JMP | Statistical Discovery. From SAS.

Discovery Summit

Exploring Data | Inspiring Innovation

SAS World Headquarters, Cary, NC | September 19-23, 2016

Abstracts

Triskaidekaphilia

John Sall, Co-Founder and Executive Vice President, SAS

Triskaidekaphilia. This word means “love of the number 13.” With the release of JMP® 13, we plan to make this word meaningful. This session is a tour of some feature highlights of the new release.

Leading With Analytics: Fostering a Supportive Analytics Culture

Tom Lange, Retired Director of R&D, Procter & Gamble

Computing has revolutionized our lives – and not just with smartphones. Computing, analytics and data literacy, as well as the ability to influence non-expert decision makers, have become the essential skills for our time. But even more elusive are the leadership qualities required for building an organization where analytics is the norm and not the anomaly.

First things first. Why must analytics be organizationally mastered? Surprisingly, there are some important lessons in our past to visit. Innovation in retail and manufacturing has often used a combination of communications and analytics. Rivers, rails, roads, wires and satellites combined with arithmetic, calculators, computers and software have all fostered economic revolutions in their respective days, disrupting the previous technologies.

Today, the data explosion and its resulting opportunities challenge the leader in all of us to navigate “these modern times.” We will explore leadership features like developing a vision, responding with courage, building mastery, and displaying your passion through the lens of leading analytics.

DOE: Is the Future Optimal?

Christopher Nachtsheim, Professor and Chair of Operations and Management Sciences at Carlson School of Management, University of Minnesota

In this presentation, I will chronicle the history of designed experiments, summarize the current state of the art, and make prognostications about the future of DOE. Along the way, I will identify the weaknesses inherent in observational studies and why cause and effect can only be rigorously identified through designed experiments. We’ll explore the negative implications of this for “big data” and predictive modeling, as well as the nature of web-based experiments in social media. I’ll illustrate state-of-the-art methods using a number of real-world applications and JMP.

Complicated Stuff in Simple Words

Randall Munroe, Creator, Webcomic xkcd

In a world filled with jargon, it’s refreshing to hear from a subject-matter expert who can communicate in a direct and uncomplicated fashion – so that even a layperson would understand.

You could say this is Randall Munroe’s mission. Munroe is masterful at using math, science and comics to make a point. His website, xkcd, showcases stick figure comics with themes in computer science, technology, mathematics, science, philosophy, language, pop culture and romance. And in his latest book, Thing Explainer, he uses the 1,000 (or, rather, ten hundred) most common words in the English language to explain concepts like how smartphones work, the periodic table and nuclear reactors. As the book’s subtitle suggests, complicated stuff in simple words.

Munroe is a former NASA roboticist who, on a typical day, puzzles over absurd hypothetical questions about science, many of which come in from fans of his blog What If?

How does he get to an answer?

Much like a statistician or data analyst, he uses what he knows to model for things that he doesn’t know. “I love calculating these kinds of things, and it's not that I love doing the math…” Munroe says in his TED talk. “What I love is that it lets you take some things that you know, and just by moving symbols around on a piece of paper, find out something that you didn't know that's very surprising.”

  • A Platform for Managing, Distributing and Tracking Add-Ins Globally        

    John Moore, Analyst, Elanco Animal Health

    • Topic: JSL Application Development
    • Level: 3

    Elanco Knowledge Solutions, part of Elanco Animal Health, helps our customers understand their data about their animals to make better decisions. Our technical consultants around the globe use JMP as their analytical tool. As our base of customers and their data increased, it became clear that we needed some automated tools to help our technical consultants with cleaning, shaping, analyzing and presenting their data. We chose JMP add-ins to make this possible. We have developed an infrastructure and set of scripts that allow us to:

    • Let technical consultants check to see if their version of the add-in is current and update it if it is not.
    • Send feedback from the technical consultants directly to the developers through email.
    • Show what’s new in the current version of the add-in.
    • Log the usage of individual scripts in the add-in.
    • Upload the activity logs to a central repository.

    We log the add-in name, user identification, script name, customer name and date/time the script was used. We have JMP tools that allow us to analyze this usage information. Our first add-in to use this platform is for our dairy technical consultants. We will be expanding it to other species.

  • Activity-Based Intelligence: Discovering the Unknown and Resolving Entities Through Behavior Analysis

    Patrick Biltgen, PhD, Technical Director for Analytics, Vencore

    • Topic: Data Exploration
    • Level: 3

    Activity-based intelligence (ABI) is a new methodology for intelligence analysis that uses spatially enabled “big data” to enhance national security. ABI methods – developed for counterterrorism – are being applied to a broad spectrum of intelligence issues. Increasingly, analysts are being challenged to think statistically and integrate multiple types of data to understand complex human behaviors over space and time. This presentation will demonstrate how JMP is used as a tool to visually explore data across space and time. We demonstrate how the linked data aspects of JMP allow an intelligence analyst to seamlessly move between spatial and statistical views, dynamically filtering data to understand patterns and trends. The intuitive graphical interface in JMP lets analysts ask questions to discover previously unknown entities (people, vehicles), correlate activities across data sets, and develop interactive “spatial stories” that describe complex activities in the human dimension. Although these methods are used by government intelligence analysts, the presenter will demonstrate public domain examples from commercial marketing and the Internet of Things to illustrate basic principles and stimulate discussion about how these methods can be cross-fertilized with techniques in other disciplines.

  • Adapting Dynamic Sensitivity Testing With the JMP® Nonlinear DOE Platform for Experiments Involving Generalized Linear Modeling  

    Douglas Ray, PhD, Lead Statistician, Statistics Group, US Army ARDEC Quality Engineering & System Assurance

    Christopher Drake, Statistician, Statistics Group, US Army ARDEC Quality Engineering & System Assurance

    • Topic: Design of Experiments
    • Level: 3

    The US Army frequently deals with testing and experimentation of systems, which involves binary responses (often referred to as “sensitivity testing”) where a stimulus (such as voltage or drop height) is applied as the primary input or factor. This case study is a grenade “starter slug” hotwire sensitivity test characterization that involved a number of real-world constraints such as test lab schedule and sample size. Design of experiments for generalized linear models involves certain challenges not encountered in experiments with continuous response data. For example, the data are not as information-rich as continuous measurements, the testing is often destructive, and the success of the experiment and usefulness of the response predictions are highly dependent on capturing the zone of mixed results. To deal with these difficulties, dynamic test approaches have been developed to adaptively generate data in just the right locations of the stimulus range to support effective modeling. This presentation will illustrate how ARDEC's statisticians recently adapted a binary search algorithm as the initial phase in a two-phase experiment, where the second phase used the Nonlinear Design platform in JMP to implement the Bayesian D-optimal design approach described by Gotwalt, Jones and Steinberg (Technometrics, February 2009).

