In this paper we present an application of statistics using real stock market data. Most, if not all, students have some familiarity with the stock market (or at least they have heard about it) and therefore can understand the problem easily. It is the real data analysis that students find interesting. Here we explore the building of efficient portfolios through optimization using examples of two and three stocks, and how covariance and correlation can help the investor to diversify his or her risk. We discuss why diversification works, but also the problems that arise in portfolio management. Stock market data can be incorporated at any level of statistics, from lower division, to upper division, to graduate courses of Mathematics and Statistics. From our experience, students find this topic very interesting and often they want to enroll in other courses related to this area.

In this paper our goal is to explain the distribution of the sample coefficient of determination in the simple regression case. We do this by using its rela- tionship to the noncentral F distribution. But first we introduce a new term, the true coefficient of determination. In a simulation study it is feasible to know the true coefficient of determination because the variance of the error term is known. The usefulness of the true coefficient of determination is in the built of relationships with predetermined strength. It answers the question: How much error should we add? The answer depends on how strong we want the association in the simple regression model to be. Once we determine this we can compute the noncentrality parameter and explain the distribution of the sample coefficient of determination. It is a simple way of explaining the distribution of the sample coefficient of determination and it is interesting at least from the educational point of view.

This paper considers spatial data z(s1), z(s2), ... , z(sn) collected at n locations, with the objective of predicting z(s0) at another location. The usual method of analysis for this problem is kriging, but here we introduce a new signal-plus-noise model whose essential feature is the identification of hot spots. The signal decays in relation to distance from hot spots. We show that hot spots can be located with high accuracy and that the decay parameter can be estimated accurately. This new model compares well to kriging in simulations.

The Statistics Online Computational Resource (www.SOCR.ucla.edu) provides one of the largest collections of free Internet-based resources for probability and statistics education. SOCR develops, validates and disseminates two core types of materials – instructional resources and computational libraries.

Portfolio performance evaluation is a tool used to judge how a portfolio performs during given period. The main evaluation methods include traditional (classical) portfolio performance evaluation and modern portfolio performance evaluation.

This thesis focuses on four typical measures of traditional (classical) portfolio performance evaluation, including Jensen’s alpha, Sharpe ratio, generalized Sharpe ratio and Treynor ratio. These four measures will be applied to three financial models: single index model, constant correlation model and multigroup model and be compared to test which measure evaluates more accurately in different situations.

We also apply two market timing ability models to different portfolios based on these three financial models to compare which measure predicts portfolio performance more accurately by collecting the measures from a given period and examining the market timing ability in the following test period.

This book contains instructional materials, pedagogical techniques and hands-on activities for technology-enhanced science education. These educational resources were presented at the 2009 SOCR Continuing Statistics Education Workshop entitled “It's Online, Therefore it Exists! 2009 SOCR Continuing Statistics Education Training & Development Workshop,” which took place at the University of California, Los Angeles, August 10-12, 2009. This book was written to provide modern pedagogical perspective into technology-enhanced blended learning and instruction. It reflects the direction of amalgamation of knowledge from multiple disciplines with recent open networking and technological advances. This trend is anticipated to accelerate in the next decade with seamless integration of open-access data, learning materials, computational resources and collaborative environments connected via language, platform and geo-politically agnostic interfaces. There are four novel features of this book – it is community-built, completely free-open-access (in terms of use and contributions), blends concepts with technology and it is electronically available online in multilingual format. This book covers the narrow scientific area of probability and statistics education; however, the principles we promote in the book can easily be extended to all other science and technology fields.

The 2010 SOCR Advanced Placement (AP) training, continuing education and development workshop will extend the efforts of the 2007 SOCR/CAUSEway workshop and the 2009 SOCR Continuing Education workshop. The aims of this workshop are to demonstrate the functionality, utilization and assessment of the current SOCR resources in the AP statistics curricula. The SOCR Motto It's Online, Therefore it Exists! clearly indicates that all of these tools, activities and materials are freely available over the Internet to the entire community. This workshop will be of most value to AP teachers and college instructors of probability and statistics classes who have interests in exploring novel technology-enhanced approaches for statistics education. The workshop will provide an interactive forum for exchange of ideas and recommendations for strategies to integrate computers, modern pedagogical techniques, the Internet and new student assessment techniques.

The 2007 joint SOCR/CAUSEway continuing education workshop demonstrates the functionality, utilization and assessment of the current SOCR (http://www.SOCR.ucla.edu) and CAUSEweb (www.CAUSEweb.org) resources. The workshop and this handbook are most value to advance placement (AP) teachers and college instructors of probability and statistics classes who have interests in exploring novel IT-based approaches for enhancing statistics education. This handbook provides the complete Workshop program (http://wiki.stat.ucla.edu/socr/index.php/SOCR_Events_Aug2007) and instructional materials presented by the Workshop instructors. New strategies for integration of computers, modern pedagogical approaches, the Internet and new student assessment techniques are presented on the handbook.

Earning statements are vital in understanding the financial condition of a company. These statements provide investors the ability to make informed decisions about their involvement with a company. Event Studies were created to measure the impact of an event on the price of a security. This thesis uses the event study methodology in conjunction with many machines learning methods to predict if there will be abnormal movement to a securities price in the stock market, following their yearly earnings announcement. Machine learning methods include logistic regression with regularization, support vector machines, random forests, and neural networks. Final analysis supports use of the Lasso logistic regression for feature selection to be converted into a random forest. The feature selection allowed the model to predict abnormal price movement with 84% accuracy.