Spelling suggestions: "subject:"forecasting"" "subject:"forecasting's""
41 |
An experiment with turning point forecasts using Hong Kong time series dataLeung, Kwai-lin. January 1900 (has links)
Thesis (M.Soc.Sc.)--University of Hong Kong, 1989. / Also available in print.
|
42 |
Meteorological measurements with a MWR-05XP phased array radarSandifer, John B. 03 1900 (has links)
Scanning strategies for research and operational applications were developed for meteorological measurements with an experimental PAR, the MWR-05XP. A tornadic storm sampling strategy was developed with a 502.26 ms volumetric update and a resolution of 1.8 Az x 2 El x 150 m range. A sampling strategy for severe thunderstorm clusters was developed with a 10 second volumetric update and a resolution of 1.8 Az x 2 El x 300 m range. An operational weather scanning strategy was developed with an 81 second volumetric update and a resolution of 1.8 Az x 2 El x 150 m range. In general, for the acquisition of weather data, single frequency phased array radars offer only a slight sampling advantage over conventional scanning radars. This research verified that for meteorological sampling with the MWR-05XP, frequency diversity, coupled with electronic elevation scanning, offers a significant sampling advantage over conventional radars. The combination of electronic beam steering and frequency diversity produces a synergistic reduction in sampling time that increases the overall volumetric update rate. This research has also shown that, based on assumptions about the MWR-05XP operating parameters, it is possible to incorporate operational weather scanning into the radar's multifunction capability.
|
43 |
The Application of Statistical Classification to Business Failure PredictionHaensly, Paul J. 12 1900 (has links)
Bankruptcy is a costly event. Holders of publicly traded securities can rely on security prices to reflect their risk. Other stakeholders have no such mechanism. Hence, methods for accurately forecasting bankruptcy would be valuable to them. A large body of literature has arisen on bankruptcy forecasting with statistical classification since Beaver (1967) and Altman (1968). Reported total error rates typically are 10%-20%, suggesting that these models reveal information which otherwise is unavailable and has value after financial data is released. This conflicts with evidence on market efficiency which indicates that securities markets adjust rapidly and actually anticipate announcements of financial data. Efforts to resolve this conflict with event study methodology have run afoul of market model specification difficulties. A different approach is taken here. Most extant criticism of research design in this literature concerns inferential techniques but not sampling design. This paper attempts to resolve major sampling design issues. The most important conclusion concerns the usual choice of the individual firm as the sampling unit. While this choice is logically inconsistent with how a forecaster observes financial data over time, no evidence of bias could be found. In this paper, prediction performance is evaluated in terms of expected loss. Most authors calculate total error rates, which fail to reflect documented asymmetries in misclassification costs and prior probabilities. Expected loss overcomes this weakness and also offers a formal means to evaluate forecasts from the perspective of stakeholders other than investors. This study shows that cost of misclassifying bankruptcy must be at least an order of magnitude greater than cost of misclassifying nonbankruptcy before discriminant analysis methods have value. This conclusion follows from both sampling experiments on historical financial data and Monte Carlo experiments on simulated data. However, the Monte Carlo experiments reveal that as the cost ratio increases, robustness of linear discriminant rules improves; performance appears to depend more on the cost ratio than form of the distributions.
|
44 |
A simple forecasting scheme for predicting low rainfalls in Funafuti, TuvaluVavae, Hilia. January 2008 (has links)
Thesis (M.Sc. Earth Sciences)--University of Waikato, 2008. / Title from PDF cover (viewed February 23, 2009) Includes bibliographical references (p. 72-75)
|
45 |
Testing the predictability of stock returns /Fuksa, Michel, January 1900 (has links)
Thesis (Ph.D.) - Carleton University, 2002. / Includes bibliographical references (p. 253-260). Also available in electronic format on the Internet.
