However, the complexity of defining skill levels in Excel shouldn’t deter us from trying, much like George Box’s observation that all models are wrong, but some are useful.

In many fields—whether it’s martial arts, language learning, or cooking—skill levels are traditionally categorized into stages like beginner, intermediate, and advanced. This classification helps learners assess their current capabilities and provides a structured pathway for progression.

The world of Microsoft Excel is no exception. Distinguishing between beginner, intermediate, and advanced skills allows both users and educators to foster a learning environment that effectively addresses diverse levels of expertise.

The benefits of classifying Excel skill levels

I believe the reluctance to classify Excel skills stems from a well-intentioned desire for inclusivity. People aim to avoid gatekeeping and promote equality.

In the short term, it’s certainly beneficial to meet learners where they are and celebrate their immediate successes. However, in the long term, having clearly defined skill levels is extremely important. It serves as a crucial milestone marker, helping individuals understand their current abilities and identify the areas they need to improve. This classification is vital for several reasons:

1. Guided learning paths: It provides learners with a roadmap for acquiring new skills in a logical sequence. Beginners aren’t overwhelmed by advanced concepts, while more experienced users can bypass basic topics and focus on areas that challenge them.
2. Skill reinforcement: While it’s possible to be an expert in one area of Excel—like data visualization—without being proficient in others—like advanced formulas—the skills in Excel are often interconnected. Improving in one area can enhance your understanding and capabilities in another. This interconnectedness ensures that as you advance in one aspect, you inherently boost your overall Excel proficiency.
3. Benchmarking and goal setting: Categorizing skills helps users set realistic goals and employers assess proficiency levels. It can guide training requirements and help in personal and professional development planning.

What constitutes beginner, intermediate, and advanced Excel skills?

Now, this is where the gloves come off. I will attempt to define what typically falls under each category. Remember, these classifications are not rigid; they are starting points designed to frame your learning journey in Excel.

This sets the ball rolling. Each person’s needs and experiences with Excel will differ, but by outlining this path, we establish a clear set of assumptions to work from, just like any other written plan or model.

Beginner skills

At the beginner level, you should be comfortable with the basic functionalities of Excel.

• Creating and formatting spreadsheets
• Basic calculations and operations like SUM(), AVERAGE(), MIN(), MAX()
• Understanding how to insert charts and perform simple data visualizations
• Basic data management: entering data, sorting, and basic filtering

In other words, you can create a basic workbook, although it might lack user-friendly features and reusability. It’s generally manual and static.

Intermediate Skills

Intermediate users delve deeper into Excel’s capabilities:

• More complex formulas and functions like VLOOKUP(), XLOOKUP(), and conditional functions (IF(), SUMIF())
• Data analysis tools like PivotTables, conditional formatting, and more sophisticated charting options
• Using named ranges and tables
• Utilizing tools like Scenario Manager, Data Tables, and Goal Seek to explore different outcomes based on varying inputs
• Creating charts that combine two or more chart types (like a line and column chart) to visualize different types of data on the same graph.
• Recording simple macros to automate repetitive tasks, and introducing basic Visual Basic for Applications (VBA) to enhance capabilities
• Using Power Query to perform a range of transformations such as filtering, sorting, merging queries, appending data, and grouping rows
• Building data models by importing tables and creating relationships between them.

Now, even as I write this, I feel somewhat like the proverbial monkey with a dartboard. Historically, proficiency in VLOOKUP() and PivotTables was deemed to me essential for someone to be considered an intermediate Excel user. However, with the introduction of XLOOKUP(), which is poised to replace VLOOKUP(), we face a conundrum, as many organizations are slow to adopt new functions.

Additionally, intermediate users should arguably be familiar with Power Query and Power Pivot. Should this new knowledge come at the expense of traditional skills like conditional formatting and IF() statements? Probably not. Consequently, the expanding scope of the program indeed complicates the classification of skill levels.

Advanced Skills

At this point, you have mastered the basic rules of the road and can develop any Excel solution you please! This is where things can get complicated, as there are so many directions to explore. However, just because there are a million pieces to play on the guitar, it doesn’t mean we can’t recognize both Jimi Hendrix and Andres Segovia as expert guitar players.

• Complex formulas and array functions.
• Automation with VBA scripts to streamline repetitive tasks and custom functions.
• Integration with other data sources and advanced data visualization tools.
• Advanced Power Query techniques, such as custom columns and error handling.
• Developing and optimizing Data Models using Power Pivot, including the use of complex DAX formulas for calculated columns and measures.
• Creating interactive dashboards and reports using slicers, timeline controls, and advanced charting techniques.
• Utilizing VBA for developing user forms, handling events, and interacting with other applications like Outlook and Word.

Embracing the Model

While there might be disagreements on the specifics—after all, not everyone uses Excel in the same way—these levels provide a useful framework for discussion and learning. By establishing a common language to describe Excel proficiency, educators can better design curricula, employers can more accurately assess skills for job roles, and users can set clearer goals for their learning journey.

Ultimately, models like this simplify the complex world of Excel. They trade real-world messiness for clarity and direction in learning and development. Whether you’re just starting out or looking to refine your advanced skills, understanding where you stand on the Excel mastery scale is the first step in leveraging Excel more effectively in both personal and professional endeavors.

What do you think about the distinctions between beginner, intermediate, and advanced Excel users? Are they helpful, or not? What do you think of my skill rankings—would you approach it significantly differently, or is this at least a good place to start? Let me know in the comments.