  • All Wafer Maps Are Wrong: An Adventure in Semiconductor Data Visualization

    Michael Anderson, PhD, JMP Systems Engineer, SAS

    • Topic: Data Visualization
    • Level: 3

    Wafer maps – the colorful representations of the spatial distribution of a response over a substrate – are one of the most common and recognizable faces of the semiconductor industry. They are ubiquitous in most branches of both manufacturing and research. They are churned out by the thousands with just the click of a button to delight managers and strike fear in the hearts of competitors. The problem is, most of the time they are wrong, or at least misleading. This presentation will demonstrate how to generate a wafer map in JMP using a Gaussian process and neural network model. Along the way, we will discuss some of the pitfalls with using wafer maps and how features in JMP can facilitate a more nuanced interpretation of these figures.   

  • Application of Text Analysis to Quality Control of Human Resources Documents

    Thor Osborn, PhD, Principal Systems Research Analyst, Sandia National Laboratories

    • Topic: Quality and Reliability
    • Level: 2

    Management of the job description set is an important human resources job function. Job descriptions factor into the selection of new hires, compensation setting, career planning, and perceptions of internal, external, and peer equity among the workforce. Clear differentiability is one of the hallmarks of a good job description set. Yet recruiting is challenged by over-specification, and hiring managers demand flexibility and adaptability. These conflicting pressures and the sheer number of descriptions necessary to support the business needs of midsize or larger firms can lead to vagueness and substantial job duty overlaps, underscoring the necessity of job description set quality control. Text analysis procedures enable automated parsing of job descriptions and processing to represent the placement of jobs within the description set's job concept space. Bootstrapping on this concept space essentially produces randomly designed jobs within the space. The estimated job-to-job distance distribution may then be used to set a minimum acceptable distance criterion to flag real job pairs for closer examination and potential revision.

  • Binary Logistic Regression: What, When and How          

    Sue Walsh, Technical Support Statistician, SAS

    • Topic: Predictive Modeling
    • Level: 1

    Analysts in many application areas often have a response variable that has only two possible levels, with one of those being the desired outcome. Binary logistic regression will allow the analyst to predict the probability of the desired outcome, determine which input variables are most closely associated with those outcomes, and produce odds ratios that provide a measure of the effect on the outcome. This presentation will provide an introduction to the analysis of this type using binary logistic regression in the Fit Y by X and Fit Model platforms of JMP. It will discuss the interpretation of the results including p-values, odds ratios, graphical displays and goodness of fit statistics.

  • Compare Designs: A New DOE Capability in JMP® 13

    Bradley Jones, PhD, JMP Principal Research Fellow, SAS

    • Topic: Design of Experiments
    • Level: 3

    The Evaluate Design capability is a useful tool for DOE diagnostics. However, there are often cases where an investigator would like to compare the properties of two or three designed experiments before choosing one to actually run. There are two cases where this may prove useful. The first is comparing designs having the same number of runs but generated using different criteria. The second is comparing designs having different numbers of runs to evaluate whether the extra runs are worth the extra cost. This talk provides examples of both cases with advice about how to use this new feature to best advantage.    

  • Conducting Survey Data Analysis Using the JMP® Fit Model Platform’s Mixed Model Personality (Fit Mixed)

    Mary York, PhD, Senior Statistical Analyst, University of Texas MD Anderson Cancer Center

    • Topic: Predictive Modeling
    • Level: 3

    In order to improve employee satisfaction, we need to know which factors influence it. We examined the relationship between employee satisfaction and the following factors: relationship with managers, relationship with co-workers, organizational culture and job fit. This was accomplished using the JMP Fit Model platform’s Mixed Model (Fit Mixed) personality, which fits multilevel models. The Fit Mixed personality was added to JMP Pro 11 and is also available in JMP Pro 12. Multilevel models can be viewed having a regression model for each level to model nesting of data. Organizations are hierarchical, so organizational survey analysis should take into account this structure. Ignoring the nesting of data may result in an ill-fitting model which can lead to misinterpretation of the results. This presentation will show the equivalent SAS PROC MIXED code as it interactively walks through the analysis of an organizational survey using the JMP Pro Fit Mixed personality.

  • Control and Modeling Shock Sensitivity of a High Explosive

    Paul E. Anderson, PhD, Chemist, US Army ARDEC            

    Douglas Ray, PhD, Statistician, US Army ARDEC

    Erik Wrobel, Explosive Engineer, US Army ARDEC

    • Topic: Predictive Modeling
    • Level: 4

    Recent formulation efforts in the US Army have led to extremely insensitive high explosives. While these insensitive munitions (IM) provide an extra layer of safety for the warfighter, the physics of detonation initiation in them differ greatly from the more sensitive legacy explosives. In this study, glass microballoons were used to sensitize a particular IM explosive. Two sizes of microballoons were mixed into the test explosive at two different loadings (1 percent and 10 percent by volume) for a total of four formulations. The shock sensitivity, or "go/no-go" point was determined through expanded large scale gap tests (ELSGT) for each formulation. In this test, the shock pressure at which the explosive will carry the detonation is identified using a standard methodology. It was found that as little as 1 percent by volume addition of microballoons resulted in a statistically significant increase in shock sensitivity. Further modeling of the test series was done using a generalized linear model with penalized regression and nested factors. The resulting models were used to further explore 50 percent point as a function of the type of microballoon and volume loading of microballoon. The result, along with significant increases in sensitivity of the other three formulations, points to porosity distribution and not density as a main factor in promoting shock sensitivity.

  • Control Chart Builder Can Do That?

    Annie Dudley Zangi, Senior Research Statistician Developer, SAS

    • Topic: Quality and Reliability
    • Level: 2

    Control Chart Builder has been in JMP since 2012 with version 10, but many don’t know the wealth of tools that this easy-to-use platform offers. The Control Chart Builder is intuitive and efficient. It senses appropriate charts for your data, avoiding the time spent on and the aggravation of researching the correct syntax and creating the charts. This presentation will review the fundamentals and flow of Control Chart Builder and include a live demonstration of the power of little-known features, as well as new methods for using familiar features. Specific topics covered by this talk include the multi-purpose phase variable, tests (both customizing the tests and accessing specific test failures) and manipulating response levels for attribute control charts. Learn how to take better advantage of the quality monitoring tool that is already at your fingertips.

  • Creating Business Value With JMP® Profiler and Optimization

    Cy Wegman, President, SY64

    • Topic: Predictive Modeling
    • Level: 3

    JMP profilers are wonderful tools that help you solve problems and visualize discoveries. The profilers are filled with features that can help unlock secrets in your data. The JMP Profiler has good optimization capability that is many times underused in the discovery process. To leverage optimization, it is essential to properly set up the desirability targets and limits. This presentation will explain why desirability is important, how desirability works and how to leverage it. We will explore its use in optimization, robustness, importance and in creating an optimal Pareto frontier, as well as demonstrating alternate visualization techniques using other JMP graphic platforms. The goal of the presentation is to demonstrate how to make better decisions using these tools in JMP.

