Here's a SAS tip for you. Most SAS programmers know that SAS provides syntax that makes it easy to specify a list of variables. For example, you can use the hyphen and colon operators to specify lists of variables on many SAS statements: You can use the hyphen operator (-)
SAS' Sophia Rowland breaks down the roles of each team member in a long-term machine learning project and how they can better combine their efforts to increase efficiency and efficacy
A colleague asked me an interesting question: Suppose you have a structured correlation matrix, such as a matrix that has a compound symmetric, banded, or an AR1(ρ) structure. If you generate a random correlation matrix that has the same eigenvalues as the structured matrix, does the random matrix have the
In a previous article, I presented some of the most popular blog posts from The DO Loop in 2024. In general, popular articles deal with elementary topics that have broad appeal. However, I also write technical articles about advanced topics, which typically do not make it onto a Top 10
AI is increasingly prevalent in our daily lives, and this trend is unlikely to change anytime soon. This comes with risks, but by understanding these risks, we can build AI systems that mitigate them.
A previous article discusses covariance matrices that have the same set of eigenvalues. The set of eigenvalues is called the spectrum of the matrix. For symmetric matrices, the spectrum contains real numbers. For covariance matrices, which are positive semidefinite, the eigenvalues are nonnegative. It turns out that two symmetric matrices
Rising fraud and shrinking staff signal an urgent need for AI in government Have you ever opened your wallet and felt panicked? You count the bills once, twice and still come up short. You rummage through every pocket, hoping to find that missing cash. Then, a thought crosses your mind,
In 2024, I wrote about 80 articles for The DO Loop blog. My most popular articles were about SAS programming, data visualization, and statistics. If you missed any of these articles, here is the "Reader's Choice Awards" for some of the most popular articles from 2024! SAS Programming The following
We all know by now that customer experience (CX) is pivotal to any organization's success. Providing seamless, secure, personalized interactions across all customer touchpoints can be transformative. To achieve this, organizations must move beyond siloed functions such as fraud detection and credit risk management, integrating these critical areas with broader
금융기관은 다양한 업무에 조직과 더불어 여러 시스템들이 갖춰져 있습니다. 그러한 시스템에는 수많은 프로그램과 모델(로직)들이 결합되어 업무 활용의 효율성과 신뢰성을 보완해주는 역할을 합니다. 특히나 AI 모델을 많이 만들고 사용하는 최근에는 그동안 기업에서 각종 규제에 맞춰 만들어진 모델들까지 포함한 전사적 모델 관리가 리스크 관리의 중요한 부분으로 떠오르고 있습니다. 여기서, 여러분이 컴플라이언스/리스크 관리
注） 本コラムは『経時的に変化する治療（Time-varying treatments）に対する因果推論』と題した以前のコラムを、時間依存性治療に関する部分と周辺構造モデルにおけるIPTW法に関する部分に分割し、内容の追加と修正を行い再構成したものの一部となります。 はじめに 以前のコラムでは、「時間依存性治療とはなにか」、「時間依存性治療の因果効果はどのように定義されるのか」、「定義した因果効果はどう推定すれば良いか」について紹介しました。時間依存性治療の因果効果の推定にあたっては、一般に条件付けに基づく手法（e.g., 回帰、層別化、マッチング）は不適であり、g-methods※1と総称される推定手法が広く用いられています。本コラムでは、それらの中でも直感的な理解や実装が最も容易である「周辺構造モデルにおけるIPTW法（inverse probability of treatment weighting (IPTW) of marginal structural models (MSMs)」の理論とSASでの実装方法について簡単に紹介します。コラム全体の流れは以下の通りです。 時間固定性治療（time-fixed treatments）※2に対する周辺構造モデルとIPTW法の紹介 IPTW法の概要 周辺構造モデルの設定がなぜ必要か 時間依存性治療（time-varying treatments）に対する周辺構造モデルとIPTW法の紹介 SASでの実装 まとめ なお、本コラムは統計的因果推論に関する基本的な理解があることを前提としております。また、文献や書籍によっては、IPTW（Inverse probability of treatment weighting）は、単にIPW（Inverse probability weighting）と記載される場合もあります。しかし、IPW（逆確率重み付け）は治療効果の直接的な推定を目的とした治療変数に関する重み付け以外にも、打ち切りに対する補正（i.e., 打ち切り変数に関する重み付け）等でも用いられることがあり、本コラムでは前者であることを強調するためにIPTWと記載します。加えて、本コラムでは連続もしくは二値であるアウトカム（結果変数）が、研究最終測定時点でのみ測定される状況を想定します。アウトカムが生存時間（time-to-event）である場合や各時点の治療実施後に繰り返し測定される場合など※3、異なる状況における議論についてはreferenceにある文献等をご参照いただくか、著者宛に別途ご連絡いただけると幸いです。 ※1 (i) Inverse probability of treatment weighting of marginal structural models（周辺構造モデルにおけるIPTW法）、(ii) g-computation algorithm formula（"g-formula"）、(iii) g-estimation of stractural nested model（構造ネストモデルにおけるg-estimation）のという3手法の総称
SAS' Natalie Patten shows you the potential of integrating a country classification transformer into data cleansing workflows.