The post How to understand the difference between beginner, intermediate, and advanced Excel first appeared on Stringfest Analytics.

Fast forward to the present, and it’s a challenge to find a professional who hasn’t heard of LinkedIn Learning. Remarkably, access to this resource is now available to anyone with a library card in Ohio, extending well beyond the confines of graduate school.

Reflecting on those days, I perceived becoming a LinkedIn Learning instructor as a significant milestone in tech authorship, akin to being an author for O’Reilly. It signifies a deep understanding of one’s field, coupled with the rare ability to distill complex technical knowledge into forms easily comprehensible to a broader audience.

For me, the role of a LinkedIn Instructor carried a certain prestige, and I believe it resonates similarly with others. This post aims to shed more light on the process of becoming an instructor. As it was written mostly spontaneously, I welcome any questions and will be more than happy to update the post to the best of my ability.

How to get started

At LinkedIn Learning, like with most content shops, there are professionals whose primary role is to scout and recruit the right talent for instructional positions. These individuals are not typically referred to as recruiters, but rather as acquisitions editors or content managers in the content and media industry.

Like a traditional recruiter, there are a couple of methods to connect with these figures. You have the option to proactively reach out to them, or alternatively, you can wait for them to initiate contact.

However, if you’re eagerly aspiring to become a LinkedIn instructor, relying on the possibility of being approached by a content manager might not be the most appealing strategy. This situation is not unique to you; many others are vying for similar opportunities. Given the high-profile nature of these positions, the competition is notably fierce.

To distinguish yourself from the multitude, it’s crucial to demonstrate a track record of clear and effective instruction. This might involve, for better or worse, initially providing your content for free. Engage in activities such as speaking at meetups, hosting webinars, or creating YouTube videos. Since the role involves on-screen teaching, it’s important to establish yourself as a confident and competent speaker in this medium.

Further enhancing your visibility involves carving out a niche. Whether it’s positioning yourself as an expert in teaching a specific tool to professionals familiar with a competing product, or focusing on a particular aspect of your professional field that could benefit from AI and machine learning, it’s vital to be recognized as an effective educator in your chosen area. My personal experience exemplifies this approach; my courses on AI for Excel largely stemmed from conducting free webinars on the same topic.

It’s important to note that providing content for free, with only a slim chance of being noticed by an acquisitions editor, can be disheartening. If you are actively engaged in this kind of work, I recommend directly reaching out to the editor. Additionally, seeking guidance from someone experienced in building a content and authority business can be immensely beneficial. This aspect of building authority is particularly crucial if you are considering self-employment. For those interested, I offer coaching services in this area, which I will link to at the bottom of this page.

What the process looks like

In the realm of LinkedIn Learning, high-level expectations primarily involve being the master of your content. While the intricate operational details are LinkedIn’s bread and butter, understanding the general process and terminology can greatly enhance your comfort, confidence, and relatability in this environment.

Initially, you’ll collaborate with a content manager to develop a comprehensive outline for your course. This includes creating a table of contents, identifying the target audience, and other preparatory steps. Crafting this blueprint not only guides your course planning but also provides the content manager with a clear overview of your course’s trajectory, keeping in mind that it’s one among many in production.

A common and crucial topic that arises early in the process is compensation. This aspect varies greatly and depends on multiple factors. My advice is to view the compensation from such a project as a stepping stone towards future opportunities, rather than a one-time financial gain. It’s essential to align it with your overall portfolio and long-term goals. While some may seek quick financial returns, a more strategic approach is to treat this opportunity as an investment that yields value over time.

Once your course outline is approved, you’ll work with a production editor who will assist you through the course’s development. This involves scriptwriting, creating slides, reviewing files, and other preparatory tasks before recording.

Scriptwriting can be a personal choice; some prefer working off an outline, while others, like myself, require a script to avoid tangents and maintain focus. It’s important to know which method works best for you.

There’s a plethora of advice and theories on producing high-quality video content, but the best practice is experience and developing your unique methods, style, and voice.

In today’s A/V-friendly world, many online learning platforms, including LinkedIn, offer the flexibility of working from home while achieving studio-quality sound. They may even provide professional gear for this purpose. Alternatively, LinkedIn and other platforms also offer the option to record in their state-of-the-art studios, often located in California, which can be an attractive aspect of the job.

Preparing for your recording

Indeed, the recording phase is the critical juncture where your content comes to life and becomes a medium for learning. It’s the stage where preparation is key.

To ensure a smooth recording experience, it’s essential to be thoroughly familiar with your script. This means practicing it extensively, understanding every aspect of it, not just memorizing the words but grasping the flow and the nuances. Being well-prepared with your material is crucial because the recording environment can be quite different from your usual workspace.

When you step into the recording booth, be prepared for elements that might be out of your ordinary routine. Bright studio lights, the experience of having gone through hair and makeup, and wearing clothes that are more formal than your daily wear can all contribute to a sense of discomfort or nervousness. These are not just physical changes but can also impact your mental state.

To navigate these challenges, patience and professionalism are vital. They stem from confidence in your knowledge and preparedness. When you know your material inside out, you can more easily adapt to the unexpected and maintain your composure, even if something throws you off balance. Remember, the more comfortable and confident you are with your content, the more effectively you can communicate it to your viewers.