  • Creating Your Own Dynamic Workflow With JMP® Custom Starter Menus

    Brady Brady, JMP Senior Systems Engineer, Global Technical Enablement Team, SAS      

    Scott Wise, JMP Principal Systems Engineer, Global Technical Enablement Team, SAS

    • Topic: JSL Application Development
    • Level: 1

    Would you like to create your own dynamic menus that make it easy for you and your users to quickly access and use just the things that they need in JMP? A new scripted tool is now available to easily create your own JMP Custom Starter Menus without additional coding or large time commitments. In this session we will explain how the tool works and show examples of JMP Custom Starter Menus created to match popular workflows in industry (Six Sigma, Quality by Design, predictive modeling, etc.) and academia (intro to stats, etc.). We will also give a live demo to show how easy it is for you to create a prototype of your own workflow using the JMP Custom Starter Menu.

  • Discovering New Consumer Survey Insights Using Partition Analysis

    Diane Navin, Section Head Consumer Modeling Leader, Procter & Gamble

    Mike Creed, Consumer Modeling Expert, Procter & Gamble

    Amy Phillips, Principal Engineer, Procter & Gamble

    • Topic: Data Exploration
    • Level: 1

    Analyzing consumer survey data can take days of running breakout after breakout to understand why a consumer rated an experience the way they did or if there was a particular demographic that was more likely to rate an experience high or low. To be successful at discovering insights, you must first turn over the right rock. Partition analysis quickly identifies the rocks with the most potential, streamlining analysis plans and helping identify new insights.

  • DOE Choice Design Versus Forced Ranking: Preventing Judges From Whining While Wining

    Don Lifke, Research and Development Engineer, Sandia National Laboratories  

    Claire Syroid, Pharmacist Clinician, Walgreens Specialty Pharmacy

    • Topic: Data Exploration
    • Level: 2

    We compare the DOE Choice Design feature in JMP to a forced ranking methodology for determining preference of items that typically only have nominal characteristics, such as taste. Rather than using data from weapons projects that can be sensitive and overly technical in nature, we instead utilized readily attainable data from a subject that can be understood by most – wine. The intent of the study was to compare the two judging methodologies, not to determine the best tasting wine. Nonetheless, the outcome provided a nice tip sheet for future wine purchases. The topic was inspired by a question about forced ranking from Doug Montgomery (author of Design and Analysis of Experiments) at last year’s Discovery Summit. Ranking (sorting in order of preference) a large set of items can be difficult. On the other hand, it is fairly simple to perform pairwise comparisons, repeatedly deciding which of two items is better. A panel of 18 seasoned wine enthusiasts was instructed to force rank 12 wines (ranking them from 1 to 12). They were also presented with a Choice Design, which asked them to compare wines in pairs; each judge had to only decide which of two wines tasted better in each of eight pairs presented to them. This particular experiment used Oregon Pinot Noir wines, which of course included Chehalem, the winery featured on the cover of Montgomery’s book. The results show surprisingly different outcomes when using DOE Choice Design versus forced ranking. It was also observed that judges clearly preferred completing the DOE Choice Design over the forced ranking. (There was significant whining while trying to complete the forced ranking.) If time permits, we will also explore data from a previous study using a basic 1-10 rating scale.

  • Driving Big Data Business Decisions Through Modeling and Scripting in JMP®

    Veeraporn Kullatham, Life Cycle and Reliability Engineer, GE Power Services      

    Brad Foulkes, Principal Engineer for Lifing Analytics, GE Power Services

    • Topic: Predictive Modeling
    • Level: 2

    To use data to drive business decisions, it often needs to be manipulated and analyzed, then put into a simple format that is easily digestible for the user. This presentation will be a case study of using JMP to translate a very messy data set into a format that my business is able to use to help customers make decisions about operations. The analysis combines physics of failure and empirical data to better understand what is driving the events and what is not, and then help predict future events and remaining time until the event. Several aspects of JMP were used along the way, including table summary and row functions, survival modeling, scripting with database connections, regression modeling and graphical features for communication of results. JMP was also used for data manipulation and aggregation, as it allowed for superior performance over other database and desktop solutions. The result is a model that was useful to the end user and a script that can be run to easily perform the analysis in the future.  

  • Effective Presentation Methods for 3-D Data Using JMP®

    Michael Thompson, Group Leader, Advanced Gauging Systems, The Timken Company

    • Topic: Data Visualization
    • Level: 2

    Presenting three-dimensional data in useful and effective ways offers challenges regardless of the visualization platform. This talk will highlight three methods that can be used within JMP to effectively present three-dimensional data sets. First, the use of a color scale as the third dimension. In one example, wear scar development on a calibrated gauge block is presented with position as one dimension, time (history) as the second dimension, and wear scar depth as the third (color) dimension. Second, using transparency to produce density as the third dimension. Here, multiple scan data sets are overlaid to show repeatability of a tactile profilometry measurement. When the data sets overlay closely, markers hide other markers and a sense of data density, and scan agreement is lost. In this case, use of transparency can help to highlight the agreement and de-emphasize outlier readings. The plot produced is effectively a density plot where marker transparency is used as a mechanism to generate a density dimension. Third, the use of time (animation) to represent a third dimension. In this case, wear scar development is presented by displaying data sets captured over some time history. The data sets are two-dimensional and concatenated into one large JMP table where a third column indicates the point in time. The data are then presented using the Local Data Filter to show data for a particular period of time. The Local Data Filter can be cycled through all times producing an animated presentation of the data. All of these methods are easy to perform within the JMP Graph Builder. They can also be combined for even greater visual effect.           

  • Estimating Gaussian Process Models for Large Data Sets in JMP® Pro 13

    Ryan Parker, PhD, JMP Research Statistician Developer, SAS

    Don McCormack, JMP Technical EnablementEngineer, SAS

    • Topic: Predictive Modeling
    • Level: 4

    Gaussian process models are a popular way to emulate the output from deterministic computer models that, given inputs to some scientific process, construct the output associated with these inputs. Computer experiments are designed to collect samples from these models over the range of the inputs. We demonstrate how to build a Gaussian process emulator for large data sets collected from these computer experiments, such as those with more than 2,500 observations, by using an approximate likelihood technique to block the observations that is available in the Gaussian Process platform in JMP Pro 13. This technique allows for the use of parallel processing to dramatically reduce the computing time needed to estimate these models. Also, we demonstrate another new feature of the Gaussian process platform: the ability to estimate models with categorical inputs.

  • Is My Model Valid? Using Simulation to Understand Your Model and If It Can Accurately Predict Events

    Brad Foulkes, Principal Engineer for Lifing Analytics, GE Power Services

    • Topic: Predictive Modeling
    • Level: 4

    Models that predict the likelihood of an event can be difficult to interpret. If the model missed an event, does that mean it was a bad model? Or were the results simply within the confidence bounds of the model? Using just one value can lead to erroneous conclusions. To try to give a better result, we developed a process to simulate the likelihood of an event occurring at a particular time and use those results to understand how we judge the model. This process is built to run using JMP and JSL to develop a user interface for inputting data and a model, run the simulation and visually provide the results to give a quick check of the validity of the model. For large data sets, this can be a particularly tedious and computationally onerous task. JMP provides the capability to store a matrix of data into a cell, and this feature is used to improve the running speed of the simulation. This presentation will walk through the overall process of validating the model, along with the JSL scripting of building the tool and interpreting the output.

