Online Program

Conversely, if one applies sound principles of statistical engineering to the Big Data problem, several potential pitfalls become obvious. We consider the consequences of four major issues: 1) lack of a disciplined approach to modeling, 2) use of “one shot studies” versus sequential approaches, 3) assuming all data are high-quality data, and 4) ignoring subject matter knowledge.

Outline & Objectives

Outline
Introduction
Uniqueness of Big Data Projects
-Relative to traditional statistics projects
New Methods for Big Data
What Could Go Wrong?
-Big blunders with Big Data
-Sequential approaches versus one-shot studies
-Integration of analytics with sound subject matter theory
-Data quality
How Statistical Engineering Can Help
-Brief review of statistical engineering
-Theory and key principles
-Building blocks of statistical engineering (major phases)
Application of Statistical Engineering to Big Data
-Discussion
-Breakout exercises
Recap and Summary
-What have we learned?


Objectives:
• Develop a clear understanding of Big Data projects; what is new and unique versus what is not.
• Develop the skills and confidence needed to attack Big Data projects in a logical, sequential manner, applying the phases and principles of statistical engineering
• Clarify how easily significant blunders that can occur in Big Data projects if fundamentals are ignored.
• Develop a solid understanding of the theory and practice of statistical engineering.

About the Instructor

Ron Snee, Dick De Veaux, and Roger Hoerl each have significant track records within ASA, and the profession in general. De Veaux has given numerous presentations on data mining, and published in that area extensively. Snee and Hoerl are primarily responsible for the development of statistical engineering as a discipline, and again, have published extensively on that topic. By partnering on this workshop, they bring a unique set of skills and experiences to the issue of enhancing Big Data projects through application of statistical engineering principles. In an effort to keep the level of documentation reasonable, we have not included vitas; these can be forwarded if needed.

Relevance to Conference Goals

We feel that this workshop relates quite well to all three of the major conference themes. Obviously, it relates directly to Big Data analytics, in that participants will be learning tangible skills that they can apply to their current or future Big Data projects. In addition, application of statistical engineering principles – especially on large, complex, unstructured problems - enhances the leadership skills of statisticians, and thereby provides a vehicle for career advancement. These principles can also be applied to enhance more traditional modeling and analysis projects, which is the third major theme.

Participants will learn that GLMMs are an encompassing family and understand the differences and similarities in estimation and inference within the family. We discuss issues in working with correlated, non-normal data such as overdispersion, marginal and conditional models, and model diagnostics. We present GLMMs for common non-normal response variables—count, binomial and multinomial, time-to-event, continuous proportion—in conjunction with common designs—blocked, split-plots, repeated measures. Numerous examples will be presented.

The afternoon continues with GLMM applications and associated issues, including comparison of estimation methods, computation of power and sample size, model selection, and inferential tasks with and without adjustments.

Numerous examples will be used to illustrate all topics. Examples use tools in SAS/STAT and R, but the principles should be applicable to any GLMM-capable software.

Outline & Objectives

1. From Linear Model to GLMM
A. General Setting
B. Linear Models and Linear Mixed Model (LM, LMM)
C. Generalized Linear Model (GLM)
D. Generalized Linear Mixed Model (GLMM)
2. Marginal or Conditional Models
A. Defining a Model from Design Properties
B. Overdispersion and Other Design-Induced Issues
C. G- and R-side Random Effects
D. GEE versus GLMM
E. Distributional Implications
3. Estimation
A. (Restricted) Maximum Likelihood
B. Quasi-Likelihood/GEE
C. Pseudo-Likelihood
D. Laplace and Quadrature
E. Model-Based and Empirical (“Sandwich”) Estimators
4. Rates and Proportions
A. Distributions
B. Binomial Proportions
C. Binary Data
D. Multinomial
E. Beta – Continuous Proportions
5. Counts
A. Distributions
B. Poisson or Negative Binomial?
C. Modeling with Offsets
D. Zero-inflated Models
6. Within-Subject Correlation
A. Repeated Measures Background
B. Review of Methods for Normally-Distributed Data
C. Extension to Non-Normal Data – Similarities and Differences
D. Spatial Variation
7. Power, Precision and Sample Size
A. Background
B. Power & Sample Size for Continuous, Count, and Binomial Data
C. Comparing Competing Designs using GLMM tools
D. Longitudinal & Spatial Data

About the Instructor

Walt is Professor in the Department of Statistics at the University of Nebraska-Lincoln. He teaches statistical modeling and design of experiments. His research concerns mixed model applications collaborating with agricultural, natural resource, medical, pharmaceutical science, education, and the behavioral science. He participated in a multi-state mixed model project that motivated the development of SAS PROC MIXED. He co-authored textbooks on SAS for linear models, SAS for mixed models, and GLMMs for Plant and Natural Resource Sciences. He authored Generalized Linear Mixed Models: Modern Concepts, Methods and Applications (2013).

