How do you explain statistical uncertainty to non-experts?

1 Use plain language

Avoid jargon and technical terms that might confuse or intimidate your audience. Instead, use simple and concrete words that convey the essence of the statistical concept. For example, instead of saying "the confidence interval is 95%", you can say "we are 95% sure that the true value is within this range". Instead of saying "the p-value is 0.01", you can say "there is only a 1% chance that this result is due to random variation".

2 Use visual aids

Visual aids can help your audience grasp the idea of uncertainty more easily than numbers or words. For example, you can use graphs, charts, or diagrams that show the distribution, range, or margin of error of the data. You can also use icons, symbols, or colors to indicate the level of certainty or uncertainty of the results. For example, you can use stars, asterisks, or shades of gray to show how confident you are about the findings.

3 Use analogies and examples

Analogies and examples can help your audience relate to the concept of uncertainty by comparing it to something they are familiar with or interested in. For example, you can compare uncertainty to weather forecasts, sports predictions, or coin tosses. You can also use examples from your own field or domain to illustrate how uncertainty affects your decisions or actions. For example, you can explain how uncertainty influences your choice of treatment, policy, or strategy.

4 Use numbers and proportions

Numbers and proportions can help your audience quantify and compare the uncertainty of different results or scenarios. For example, you can use percentages, fractions, or ratios to express the likelihood or frequency of an event or outcome. You can also use absolute or relative numbers to show the difference or impact of uncertainty. For example, you can say "this result is 10% more uncertain than the previous one" or "this result could change by 5 points in either direction".

5 Use qualifiers and modifiers

Qualifiers and modifiers can help your audience understand the degree and direction of uncertainty in your statements or claims. For example, you can use words like "probably", "likely", "possibly", "roughly", "approximately", or "about" to indicate that you are not certain or precise. You can also use words like "more", "less", "higher", "lower", "better", or "worse" to indicate that you are comparing or contrasting different levels of uncertainty.

6 Use caution and honesty

Caution and honesty can help your audience trust and respect your communication of uncertainty. For example, you can use words like "may", "might", "could", or "suggest" to indicate that you are not making definitive or causal statements. You can also acknowledge the limitations, assumptions, or sources of uncertainty in your data, methods, or results. For example, you can say "this result is based on a small sample size" or "this result depends on how we define this variable".

7 Here’s what else to consider

This is a space to share examples, stories, or insights that don’t fit into any of the previous sections. What else would you like to add?