  • JMP® 13 – Association Rules and Visual Exploration 

    Matt Flynn, PhD, Senior Director, AIG Science   

    Mary Loveless, JMP Systems Engineer, SAS

    • Topic: Data Exploration
    • Level: 3

    Association rules are becoming a popular data mining technique for exploring relationships from large databases aiming to extract interesting correlation and relation among huge amounts of data. In the past, we examined association rules at JMP Discovery Summit via the great capabilities in JMP for connecting to external tools such as SAS and R. But JMP 13 now includes the capability to run association rules methods internally! We will demo this new functionality. Mining association rules often results in a very large number of found rules, leaving the analyst with the task to go through all the rules and discover interesting ones. We will use the interactive visualization and reports in JMP to sort through, select and communicate interesting rules.

  • Lessons From Definitive Screening Designs

    Stu Janis, Lean Six Sigma Coach, 3M Company

    • Topic: Design of Experiments
    • Level: 4

    Definitive screening designs (DSDs) represent an exciting new approach for screening many factors with considerably fewer runs and better resolution than classic fractional factorial designs. This talk will cover lessons learned during the design and analysis of several DSDs at 3M. Lessons range from theoretical (fake factors to generate extra runs for additional power and lower correlations among two-factor interactions, differences between JMP 12 and JMP 13 approaches to DSD analysis) to practical (pay attention to how the experimenters collect and report their data).

  • Letting Go of Excel: Hello Formula Editor

    Mark Chahl, Senior Staff Engineer, ExxonMobil Chemical       

    Jerry Cooper, JMP Systems Engineer, SAS

    • Topic: Data Exploration
    • Level: 1

    JMP has a very powerful, easy-to-use Formula Editor, but can be a daunting transition from the world of Excel formulae. So daunting that I used JMP for 16 years before really learning how to use the Formula Editor to do complex calculations six years ago. This beginner-level demo workshop will showcase creating formulas without Formula Editor; Formula Editor basics; use of local variables and parameters; statistical functions; row functions; efficient conditional formula writing and testing; using column properties in formulas; and test functions.

  • Longitudinal Analysis Through Multiple Process Steps, Mean and Variability

    Tony Cooper, PhD, Analytical Consultant, SAS

    • Topic: Design of Experiments
    • Level: 4

    “Raw” parts might be randomly fed into an experimental subsequent process stage. How do you control for the initial value? How do you determine whether the experimental process stage seems better than the original version? What if there are many subsequent stages? What if the stages affect the variability, as well as the mean? Is a split-plot analysis the best option? What if the parts cannot be randomized, but must be fed into the next stage immediately? Industrial practitioners are familiar with the special cause/common cause model of causal instruction introduced by Shewhart and popularized by Deming. They may not be aware of the longitudinal repeated measures designs class of process studies. This presentation discusses the application of the special cause/common cause to longitudinal repeated measures designs. An immensely graphical tool is introduced that adheres to the Shewhart principles and, as a bonus, evaluates compound symmetry. An example of data collected on parts after each stage of the process will be used to demonstrate the synergistic use of control charts, ANOMV and mixed modeling.

  • Managing Complexity and Enhancing Knowledge Retention as Process Understanding Evolves     

    Martin Owen, Director, Insight by Design

    • Topic: Data Access and Manipulation
    • Level: 1

    As we develop and transfer processes into manufacturing, scientists and engineers perform studies iteratively and develop process and product understanding. To help teams or organizations with high staff turnover retain insights, we need to address several challenges. How can we:

    • Help teams compare and contrast the efficiency and effectiveness of historical experimentation?
    • Show what assumptions were made and identify knowledge gaps?
    • Help teams gain additional insight from disconnected tabulated data sets and free text?
    • Discover what we need to know when it’s not always clear?

    I have challenged participants in both industry and academia to study the same process in a series of workshops. Teams select different factors and ranges and perform different classical, custom and definitive designs. I then help participants compare their own output with studies carried out in previous workshops by different teams. We use the holistic learnings to generate new ideas and actionable decisions. The JMP 13 Early Adopter program has given additional insight as to how we can enhance our use of prior information. This presentation will illustrate how new functionality in JMP 13 (e.g., Query Builder and Text Explorer) can help us build a more accessible and structured “organizational memory” of both observational and experimentally derived data.

  • Mind the Gap: JMP® on the Text Explorer Express

    Heath Rushing, Principal Consultant and Co-Founder, Adsurgo

    James Wisnowski, PhD, Principal Consultant and Co-Founder, Adsurgo

    • Topic: Data Exploration
    • Level: 2

    There is an enormous gap between the massive resources that companies devote to collecting, storing and organizing unstructured data and their ability to actually discover meaningful information that affects business decisions. Text Explorer in JMP 13 will fundamentally change how users view the power of analytics. This new platform uses familiar multivariate methods to close the gap in unstructured data exploration and discovery. This session will use multiple case studies to demonstrate not only the remarkable capabilities of Text Explorer, but also its extraordinary ease of use. First, presenters will show the simplicity of string processing in Text Explorer, specifically focusing on common obstacles: stopwords, synonyms and parsing terms, along with multi-word phrases. Next, the presenters will illustrate the analytical and graphical capabilities of Text Explorer to quickly uncover previously unknown information in unstructured data: term frequencies, word clouds and topic extraction. Lastly, they will show how Text Explorer can capitalize on the powerful predictive analytics capabilities already in JMP to explore relationships and build better models by using both your unstructured and structured data.

  • Multivariate Analysis Overcomes Complexities in Injection Molding

    David Calder, Six Sigma Black Belt, Magna International

    Wayne Levin, President, Predictum

    • Topic: Quality and Reliability
    • Level: 2

    Over the years, automotive exterior parts have become more complex and substantially larger, yet are molded at faster cycle times. The transformation in design and challenging manufacturing demands have driven changes in tool design, hot runner design, material formulation and molding machine functionality. With these increasing challenges, we have to ask ourselves if conventional methods of quality control, which are typically univariate, are still effective. The short answer is no. This presentation demonstrates how multivariate analysis extracts pertinent information from large amounts of complex data. It is then able to identify the correlation structure and relationships that exist between multiple process variables and present it visually. We’ll present a project comparing univariate and multivariate approaches. These methods hold the promise to both reduce the dependency on subjective, visual inspection and make lights-out manufacturing more viable.

