Statistics and Probability for AI

Statistics sums up data with mean, median, mode and range; probability measures how likely an event is, from 0 to 1.

Key ideas

The mean shares the total equally; the median is the middle of the sorted data; the mode is the most common value.
With an even number of values, the median is the average of the two middle ones.
The range, largest minus smallest, shows how spread out the data is.
Probability = favourable outcomes ÷ all outcomes, written as a fraction in lowest terms.
An impossible event has probability 0 and a certain event 1; the chance of “not A” is 1 − P(A).
AI models use these ideas: averages to sum up data, probability to say how sure a prediction is.

Mean	sum ÷ number of values
Median of 22, 29, 33, 34, 37, 37	(33 + 34) ÷ 2 = 33.5
Probability	bag of 3 red, 5 blue, 2 green: P(red) = 3/10, P(not blue) = 5/10 = 1/2
P(A or B), no overlap	P(A) + P(B)
Words	0 impossible; less than 1/2 unlikely; 1/2 equally likely; more than 1/2 likely; 1 certain

Find the median of 29, 34, 37, 37, 22, 33.

Working: in order: 22, 29, 33, 34, 37, 37; average of the middle two

Answer: 33.5