A previous article discusses how to generate a random covariance matrix with a specified set of (positive) eigenvalues. A SAS programmer asked whether it is possible to produce a correlation matrix that has a specified set of eigenvalues. After discussing the problem with a friend, I am happy to report
SAS' Mary Osborne, Ali Dixon Ricke, and Franklin Manchester break down what insurers still need to learn about generative AI.
O Christmas tree, O Christmas tree, How lovely are your branches! SAS programmers have a long history of creating yuletide-themed graphics. Christmas trees are a popular image because of their simplicity. I admit that I have indulged more than once in this holiday tradition: An old-school ASCII art image A
Review these three cool use cases for SAS users, built using SAS Viya Workbench. SAS and Python for better working together!
As populations around the world the U.S. continue to grow, both condensing in urban areas and sprawling in more rural areas, the importance of a functioning distribution network for utilities grows proportionally. The complexity and interconnected nature of say, the electric distribution network, is already staggering; one can hardly imagine
AI/ML 모델 개발 상의 어려움과 이를 해결하기 위한 접근법으로서 ModelOps의 필요성이 대두되고 있습니다. (참조 : AI/ML 기반 모델 개발, 과제와 해결방안은?) 이번 글에서는 ModelOps가 구체적으로 어떤 제품인지, 어떤 장점을 제공하며 구현방법은 어떠한지 등에 대해 설명드리도록 하겠습니다. 이에 앞서 ModelOps의 구현에 중요한 역할을 하는 ‘모델 거버넌스’에 대해 잠깐 짚어보도록 하겠습니다. 모델
SAS' Shawn Romero introduces you to the SAS Payment Integrity for Food Assistance model.
SoDA를 이용해 쉽게 배우는 데이터 과학 #4 지난 포스팅에서는 SoDA 인터페이스 구성과 그 기능에 대해 알아보았습니다. 오늘은 SoDA 인터페이스 중 ‘작업 모드’와 ‘프로세스 플로우’ 두 가지 요소에 대해 알아보겠습니다. 이 두 요소는 코딩에 익숙한 사용자와 코딩이 낯선 사용자 모두 쉽게 사용할 수 있도록 구성되어 있습니다. 이제부터 각각을 자세히 살펴보겠습니다. 1.
While researching the topic of Latin hypercube sampling (LHS), I read an article by Emily Gao (2019) that shows how to use PROC IML in SAS to perform the algorithm. It is possible to simplify Gao's implementation of Latin hypercube sampling in SAS while also making the computation more efficient.