  • New Features in Choice Modeling for JMP® 13 and JMP® Pro 13

    Melinda Thielbar, PhD, JMP Senior Research Statistician Developer, SAS

    • Topic: Data Exploration
    • Level: 2

    JMP 13 brings a host of new features for Choice modeling, including Maximum Difference analysis, options for modeling no-choice responses, a MaxDiff Designer, and improved features for market segmentation. This demonstration will cover how to use the new features, as well as the research behind the computations. We’ll use a case study approach, demonstrating features by analyzing real-world data sets collected through choice experiments conducted by JMP developers. Session attendees new to Choice modeling will leave with an appreciation for the method’s versatility and value. Attendees familiar with Choice analysis will have a more in-depth understanding of the specific capabilities and unique features in JMP.

  • Novel Descriptions of Misshape of Round Objects Using JMP®

    Casey Volino, Engineering Associate and Senior Statistician, Corning

    • Topic: Predictive Modeling
    • Level: 3

    This paper covers an informative way to describe misshape in round or cylindrical objects that goes beyond traditional metrics, such as “out-of-round,” and even modern GD&T (geometric dimensional tolerancing) metrics, such as “circularity.” I will show that the traditional metrics of misshape act only as indicators of the degree of misshape, but are non-informative in terms of type and orientation. I will present two related approaches, both based on Fourier frequencies that are more detailed descriptions of patterned deviations from a circle. One approach is preferred in the case when measurement orientation is consistent. A second and easier approach can be used when measurement orientation is thought to be random or unreliable. Only a basic familiarity with ordinary least squares regression is assumed. JMP will be used as both the analysis and visualization software for this talk, but the technical details are not specific to any particular JMP feature or platform. A paper will be made available after the talk as well as all data sets used, which are not proprietary.

  • Novel Multivariate Approach for the Assessment of Product Comparability

    Janet Alvarado, Senior Specialist for Quantitative Sciences, Merck           

    Nelson Lee Afanador, PhD, Associate Director for Quantitative Sciences, Merck

    • Topic: Data Exploration
    • Level: 3

    It is a regulatory requirement to demonstrate product comparability before and after process changes in vaccines, biologics and pharmaceutical manufacturing occur. The demonstration of comparability, as described in ICH Q5E, does not mean that pre- and post-change products have to be identical, but rather highly similar. In this work, we explore the use of a novel approach for the evaluation of comparability. This multivariate approach makes use of the dissimilarity matrix from a random forest model as the input to a principal coordinate analysis as a way to examine similarity of observations from pre- and post- process changes. Confidence ellipses can be used to assist in a visual assessment of comparability, where highly overlapped ellipses would suggest similarity. We assess variable importance to shed light on what variables are contributing the most to the separation between groups, which subsequently helps determine if a more focused approach is needed. We’ll compare the results of this potential approach to those from other more common multivariate techniques, such as partial least squares analysis, and present several case studies.

  • Optimizations of High Energy Explosives Utilizing JMP®

    Edward Cooke, Chemist, US Army ARDEC

    Eric R. Beckel, PhD, Chemical Engineer, US Army ARDEC

    Paul E. Anderson, PhD, Chemist, US Army ARDEC

    Alexander J. Paraskos, PhD, Chemist, US Army ARDEC

    • Topic: Design of Experiments
    • Level: 2

    Explosives research and development is a constant balance of trade-offs between explosive energy output and material sensitivity. One solution to optimizing a formulation for maximum performance with minimal sensitivity is energy partitioning, in which non-crystalline energetic binder materials are used to reduce the concentration of highly sensitive crystalline explosive ingredients. For this reason, a cast-cure binder system containing a novel energetic pre-polymer has been considered to replace the inert binders of legacy formulations. In order for the new ingredient to be incorporated and tested, two types of statistical optimizations were performed. First, the binder components and cure chemistry were optimized through a factorial design including continuous and categorical factors. Second, a mixture design of experiments was created to determine the optimal ingredient ratios capable of meeting and outperforming a legacy cast cure explosive. Thermodynamic calculations were used to populate a series of explosive performance responses in order to create models capable of predicting theoretical formulation characteristics. Both binder and formulation optimizations were analyzed using various JMP capabilities to balance trade-offs and visualize the working design space. This presentation will cover the background of cast cure explosive formulations plus the binder and explosive formulation optimizations utilizing JMP profilers.

  • Organizational Systems Thinking Using Custom Mapping in JMP®

    David Sais, Lean Six Sigma Black Belt, Sandia National Laboratories

    • Topic: Data Visualization
    • Level: 3

    Managers have a detailed working knowledge of their responsibilities for their department, but may not always have a high-level view or systems perspective of the center or organization to which their department belongs. This limited view can result in managers making wasteful or detrimental decisions. Using custom mapping in JMP, combined with Application Builder and local data selection filters, I will create a deceptively simple yet powerful model to elevate managers’ perspectives to a high level and promote a more strategic mindset. I will use the interactive and dynamic elements of JMP to present a custom map of my organization and demonstrate how various training and resource management decisions affect the organizational system as a whole.

  • Predicting Patient Recruitment in Multicenter Clinical Trials

    Xiaotong Jiang, JMP Life Sciences Summer Intern, SAS, and Biostatistics PhD Student, University of North Carolina at Chapel Hill

    Richard Zink, PhD, JMP Principal Research Statistician Developer, SAS

    • Topic: Predictive Modeling
    • Level: 1

    The initial recruitment timeline for a clinical trial is often determined by enrollment rates of past trials. Despite best efforts, challenges in identifying and recruiting the necessary patients in order to appropriately power the clinical trial may delay study completion. Extended timelines result in increased costs for the ongoing study and delays in downstream activities, which may include additional clinical trials or a potential regulatory submission. An interactive implementation of the Anisimov and Fedorov (2007) algorithm is implemented to predict remaining recruitment time in JMP Clinical. The arrival of patients at each center follows  an independent Poisson process with rate sampled from a gamma distribution with unknown parameters. Given current enrollment information, model parameters are estimated using maximum likelihood, which are then used to predict the remaining recruitment time and confidence intervals through simulation. Further, if there is a high probability of missing the recruitment deadline, the number of additional clinical centers needed to meet the deadline is determined, adaptively adjusting the number of centers until the target time is achieved. This feature is geared to different customer needs via pre-specified options and could possibly be modified to predict recruitment in areas such as business and finance in the future.

  • Pseudo-Scientific Versus DOE Approaches to Solving Problems

    Jed Campbell, Quality Manager, US Synthetic

    • Topic: Design of Experiments
    • Level: 2

    Experimenters may occasionally feel they lack sufficient time and/or resources to do a properly designed experiment, instead opting for a "Hail Mary" with a few experimental runs they intuitively feel may include the best solution. This presentation will walk the audience through a typical Hail Mary set of experimental runs that, at first glance, look promising. However, as we use Graph Builder to look at the experimental runs over time, look at scatterplots of the design space used, and use stepwise regression to attempt to build a model, we will realize that the data suggest a better set of factors might exist, but in a location that we didn’t originally test. We’ll evaluate the original design, learning that there is much confounding of potential interactions, and see very low optimality scores. We’ll then compare the original design to a simple DOE with no interactions, a response surface and a definitive screening design. We’ll conclude that the Hail Mary approach is lacking, and a properly designed experiment will yield better results using a similar amount of time and resources. The presentation will use JMP exclusively and will not rely on any PowerPoint slides.