While recording

Recording even a simple screenshare video can be fraught with challenges. Issues such as poor or non-existent audio, sharing the incorrect screen, or encountering corrupted files can arise unexpectedly.

Now, consider these challenges in the context of a professional studio, replete with a range of processes, cameras, and teleprompters. The task of recording a mere two-minute video could necessitate over an hour of preparation, including audio tests, video checks, and hair and makeup. It’s important to remain patient and understand that neither you nor the studio is at fault.

Generally, it’s best to approach this process calmly and avoid feeling overwhelmed. Remember, your production editor is experienced and will support you throughout this journey. They have allocated ample time for you to complete your tasks.

However, if you find yourself in a flow state, feel free to embrace it! Should this mean taking a late lunch because you’re engrossed in your work, rest assured, your editor will be understanding. It’s crucial to do what feels right for you.

In the studio, you’ll enter the booth to record your tutorials, including walking through your slides and demonstrations. While it’s important to aim for a high-level synchronization between your demonstrations and your script, avoid overdoing it. The studio’s post-production team is skilled in editing and will handle the finer details, ensuring everything comes together seamlessly.

After recording

After you’ve completed recording and returned home, it will take a few weeks for your course to be fully produced and published on LinkedIn Learning’s platform. Your editor will provide a launch date, and you will also receive an automatic email notification when the course goes live.

Promoting your course actively is essential. It’s a common misconception that your content will naturally attract viewers just by being available. Instead, it’s important to start sharing your content early and often. Keep in mind that only a fraction of your social media followers will see each of your posts, so don’t shy away from reposting and repurposing your content. LinkedIn offers a helpful feature for increasing visibility: you can share a special link to your course that allows anyone to view it for free, which not only boosts your visibility but also helps establish you as an expert within your network.

Remember, making sure your audience knows about your course is crucial for its success.

Congratulations are in order – you’re now a LinkedIn author!

These were some quick thoughts on the process, along with potential questions you might have. Please feel free to reach out if you have more inquiries! I’ll also include a link to my coaching services below. If you’re considering a career in analytics as a freelancer, this could be an excellent opportunity to establish your authority and master content marketing.

The post What it’s like to be a LinkedIn Learning instructor first appeared on Stringfest Analytics.

Just as a writer cannot craft a compelling story without a strong grasp of language basics, professionals in data analytics and programming cannot rely solely on AI tools without understanding the core principles of their domain.

The enduring relevance of 'hello, world'

The concept of 'hello, world' – the simplest program in any programming language – remains a vital starting point for learning. This basic exercise isn’t just about writing a line of code; it represents the learner’s introduction to the fundamental concepts of programming languages, logic, and computational thinking.

Similarly, in data analytics, understanding the basics – such as statistical theories, data collection, cleaning processes, and visualization – forms the foundation upon which all further learning and application is built. This foundational knowledge is crucial for interpreting the results generated by AI tools and for understanding the limitations and biases that might be inherent in automated processes.

Generative AI has the potential to greatly enhance the learning and application of data analytics by automating repetitive tasks and generating complex data models. However, it should be seen as a tool that complements human skills rather than replaces them. The ability to critically analyze AI-generated outcomes, debug issues, and tailor solutions to specific needs remains a distinctly human domain.

AI can provide suggestions and insights based on vast data sets, but the final interpretation and decision-making lie with the human analyst, who must understand the foundational principles to make informed judgments.

The evolution of analytics training (or not)

The rise of generative AI is changing the way training is delivered in data analytics. Traditional classroom settings are being complemented by AI-driven tools that offer personalized learning experiences and simulate real-world scenarios. These tools can adapt to individual learning styles and provide immediate feedback, enhancing the learning process. However, they do not replace the need for a structured approach to learning the basics of data analytics. The understanding of fundamental concepts ensures that learners can effectively use AI tools, contribute to data-driven decision-making, and understand the ethical implications of their work.

Despite the advantages of AI in training delivery, the traditional ‘sage on the stage’ approach continues to hold significant value. In a classroom or workshop setting, learners benefit from the experience and insights of expert instructors who can provide context, clarify complex concepts, and share real-world applications.

The interactive nature of these environments encourages discussion, fosters collaboration, and helps build a community of learners. This aspect of communal learning is particularly important in data analytics, where ideas and solutions often emerge from collaborative efforts.

Traditional training environments often provide structured learning paths that ensure a comprehensive understanding of all necessary topics. This structure is especially beneficial in a complex field like data analytics, where a sequential understanding of concepts is essential for effective application.

Additionally, the accountability and motivation inherent in attending classes, completing labs, and participating in projects and hackathons drive deeper engagement with the material, which is crucial for developing a thorough understanding of data analytics.

AI and analytics democratization

The widespread availability of AI-driven analytics tools is leading to a democratization of data analytics within organizations. Where once data analysis might have been the domain of a few specialized individuals, it is now becoming an essential skill for a much broader range of roles. This shift requires a corresponding emphasis on basic analytics training for all employees.

With more individuals gaining access to tools that can build, interpret, and understand models, the need for foundational knowledge in data quality, bias recognition, and analytical intuition becomes more critical. These skills are essential for ensuring that the insights derived from data are accurate, relevant, and ethically sound.

As AI augments the capabilities in data analytics, organizations must focus on building a data-literate workforce. This means not only equipping employees with the skills to use AI tools effectively but also ensuring they have a solid understanding of the basic principles of data analytics. This foundational knowledge is essential for making informed decisions, contributing to data-driven strategies, and responsibly managing and interpreting data.