Elizabeth is a doctoral candidate completing her dissertation concerning bias correction for variance component estimation in GLMMs. With Walt, she has co-taught UNL’s graduate-level design of experiments course and assisted with the advanced modeling course. She has been primary instructor of introductory undergraduate statistics courses and has consulted with researchers from a variety of disciplines. She worked at JMP testing new applications. She presented preliminary results of her research at JSM 2013. Elizabeth’s expects to graduate May, 2014.

Relevance to Conference Goals

Modeling in the 21st century has grown beyond the basic ANOVA and linear model as most people learned them. This is especially true when the data cannot reasonably be assumed to be normally distributed. When data aren’t normal, why should your statistical analysis be? With the continued improvements in computing power and a wide variety of software options, the ability to model complex experiments and quasi-experiments with a variety of response variable distributions not limited to Gaussian is a required skill for data analysts. This course will introduce (or provide a refresher to) generalized linear mixed models as an overarching family that contains all of its predecessors to participants. The course will familiarize participants with the essential thought-processes required to use GLMMs effectively and with a wide variety of practical applications.

Outline & Objectives

The outline for this course is as follows:

1) Overview of R Studio (e.g., installation, menus, workflow);
2) Basics of ggplot2 (e.g., philosophy, capabilities, syntax);
3) Producing standard graphics with ggplot2 (e.g., histograms, boxplots, scatter plots, time series plots, bar charts);
4) Producing advanced graphics with ggplot2 (e.g., scatterplot matrices, conditional plots obtained through faceting);
5) Customizing graphics constructed with ggplot2 (e.g., labels, titles, symbols, colours, legends, scales, annotations, layers and themes);
6) Saving graphics constructed with ggplot2 in a variety of formats (e.g., pdf, jpeg, png);
7) Embedding ggplot2 graphics in automated reports and presentations.

The objective of this course is to teach participants how to produce, customize and export publication-quality graphics using R Studio and ggplot2. By exploiting ggplot2's power and versatility, participants will be able to create elegant, complex, multi-layered statistical graphics which will facilitate the communication of data-driven insights.

About the Instructor

Dr. Isabella R. Ghement is an independent statistical consultant and trainer based in Vancouver, Canada, British Columbia. She has extensive R training experience and presented the course "A Crash R Course on Statistical Graphics" at the ASA Conference on Applied Statistical Practice held in New Orleans in February 2013. Since 2007, Dr. Ghement has taught on a yearly basis an advanced regression course using R to graduate students in the Sauder School of Business at the University of British Columbia. Dr. Ghement’s statistical consulting clients include federal and provincial government agencies, contract research organizations and academic researchers. Her research expertise covers areas such as partially linear regression modeling, robust regression modeling and mixed treatment comparisons.

Relevance to Conference Goals

This course falls under the umbrella of the following conference theme: Theme 4 (Software and Graphics). As such, the course will help participants to master and employ modern data visualization methods using the R Studio software and the R graphical package ggplot2. The course will also encourage participants to adhere to good principles of reproducible research when producing automated reports and presentations which include graphical output.

Outline & Objectives

1. Identify your top interest and skill areas;
2. Determine the contributions those can make in your current organization - and areas within your organization that align with those skills and interests.
3. Learn to network effectively with people in those areas of your organization so that you can best position yourself to find new opportunities that support your organization's objectives.

About the Instructor

Bill Williams is an Organizational Learning Consultant and has been a part of the Conference of Statistical Practice since its inaugural year.

Relevance to Conference Goals

This session will both help participants learn how to better navigate their career and learn how to have a more positive impact on their organization.

This workshop explores this question and provides concrete, practical advice for applying modern regression to solving big data problems. The presenter is author of A Modern Approach to Regression with R.

Outline & Objectives

1. Challenges and Issues for Applying Regression Modeling to Big Data Problems.

2. Practical Approaches and Advice on Using Regression Modeling in Modern Applications.

3. Modeling average airline ticket price across more than 5000 routes in the USA.

4. Modeling interest in NFL games using social media and other data.

5. Modeling loan defaults.- a case study involving logistic regression.

About the Instructor

Professor Sheather brings a wide scope of experience in both management and the integration of analytics into organizations and businesses. He received his BSc (Hons) degree from Melbourne and a Ph.D. in Statistics from La Trobe. Currently Simon is Professor and Head of the Statistics Department at Texas A&M University. Previously he was a faculty member at the Australian Graduate School of Management at the University of New South Wales.

