for process models, stakeholders could then use these models to assess possible impacts on their sector of interest due to anticipated changes in climate conditions. In this work, an ?ad hoc? resampling approach was developed to create sets of daily synthetic weather series consistent with seasonal climate forecasts in the Southeastern United States. In this approach, the output of the hybrid weather generator was resampled based on forecasts in two different formats: the commonly used tercile format and a probability distribution function. This resampling approach successfully created sets of synthetic series which reflected different forecast scenarios (i.e. wetter or drier conditions). Distributions of quarterly total precipitation from the resampled synthetic series were found to be shifted with respect to the corresponding historical distributions, and in some cases, the occurrence and intensity statistics of precipitation in the new weather series had changed with respect to the historical values.

In this dissertation, I examine investors' use of balance sheet information to infer earnings management constraint and the extent to which they utilize that information to assess the quality of subsequent earnings surprises. Ex-ante constrained firms may not have sufficient ability to manage earnings towards desired earnings thresholds and thus their reported earnings surprises are more likely to be the result of real performance. Ex-ante flexible firms, however, have more room to manage earnings and so it becomes less clear to investors whether the reported earnings surprises are the result of real performance or earnings management. My tests provide mixed support for the constraint theory. I find evidence that the market reacts more to small positive earnings surprises when they are reported by ex-ante constrained firms than when reported by ex-ante flexible firms. This suggests that the market interprets the earnings surprise reported by constrained firms to be of higher quality. However, I also find that earnings surprises reported by ex-ante constrained firms are no more persistent with regard to one-year-ahead earnings than those reported by ex-ante flexible firms, a result that is not consistent with the differential reaction to earnings surprises.

This thesis uses data-driven techniques to analyse and assess both point and probability forecasts within a prequential framework. Point forecasts are assessed using recursive residuals. Examination of the properties of the recursive residual found them to be unique to this residual. Recursive residuals for the hidden state of HMM are also defined by taking the difference between the one step ahead forecast and the forecast's filtered update. The quality of forecasts generated from different models can be assessed by comparing the information content in their corresponding residuals. When faced with model to correct this misspecification it is shown how this residual can be modelled to correct this misspecification, thereby improving forecasts. It is also shown how the residual content can be used to judge the predictive sufficiency of alternative forecasting methods. Using the theory of probability forecasting, the technique of forecasting assessment by calibration is extended to HMM's to assess how well the one step ahead forecast is explained by its filtered update. A test statistic to test the empirical calibration of the forecasts is also defined and applied to the real world problem of CpG island detection in Human DNA sequences. The distribution of the test statistic is investigated using a prequential frame of reference and is found to be N(0.1). Calibration of HMMs is also examined using smoothed predictions and cross- validation forecasts. A test statistic is defined for this scenario and the its distribution is examined using a cross- validation frame of reference. A prequential estimation algorithm for HMMs is also developed.

I investigate the way in which Australian managers issue their earnings forecasts, and the impact this has on the reaction of equity investors and security analysts. Using a sample of 233 management earnings forecasts issued from 1994 to 2001, I find that managers are more likely to issue earnings forecasts when they have bad earnings news than good earnings news. I find that a vast majority of forecasts are ???framed??? by the use of an accompanying earnings benchmark. Forecasts are issued with varying degrees of specificity (or precision) and also with variation in additional accompanying disclosures. Forecasts issued with negative framing (forecast earnings less than benchmark earnings) are more likely to be accompanied by statements about factors external to the firm in explaining performance, while forecasts issued with positive framing (forecast earnings greater than benchmark earnings) are more likely to be accompanied by additional verifiable forecasts of components of earnings. I find the market reaction to earnings forecasts released with positive framing is higher than for forecasts released with negative framing, after controlling for forecast news and other forecast properties. I also examine security analysts??? forecasts around the release of management earnings forecasts and find that after the release of a management earnings forecast, analyst activity increases, but that analysts??? forecasts become less accurate and more biased. Neither the extent of analyst activity nor changes in analysts??? forecast accuracy or bias is related to forecast framing.

Weather affects agriculture more than any other variable. For centuries, growers had to depend upon small bits and pieces of local climatological data collected and passed down in almanacs. Over the last 100 years, however, scientists have developed complex Numerical Weather Prediction (NWP) models that are able to forecast weather with increasing accuracy. The objective of this work was to use a probabilistic NWP model (the European Centre for Medium-Range Weather Forecasts (ECMWF) Ensemble Prediction System (EPS)) as a component to couple with agricultural decision-making tools and models. First, customized ECMWF EPS forecasts were used as an irrigation scheduling aid for a field trial. Next, the CROPGRO Cotton Model was used to simulate the field experiment as well as an additional irrigation scheduling strategy. Finally, a cotton canopy temperature model was developed and coupled with customized ECMWF EPS forecasts to generate hourly canopy temperature forecasts. These forecasts were used to create a heat stress warning system. Results from the field trial indicate that using precipitation forecasts to schedule irrigation could provide a convenient alternative relative to a standard method. Results from the simulated field trial suggest using precipitation forecasts issued on the day of irrigation could be more efficient than using forecasts issued one to two days prior. Last, results from the heat stress project indicate forecasts were skillful to 10 days, allowing enough time for growers to protect crops if needed. In light of the above, implications for the agricultural community could be significant. Coupled atmospheric-agricultural models have the ability to put weather forecasts in terms producers can understand and can quickly use to make strategic on-farm decisions, therefore, possessing the potential to make a large positive global impact.