Conclusion

As we continue to explore the evolving landscape of data analytics in the age of AI, it’s crucial to consider how basic analytics training is adapting to these changes. How is your organization integrating foundational data analytics training with the advancements in AI? What challenges and opportunities do you foresee as data analytics becomes more democratized? Let’s talk in the comments.

The post The rise of AI means more analytics training, not less first appeared on Stringfest Analytics.

Before this experience, I was skeptical of the market. I thought only a traditional academic institution could offer a worthwhile program.

But now, I openly support the bootcamp space and encourage younger professionals to consider enrolling in them. Universities still have their place (I will dicuss this in a later post)… but so do bootcamps.

The common objections to coding bootcamps range from the misguided to the misinformed. I will bust some common myths below, but if you have other concerns/hesitations about the bootcamp space, let’s discuss them in the comments.

Some disclaimers: I am not an industry expert and am speaking largely from my experience, which is with the data programs of one particular bootcamp. That said, the positive experience I’ve had is backed up by solid career outcomes and grad placements.

“You don’t know who is writing the curriculum”

This is a frequent charge: that the instructional assets for the bootcamp could have been written by any old hack.

I think what this is really getting at is that the quality of the instructional material may be subpar or unpredictable, and there is not the normal transparency of authoring as with many media.

While I do think that bootcamps could do a better job in signalling the merit of their instructional assets, I do not see how this matter for the students or the outcomes.

What are the alternatives for getting instructional material these days? You could go to a textbook, which undergoes a rigorous vetting and review process, but those are expensive and often written unapproachably.

So, how about a blog or YouTube channel? Those can quite honestly be better than most textbooks, but guess what? Anyone can author those assets, too! So why is this a deal-breaker for where bootcamps source their content?

Once we parse the real objection behind “Anyone can write the material,” it’s easy to bust this myth.

“They don’t have educational backgrounds”

This one may be easier to bust than the last one!

The idea here is that the authors and educators may not be any good, since they don’t go through the rigorous vetting process of academics.

Yawn.

Guess what? By and large, academics don’t give a damn about teaching. It is a nuisance to them which distracts from their research.

And when academics do get dragged into teaching (Hey, the school has to keep the lights on somehow!), it’s not like they’ve been trained for it!

There are lots of ways to be good at teaching, and academic experience isn’t a guaranteed one. With the internet, anyone can learn how to teach well, and practice.

So, this is another objection that doesn’t stand up.

“I could just learn it myself”

This objection is harder to take down, because it could be true. It is indeed possible to be a totally self-taught data analyst or data scientist. But I wouldn’t recommend it. Why?

One of the best ways to learn is to make it social. A good bootcamp will give you a podium to work through ideas with mentors, educators and other studetns. This also has the benefit of building a network, which is needed to get hired.

So, this one isn’t so much untrue as it is overlooking the benefits of not going it alone.

So what are the downsides?

It wouldn’t be fair in an article like this not to mention the downsides of a coding bootcamp.

Bootcamps are designed to help candidates get their foot in the door of an industry. And for that, the track records are good, and getting better.

I am less optimistic that a bootcamp education can help candidates keep their foot in the door. Bootcamps are effectively vocational training, which I have no objection to.

But in a rapidly evolving economy, vocational training may not be enough. I believe that professionals are best served to weather their careers with the depth and breadth granted by a liberal arts education. If that sounds nuts, check out my post on creating the future with the liberal arts.

Bootcamps on balance..

But the thing about a liberal arts education is it doesn’t get your foot in the door. So, back to the bootcamp. (See what I mean about bootcamps and traditional learning institutions each having a role to play?)

Every program has its costs and benefits. At least with a bootcamp, you won’t need to uproot your career and way of life to do it. And, upon closer inspection, many of the dissimilarities to traditional education aren’t such downsides after all.

Yes, bootcamps have a way to go, and I’ve heard some stories that would probably change my tune about them if they’d happened to me as well.

That said, if there were nearly as much scrutiny toward colleges and universities as there is toward coding bootcamps, then the bootcamps may be the shining beacons.

So, have I convinced you? What else causes you concern about bootcamps? Or maybe you’ve bought in and want to share your reasoning or experiences? Let’s discuss.

The post Busting the myths about data bootcamps first appeared on Stringfest Analytics.

Now, I’m by no means a trained instructional designer or learning theorist, and like many academic pursuits I think that the fluff/nugget ratio is pretty high in these fields. But I have spent enough time adjacent to them that I’ve been able to identify those nuggets and incorporate useful learning theories into Advancing into Analytics.

What this means in theory (pun intended) is that Advancing into Analytics is written for you to learn and retain the most knowledge possible, without having to work too hard at it.

Here are some of the topics and techniques I used to do that. I especially rely on Make it Stick: The Science of Successful Learning by Peter C. Brown et al. and Powerful Teaching: Unleash the Science of Learning by Pooja K. Agarwal and Patrica M. Bain for making it happen.

Transfer learning

Learning happens by relating new knowledge to existing knowledge. Transfer learning is the practice of explicitly making this connection part of the learning.

I’ve said it before and I’ll say it again: Excel kicks off a great learning path to more advanced analytics. Spreadsheet users know from experience the main operations and tasks of data cleaning and analysis. Technical elites too often sneer at spreadsheets, and attempt to write their audience’s knowledge about data to zero, so they can start from a “purer” approach. Talk about negative yardage!