|
46 |
The current status of forecasting techniques in Hong KongLing, Roger., 林蔭. January 1982 (has links)
published_or_final_version / Business Administration / Master / Master of Business Administration
|
47 |
A monthly forecast strategy for Southern AfricaTennant, Warren James January 1998 (has links)
Dissertation submitted to the Faculty of Science,
University of the Witwatersrand, Johannesburg
for the Degree of Master of Science / Various techniques and procedures suited to monthly
forecasting are investigated and tested. These include using the
products generated by atmospheric general circulation models during
a 17-year hindcast experiment, and downscaling the forecast
circulation to regional rainfall in South Africa using circulation
indices and canonical correlation analysis. The downscaling methods
are evaluated using the cross-validation technique. Various model
forecast bias-correction methods and skill-enhancing ensemble
techniques are employed to improve the 30-day prognosis of the
model. Forecasts from the general circulation model and each
technique are evaluated. Those demonstrating reasonable skill over
the southern Africa region, and which are feasible when considering
available resources, are adopted into a strategy which can be used
operationally to produce monthly outlooks. Various practical issues
regarding the operational aspects of long-term forecasting are also
discussed. / Andrew Chakane 2019
|
48 |
The aliased and the de-aliased spectral models of the shallow water equationsUnknown Date (has links)
"The most widely used spectral models with the transform method are the de-aliased spectral model in which the de-aliased technique is used in the discrete Fourier transform according to the 3/2-rule. From the viewpoint of the Walsh-Hadamard transform, the multiplications of the values of the variables on the gridpoints do not yield the aliasing terms. In the shallow water equations, we compare the aliased spectral model with the de-aliased spectral model using the initial conditions of the Rossby-Haurwitz wave and the FGGE data. The aliased spectral models are more accurate and more efficient than the de-aliased spectral models. For the same wavenumber truncation, the computational amount of the aliased spectral model is only 60 percent of the de-aliased spectral model. We have not yet discovered the phenomenon of the nonlinear computational instability induced by the aliasing terms in the long time integration of the aliased spectral models. Thus, in the spectral models with the transform method the necessity of using the 3/2-rule in the discrete Fourier transform may be viewed with suspicion"--Abstract. / Typescript. / "Spring Semester, 1991." / "Submitted to the Department of Meteorology in partial fulfillment of the requirements for the degree of Master of Science." / Advisor: Richard L. Pfeffer, Professor Directing Thesis. / Includes bibliographical references (leaves 92-95).
|
49 |
Statistical surface wind forecasting at Goodnoe Hills, WashingtonCurtis, Joel C. 09 March 1983 (has links)
Multiple linear regression was used to develop equations for 12-,
24-, and 36-hour surface wind forecasts for the wind energy site at
Goodnoe Hills. Equations were derived separately for warm and cool
seasons. The potential predictors included LFM II model output, MOS
surface wind forecasts extrapolated from surrounding stations, pressure
observations corrected to mean sea level, and two types of climatological
variables.
Forecasts of wind speed and direction were formulated for an independent
sample of predictands and predictors. The forecasts
were evaluated using standard methods of forecast verification and the
results are summarized in terms of several verification scores. Comparisons
of scores were made by season, projection time, and cycle (or
preparation) time, and some patterns were evident in the scores with
respect to these stratifications. The minimum value of the mean absolute
error attained by the forecast system presented here was 5.64 mph
for a 12-hour, cool season forecast equation. The minimum value of the
root mean square error was 7.57 mph for a 12-hour, warm season forecast
equation. Comparison of these results with the results of other
statistical wind forecasting studies indicates that the forecast
equations for Goodnoe Hills are of comparable accuracy to the
equations developed for other wind energy sites. Suggestions for
future investigations of statistical wind forecasting are offered
as well as recommendations concerning ways of improving the
forecasting system described in this study. / Graduation date: 1983
|
50 |
Boundaries of research : civilian leadership, military funding, and the international network surrounding the development of numerical weather prediction in the United StatesHarper, Kristine C. 25 April 2003 (has links)
American meteorology was synonymous with subjective weather forecasting in the
early twentieth century. Controlled by the Weather Bureau and with no academic
programs of its own, the few hundred extant meteorologists had no standing in the
scientific community. Until the American Meteorological Society was founded in
1919, meteorologists had no professional society. The post-World War I rise of
aeronautics spurred demands for increased meteorological education and training.
The Navy arranged the first graduate program in meteorology in 1928 at MIT. It
was followed by four additional programs in the interwar years. When the U.S.
military found itself short of meteorological support for World War II, a massive
training program created thousands of new mathematics- and physics-savvy
meteorologists. Those remaining in the field after the war had three goals: to create
a mathematics-based theory for meteorology, to create a method for objectively
forecasting the weather, and to professionalize the field. Contemporaneously,
mathematician John von Neumann was preparing to create a new electronic digital
computer which could solve, via numerical analysis, the equations that defined the
atmosphere. Weather Bureau Chief Francis W. Reichelderfer encouraged von
Neumann, with Office of Naval Research funding, to attack the weather forecasting
problem. Assisting with the proposal was eminent Swedish-born meteorologist
Carl-Gustav Rossby. Although Rossby returned to Stockholm to establish his own
research school, he was the de facto head of the Meteorology Project providing
personnel, ideas, and a publication venue. On-site leader Jule Charney provided the
equations and theoretical underpinnings. Scandinavian meteorologists supplied by
Rossby provided atmospheric reality. Six years after the Project began,
meteorologists were ready to move their models from a research to an operational
venue. Attempts by Air Force meteorologist Philip D. Thompson to co-opt
numerical weather prediction (NWP) prompted the academics, Navy, and Weather
Bureau members involved to join forces and guarantee that operational NWP
would remain a joint activity not under the control of any weather service. This is
the story of the professionalization of a scientific community, of significant
differences in national styles in meteorology, and of the fascination (especially by
non-meteorologists) in exploiting NWP for the control of weather. / Graduation date: 2003
|
Page generated in 0.0568 seconds