In SAS, you can approximate the exponential of a matrix by using the EXPMATRIX function in SAS IML software. This article discusses the exponential of a matrix: what it is, how to compute it, why it is useful, and why you should think of it as a linear map that
Uncategorized
Over 40 years ago Steven Hayes developed ACT Therapy (pronounced as the word "act") which incorporates practices of psychological flexibility and a focus on values. For Work/Life's recent email series, A Month of Values Based Living, Triangle area therapists shared introductions to the six components of ACT Therapy and related
Who is responsible for ensuring that new AI technologies are fair and ethical? Does that responsibility land on AI developers? On innovators? On CEOs? Or is the responsibility more widespread? At SAS, we believe that it is everyone’s duty to innovate responsibly with AI. We believe that adhering to trustworthy
In a previous article, I showed how to overlay a density estimate on a histogram by using the Graph Template Language (GTL). However, a SAS programmer asked how to overlay a curve on a histogram when the curve is not a density estimate. In this case, the vertical axis for
はじめに 統計的因果推論における1つの達成目標として「介入を行った場合には行わなかった場合と比較してどの程度結果(アウトカム)が変わったのか」という因果的な疑問に対し、定量的に答えることが挙げられるかと思います。以前のコラムでは、こういった因果効果を数学的・統計学的に議論していくために潜在アウトカムという考え方を導入し、その値を推定していくために重要ないくつかの仮定について紹介を行いました。この因果効果の推定の手法には様々なものがありますが、次回以降のコラムで紹介をする交絡調整に基づく因果効果の推定手法 (e.g., 回帰、層別化、傾向スコアを用いた手法)では、興味のある因果効果の推定値をバイアスなく得るためには、交絡や選択バイアスの調整に必要な全ての変数が完全に特定・測定されているという仮定が成立している必要があります。この仮定はデータからその成立を検証することはできず、もしもいずれかが成立しない場合には得られる推定値にはバイアスが含まれ、いわゆる残差交絡 (redidual confounding) が存在する状況となります。現実的に仮定が全て厳密に成立するケースというのは比較的稀ですので、そのような意味では大部分の研究結果(特に観察研究)・解析結果には一定のバイアスが含まれているとみることもできるかと思います。ただし交絡調整に基づく手法がダメだと言っているわけではなく、調整が不完全ながらもバイアスを軽減することは十分に意義があり、また最終的に結果に含まれるであろうバイアスの大きさとその方向(過大評価 or 過小評価)を議論することが重要かと思います。 今回のコラムでは、操作変数法(instrumental variable methods, IV methods)という因果効果の推定手法について紹介と解説を行っていきます。この推定手法は、操作変数 (instrumental variable, instrument) と呼ばれるいくつかの条件を満たす特殊な変数を利用することで因果効果の推定を行う手法になります。医学分野では、先行研究の結果(e.g., 医学的な知見)から交絡因子となりうる変数の特定・測定が比較的容易であることから先ほど言及した交絡調整に基づく推定手法が用いられるケースが比較的多いですが、経済学や社会科学といった分野ではそもそもの特定が出来なかったり、仮に交絡因子であろうと見込んだ場合であってもそれを測定することができないケースが非常に多く存在します。そのため交絡調整に基づかない手法である操作変数法というのは経済学や社会科学において、特にその理論が発展してきたという歴史的な背景があります。なお詳細については後述しますが、操作変数法は交絡因子の測定を必要としないというメリットもある一方、いくつかの検証不可能な仮定に基づく手法です。したがって、解析を行う研究・データにおいて因果効果の推定のために要求される仮定の成立を認めることがどの程度妥当であるかの議論が他の手法と同様に必要であることにご注意ください。 操作変数の3条件 操作変数法では、ある介入AのアウトカムYに対する因果効果を推定するために以下の3つの条件を満たす変数Zを利用します。この変数Zは操作変数 (instrumental variable, instrument) と呼ばれます。 操作変数の3条件 (Theree instrumental conditions) Z is associated with A ZはAと関連する Z does not affect Y except through its potential effect on Y ZはYに対してAを介した以外の効果を持たない Z
In her first blog post, SAS' Mu He shows you how to train a convolutional neural network that can accurately detect patients with COVID-19 using the transfer learning technique.
You can start learning about ModelOps and SAS Model Manager now. Compare the various educational resources provided by SAS according to your learning preference.