In my book, I instead directly relate Excel knowledge to broader analytics equivalents:

• What does the VLOOKUP() tell us about database joins?
• How do you recreate Excel’s Custom Sort menu in R?
• How to the Rows and Values areas of a PivotTable relate to grouping and aggregrating fields in Python?

Active Recall

Have you ever read and re-read a book, thinking you’ve nailed the content, only to find that you can’t remember any of it when tested? Maybe you even used a highlighter and sticky notes, but to no avail.

The issue with learning this way is that it focuses purely on the consumption of material and not its implementation. To really master a subject, you need to actively apply it to new material. As Pooja K. Agarwal and Patricia M. Bain write in Powerful Teaching: “One of the best ways to make sure something sticks and get stored is to focus on the retrieval stage, not the encoding stage.”

Now, I’ll admit that I tend to skip end-of-chapter book exercises. They’re usually dull (literal) textbook exercises, and it can be hard to find the solutions anyway. Why not just continue reading and keep the book’s momentum going? I’ve noticed that many technical authors don’t even include book exercises, likely for these reasons (and because, let’s be honest, exercises take more work).

I provide exercises for nearly all chapters of Advancing into Analytics, using real-life datasets to practice data exploration and hypothesis testing in Excel, Python and R. What’s more all exercise solutions are conveniently available in the book’s public GitHub repository. If you read the book, please do these exercises. It’s how you’ll remember the content.

Interleaving

As my business’s name might attest, I am a (mostly erstwhile) musician. Of the many lessons learned from music is the power of interleaving.

It’s tempting to practice a piece from start to end each time, but that’s not so effective. The problem is that gaps may form in the music covered (i.e., you may only practice the beginning of a piece, or your favorite or easiest parts). You can easily fall into a slump when you know what order to expect each time you practice.

A better approach is to mix it up. Pick a random part of a piece and start playing and re-playing. Try sections out-of-order or even backwards. Add some variety to the way in which you practice.

Learning often follows a blocked approach, where one topic is studied very thoroughly before moving onto the next, often in the same order. By contrast, interleaving mixes topics in a spaced, often varying, order.

Advancing into Analytics is arranged into three sections: first, the statistical foundations of analytics are demonstrated in Excel. The reader then learns analytics in R and later Python.

Rather than treat these topics as three disconnected parts, I interleave related concepts among them. For example, readers will recreate the same analysis of a dataset using all three applications. Statistical and data cleaning know-how is introduced and re-introduced in different contexts, so that we’ll conceptualize a data table in Excel, then build it in R and Python.

Now, if you’re thinking that this is how knowledge usually works in reality anyway… well, you’re probably right. Learning tends to be iterative and incremental, and there’s no clean break between mastering one topic and getting started in another. Traditional education isn’t always modeled this way, but Advancing into Analytics is. It’s just not possible to master hypothesis testing, for example, in a single chapter, so you’ll see the topic appear in different contexts throughout the book.

Learn analytics fast

Getting into analytics isn’t easy. In many cases, it literally requires learning a new language (of the programming variety). You’ve got enough on your plate: a battle of wits with a technically gifted but pedagogically unaware author shouldn’t be there.

In Advancing into Analytics, you’ll learn not one but two programming languages. Not only that, you’ll discover hypothesis testing, data wrangling, even a smidge of what could be called machine learning, all in 250 pages. This is possible with the help of learning theory. I hope the book can serve as the straightest path to analytics out there.

Learn more about Advancing into Analytics: From Excel to Python and R

The post The learning theories behind Advancing into Analytics first appeared on Stringfest Analytics.

In that spirit, this post answers frequently-asked questions about my O’Reilly Media book, Advancing into Analytics: From Excel to Python and R:

Why did you write the book?

Good question! I actually wrote a whole blog post answering this. That post expands on five reasons, which are:

1. To help “past me”
2. To provide a clear learning path
3. To properly situate analytics tools
4. To properly situate analytics techniques
5. To curate my best material

To learn more, check out the original post.

What is the objective of the book?

Reading a technical book is not a light commitment, so I want to provide readers a guarantee about what they’ll get out of Advancing into Analytics. The book’s learning objective, from the Preface, is as follows:

By the end of this book, you should be able to conduct exploratory data analysis and hypothesis testing using a programming language.

Who is this book written for?

This book is written for people who primarily interact with data using spreadsheets (namely, Excel) and would like to learn more advanced data analysis techniques. The Excel audience is huge, but there’s not much content on how they can embrace a fuller data analytics stack by picking up not just tools like Python and R, but conceptual techniques like exploratory data analysis and hypothesis testing.

I think a lot of this has to do with a grudge against Excel from the technical elites, which is such a missed opportunity for them to teach and spreadsheet users to learn. I hope this book can fill that market gap.

Are there any prerequisites?

It sounds ambitious to guarantee a reader will learn to code in R, and Python, and learn statistical techniques like exploratory data analysis and hypothesis testing in a 250-page book.

