Showing 1 - 10 of 45
Persistent link: https://www.econbiz.de/10000672971
Persistent link: https://www.econbiz.de/10000672974
This paper illustrates the Support Vector Method for the classification problem with two and more classes. In particular, the multi-class classification Support Vector Method of Weston and Watkins (1998) is correctly formulated as a quadratic optimization problem. Then, the method is applied to...
Persistent link: https://www.econbiz.de/10009783553
When comparing methods for classification, often the rating relies on their prediction accuracy alone. One reason for this is that this is the aspect that can be most easily measured. Yet, often one wants to learn more about the problem than only how to predict. The interpretation of the...
Persistent link: https://www.econbiz.de/10009783556
Error measures for the evaluation of forecasts are usually based on the size of the forecast errors. Common measures are e.g. the Mean Squared Error (MSE), the Mean Absolute Deviation (MAD) or the Mean Absolute Percentage Error (MAPE). Alternative measures for the comparison of forecasts are...
Persistent link: https://www.econbiz.de/10009783558
Econometric models are a widely used and powerful tool in macroeconomic analysis and forecasting. Admittedly, their acceptance by the scientific community has had some hard times during the seventies and eighties: a general decline in the reputation of macroeconomics, the Lucas critique, and...
Persistent link: https://www.econbiz.de/10009789911
In many fields of applied statistics samples from several locations in an investigation area are taken repeatedly over time. Especially in environmental monitoring the chemical and physical conditions in water, air and soil are measured using fixed and possibly mobile monitoring stations. The...
Persistent link: https://www.econbiz.de/10009793268
We build a discrete-time non-linear model for volatility forecasting purposes. This model belongs to the class of threshold-autoregressive models, where changes in regimes are governed by past returns. The ability to capture changes in volatility regimes and using more accurate volatility...
Persistent link: https://www.econbiz.de/10011545111
Persistent link: https://www.econbiz.de/10010467708
Noisy observations form the basis for almost every scientific research and especially in environmental monitoring. The Noise is often an effect of imprecise instruments which cause measurement errors. If the noise variance is known it is possible to filter out the contaminating noise from the...
Persistent link: https://www.econbiz.de/10010467710