  • Run Program – JMP® Software’s Link To Other Programs

    Michael Hecht, JMP Principal Systems Developer, SAS

    Stan Koprowski, JMP Customer Care Systems Engineer, SAS

    • Topic: JSL Application Development
    • Level: 4

    JSL’s Run Program() function launches other programs, sends data and commands to them, and retrieves their output. With this powerful tool, script authors can extend the reach of JMP to drive all the capabilities of their machines. But harnessing this power can be challenging, even for experienced script authors. Several examples of Run Program() are presented, to demonstrate all of its various options and modes.

  • Scoring Outside the Box

    Nascif Abousalh-Neto, JMP Principal Software Developer, SAS

    Daniel Valente, PhD, JMP Senior Product Manager, SAS

    • Topic: Predictive Modeling
    • Level: 3

    Scoring – the process of using a model created by a data mining application like JMP to make predictions for new data – has been called the "unglamorous workhorse of data mining." Like a dark yin to the bright yang of predictive modeling, scoring plays a fundamental role in the implementation of a complete data mining life cycle. Scoring requires that the model is first adapted so that it can run where the new data is produced or stored. This process is usually a time-consuming and error-prone endeavor. In this paper, we will see how the new score code generation features in JMP 13 can assist you in extending the reach of your models while minimizing the work required to adapt them.

  • Sharing Interactive Web Reports in JMP® 13

    Heman Robinson, JMP Principal Software Developer, SAS

    • Topic: Data Visualization
    • Level: 1

    Interactive HTML supports many of the exploratory features of JMP, including point identification, linking and brushing.  Saved reports can be uploaded to a web server or emailed to colleagues.  Reports can be viewed in any modern web browser. JMP 13 adds support for the most frequently used features of Graph Builder, including points, smoothers, ellipses, lines, bars, areas, box plots, histograms, heat maps, mosaic plots, caption boxes and map shapes. With examples from Graph Builder and other JMP reports, this paper describes when and how to use interactive HTML to share JMP results.

  • Simulate Responses: Revamped in JMP® 13      

    Ryan Lekivetz, PhD, JMP Senior Research Statistician Developer, SAS

    • Topic: Design of Experiments
    • Level: 4

    The Simulate Responses option in most design of experiments platforms is useful for generating simulated data for an experiment. In JMP 13, we have improved the response simulator by allowing for normal, Poisson and binomial distributed responses. We also create a column formula that generates the data. This feature is even more effective when used with the new JMP Pro Simulator to do empirical power calculations. This talk will demonstrate the new Simulate Responses and how to use it to perform empirical power calculations with JMP Pro.

  • Solving Common Data Table Problems With JMP® 13: Can We Replace Summary and Join With the New JMP Query Builder?

    Daniel Valente, PhD, JMP Senior Product Manager, SAS

    Jon Weisz, JMP Vice President of Sales and Marketing, SAS

    • Topic: Data Access and Manipulation
    • Level: 2

    JMP 13 introduces two new tools that make it easy for the analyst to deal with common data problems. Often two or more data tables are related by a common key, yet they are very different in terms of fact-sampling frequency or dimensions (e.g., long versus wide). Doing an actual join of these two (or more) tables may create a resulting table that gets very large in memory. While this is a nuisance when the fact and dimension tables are relatively compact, it can quickly generate a joined table that is too big to fit in memory. The solution is to use a virtual join, which preserves the joined relationship without actually creating  the joined table – effectively enriching the fact table without burdening it. Analysts often find themselves needing to make complex table joins or summarizations in database and writing SQL, which is another common set of pains. This is especially true when there are complex relationships like slowly changing dimensions. The JMP Query Builder serves as an easy SQL-generating and writing tool. This code can then be executed in a database. The Query Builder lets you drag and drop to a correct and desirable query and automatically writes the SQL code for you, obviating the need for tedious manual and error-prone work.

  • Speeding Up the Dirty Work of Analytics

    Robert Carver, PhD, Professor of Business Administration, Stonehill College

    • Topic: Data Access and Manipulation
    • Level: 3

    “Big data” is rarely ready for analysis when it arrives on your desktop. The issues are familiar, yet they aren’t often what comes to mind in discussions of the “Sexiest Job of the 21st Century.” These are tasks that consume a massive fraction of project time, yet receive comparably little attention in textbooks, professional journals or blogs. The dirty work includes activities such as assembling a data set from disparate sources, exploring data for various forms of messiness, imputing and otherwise addressing missing data, identifying and dealing with outliers, recoding observations to regularize inconsistencies and reduce dimensionality. Fortunately for JMP users, the latest versions of JMP provide intuitive and highly visual tools to perform diagnostics and automate some of the nastier janitorial chores in the analytics workflow. This presentation demonstrates some of the ways that the Query Builder, other Tables menu platforms and Column utilities can expedite the dirty work with some large, publicly available data sources.

  • Storytelling With Data to Executives

    Jim Grayson, PhD, Professor, Augusta University

    Mia Stephens, JMP Academic Ambassador, SAS

    • Topic: Predictive Modeling
    • Level: 1

    Teaching business analytics to students has its challenges. But while students can typically develop an understanding of tools and techniques used in predictive modeling, they often struggle with communicating what they have learned and explaining the results in the language of the business.Telling the data story to executives is difficult. As analysts we want to impress them with the models we have built and all the hard work we have done. In reality, management is interested first in the conclusion and business impact, and then will ask questions to gauge our competence and credibility and develop confidence in our proposed recommendations or solutions. This talk will illustrate, through a case example, how to effectively tell your data story. We begin by discussing what executives want to hear and the importance of earning trust and credibility with core decision makers. Then we illustrate how to translate statistical conclusions to business results using built-in graphical and visualization tools. We use core features in JMP, including Data Filter, Graph Builder and the Profiler. We also illustrate the use of new features in JMP 13, such as web reporting and interactive dashboards.

  • Strategies for Optimization of an Organic Light Emitting Diode (OLED) Device

    David Lee, Director of Quality and Reliability, OLEDWorks

    • Topic: Design of Experiments
    • Level: 4

    Every experiment yields multiple data types, each requiring unique analyses and controls due to the sub-micron nature of an innovative organic light-emitting diode (OLED). Three specific data methods will be discussed. First, the premise of the study centers on a six-factor definitive screening design that was built utilizing new features incorporated in JMP 13 for improved power and signal detection. Multiple responses were modeled with a defect model generated via use of the Profiler and Simulation studies. Second, devices are continually monitored for radiance loss in an accelerated fade test. Frequently, devices are removed from the test prior to reaching their failure point. Predicted failure times can be estimated by utilizing a custom nonlinear model in either the Reliability Degradation or Nonlinear Model platforms. Estimated failure times were then incorporated into traditional parametric survival techniques, as well as new features in the Generalized Regression platform. Lastly, radiance data is collected across the visual spectrum, resulting in approximately 100 correlated responses.