But knowledge of Excel offers a massive head start in getting into analytics. That said, I do ask the reader to come to the book with some intermediate knowledge of Excel:

• Absolute, relative, and mixed cell references
• Conditional logic and conditional aggregation (IF() statements, SUMIF()/
  SUMIFS(), and so forth)
• Combining data sources (VLOOKUP(), INDEX()/MATCH(), and so forth)
• Sorting, filtering, and aggregating data with PivotTables
• Basic plotting (bar charts, line charts, and so forth)

If you would like more practice with these topics before getting started, I suggest Excel 2019 Bible by Michael Alexander et al. (Wiley). With this foundation assumed, I can help you “pivot” readers’ existing skills into statistics, programming, and related topics.

What’s with the bird on the cover?

(This may in fact be the most common question.)

First of all, animal illustrations on covers are O’Reilly’s thing for reasons explained at this post. My book follows in a great tradition in particular of bird covers: this one the Clark’s Nutcracker (named, in fact, after William Clark of Lewis & Clark fame).

This bird, which is native to the Rocky Mountains, is known for burrowing away thousands of pine seeds. It also has a penchant for being bold around humans and is known as a “camp robber” for stealing food.

I don’t know how much of this was intentional by the illustrator, but the analogies between this bird and the book’s topic is worth blogging about, so stay tuned.

Why do you teach both R and Python?

One common surprise or objection to the book is that it covers both R and Python. I had originally planned just to cover the former in this book, but the editors asked for the latter as well. In retrospect, it turned out well: there was plenty of real estate in the book’s 250 pages to teach both.

Readers are also well-served to know both languages: on a pragmatic level, they’re covering their bases in response to varying work needs. But it’s not just ticking a box: each language has its own unique features, and it’s becoming increasingly common to combine them in building data products, as this upcoming O’Reilly book documents.

Why do you even teach R or Python?

Now, the title of this book is Advancing into Analytics, but R and Python are often usually seen more as data science tools than data analytics. In a world of Power BI, Tableau, and other self-service BI tools, why would an analytics book cover R or Python, let alone both?

I openly admit in the book that some data analysts get away without R or Python in their toolkit. At the same time, data analysts need some familiarity with statistical modeling, and I find these tools the most conducive for doing it.

But it’s not just for statistics — learning to code is a great skill to have, not just as a data analyst but as a modern professional. I know we keep hearing about these low- and no-code tools which use AI and other technology to lower technical barriers, but I remain skeptical — at least in the analytics space.

At the same time, BI tools are increasingly designed to work with rather than instead of statistical programming software. For example, you can use Python in Power BI to manipulate and visualize data, as well as build predictive models.

So I don’t see these skills as superfluous or soon-to-be-obsolete for data analysts.

Where can I get the book?

The book is available in both paperback and digital versions at most major booksellers, as well as O’Reilly Media’s Online Learning subscription platform. Learn more about how to access the book here.

How can I support the book?

Well, I don’t know this is an FAQ , but if you are so inclined to spread the message of the book, I offer five ways to support Advancing into Analytics without even buying it:

1. Order it from your library
2. Promote it synchronosly
3. Promote it asynchronously
4. Leave a review
5. Subscribe to my newsletter

To get the specifics, head to the post.

Did I miss a question?

These are the questions I’ve heard repeatedly so far, but do you have others? You’ll need two of your friends for me to write it here, in the spirit of my Law of Content Marketing… just kidding. Please, ask away in the comments, or by contacting me directly.

I look forward to sharing this book with the community.

Advancing into Analytics is now available.

The post Advancing into Analytics: FAQ’s about the book first appeared on Stringfest Analytics.

Enrollment in the academy is a good time to take stock of candidate skills: after all, the nature of the education depends on the current skill levels of its students. So, what are some ways to assess the data skills of your candidates in relation to what your organization needs?

Quantifying data skills

This is data education, right? So of course we would have some quantitative measures of candidate skills! While you’ll see that there are other ways to assess skills, this is one is easy to implement and can signal what immediate payoffs might result from your academy.

Self-rating

Here you ask students to self-rate their abilities on a Likert scale, something liks this:

Rate your Excel skills on a scale of 1 to 5.

This type of assessment may seem pretty ridiculously simple. But there is actually a lot of interesting math you can do with this data, as you will learn if you check out my DataCamp course on survey development in R.

In that course, you will learn that it while it’s pretty easy to collect this type of data, it takes effort to build them in a way that tells us much.

Rating your Excel skills on a scale of 1 to 5 could mean lots of different things to different people. To some, a “5” means nesting an IF() statement, while to others it means building an animated dashboard.

On top of that, some may under- or over-estimate their ratings to be in line with what they perceive to be more acceptable to their employer, co-workers or test proctor: so-called ‘social-desirability bias.’

While self-ratings of this nature have a place in skills assessments, let’s not end there.

Time estimates 

Not to be too crass, but time is money, right?

In the face of rapid automation and workforce displacement, both employers and employees ought to think about where poor data workflows are leading to lost productivity.

To get a sense of how bad the problem is, a question like this may be in order:

Approximately how many hours a week do you spend cleaning and preparing data for analysis and reporting?

Don’t be alarmed by a big number in itself: data professionals typically spend the majority of their time cleaning data.

However, if you get the sense that your analysts no longer, well, analyze data, and instead just manually clean and prepare it, then it’s time to examine what needs to change in the data workflow.

Looking at the data skills in terms of productivity can make a great benchmark when it comes time to measure the ROI of the data academy.

Learning assessments

Rather than a self-rating of skills, how about asking specific technical questions like the following?

Which tab on the home ribbon allows you to create a PivotTable?

