Online Program

We begin with a graphical approach to bootstrapping and permutation testing, illuminating basic statistical concepts of standard errors, confidence intervals, p-values and significance tests.

We consider a variety of statistics (mean, trimmed mean, regression, etc.), and a number of sampling situations (one-sample, two-sample, stratified, finite-population), stressing the common techniques that apply in these situations. We'll look at applications from a variety of fields, including telecommunications, finance, and biopharm.

These methods let us do confidence intervals and hypothesis tests when formulas are not available. This lets us do better statistics, e.g. use robust methods (we can use a median or trimmed mean instead of a mean, for example). They can help clients understand statistical variability. And some of the methods are more accurate than standard methods.

Outline & Objectives

Introduction to Bootstrapping
General procedure
Why does bootstrapping work?
Sampling distribution and bootstrap distribution

Bootstrap Distributions and Standard Errors
Distribution of the sample mean
Bootstrap distributions of other statistics
Simple confidence intervals
Two-sample applications

How Accurate Is a Bootstrap Distribution?

Bootstrap Confidence Intervals
Bootstrap percentiles as a check for standard intervals
More accurate bootstrap confidence intervals

Significance Testing Using Permutation Tests
Two-sample applications
Other settings

Wider variety of statistics
Variety of applications
Examples where things go wrong, and what to look for

Wider variety of sampling methods
Stratified sampling, hierarchical sampling
Finite population
Regression
Time series

Participants will learn how to use resampling methods:
* to compute standard errors,
* to check the accuracy of the usual Gaussian-based methods,
* to compute both quick and more accurate confidence intervals,
* for a variety of statistics and
* for a variety of sampling methods, and
* to perform significance tests in some settings.

About the Instructor

Dr. Tim Hesterberg is a Senior Data Scientist at Google. He previously worked at Insightful (S-PLUS), Franklin & Marshall College, and Pacific Gas & Electric Co. He received his Ph.D. in Statistics from Stanford University, under Brad Efron.

Hesterberg is author of the "Resample" package for R and primary author of the "S+Resample" package for bootstrapping, permutation tests, jackknife, and other resampling procedures, is co-author of Chihara and Hesterberg "Mathematical Statistics with Resampling and R" (2011), and is lead author of "Bootstrap Methods and Permutation Tests" (2010), W. H. Freeman, ISBN 0-7167-5726-5, and technical articles on resampling. See http://www.timhesterberg.net/bootstrap.

Hesterberg is on the executive boards of the National Institute of Statistical Sciences and the Interface Foundation of North America (Interface between Computing Science and Statistics).

He teaches kids to make water bottle rockets, leads groups of high school students to set up computer labs abroad, and actively fights climate chaos.

Relevance to Conference Goals

Resampling methods are important in statistical practice, but are omitted or poorly covered in many old-style statistics courses. These methods are an important part of the toolbox of any practicing statistician.

It is important when using these methods to have some understanding of the ideas behind these methods, to understand when they should or should not be used.

They are not a panacea. People tend to think of bootstrapping in small samples, when they don't trust the central limit theorem. However, the common combinations of nonparametric bootstrap and percentile intervals is actually accurate than t procedures. We discuss why, remedies, and better procedures that are only slightly more complicated.

These tools also show how poor common rules of thumb are -- in particular, n >= 30 is woefully inadequate for judging whether t procedures should be OK.

Communicating Data Clearly describes how to draw clear, concise, accurate graphs that are easier to understand than many of the graphs one sees today. The course emphasizes how to avoid common mistakes that produce confusing or even misleading graphs. Graphs for one, two, three, and many variables are covered as well as general principles for creating effective graphs.

Outline & Objectives

This course begins by reviewing human perception and our ability to decode graphical information. It continues by:

• Ranking elementary graphical perception tasks to identify those that we do the best.

• Showing the limitations of many common graphical constructions.

• Demonstrating newer, more effective graphical forms developed on the basis of the ranking.

• Providing general principles for creating effective graphs.

• Commenting on software packages that produce graphs.

• Comparing the same data using different graph forms so the audience can see how understanding depends on the graphical construction used.

• Discussing Trellis Display (a framework for the visualization of multivariate data) and other innovative methods for presenting more than two variables.

• Presenting some graphical methods for categorical data.

Since scales (the rulers along which we graph the data) have a profound effect on our interpretation of graphs, the section on general principles contains a detailed discussion of scales.

The course concludes with before and after examples that reinforce the topics covered.