지난 25년 동안, 대한민국의 금융기관들은 금융 감독기관과 은행, 증권사, 보험사 등 관련 기관들의 꾸준한 노력 덕분에 안정적이고 건실한 리스크 관리 체계를 구축해 왔습니다. 특히, BIS 규제를 준수하기 위한 업무 및 시스템이 정립되어 금융기관의 자본 강화, 리스크 관리 및 리스크 보고의 기본 틀이 마련되었습니다. BIS 규제는 금융기관이 안정성을 유지하는 데 필수적인
In most countries, the government sector isn’t the first place people look for technological innovation or the rapid adoption of a proven technology. However, governments everywhere are increasingly under pressure to be more productive and to get better value for taxpayers’ money. Many private sector organizations are looking to AI
I don’t know about you, but it feels like the year has gone by in a blink – it’s hard to believe we’re already talking 2025 predictions and holiday plans! The year zoomed by so quickly that you might have missed some of our favorite stories of 2024. As you’re
「金のなる木」という植物があるが、意外にも花が咲くことをご存じだろうか。実は、11月から晩秋から冬にかけて、白や淡いピンクの可憐な花が咲くのだ。もちろん、品種や育て方によって差はあるが、株が大きく成長し、日照や水やりに気を配ることが大切な条件となる。もちろん一定の寒さに当てることも欠かせない。花が咲くと、「幸運を招く」「富をもたらす」「一攫千金」など、縁起が良いとされている。ちなみに、英名は「dollar plant」、まさに金のなる木である。 ところで、マーケティングの世界では、相対的市場シェアと市場成長率を基に商品や事業を4つのカテゴリー、「金のなる木」「問題児」「花形」「負け犬」に分類して分析する手法がある（プロダクトポートフォリオ）。この手法は、ボストン・コンサルティング・グループ（BCG）が開発した「BCGマトリクス」として知られており、例えば、マーケットシェアと市場成長率が高いものは「花形」、成長は高くないがシェアが高い、つまり収益性の高いものは「金のなる木」と分類される。商品戦略としては、取捨選択を行い、負け犬の事業や商品からは力を抜き、金のなる木に力を入れる、といった具合となる。 さて、SASでは様々なトレーニングメニュー（コース詳細とスケジュール）が提供されており、SASプログラミングの初級・中級コースやSAS Enterprise Guideの操作入門、統計初級コースは「金のなる木」に当たり、特に人気が高いため、受講を検討してみてはいかがだろうか。一方で、SASでは分析基礎トレーニングやデータサイエンティスト超入門講座なども提供されており、論理的思考やロジカルシンキング、データ分析のスキルを磨きたい方は、ぜひお問い合わせいただければ幸いである。 2024年12月初旬 相吉
To stay ahead, organizations must thrive rather than compete. Demand forecasting is one of the most critical tools in this pursuit. Organizations that excel at demand forecasting have a clear edge, whether anticipating customer needs or managing supply chain disruptions. By predicting what customers want and when they’ll want it, companies can
Decades ago, it was a challenge to generate (pseudo-) random numbers that had good statistical properties. The proliferation of desktop computers in the 1980s and '90s led to many advances in computational mathematics, including better ways to generate pseudorandom variates from a wide range of probability distributions. (For brevity, I
대한민국을 포함한 아시아태평양 지역의 데이터 및 AI 성숙도는 어느 정도일까요? ChatGPT 등장 이후 AI에 대한 관심이 급격히 높아지면서 많은 기업들이 AI 및 생성형 AI의 활용과 적용에 적극 나서고 있습니다. SAS는 최근 IDC에 의뢰해 기업의 AI 투자와 해결과제, 향후 계획에 대한 흥미로운 연구를 진행했습니다. 그 결과를 통해 AI 선도기업이 되기 위한
SoDA를 이용해 쉽게 배우는 데이터 과학 #3 지난 포스팅에서는 SoDA의 서비스 가입 방법을 알아보았습니다. SoDA는 클라우드 환경을 이용하기 때문에 따로 설치할 필요가 없었고, 클라우드 할당을 위한 서비스 가입이 필요했습니다. 이번에는 SoDA 사용 환경인 SAS Studio의 다양한 구성을 살펴보도록 하겠습니다. SoDA는 SAS Studio를 통해 사용할 수 있습니다. SAS Studio는 웹 브라우저로
The article "Order two-dimensional vectors by using angles" shows how to re-order a set of 2-D vectors by their angles. Because angles are on a circle, which has no beginning and no end, you must specify which vector will appear first in the list. The previous article finds the largest