  • Text Mining Online Reviews With JMP® 13

    Vishal Singh, PhD, Associate Professor of Marketing, New York University           

    Qianyun (Poppy) Zhang, Research Assistant, New York University

    • Topic: Data Visualization
    • Level: 3

    This talk focuses on text analytic capabilities of JMP 13 Text Explorer. We demonstrate the ease and capabilities of JMP 13 in analyzing textual data, and compare the results to popular text mining packages in R. The context of our study is online customer reviews from Amazon and IMDB. We construct a wide array of attributes to quantify the information content of reviews: length and timing of review, its syntactic and semantic features, star rating, price and characteristic of the product. We demonstrate how textual data can be combined with such numerical information to generate useful insights.

  • The Life Cycle of the Analytical Data Mining Process     

    Sam Edgemon, Principal Technical Consultant, SAS          

    Tony Cooper, PhD, Analytical Consultant, SAS

    • Topic: Predictive Modeling
    • Level: 2

    Too often, the technical aspects of building models overshadow vital and foundational aspects of the process. This presentation focuses on important but often overlooked aspects of analytics: discovery, data quality, the presentation of analytical findings to management, deployment, the evaluation of models in the field, and the concept of challenger models. JMP has excellent support for aggressive, dynamic experimentation and observational studies; however, JMP also supports other aspects of analytics, namely the data mining of stored data. We will use JMP Pro to analyze data and build models to truly demonstrate the life cycle of the analytical data mining process.

  • The Perils of Mining Manufacturing Data and the JMP® Advantage

    Bradley Novic, PhD, Principal Consultant, PhaseTwo Analytics

    • Topic: Predictive Modeling
    • Level: 2

    Mining manufacturing data can be a perilous endeavor from data assembly to analysis to interpretation and implementation of results. What sets data mining in manufacturing apart from data mining in, say, marketing or finance, is that prediction alone is not good enough in manufacturing. In manufacturing the end game is improved control, and that requires getting to root cause. Decision trees are a wonderful tool for discovery, but left to their own devices can select variables that, although predictive, make no sense to a process engineer from a control standpoint. This requires a more careful approach to tree building that is afforded by the stepwise approach provided in the JMP Partitioning platform and unavailable in most other decision tree software programs. This paper will provide examples of data mining successes using JMP in manufacturing and issues in mining manufacturing data. It will also demonstrate the integration of expert knowledge into the JMP partitioning process, to deal with the issue of correlation in predictor variables and provide rules that permit validation and deployment of results.

  • Using JMP® for Group Segmentation and Predictive Modeling for Indicators of High Utilization in a Rural North Carolina Hospital

    Jason Brinkley, PhD, Senior Researcher, American Institutes for Research             

    Elizabeth Horner, PhD, Senior Researcher, American Institutes for Research

    • Topic: Predictive Modeling
    • Level: 3

    Patterns of hospital utilization are multifaceted with causal mechanisms as diverse as patient populations. There is a need to identify patients with preventable high hospital utilization. Most research employs a direct modeling of utilization counts. This strategy largely identifies immutable factors (i.e., race and age) and provides little guidance on policy changes. We propose an alternate framework – segmenting the utilization population into groups and establishing that one group “uses” hospital services at higher rates than others. Using administrative data, we employ predictive modeling to determine whether individuals are likely to fall into a particular segment. We apply the framework to data from a rural hospital, examining transitions from home to long-term care among older at-risk patients. This segment represented approximately 20 percent of inpatient high utilization, 15 percent of ER utilization and 11 percent of 30-day readmissions. Predictive modeling then identified unique ICD-9 code groups with increased likelihood of later transition. These groups provide opportunities to intervene, either preventing further hospital utilization or providing guidance for likely later transfer. While this technique is popular in business analytics, it is not as widespread in health care. We demonstrate that applying the framework allows for discussion of policy changes and interventions.

  • Using JMP® Scripts to Automate Generation of Graphs and Analysis for Large Molecule Manufacturing Changes

    Jessica  Behrle, Senior Principal Biostatistician, Janssen R&D       

    Yinglei Li, PhD, Senior Biostatistician, Janssen R&D

    Barry Hogan, PhD, Senior Scientist, Janssen R&D

    Yonghui Wang, PhD, Senior Scientist, Janssen R&D

    Michael Nedved, PhD, Associate Director, Janssen R&D

    • Topic: JSL Application Development
    • Level: 2

    For process changes (site, scale, formulation, etc.) made to biopharmaceuticals (e.g., proteins, DNA, vaccines), comparability studies of pre-change and post-change materials are required to ensure quality at product release and during storage. Degradation studies at various temperatures are used to assess differences in stability profiles over time for pre- and post-change product using analytical methods for various product attributes. In addition to pre- and post-changes, these studies take into account factors such as dosage. Unfortunately, there is no point-and-click approach to do pairwise comparisons when there are three or more estimated slopes. With a powerful tool – a JMP script – all data is modeled and pairwise comparisons of the simple linear degradation slopes are performed. For each of the 20 or more measured analytical responses, the JMP scripts graph the observed data as a function of time, create the analysis, and automate all output into one JMP Journal. With the abundance of data from a study and the increasing frequency of such studies at Janssen R&D, automation of the statistical output via JMP performed by either a statistician or an analytical development scientist provides opportunities for increased efficiency.

  • Using JMP® to Optimize Performance-Sensitive Semiconductor Products

    Scott Rubel, Senior Principal Engineer, NXP Semiconductors

    Todd Jacobs, PhD, Principal Engineer, NXP Semiconductors

    James Nelson, Software Engineer and Six Sigma Black Belt, Independent Contractor

    • Topic: JSL Application Development
    • Level: 3

    Modern chip designs incorporate multiple components, each with their own process, voltage and temperature sensitivities. These designs must meet overall customer speed and power requirements, and their capability must be optimized prior to finalizing a product’s design. Monte Carlo techniques are well-suited to this analysis, but the number of parameters and their complex constraints requires a custom solution. This complexity makes it critical to have a standardized workflow incorporating best practices, along with a consistent look and feel that captures all relevant parameters. The tool must also be flexible enough to rapidly work different input/constraint scenarios during the prototyping phase; during this time thorough documentation is especially critical. JMP is an ideal tool to meet all of these requirements: The complex data structures available in JMP can store a mix of inputs, as well as the statistical parameters the simulation requires, while the scripting language’s built-in statistical functions support customized Monte Carlo simulations. Finally, JMP Journals are perfect for merging the input documentation with the simulation output: They ensure consistent and thorough documentation, while allowing further customization where needed. As a result, significant improvements can be made in product development cycle time and accuracy.

