Because important people in your life -- your co-workers, your students, your kids, your boss, maybe even you
-- are afraid to analyze data.
There's no shame in that. In fact, there are pretty good reasons for people to feel some trepidation (or even outright panic) at the prospect of making sense of a set of data.
I know how it feels to be intimidated by statistics. Not long ago, I would do almost anything to avoid analyzing data. I wanted to know what the data said -- I just didn't believe I was capable of analyzing it myself.
So in this post I'm going to share my three top fears about analyzing data. And I'll talk about how Minitab can help people who are struggling with dataphobia.
Fear #3: I Don't Even Know Where to Start Analyzing this Data.
Writers confront a lurking terror each time they touch the keyboard. It's called "The Blank Page," or maybe "The Blank Screen," and it can be summed up in a simple question: "Where do I start?" I know that terror well...but at least when confronting the blank page, I always had confidence that I can write.
When it came to analyzing data, not only was I not sure where to start, I also had no confidence that I'd be able to do it. I always envisioned getting off on the wrong foot with my analysis, then promptly stumbling straight off some statistical cliff to plunge into an abyss of meaningless numbers.
You can understand why I tried to avoid this.
We want to help people overcome those kinds of qualms. Minitab does this with the Assistant
, a menu that guides you through your analysis and helps you interpret your results with confidence.
Man, I wish the Assistant had been there when I started my career.
The Assistant can guide you through 9 types of analysis. But what if you don't remember what any of those analyses do? No problem. The Assistant's tool tips explain exactly what each analysis is used for, in plain language.
If I had data about the durability of four kinds of paper, the explanation of Hypothesis Tests would grab my attention:
Of course, if you already know a thing or two about statistics, you know there's more than one kind of hypothesis test. The Assistant guides you through a decision tree so you can identify the one that's right for your situation, based on the kind of data you have and your objectives. If you can't answer a question, the Assistant provides information so you can respond correctly, such as illustrated examples that help you understand how the question relates to your own data.
The Assistant leads me to One-way ANOVA to compare my paper samples.
Now I know where to start my analysis. But I still face....
Fear #2: I Don't Know Enough about Statistics to Get All the Way Through this Analysis.
Getting started is great, but what if you're not sure how to continue?
Fortunately, after you've chosen the right tool, the Assistant comes right out and tells you how to ensure your analysis is accurate. For example, it offers you this checklist for doing a one-way ANOVA:
The Assistant provides clear guidelines, including how to set up, collect, and enter your data, and more.
What's more, the Assistant's dialogs are simple to complete. No need to guess about what you should enter, and even relatively straightforward concepts like Alpha value are phrased as common-sense questions: "How much risk are you willing to accept of concluding there are differences when there are none?"
The Assistant will help you finish the analysis you start. But my biggest fear about data is still waiting...
Fear #1: If I Reach the Wrong Conclusion, I'll Make a Fool of Myself!
Once you finish your analysis, you must interpret what it means, and then you usually need to explain it to other people.
This is where the Assistant really shines, by providing a series of reports that help you understand your analysis.
Take a look at the summary report for my ANOVA below and tell me if the means of my four paper samples differed.
The bar graph in the left corner explicitly tells me YES, the means differ, and it gives me the p-value, too...but I don't need to interpret that p-value to draw a conclusion. I don't even need to know what a p-value is. I do know what's important: that the means are different.
This summary report also tells me which means are different from each other. With this report, I could tell my boss that we should avoid paper #2, which has a low durability compared to the others, but that there's not a statistically significant difference in durability between papers 1, 3, and 4, so we could select the least expensive option.
In my early career, a tool like this would have made all the difference when questions about data came up. I wouldn't have needed to avoid it.
What If I'm Already an Experienced Data Analyst?
Today I know enough about data analysis that I could easily run the ANOVA without the Assistant, but I still like to use it. Why? Because the simplicity and clarity of the Assistant's output and reports is perfect for communicating the results of my analysis with people who fear statistics the same way I used to.
And as you probably know, there are lots of us out there.