MERLOT Search - materialType=Presentation&category=2219&sort.property=overallRating
http://www.merlot.org:80/merlot/
A search of MERLOT materialsCopyright 1997-2015 MERLOT. All rights reserved.Tue, 31 Mar 2015 02:51:56 PDTTue, 31 Mar 2015 02:51:56 PDTMERLOT Search - materialType=Presentation&category=2219&sort.property=overallRatinghttp://www.merlot.org:80/merlot/images/merlot.gif
http://www.merlot.org:80/merlot/
4434Time Series Analysis and Forecasting Techniques
http://www.merlot.org/merlot/viewMaterial.htm?id=76226
This site is intended to help managers and administrators do a better job of anticipating and hence a better job of managing the uncertainty by using effective forecasting techniques.Toma de Decisiones con Periodos de Tiempo Crítico
http://www.merlot.org/merlot/viewMaterial.htm?id=81835
Este sitio tiene el objetivo de ayudar a los gerentes y administradores a hacer un mejor trabajo al momento de anticipar hechos, y por lo tanto, un mejor manejo de la incertidumbre mediante el uso de técnicas de predicción y pronóstico efectivas.Business Statistics
http://www.merlot.org/merlot/viewMaterial.htm?id=80550
This Web site is a course in statistics appreciation; i.e., acquiring a feeling for the statistical way of thinking.Graphical Causal Models for Time Series Econometrics: Some Recent Developments and Applications
http://www.merlot.org/merlot/viewMaterial.htm?id=975361
This video was recorded at 23rd Annual Conference on Neural Information Processing Systems (NIPS), Vancouver 2009. Structural vector-autoregressive models are potentially very useful tools for guiding economic policy. I present a recently developed method to estimate and identify the causal structure underlying the data generating process. The method, which is based on graphical models, exploits conditional independence tests among estimated VAR residuals to infer the causal relationships among contemporaneous variables. I first show how this method works in the Gaussian linear setting. Then I present some developments for both the linear non-Gaussian and nonlinear settings.Pointwise Exact Bootstrap Distributions of Cost Curves
http://www.merlot.org/merlot/viewMaterial.htm?id=945550
This video was recorded at 25th International Conference on Machine Learning (ICML), Helsinki 2008. Cost curves have recently been introduced as an alternative or complement to ROC curves in order to visualize binary classifiers performance. Of importance to both cost and ROC curves is the computation of confidence intervals along with the curves themselves so that the reliability of a classifier's performance can be assessed. Computing confidence intervals for the difference in performance between two classifiers allows to determine whether one classifier performs significantly better than another. A simple procedure to obtain confidence intervals for costs or the difference between two costs, under various operating conditions, is to perform bootstrap resampling of the testset. In this paper, we derive exact bootstrap distributions of these values and use these distributions to obtain confidence intervals, under various operating conditions. Performances of these confidence intervals are measured in terms of coverage accuracies. Simulations show excellent results.Razonamiento Estadístico para la Toma de Decisiones Gerenciales
http://www.merlot.org/merlot/viewMaterial.htm?id=80738
Este sitio Web es un curso de valoración estadística; es decir, para adquirir un sentido a la manera del razonamiento estadístico. Este es un curso introductorio de estadística que esta diseñado para proveer los conceptos básicos y métodos de análisis estadístico en la toma de decisión bajo incertidumbre.Sparse Canonical Correlation Analysis
http://www.merlot.org/merlot/viewMaterial.htm?id=979765
This video was recorded at Workshop on Sparsity and Inverse Problems in Statistical Theory and Econometrics, Berlin 2008. We present a novel method for solving Canonical Correlation Analy- sis (CCA) in a sparse convex framework using a least squares approach. The presented method focuses on the scenario when one is interested in (or limited to) a primal representation for the ﬁrst view while having a dual rep- resentation for the second view. Sparse CCA (SCCA) minimises the number of features used in both the primal and dual pro jections while maximising the correlation between the two views. The method is demonstrated on two paired corpuses of English-French and English-Spanish for mate-retrieval. We are able to observe, in the mate-retreival, that when the number of the original features is large SCCA outperforms Kernel CCA (KCCA), learning the common semantic space from a sparse set of features.Stability Selection for High-Dimensional Data
http://www.merlot.org/merlot/viewMaterial.htm?id=979761
This video was recorded at Workshop on Sparsity and Inverse Problems in Statistical Theory and Econometrics, Berlin 2008. Despite remarkable progress over the past 5 years, estimation of high- dimensional structure, such as in graphical modeling, cluster analysis or variable selection in (generalized) regression, remains diﬃcult. Among the main problems are: (i) the choice of an appropriate amount of regularization; (ii) a potential lack of stability of a solution and quantiﬁcation of evidence or signiﬁcance of a selected structure or of a set of selected variables. We introduce the new method of stability selection which addresses these two ma jor problems for high-dimensional structure estimation, both from a practical and theoretical point of view. Stability selection is based on sub- sampling in combination with (high-dimensional)selection algorithms. As such, the method is extremely general and has a very wide range of ap- plicability. Stability selection provides ﬁnite sample control for some error rates of false discoveries and hence a transparent principle to choose a proper amount of regularization for structure estimation or model selection. Maybe even more importantly, results are typically remarkably insensitive to the chosen amount of regularization. Another property of stability selection is the empirical and theoretical improvement over pre-speciﬁed selection meth- ods. We prove for randomized Lasso that stability selection will be model selection consistent even if the necessary conditions needed for consistency of the original Lasso method are violated. We demonstrate stability selection for variable selection, Gaussian graphical modeling and clustering, using real and simulated data. This is joint work with Nicolai Meinshausen.Video Lectures Regarding Chance Probability
http://www.merlot.org/merlot/viewMaterial.htm?id=90109
This is a series of video lectures featuring a diverse group of speakers with a range of topics. The videos require Real Player to run. Topics include Risk, Weather Forecasting, Stock Market Evaluation, Polls, etc. Don't miss the one on DNA Fingerprinting that discusses the statistics used in the O.J. Simpson case. At the end of the list are audio recordings from various NPR programs that discuss chance and include "Car Talk."