  • Visually Exploring Design of Experiments Models With the Generalized Regression Platform

    Chris Gotwalt, PhD, JMP Director for Statistical Research and Development, SAS

    Clay Barker, PhD, JMP Senior Research Statistician, SAS

    • Topic: Design of Experiments
    • Level: 3

    The Generalized Regression platform (GenReg) has evolved into a world-class framework for the analysis of designed experiments. In this presentation, we use simple case studies to demonstrate how easy it is to use GenReg's powerful new automated model selection capabilities such as the double lasso and two stage forward selection. Most importantly, we will show how GenReg's interactive diagnostic plots demystify the analysis of designed experiments. The case studies will include supersaturated designs, definitive screening designs, and designed experiments for binomial responses. As a part of the presentation, we will also introduce the new Simulate capability in JMP Pro 13 as a way to evaluate the statistical power of the model selection capabilities in GenReg. Finally, we will show how to use GenReg and Simulate together to obtain power calculations for non-standard analyses like the logistic regression for designed experiments with binary outcomes.

  • Working With Excel: The Advanced Edition       

    Brian Corcoran, JMP Director of Research and Development, SAS

    • Topic: Data Access and Manipulation
    • Level: 2

    There have been quite a few additions to JMP since the Excel Wizard was introduced in JMP 11. This session will explore some of the new advanced options in JMP 13, including working with colors and the mysterious "multiple series stack.” We will also discuss the new Create Excel Workbook feature, and some ease-of-use additions from JMP 12.

  • Beginner: 1
  • Intermediate: 2
  • Advanced: 3
  • Power user: 4

  • JMP® Helps the Army “Go Green”

    Edward Cooke, Chemist, US Army ARDEC

    Kevin Singer, Statistician, US Army ARDEC

    Peggy Sanchez, Chemist, US Army ARDEC

    Shauna Dorsey, Environmental Engineer, US Army ARDEC

    Pamela Sheehan, Environmental Engineer, US Army ARDEC

    JMP® Pro 13 Modeling Workflow Enhancements With Predictor Screening, Generalized Regression and the New Formula Depot

    Karen Copeland, Statistician, Boulder Statistics

    Exploring the Relationship Between Patient Satisfaction and Provider Productivity In US Army Medical Facilities

    Melissa Gliner, Senior Health Policy Analyst, US Army Office of the Surgeon General      

    Dawn Garcia, Nurse Methods Analyst, US Army Medical Command

    Kenneth R. Kovats, Senior Nurse Analyst, US Army Medical Command

    Richard E. Thorp, Deputy Chief of Analysis and Evaluation, US Army Medical Command  

    Robert Goodman, Deputy Chief of Staff for Resources, Infrastructure and Strategy, US Army Office of the Surgeon General  

    Using JMP® to Develop and Execute an Administrative Cost Efficiency Model for the US Army Medical Command

    Kenneth R. Kovats, Senior Nurse Analyst, US Army Medical Command

    Richard E. Thorp, Deputy Chief of Analysis and Evaluation, US Army Medical Command  

    Richard S. Meyer, Decision Science Analyst, Analysis and Evaluation Division, US Army Medical Command Analysis and Evaluation Division     

    Robert Goodman, Deputy Chief of Staff for Resources, Infrastructure and Strategy, US Army Office of the Surgeon General  

    Experience the Flow: Using JMP® to Build Applications That Encourage Use

    Matthew Goodlaw, Director of Assessment and Evaluation, New Mexico Public Education Department

    Mars 2020 Coring Drill: Prototype Testing and Analysis

    Kristopher Kriechbaum, Mechatronics Engineer, Jet Propulsion Laboratory, California Institute of Technology    

    Kyle Brown, Mechatronics Engineer, Jet Propulsion Laboratory, California Institute of Technology            

    Avi Okon, Robotics Engineer, Jet Propulsion Laboratory, California Institute of Technology

    Influence of Motivational and Prevention Factors on Consumer Recycling Behavior

    Shaghayegh Rezaei, Research Assistant, North Carolina State University               

    Kristin A. Thoney-Barletta, Associate Professor, North Carolina State University

    Jeffrey A. Joines, Associate Professor, North Carolina State University

    Lori Rothenberg, Associate Professor, North Carolina State University

    Prediction of Students’ Final Results Using JMP® Pro 12

    Juana Rodriguez, Student, Oklahoma State University   

    Thai Cao, Student, Oklahoma State University

    Comprehensive Analysis of Performance Data for Energized Vessel Sealing Devices Using JMP® Pro 12

    Susan Roweton, Research Manager, Medtronic

    Jim Pappas, Statistics Manager, Medtronic

    J. Bruce Dunne, Director, Medtronic

    Examining Influencing Factors in the Associated Press Preseason College Football Rankings

    James Rush, MBA Student, Oklahoma State University 

    Nhung Nguyen, Student, Oklahoma State University

    Building Dashboards in JMP® 13

    Dan Schikore, JMP Principal Developer, SAS

    Using Process Screening in JMP® Pro to Analyze JMP JSL Testing Processes

    Audrey Shull, JMP Senior Manager, SAS               

    Fast, Powerful, Efficient: Joining Without Joining to Explore Summer Games Data With JMP®

    Mandy  Chambers, JMP Principal Development Tester, SAS        

    Chung-Wei Ng, JMP Principal Systems Developer, SAS  

    Racial Effect Analysis Using JMP® in Supporting Drug Application for ST-101: A Fixed Dose Combination of Olmesartan and Rosuvastatin

    Wen Wang, Director of Clinical R&D, Autotelic   

    Larn Hwang, Chief Scientific Officer, Autotelic

    Vuong Trieu, Chairman and Chief Regulatory Officer, Stocosil     

    Added Dimensions of Difficulty: Image Analysis and 3-D Visualization in JMP®

    Michael Anderson, JMP Systems Engineer, SAS                

    When Not to Run a Mixture Experiment  

    Ronald Andrews, Senior Process Engineer, Bausch + Lomb

    Using the Power of JMP® Scripting and Data Visualization to Easily Apply ASTM Standards in Blend and Content Uniformity

    Tanya Davis, Assistant Statistician, Perrigo           

    Perry Truitt, Director of Consumer Healthcare Research and Development, Perrigo

    Using Funnel Plots to Develop Risk-Based Monitoring Rules for Binomial and Poisson Outcomes in Clinical Trials

    Anastasia Dmitrienko, Student, Blue Valley North High School   

    Richard C. Zink, JMP Principal Research Statistician Developer, SAS

    JMP® Meets SQL: Using Query Builder for JMP Data Tables

    Eric Hill, JMP Principal Software Developer, SAS

    Managing and Reusing Data and Analyses

    Wayne Levin, President, Predictum

    Farhan Mansoor, Analyst/Programmer, Predictum

    New Features in Choice Modeling for JMP® 13 and JMP® Pro 13

    Melinda Thielbar, JMP Senior Research Statistician Developer, SAS

    PosNegNMF: Positive Negative Non-Negative Matrix Factorization

    Stan Young, CEO, CGStat             

    Paul Fogel, Independent Statistical Consultant  

    Using JMP® Image Analysis Capabilities to Extract Skin Lesion Characteristics

    Julia Gong, JMP Marketing Intern, SAS, and Student, Cary Academy 

Back to Top