Simon has over 20 years of experience applying analytics and statistical methods in business. His clients included banks, biotechnology, hospitality service companies, fashion, transportation, real estate, consumer products and government. During this time he published over 75 papers and 2 books. He is listed on the ISIHighlyCited.com website among the top one-half of one percent of all mathematical scientists for citations of published work.

Relevance to Conference Goals

The conference attracts statisticians involved in the practice of statistics in companies and organizations internationally. This workshop discusses how the application of a well known tool in statistical practice can be used to address modeling issues involving big data. It also discusses modern regression modeling can be misused when applied to big data problems.

The first part of the course provides a gentle introduction to Bayesian inference and covers the fundamentals of prior distributions and concepts in estimation. The course also will cover MCMC methods and related simulation techniques, emphasizing the interpretation of convergence diagnostics in practice.

The second part of the course involves applications using Bayesian capabilities in SAS/STAT software in the GENMOD, LIFEREG, PHREG, and FMM procedures. Examples will include methods such as linear regression, generalized linear models, survival analysis, and finite mixture models.

The third part of the course takes a topic-driven approach to cover broad Bayesian topics such as random-effects models, sensitivity analysis, prediction, and model assessment.

Outline & Objectives

Part I - Introduction to Bayesian statistics (30 to 40 minutes)
A. Concepts in Bayesian Methods
a. Motivations and Difference between Classical and Bayesian
Inference
b. Estimation (point and interval)
c. Prior Distributions
B. Computational Methods
a. Markov Chain Monte Carlo
b. Metropolis and Gibbs Samplers
C. Convergence Diagnostics
a. Terminologies
b. Diagnostics Tests
c. Visualization
d. Assessing Simulation Variability

Part II - Bayesian Computation using SAS (1 hour)
A. Introduction
B. Procedures with Bayesian Capabilities
a. GENMOD
b. PHREG
c. LIFEREG
d. FMM
C. Statistical Models and Topics (not necessarily in these order)
a. Linear Regression
b. Generalized Linear Model
c. Cox Regression and Piecewise Exponential Model
d. Frailty Model
e. Finite Mixture Model

Part III - Additional Bayesian Topics
A. Primer on PROC MCMC
B. Statistical Topics (not necessarily in these order)
a. Inference on Functions of Paramete

About the Instructor

Fang Chen is a Senior Manager of Bayesian Statistical Modeling and a
member of Advanced Analytics Division at SAS Institute Inc. Among his
responsibilities are development of Bayesian analysis software and MCMC procedure. He has written about Bayesian modeling using the MCMC
procedure and taught continuing education course on practical Bayesian
computation at JSM. Prior to joining SAS Institute, he received his
degree in statistics from Carnegie Mellon University in 2004.

Relevance to Conference Goals

Attendees will understand basic concepts and computational methods of
Bayesian statistics, and how to deal with practical issues that arise
from Bayesian analysis. Attendees will also be able to program using
SAS/STAT procedures with Bayesian capabilities to implement various
Bayesian models.

Outline & Objectives

I. Introduction – An introduction to R: R syntax and data structures; working interactively and in batch; alternative IDEs and GUIs; adding functionality through packages; common programming mistakes; getting unstuck – were to find answers to your questions.
II. Data Management – Importing, cleaning, and reformatting data: transforming and recoding variables; subsetting, merging, and aggregating data; control structures; user-written functions.
III. Graphics – Taking advantage of R’s powerful graphics: creating basic and advanced graphs; customizing and combining graphs; innovative methods for visualizing complex data.
IV. Statistical Analysis and Data Mining – Using R for description, prediction, and classification: descriptive statistics and multi-way tables; ANOVA variants; regression (e.g., linear, logistic, Poisson), classification trees, cluster analysis, and other multivariate methods; dealing effectively with missing data; Going further.

About the Instructor

Dr. Robert Kabacoff has twenty five years of experience teaching and consulting in the areas of statistics and computing for academia, healthcare, business, and government. Currently he is Vice President of Research for Management Research Group, a global human resource development firm, where he has provided research and statistical consultations to organizations around the world for the past 15 years. Prior to joining MRG he was a Professor of Psychology in the Center for Psychological Studies at Nova Southeastern University, where he taught graduate courses in research methodology, statistical computing and statistics.