A. Data
B. Insert
C. View
D. Home

It seems like this would be the most objective assessment strategy, right? There’s no hiding data talents this way.

However, as you probably know from your own work, problems don’t come to data analysts in the form of multiple choice questions. Perhaps more important than raw knowledge is the ability to apply it in a given context.

Maybe you don’t want to be as specific, but would like a broader sense of candidate know-how. A question like this can work well as a skills assessment:

Which of these best describe how easily you could perform a left outer join in Power Query?
A. I wouldn’t know where to start
B. I could struggle through with trial and error and lots of web searching
C. I could do it quickly wiht little to no use of external help

Questions like this can give a more contextual look at candidate skills, without digging into hard-to-generalize specifics.

Qualifying data skills

Given these limitations of quantifying candidate data skills, perhaps we should consider — yes, really — qualifying the skills.

It sounds hokey, but being a data analyst is as much about mindset and attitude as it is raw technical ability. So we might want to try getting inside the minds of our candidates and understand their perspectives on data.

Experiences

Really take the time to understand the pain points of how your candidates work with data — this should be about more than just pinching pennies on productivity.

Understand: what are the pain points that people have in working with their data? What do they wish they could do, if they knew how? What’s holding them back in the current environment?

To learn about particular experiences, you could ask something like this:

What systems do you pull your data from and to what extent do they interface?

Your candidates may be able to articulate what works and doesn’t but doesn’t have the know-how or the clout to do anything about it. This is what you need to figure out in the enrollment process.

Emotions

Now this really seems nuts for a cold, exacting field like data analytics. But working with data can be scary!

You’re working with tons of data in difficult-to-control processes with no technical support. You may try to fix something yourself, but feel like an idiot for not knowing it already. And without buy-in from the organization as a whole, these efforts don’t amount to much.

Your data people may be constantly afraid of making mistakes and feel a total loss of control over their work. Not a great environment, right? It’s one you can change with a solid data up-skilling initiative, of which the data academy is a plank.

What excites you with working with data? What frustrates you?

Goals

For all the data academy can do to improve your organization, don’t discount the intrinsic motivation of your candidates!

A study from the learning & development consultancy Towards Maturity found that employees rated learning for personal development only behind wanting to do their job better and faster as top motivators.

So, try to learn what motivates your candidates coming into the program: do they hope to advance their statistical analysis abilities? Learn to code? Automate particular reports? Or is it out of pure curiousity? You could learn this with as simple a question as:

Why do you want to enroll?

Where to go from here?

A solid skills assessment is crucial to a successful data academy. But what do you do after the assessment?

Please check out the rest of my posts on the data academy to learn more. You’re also welcome to contact me directly or set up a free consult call.

Take the time to assess your candidate data skills and motivations and you’ll be surprised at the talent you’ve got in house. The data academy will cultivate that talent.

The post Building the data academy: assessing candidate skills first appeared on Stringfest Analytics.

But, if you are counting on your employees to use YouTube (or really any autodidactic medium) for their data upskilling, you are setting up your company for failure. Here’s why.

It’s inefficient

If you want efficient workers, you will give them efficient learning resources. And YouTube is not one of them.

It sounds like a great idea to hop on and off YouTube when you need to learn how to do something. But we’ve all fallen down the YouTube rabbit hole.

Many of the best YouTube instructors use their channel as adversiting for their paid courses. Sure, you can get a lot of good content off the channel for free — but when you pay, you get efficiency: everything you need is packaged in one straight path.

It’s of inconsistent quality

Related to the inefficiency, the quality of YouTube tutorials is all over the place. There’s no content QA process for what lands on your feed: it’s all up to the whims of the algorithm.

Wouldn’t you rather incorporate a strategy with some eye toward your organization’s specific needs and circumstances? And use content that’s been vetted by experts for its instructional rather than entertainment value?

Your best and brightest will leave

Employers want “self-starters,” which is understandable. But there’s a fine line between “be a self-starter” and “figure it out yourself, because I can’t/won’t/don’t care.”

Often, management has failed to build sound data workflows and processes in the organization, and employees need to figure it out themselves, usually without the resources or power to actually fix the system.

Access to learning and training is one needed resource to fix the system. With no plan in place here, organizations are implicitly asking their employees to figure it out on YouTube. This isn’t going to end well and looks something like this:

1. The data analytics process is broken, due to poor data definitions, storage methods, or (but most likely and) unclear business objectives.
2. A digitally-savvy junior-level analyst is hired to figure out these problems.
3. Over time, the analyst begins to watch more and more YouTube videos and can frame the organization’s data problems clearly. They can see what apparently no one else can or will see: that the status quo is not going to work.
4. Without the resources or culture to enact the desperately needed changes, the analyst gets frustrated and seeks greener pastures.

What’s the alternative?

YouTube is but one of many low-cost ways to learn data analytics. With all these choices, it may seem absurd to pay for white-label data education. However, a “do-it-yourself” upskilling initiative is bound to fail: not just for the inconsistent quality of the content, but for the rift it creates in your organization’s data culture.

Leave your best and brightest to figure out your organization’s data woes themselves, and they will: they’ll figure out that they should go somewhere “that gets” data. 

That means that the alternative is to build an in-house data training academy. This will upskill your workforce the right way: evenly distributed. You control the quality of the content. You have the chance to directly audit your current practices against industry standards.

