Matthew K Temba

𝐃𝐚𝐭𝐚 𝐬𝐨𝐮𝐫𝐜𝐞 𝐭𝐫𝐢𝐚𝐠𝐢𝐧𝐠 - Just as patients in an ER need to be triaged to prioritize care and stabilize those in need, data science demands a similar triage approach. Not all data sources are created equal, and some might require substantial cleaning, analysis and transformations before they're usable. The 80/20 rule of data triaging means we are going to quickly determine whether a data set will be useful by examining some key factors. ●     First is Availability: Is the data public? Is it behind a paywall? Do you need special permissions and are there security concerns? Knowing major logistics barriers can prevent chasing a dead end. ●     Second is Costs: Data can be surprisingly expensive. Are there usage fees? Storage costs? Will you need to invest in new software to process it? ●     Third is Utility: Does the data actually contain the information you need? Beware of proxies - just because it's related to your topic doesn't mean it's the right fit. ●     Fourth is Frequency of Updates: If you're predicting a real-time outcome, then stale, annually updated data probably won't cut it. Find data with a time resolution and update frequency that aligns with your problem. ●     Fifth is Geographic Resolution: Studying zip code level sales trends? Nationwide data won't help. Make sure the granularity of the data matches your scope.   I always find it is useful to obtain a quick sample of the data. This quick look can often reveal formatting issues, missing values, and whether it's worth a deeper dive. Data triage is about making tough calls. Perfectly clean, well-aligned data is the unicorn of our field. Be prepared to say "no" to a source that looks initially promising but will take an inordinate amount of time to fix for minimal gain. Being resourceful is key! Don't be afraid to ask colleagues, search online forums, and get creative. Sometimes a great data source is hiding in plain sight. #data #datascience #datasources

8

These data science podcasts are fantastic, keep up the good work Bill Franks! In this episode my friend & TAG Data Governance Society Board Member Nathan Ghadirifard provides perspectives on healthcare analytics. #KSU📚 #GoOwls🦉#AI🧨 #VicianaData🔥

3

1 Comment

Why is data fluency important? Every day frontline teams use information to provide great services to patients and clients. Managers need data to make good decisions and ensure the delivery of consistent, high-quality care. The executive rely on intelligence to help drive the business in a sustainable and successful direction. In order to get the most from our data, it’s important that it’s presented in a way that individual roles can understand and find useful. The best outputs/data products are co-designed with end users. Bringing together analytics capability with business expertise. This approach helps improve data literacy through exploring hypotheses, testing materiality and ultimately questioning- “what will we do with this information?”. Analysts learn the nuances of various roles and processes and can help users understand how different types of measurements or analysis can help drive an outcome. I have seen prolific outputs by analysts that are for analysts. Times are changing - most roles now include an element of knowledge work. As data leaders we play a key role in ensuring that the right information is available at the right time, right place and most importantly that it can be used and understood.

35

2 Comments

Here is the latest piece in the IIA Accelerating Your Data Innovation Journey (AYDIJ) series. In this piece, we shift focus from the hospital to how research informatics is powering the ecosystem of care. I want to express gratitude to Phil for sharing his wealth of knowedge and experience. This is an excellent piece, and I am sure you will enjoy it. #AYDIJ #datainnovation #healthcareanaltyics #researchanalytics https://lnkd.in/gUz44ezb

27

🙏 Please excuse the 3-slice pie chart.   🤔 Now, are we saying Analytics aren't important? No.   📘 But this chart, from an article which is essentially the basis of the book You Are About to Make a Terrible Mistake, shows why decision-making deserves attention - a lot of attention.   (🔗Links in comments.)   To paraphrase the concluding text around this graph: ✔ Process mattered more than analysis—by a factor of SIX ✔ Almost no decisions surviving a strong process were backed by weak analysis ✔ Superb analysis cannot survive a dysfunctional decision-making process   So analytics still matter. They are critical to good decisions.   But bad decisions can still be made with good analytics.   If a "data-driven decision" only means that you looked at a graph and then "went with your gut", well, if you're still employed, you’re currently enjoying a finite streak of luck.   Good decisions require: ✔ diversity in the backgrounds of team members (domain/paradigm diversity matters, unfortunately demographic diversity doesn't) ✔ processes to circumvent or overcome cognitive biases ✔ a work culture of trust ✔ leadership with ego strong enough not taking dissent personally   ❓ What can we do as analysts?   Let's start by modeling good decision-making in our own teams.   🏗→🧠 Build to Learn!   💭🚶‍♀️🚶‍♂️ Follow for more.   #tableau #data #analytics #VizoftheRay

9

4 Comments

The great myth of analytics is that there is some utopian future of self-service BI products that will collectively solve every business problem. And it's always just one dashboard away: "We're so swamped in ad hocs now, but after we finish this dashboard, it will free up so much time!" ...so much time for what? 🤔 Somewhere along the line, "ad hoc" gained a negative connotation. But is the future of a gazillion dashboards even one we want to live in? And how well do those gazillion dashboards answer the most valuable business questions? Some dashboards are super valuable, undeniably. The other 80% might be us forcing BI onto an ad hoc. 💡 Ad hocs are never going away no matter how much BI you build. And that's a good thing, because ad hocs often answer the most pressing and most valuable questions the business has. #analytics #data #BI

38

8 Comments