Dr. Kabacoff is author of the book R in Action: Statistics and graphics with R (www.manning.com/kabacoff) and maintains Quick-R (http://www.statmethods.net), a popular tutorial site on the R language. In the past two years he has taught workshops on R programming for such organizations as the Association of Computing Machinery, the Society of Industrial and Organizational Psychology, and the United States Department of Defense.

Relevance to Conference Goals

Using freely available open source software, participants will learn practical data analytic skills covering the full range of the research endevour, from data aquisition and data munging, to building and testing models, visualizing results, and communitating finding to their constituencies. Additionally, suggested paths for continued learning (including online resources and help resources) are provided.

Outline & Objectives

Outline of course topics:

(1)Identifying and fitting ARMA models,

(2)Diagnostics,

(3)Incorporating inputs: Regression with Time Series Errors,

(4)Intervention Analysis,

(5)Nonstationarity: Unit Roots and Stochastic Trends,

(Optional: Seasonal models time permitting)

Benefits of the course include an understanding of new issues encountered when data are taken over time and how to deal with these issues. Not only are new techniques of analysis necessary, which the student will learn, but additional terminology arises in these cases.
Examples and practical interpretation along with the strengths and weaknesses of competing forecasting methodologies will be emphasized.
I hope to give examples of interesting data analyses that can be used as templates for analyzing the participants' data when they return home.

About the Instructor

David A. Dickey received his PhD in statistics in 1976 from Iowa State University working with Dr. Wayne A. Fuller. Their “Dickey-Fuller” test is a part of most modern time series software packages. He is on the ISI’s list of highly cited researchers and is an ASA Fellow. Dickey is William Neal Reynolds Professor of Statistics at North Carolina State University where he does time series research, teaches graduate level methods courses, does consulting, and mentors graduate students. He is coauthor of several books on statistics, including “The SAS System for Forecasting Time Series,” a publication of SAS Institute. He has presented at many conferences including the 2013 ASA Conference on Statistical Practice and several JSM sessions. He has been a contact instructor for SAS Institute since 1981 teaching courses in statistical methodology, including time series, and has helped write some of their course notes. Recently Dickey has been teaching for NC State University's Institute for Advanced Analytics which offers an intensive applied Master’s degree in a 9 month cohort program. He has appointments in Economics and the NCSU Financial Math program.

Relevance to Conference Goals

The student will be better able to communicate intelligently with clients having data taken over time by learning the terms and the concepts behind them. The benefits of being able to better forecast what is going to happen next should be of obvious value to any company collecting data over time. The successful student should be able to carry out an analysis of time dependent data from model identification, through fitting and diagnostic checking, all the way to producing forecasts.

Computer scientists have developed sophisticated algorithms for extracting and compiling complex summaries of text data. Statisticians have adaptive statistical methods for text analytics designed to solve sophisticated business and government problems. This is rapidly evolving as the available data and applications change. In the beginning, text analytics involved the analysis of simple word counts. Now, with available software for natural language processing, text analytics is challenged with the analysis of contextual information.

This half-day workshop explores the terminology, common methodology, and software for analysis of large, complex text data.

Outline & Objectives

1. Text Analytics - History and Terminology
2. Concept and Content Extraction
3. Summarization and Categorization
4. Content Management & Sentiment Analysis
5. Useful Approaches to Applying Text Analytics

About the Instructor

Dr. Jones has a Ph.D. degree Statistics from Virginia Tech and a B.S. in Computer Science from Texas A&M University - Commerce. Currently he teaches data mining and analytics at Texas A&M University. He also mentors graduate students in data mining and analytics team competitions. He is also co-founder and Vice President of Texas A&M Statistical Services.

He has over 10 years in the development of statistical and data mining software for companies in Silicon Valley and Rogue Wave Software. He supervised the design, development and testing of the IMSL (International Mathematics and Statistics Library) data mining software.

Relevance to Conference Goals

The Conference on Statistical Practice attracts hundreds of statistical practitioners and researchers. With increasing applications involving text mining and text analytics, this workshop will provide the background applied statisticians can use to expand their field of practice to include problems involving text analytics and text mining.

