Why simple averages often lie to you about the truth

Why simple averages often lie to you about the truth
Image: Intellect (generated)

In short: When calculating an average, assuming every data point carries equal importance can lead to significant errors. If one group is larger than another, a standard arithmetic mean ignores the scale of the population, potentially distorting the real picture. To find the true center, you must learn to assign weight.

The standard arithmetic mean is a specific, limited case of the weighted arithmetic mean where every data point contributes equally. However, in many real-world scenarios, certain elements deserve more influence. This is particularly vital when aggregating groups of different sizes. For instance, if you have a morning class of 20 students with a mean grade of 80 and an afternoon class of 30 students with a mean of 90, simply averaging the two means gives you 85. This figure is misleading because it fails to account for the extra 10 students in the afternoon session.

To find the true average student grade, you must use a weighted approach. By weighting the class means by their respective student counts, you calculate the sum of all grades (4300) divided by the total population (50), resulting in a true mean of 86. This method allows you to find the aggregate average without needing every individual score; you only need the group means and the number of participants. Mathematically, this is often expressed as a convex combination, where weights are normalized to sum to exactly one, such as using 0.4 for the smaller class and 0.6 for the larger one.

The mechanics of weighting extend into advanced probability. When dealing with data from different probability distributions, one sophisticated strategy is to use weights based on the reciprocal of the variance. In this 'inverse-variance' approach, data points with higher precision (lower variance) are given more influence. This ensures that more reliable information carries more weight in the final calculation, helping to minimize the standard error of the weighted mean.

Opens the Intellect+ feed with this card first. Swipe up for the next one.

Sources

To cite this card, link to https://intellectplus.co.uk/app/science-weighted-arithmetic-mean.

How we source, check and correct cards: Editorial standards.

General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.

Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?

Related

Finding something worth knowing…