In honor of Women's History Month, SAS organized various events to celebrate and empower women. Keep reading to see how we highlighted women's contributions and achievements in various fields. Fair Play discussion Fair Play makes the “invisible care” work historically held by women visible, inspiring a more balanced future for
When the SAS statistical graphics (SG) procedures were designed in the early 2000s, a goal was to create a comprehensive Graph Template Language (GTL) and leverage the GTL by using SG procedures that perform common tasks easily without having to write any GTL. This project was hugely successful, and "ODS
For several years Kim Andreaus and I have taught Powerful Tools for Caregivers, an evidence-based program that teaches skills for self-care and stress management. One of the lessons from the class that always resonates with me is the concept of guilt versus regret. Guilt is shame-based and implies there was
A previous article discusses how to compute the union, intersection, and other subsets of a pair of sets. In that article, I displayed a simple Venn diagram (reproduced to the right) that illustrates the intersection and difference between two sets. The diagram uses a red disk for one set, a
Artificial Intelligence (AI) can drive environmental innovation (EI) in sustainability and reduction of carbon emissions. However, the use of AI itself also comes with environmental costs. The high computational requirements of AI-based systems lead to significant energy consumption, contributing to greenhouse gas emissions. The energy consumption of AI systems can
Retailers are always looking for ways to maximize customer interactions and develop new revenue opportunities, particularly in the face of social and economic challenges. Retail media networks (RMNs) have recently emerged as an attractive investment option for retailers and brands or consumer packaged goods (CPG) companies. Retail media refers to
The spring is a time of rebirth and renewal. The birds are singing, plants are emerging from the ground and flowers are blooming in their brightness. For me, I feel better when I'm immersed in nature. What’s even better is bringing nature inside. In honor of Earth Month, I
The fundamental operations on sets are union, intersection, and set difference, all of which are supported directly in the SAS IML language. While studying another programming language, I noticed that the language supports an additional operation, namely the symmetric difference between two sets. The language also supports query functions to
앞선 두번의 연재를 통해 자금세탁 방지 기술이 향후 어떤 방식으로 발전되어갈 것인지, 금융기관이 현재 운영중인 자금세탁 환경을 앞으로 어떻게 변화시켜 나가야 하는지를 살펴보았습니다. 이를 위해 SAS는 ‘AML Compliance Analytics Maturity Model’을 제시했고, Maturity Model의 단계를 소개함으로써 현재 각 금융기관이 AML을 위해 내부적으로 어느 정도 데이터 분석을 적용하고 있는지에 대한 자체
Analytics are vital to a safer future. As a renowned sustainability leader, SAS is committed to making a positive impact on our customers, employees, and the planet. Climate change is more important than ever, and the explosion of big data is essential to navigating this crisis. Learn how analytics is
The "Teacher’s Corner" of The American Statistician enables statisticians to discuss topics that are relevant to teaching and learning statistics. Sometimes, the articles have practical relevance, too. Andersson (2023) "The Wald Confidence Interval for a Binomial p as an Illuminating 'Bad' Example," is intended for professors and masters-level students in
Desde que en 2019 se constituyese la Red de Destinos Turísticos Inteligentes (RDI), el camino recorrido por la industria del turismo, capital para la economía española, no ha sido fácil, con una pandemia que dió de lleno en la línea de flotación de este sector. Hoy, el panorama comienza a
SAS' Scott Pope introduces you to an action set in SAS Viya called dlModelZoo that supports importing PyTorch models.
A journal article listed the mean, median, and size for subgroups of the data, but did not report the overall mean or median. A SAS programmer wondered what, if any, inferences could be made about the overall mean and median for the data. The answer is that you can calculate
A SAS user asked how to interpret a rank-based correlation such as a Spearman correlation or a Kendall correlation. These are alternative measures to the usual Pearson product-moment correlation, which is widely used. The programmer knew that words like "weak," "moderate," and "strong" are sometimes used to describe the Pearson
We're thrilled to announce that Michael Lewis, best-selling author of The Premonition, The Blind Side, Moneyball, and The Big Short, will join us at SAS Innovate: Orlando for a fireside chat. Michael Lewis has been shedding light on the inner workings of the financial world for decades. From his early work in Liar's Poker to
A previous article discusses rank correlation and lists some advantages of using rank correlation. However, the article does not show examples where an analyst might prefer to report the rank correlation instead of the traditional Pearson product-moment correlation. This article provides three examples where the rank correlation is a better
SAS' Brandon Reese the EURO Meets NeurIPS 2022 Vehicle Routing Competition, which combined efforts of operations research and machine learning experts.
I recently discussed introductory programming with a colleague who teaches Python at a university. He told me about the following introductory programming assignment: Let N be an integer parameter in the range [1, 9]. For each value of N, find all pairs of one-digit positive integers d1 and d2 that
Las organizaciones de todos los sectores iniciaron un año 2023 más conscientes de que el entorno económico, político y social no permanece estático, y que las condiciones bajo las que operan a diario pueden cambiar con relativa frecuencia. Han aprendido a ser resilientes y prestar atención a lo que sucede
SAS Hackathon team, Data Hack Freaks, created an artificial intelligence (AI) and machine learning (ML) based dynamic pricing approach that allows insurance providers to adjust pricing based on the changing nature of the risk behavior of their customers. This solution has three major components: The loss ratio score, telematics score
A previous article discusses the issue of a confounding variable and uses correlation to give an example. The example shows that the correlation between two variables might be affected by a third variable, which is called a confounding variable. The article mentions that you can use the PARTIAL statement in
The SAS Resiliency Rules report explores the global resiliency landscape. This report highlights country-specific findings about the ongoing market challenges, the difference between an importance in attaining resiliency versus perceived resiliency, and the principles companies need to follow to drive business resiliency. Our research defines resiliency as the ability of