If you are interested in learning more about what a data academy can do for your organization, sign up below for exclusive access to my resource library. You will find workshop outlines, demo guides and more. Consider this my attempt to “open source” what your organization’s data academy will look like.

You can also drop me a line or schedule a free call on Microsoft Bookings.

I look forward to seeing what solutions you deliver for data education.

The post YouTube is not a data upskilling strategy first appeared on Stringfest Analytics.

Here’s why:

It reduces cognitive overhead

Cognitive overhead is described as “how many logical connections or jumps your brain has to make in order to understand or contextualize the thing you’re looking at.”

Often an analytics learning journey looks like this:

1. Learn a brand-new statistical technique.
2. Learn how to implement the brand-new technique using brand-new coding techniques
3. Progress to more advanced statistical and coding techniques, without ever having felt really comfortable with the basics.

It’s hard enough to learn the statistical foundations of analytics. To learn this while also learning how to code invites sky-high cognitive overhead.

Now, I do believe there is great virtue to practice analytics via coding. But it’s better to isolate these skill sets while mastering them.

Excel provides the opportunity to learn statistical techniques without the need to learn a new programming language at the same time. This greatly reduces cognitive overhead.

It’s a visual calculator

The first mass-market offering of a spreadsheet was called VisiCalc — literally, a visual calculator. I think of this often as one of the spreadsheet’s biggest selling points.

Especially to beginners, programming languages can resemble a “black box” — type the magic words, hit “play” and presto, the results. Chances are the program got it right, but it can be hard for a newbie to pop open the hood and see why.

By contrast, Excel lets you watch an analysis take shape each step of the way. It lets you calculate and re-calculate, visually.

Seeing is believing, right?

You can’t take shortcuts

Open-source tools like R and Python give you access to a wide variety of packages, which usually means you don’t have to “start from scratch” with basic functions.

While Excel add-ins for analytics are available, many of them cost. But that’s OK! In fact, left with the bare building-blocks of Excel, there’s more opportunity to get face-to-face with what’s being built.

In Excel, we can’t always rely on an external package to conduct our analysis for us. We’ve got to get there by our own devices.

It forces you to be agile

A temptation in data analysis is to build the most complicated possible model at first, and then work backward to find something that works. It’s better to go in reverse: start with a minimum viable product, and iterate from there.

It’s a lot harder to build a complicated model in Excel than in Python — which is a limitation, when we need complicated models — but as a prototyping tool, this is great, because it forces us to start small.

We’re not making production models here

I just highlighted some of the many benefits of learning analytics in Excel. Can you think of others? Or maybe you’re not convinced?

One of the biggest objections to doing analytics in Excel is that it can be error-prone and hard to reproduce.

That is absolutely true, but we’re just learning here. We’re not making production models.

Don’t discard Excel’s aptitude as a teaching tool for its flaws as a fast, reproducible analytics workflow.

Learning analytics in Excel: What next?

I’ve learned more about statistics and analytics by experimenting in Excel than any other tool, and I hope this approach can work for you too.

If you’d like to see what Excel can do for your learning path, check out my book Advancing into Analytics: From Excel to Python and R. The first part of the book demonstrates crucial analytics concepts and techniques in Excel, then builds on this knowledge in R and Python.

Learn more about Advancing into Analytics, including how to read for FREE, here.

How do you prefer to learn statistics and analytics? Do you see other pros or cons of using Excel? Let’s talk in the comments.

The post Why Excel is the best way to learn data analytics first appeared on Stringfest Analytics.

“This is good,” a fellow doctoral student told me at our meeting the other day. “You are asking people for help. I should have done that.” 

One suggestion this older student gave to me was not to be afraid to contact researchers who were doing similar work to mine and ask them for feedback, too. 

Intimidated by the dog-eat-dog world of research, I would not have dared do this earlier. But, he gave me plenty of other good advice. Why not try this?

Good advice. I made an ally whom I will likely run into later in my career. Not only this, but this new contact tipped me off to something pretty obvious that I am very embarrassed I missed.

My research topic (on physician incentives and quality) has very strong relations to the research done by this year’s Nobel Prize winner in economics. 

Say what?

Even with the Internet, in 2016, it’s possible to miss out on information that won someone a Nobel prize. So ask. 

I have had no reservations with asking people for advice, feedback, criticism, etc. And why not?

No one is going to take your idea.  This is a common pushback. “If I come to someone with a new idea, they might steal it!” Yes, be prudent and find someone who can truly give you helpful feedback. Anyone who can be this helpful is going to be too busy with their own ideas to take yours.

People like to feel smart.  Go ahead. Play the “student card.” “What would you do to start out on X? Is it smart to do Y like this?” This shows your humility but also your initiative (something, not to be humble, that the older student applauded me on.)

But don’t push it. We all know the axiom about teaching a man to fish. Well, your questions should be designed to help someone teach you how to fish, not give you a fish. Example —

Teaching question: “Hello, I have an idea to write about X. Can you recommend any books on that topic?” (Indicates I accept the workload of reading the books and just need a point in the right direction.)

Giving question: “Hi, can you read this 60-page paper and tell me what you think?” (Adds lots of work to the requester — and makes less work for you.) 

No learner is an island.

This is why schools and universities exist. And, while more and more learning can occur independently, I fear recent trends swing too far toward autodidactism. 

Sure, Google exists. But it took the help of an experienced researcher to point me to what really mattered to my topic. 

The post No Learner an Island first appeared on Stringfest Analytics.