Math & Statistics
Correlation Coefficient: How to Calculate and Interpret r
Pearson's r measures how closely two variables follow a straight line. Here is the hand calculation, how to read the result, and where the number can fool you.
Math & Statistics
Guides to percentages, fractions, averages, probability and statistics, with worked examples and the reasoning behind each formula.
Math & Statistics
How Big a Sample Do You Need? Sample Size and Margin of Error
Sample size is a trade-off between precision and cost. Here is the survey formula, a worked example, and why bigger is not always better.
Math & Statistics
How to Calculate Standard Deviation by Hand, Step by Step
Standard deviation tells you how spread out a set of numbers is. This walkthrough does it by hand on eight values and explains when to divide by n or n minus 1.
Math & Statistics
How to Read a Confidence Interval (and What 95% Means)
A confidence interval is a range built from sample data. Learn how to calculate one for a mean and a proportion, and how to describe it without overclaiming.
Math & Statistics
Odds vs Probability: How to Convert Between Them
"1 in 4" and "odds of 1 to 4" are not the same thing. Learn the two conversion formulas and how odds ratios differ from risk ratios.
Math & Statistics
P-Values Explained: What 0.05 Does and Does Not Prove
A p-value is often read as the chance a result is a fluke, which it is not. Here is what it measures, with a worked coin-flip example and the mistakes to avoid.
Math & Statistics
Percent Error Formula: How to Calculate It With Examples
Percent error tells you how far a measurement is from the accepted value, relative to that value. Here is the formula, two worked examples and the usual traps.
Math & Statistics
How to Write Numbers in Scientific Notation, Step by Step
Scientific notation writes any number as a value between 1 and 10 times a power of ten. Here is how to convert, calculate and read calculator output.
Math & Statistics
Z-Scores Explained: Comparing Values on Different Scales
A z-score re-expresses any value as a number of standard deviations from the mean, which lets you compare results that use different scales.