About the Instructor

Naomi B. Robbins is a consultant and seminar leader who specializes in the graphical display of data. She offers keynotes, short courses and workshops to train employees of corporations and organizations on the effective presentation of data. She also reviews documents and presentations for clients, suggesting improvements or alternative presentations as appropriate. She is the author of Creating More Effective Graphs, published by Chart House (2013). Dr. Robbins has been the keynote speaker at international conventions and has spoken on graphs to universities, professional societies, corporations, and non-profits. She received her Ph.D. in mathematical statistics from Columbia University, M.A. from Cornell University, and A.B. from Bryn Mawr College. She had a long career at Bell Laboratories before forming NBR, her consulting practice. Naomi was chair of the Statistical Graphics Section of the American Statistical Association and is the organizer of the Data Visualization New York Meetup.

Relevance to Conference Goals

Attendees will be exposed to graphical techniques, some of which may be new to them. Ideas covered are immediately applicable.

The entire emphasis of the course is to use best graphical practices to communicate quantitative information better.

Effective charts and graphs and understanding data better lead to better decisions which have a positive impact on the company. Communicating data better saves time at meetings.

Better communication of data enhances one’s career and avoids the loss of credibility that comes with using confusing, misleading or deceptive figures.

This half day workshop discusses growth models from the multilevel and structural equation modeling perspectives. Growth models have become a mainstay of longitudinal data analysis in the social and behavioral sciences to examine how individuals change over time and how individuals differ in their change process. The workshop covers several introductory topics that range from linear and nonlinear growth models to the inclusion of time-invariant and time-varying covariates. For analysis, we will discuss and use the structural equation modeling and multilevel modeling frameworks available through R and Mplus. The training is intended for faculty, postdocs and advanced graduate students who are familiar with structural equation modeling and multilevel modeling.

Outline & Objectives

The objectives of this full day workshop are to (1) understand the uniqueness of longitudinal data and the challenges of modeling individual change over time, (2) estimate linear and nonlinear growth models using R and Mplus, (3) interpret model parameters and their importance, and (4) estimate models with time-invariant and time-varying covariates while distinguishing between within- and between-person effects.

About the Instructor

Kevin J. Grimm, Ph.D., is a Professor in the Department of Psychology at Arizona State University, where he teaches classes on the analysis of variance, longitudinal growth modeling, machine learning, and structural equation modeling. He received his B.A. in Mathematics and Psychology with a concentration in Education from Gettysburg College in 2000, his M.A. and Ph.D. in Psychology from the University of Virginia (2001-2006). His research interests include longitudinal methodology, exploratory data analysis, and data integration, especially the integration of longitudinal studies. His recent research has focused on nonlinearity in growth models, growth mixture models, extensions of latent change score models, and approaches for analyzing change with limited dependent variables. Dr. Grimm directs the American Psychological Association’s Advanced Training Institutes on Structural Equation Modeling in Longitudinal Research and Big Data: Exploratory Data Mining.

Relevance to Conference Goals

This workshop is in line with the goals of the conference for Data Modeling and Analysis and well as Communication. This workshop will engage the audience to consider the various possibilities of modeling longitudinal data, and be able to communicate their findings to wider audiences.

Decisions on projects are often not made only from algorithms or based on the recommendation of statisticians. The importance of well-balanced technical and non-technical skills is essential for a statistician to be successful in collaborating and leading multi-disciplinary projects. With a well-balanced skill set, statisticians have the opportunity to use their analytical abilities to the fullest extent. However, to maximize the use of these skills, this requires statisticians to move outside of their comfort zone in order to excel in the leadership of cross-functional teams, to demonstrate strong communication and collaboration skills and to manage the conflicts that may occur when facing challenges outside of the realm of statistics.

Outline & Objectives

This short course will focus on providing statisticians with the guidance on the non-technical skills that they need to develop expertise to be successful in quantitative decision making when working with non-statisticians. The first half of the course will focus on providing guidance on the best practices for statisticians to be successful with their oral and written communication through case studies of real world scenarios from work as a statistician operating in cross-functional teams. The scope of these topics will include coverage of: active listening, asking the right questions, using the right vocal tones for the situation, networking, emotional intelligence, self-awareness of the surround environment, and receiving and providing further feedback. References to further reading and online material will be given. The second half of the short-course will focus on how statisticians can make best use of their analytical skills and become successful cross-functional leaders. Time will also be spent on understanding how to best handle conflicts and how to use analytical skills to win the right battles that statisticians face on a daily basis.

About the Instructor

The two speakers have more than 40 years of experience combined as statisticians in the pharmaceuticals industry. Dr. Mesenbrink has been an active spokesperson for the Leadership Initiative within the American Statistical Association while Dr. Guettner is leading an initiative within Novartis on leadership and soft skill development for statisticians. In addition to external publications and presentations on the subject matter, Dr. Mesenbrink is currently finishing the writing of the book: How to be a Successful Biostatistician in Industry for CRC Press which is projected to be published by the end of 2018.

Relevance to Conference Goals

As a meeting that is intended to help statisticians obtain practical needed for them to grow in their careers, this short course is aligned with the conference goals to provide statistician with practical knowledge needed to help them to continue grow and expand their potential career paths.