What’s next: The future of data literacy education
AI changes what we teach, not just how. Episode 5 looks at open questions — curriculum, assessment, equity — and where statistical education goes from here.
AI changes what we teach, not just how. Episode 5 looks at open questions — curriculum, assessment, equity — and where statistical education goes from here.
"The AI said so" — a student's answer to a completely misinterpreted regression. Episode 4 looks at the real risks of AI in the statistics classroom, and four practical guardrails that keep students thinking instead of just approving output.
What if students could ask their analysis question in plain English and get a real result in seconds? Episode 3 looks at JMP Assistant in practice — what it does well, and why the instructor's role just got more interesting, not smaller.
I attended a conference recently with, not surprisingly, several talks on LLMs. A couple things became clear: Everyone is wondering when they’ll be able to trust LLMs 100% of the time.People are using LLMs as a natural language user interface for difficult-to-execute tasks. In the context of statistical modeling, what’s interesting to me is: We already have tools that are deterministic and can be ...
Students can produce statistical output faster than ever. Evaluating it is a different skill — and that's where the real teaching challenge lies. Episode 2 of my series on AI in the statistics classroom: what changes, what helps, and what's actually on the instructor.
Before AI enters the statistics classroom, what does a genuinely good teaching tool look like without it? Episode 1 of my new series makes the case for JMP Student Edition - a professional environment, not a simplified one.
Bayes(ベイズ)最適化は、「少ない実験回数で最適解を見つけられる」だけでなく、応答曲面法のように特定の関数形を仮定せず、複雑な非線形関係や多峰性にも対応できる点が大きな特長です。本記事では、酵素反応のシミュレーションを用いて実験計画法と比較した結果、Bayes最適化は14回の実験で90%以上の収率を達成した一方、応答曲面法では18回の実験でも高収率条件を見つけられませんでした。応答と因子の関係が未知で複雑な実験では、Bayes最適化が有力な選択肢となります。
Video made with JSL.
Designed for 1920x1080 display.
The JSL uses a data table to keep a row of data per moving point in the video.
The ForEachRow loops use the column name variables rowpos and colpos to place a point at a row,column in the bitmap matrices and rowstep and colstep to advance the rowpos and colpos for each frame.
dt = New Table( "points", "private", // private is *much* faster
A...
A recurrence analysis acknowledges that an adverse event may occur more than once within a patient over time and accounts for these re-appearances within the analysis. Going further, recurrence analysis accounts for the timing at which the events occur. The Recurrence Report in the forthcoming JMP Clinical 19 makes it easy to screen a clinical trial for noteworthy safety issues while considering p...
So, you've spent and hours writing up a report on an an experiment and copying in carefully formatted figures from JMP. Now a week later you have updated data and are absolutely thrilled at the prospect of deleting and replacing all the figures from last week with the new updated figures from this week. Wouldn't it be awesome if there were some way to just run the analysis in JMP from your saved ...
The latest version of JMP Live focuses on accelerating triage, tightening governance, and making it easier to communicate insights.
Prompting the user to select columns is a very common task for a JMP script. But how do you get started? What things should you consider? In this post, I will discuss ways to create modal windows to prompt users to select columns that will be used in an analysis. In addition, we will look at methods to extract the user’s selections from these windows.
Adding PowerPoint export to Workflow Builder The Engineering Mailbag Episode 8: The Last Mile Every now and again, as systems engineers, we run into interesting questions that would fall somewhat outside the typical range of JMP usage. Other times the question is just interesting and gives me an opportunity to explore the deeper reasons of why we do things the way we do in JMP. This question has ...
Introduction Welcome to the finale of our space filling DOE series! After establishing our framework and evaluation methodology in the previous posts, we now present the comprehensive results of our comparative study. The findings provide clear guidance on when and how to select the most appropriate space filling design for your specific application. Summary of key findings Our analysis across f...
The Funnel Plot add-in produces funnel plots for continuous, binary, and count endpoints to assess the performance of mutually exclusive subgroups when compared to the entire population.
Learn how JMP can be used for environmental monitoring to ensure stable processes, detect shifts early, and support regulatory compliance with real-world examples.
In JMP Live (and in JMP), it's possible for one local data filter to affect more than just one output in a window. Read on to learn how to use a data filter context box to make this happen.
The multiple response modeling type maintains a one-row-per-patient data table while producing more informative analyses.