Outline & Objectives

1. Introduction:

a. The basics of ODS Graphics

i. Enable ODS Graphics

ii. Procedures that support ODS Graphics

b. One step beyond the basics

i. Destinations

ii. Optional graphs

iii. Change graph style

iv. Editable graphs

v. Commonly used options

2. Graph and Style Template Languages

a. Templates and item stores

i. Template source

ii. SAS libraries

iii. ODS path

iv. Clean up

b. Graph template modification

i. Titles, ticks, axis labels, grids

ii. Adding date and project information

iii. Axis labels

iv. Graph data object

v. Dynamic variables

vi. Survival plot

c. Style template modification

3. The SG procedures and the GTL

a. Graph Template Language (GTL)

b. PROC SGPLOT - scatter plot, fit plot, histogram and density plots, bar chart, box plot, text insets, unicode, series plot and drop lines


c. PROC SGSCATTER - scatter plot matrix, panel of scatter plots

d. PROC SGPANEL - Data panel

e. Residual Panel (with GTL)

4. Conclusions

About the Instructor

Warren F. Kuhfeld is director of the SAS Advanced Regression Models R&D group. He received his Ph.D. in psychometrics from UNC Chapel Hill in 1985 and joined SAS in 1987. He has used SAS since 1979 and has developed SAS procedures since 1984. Warren wrote the SAS/STAT documentation chapters, “Using the Output Delivery System,” “Statistical Graphics Using ODS,” “ODS Graphics Template Modification,” and the SAS Press book Statistical Graphics in SAS: An Introduction to the Graph Template Language and the Statistical Graphics Procedures. Warren currently develops eleven SAS/STAT procedures and over twenty SAS macros for experimental design.

Relevance to Conference Goals

This tutorial addresses Theme 4: Software and Graphics.
Participants will learn how to create, manage, and customize a variety of graphs. Modern statistical graphics enable statisticians to better communicate statistical information. Knowledge of ODS Graphics is an indispensable skill for statisticians who use SAS to manage and analyze their data.

Outline & Objectives

Outline:
Introduction,
Traditional model selection methods,
Customizing the selection process,
Penalized regression methods,
Model averaging,
Selection for nonparametric models with spline effects

The objective of this course is to teach the goals of model selection and difficulties of implementing it for a real data. The participants will learn how to mitigate these difficulties using extensive capabilities of the GLMSELECT procedure of SAS/STAT software.

About the Instructor

I am a Research Statistician in the Statistical Applications Department at SAS. I completed my PhD in statistics from North Carolina State University with focus in model selection methods.

As a research statistician in statistical R&D at SAS, I often give expository talks and two-hour tutorials at JSM and ENAR on a variety of topics, including mixed models, model selection, and Bayesian statistics. These presentations emphasize basic concepts, and they introduce applied statisticians to new methodology with relevant examples.

Relevance to Conference Goals

I attended the first CSP in 2012 and was impressed by the goals of the conference. I especially enjoyed meeting statistical practitioners and learning how they use statistics in their work. Based on that experience, I think the CSP audience is a perfect fit for the content and level of the presentations that I give, and I would love to participate.

Outline & Objectives

Tutorial participants will have read about the POWER process before arriving at the conference and will work in groups at the beginning of the tutorial to apply their understanding of the readings to answer questions and solve problems in the context of statistical consultations and collaborations. Dr. Vance will briefly lecture on any concepts of the POWER process the participants had trouble understanding or applying. At the end of this section of the tutorial, participants will solidly understand the five steps in the POWER process that lead to effective statistical collaborations.

The second section of the tutorial will consist of role plays in which the participants practice the key concepts of the POWER process. Alternating between the roles of client, statistical collaborator, and observer—while giving feedback to their peers—the participants will practice the skills they will use to unlock their collaborative potential.

The last section will show participants how to video record themselves during meetings with clients and, more importantly, how to analyze that video to systematically improve their statistical collaboration skills upon their return to their organizations.

About the Instructor

Dr. Eric Vance is a statistician and data scientist in the Department of Statistics at Virginia Tech. He is the Director of LISA (Laboratory for Interdisciplinary Statistical Analysis). LISA’s mission is to train statisticians to become statistical collaborators and promote the value of statistical thinking in all phases of scientific research by helping researchers design experiments; collect, analyze, and plot data; run statistical software; interpret results; and communicate statistical concepts to non-statisticians. From 2008-2012, LISA has helped solve research problems on 1,629 collaborative projects in 76 departments at Virginia Tech, helped 1,262 visitors during Walk-in Consulting, and taught the application of statistics to 2,223 attendees at LISA Short Courses for a total of 5,114 LISA clients in its first five years in existence.

Relevance to Conference Goals

This tutorial will help the participants develop statistical collaboration skills that will improve their personal effectiveness as statisticians. Participants will learn best practices in statistical consulting and collaboration that will enhance their organizational impact and potentially lead to career development and advancement. Participants will return to their jobs with new ideas, techniques, and strategies to improve their ability to communicate and collaborate effectively, resulting in a greater impact on their organizations.

Refreshments will be served and ASA staff will be raffling great prizes. The closing session is also a great time to let the CSP Steering Committee know if you are interested in helping out with future conferences. Please plan to attend!