I live in Jacksonville, Florida, where the odds of a hurricane on any given day are "**improbable**". But does that mean I shouldn't stock up on hurricane supplies and have an emergency preparedness plan? Far from it. Hurricane Irma blew through my city in 2017, causing around $85 million in damage and the worst flooding in the city's 150 year history.

The key here is the word "*improbable*." In everyday use, if you tell someone the chances of rain are improbable today, they hear "it isn't going to rain." But if you tell a mathematician that same thing, they'll carry an umbrella. Or possibly not, depending on what their definition of improbable is.

And therein lies the problem with terms in probability such as: **likely, unlikely, certain, and impossible.** Those loose definitions that mean something different not just from one layperson to the next, but from one mathematician to the next. As far as words like *likely* and *unlikely*, we can probably delete those from our probability vocabulary, because probability should never be defined in terms of being likely, or not (Deborah Mayo).

So let's take a look at *improbable, certain and impossible* a little more closely.

"You have to decide two things...what is your definition of likely or probable and conversely what is your definition of improbable? (UDEL)"

An "improbable" 28-second earthquake in L'Aquila, Italy killed 297 people in 2009 (and led to the conviction of seven scientists for manslaughter). Many people heard the word improbable and equated it to not likely. This is not surprising, because the general definition of the word, according to Google is "not likely to be true or happen." However, in terms of probability, "improbable" usually means a fair chance of happening.

In David Hefland's seminal book *A Survival Guide to the Misinformation Age: Scientific Habits of Mind*, he states that "Improbable things happen all the time and, Rare events are not necessarily rare at all" (p.144). But **how exactly do we quantify an improbable event?** That simple question is not easy to answer. Ask a statistician and you'll get a response somewhere around a 20% chance; Depending on who you ask, that probability could be as high as 25.3% or as low as 10.6% (Hillson, 2005). Other words that have a fairly wide interval:

- Highly probable: 64.2% to 78.3%
- Probable: 47.5% to 66.7%
- Highly unlikely: 9.8% to 23.3%

Oddly enough, "better than even" was defined in Hillson's survey as a probability of anywhere between *47.1%* and 65.6% (think about that for a second).

A strict definition for improbable is impossible to pin down, or is it? By "impossible" I mean "it's not going to happen, Lad." But am I correct to use that particular word? Unfortunately, I'm not. What I *should* say is "There is a 0% chance of pinning down a definition for improbable." But is that even correct?

Yesterday, when I checked my weather app, it said there was a 0% chance of rain. Which should mean impossible, yet I got drenched on a walk in the park with my dog. What I should have realized is that the definition of impossibility depends on what the app *meant* by 0%. Did it mean:

- Mathematically, the probability is zero?
- Mathematically, the probability is close to zero?
- The event (rain) has never happened before under the expected weather conditions, so the probability is zero (but this is fluid and could change after the weatherman's coffee break and another gander of the data).
- No idea at all, let me put a placeholder there while we figure this front out.

Alas, if you were reading this blog post to pin down a definition for any of the loose terms in the title, I'm sorry to disappoint. Perhaps it's because statisticians think in confidence intervals and margins of error that they are hesitant to formulate agreed-upon definitions for certain words. Although it's likely (probable?) that mathematicians think in numbers and not words. Of that, I'm almost certain.

Describing probability: The limitations of natural language

Top stories of 2017: Irma's rain, floodwaters damaged homes ...

FRONTIERS OF SCIENCE: Scientific Habits of Minds

UDEL: STATISTICAL INFERENCE

© 2020 TechTarget, Inc. Powered by

Badges | Report an Issue | Privacy Policy | Terms of Service

**Most Popular Content on DSC**

To not miss this type of content in the future, subscribe to our newsletter.

- Book: Applied Stochastic Processes
- Long-range Correlations in Time Series: Modeling, Testing, Case Study
- How to Automatically Determine the Number of Clusters in your Data
- New Machine Learning Cheat Sheet | Old one
- Confidence Intervals Without Pain - With Resampling
- Advanced Machine Learning with Basic Excel
- New Perspectives on Statistical Distributions and Deep Learning
- Fascinating New Results in the Theory of Randomness
- Fast Combinatorial Feature Selection

**Other popular resources**

- Comprehensive Repository of Data Science and ML Resources
- Statistical Concepts Explained in Simple English
- Machine Learning Concepts Explained in One Picture
- 100 Data Science Interview Questions and Answers
- Cheat Sheets | Curated Articles | Search | Jobs | Courses
- Post a Blog | Forum Questions | Books | Salaries | News

**Archives:** 2008-2014 |
2015-2016 |
2017-2019 |
Book 1 |
Book 2 |
More

**Most popular articles**

- Free Book and Resources for DSC Members
- New Perspectives on Statistical Distributions and Deep Learning
- Time series, Growth Modeling and Data Science Wizardy
- Statistical Concepts Explained in Simple English
- Machine Learning Concepts Explained in One Picture
- Comprehensive Repository of Data Science and ML Resources
- Advanced Machine Learning with Basic Excel
- Difference between ML, Data Science, AI, Deep Learning, and Statistics
- Selected Business Analytics, Data Science and ML articles
- How to Automatically Determine the Number of Clusters in your Data
- Fascinating New Results in the Theory of Randomness
- Hire a Data Scientist | Search DSC | Find a Job
- Post a Blog | Forum Questions

## You need to be a member of Data Science Central to add comments!

Join Data Science Central