Convert between probability, odds, and odds ratios. Essential for epidemiology, betting, and statistical analysis.
Last updated: March 2026
Odds express the likelihood of an event as a ratio of favorable to unfavorable outcomes. While probability uses a 0-1 scale, odds use a ratio format (e.g., 3:1 or "3 to 1"). Both represent the same underlying likelihood but in different forms.
The Odds Ratio (OR) compares odds between two groups and is fundamental to epidemiology, case-control studies, and logistic regression. OR >1 indicates higher odds in the exposed/treatment group, OR < 1 indicates lower odds, and OR = 1 indicates no association.
A 2×2 contingency table organizes data as: a (both factors present), b (factor 1 only), c (factor 2 only), d (neither factor). The odds ratio is calculated as OR = (a×d)/(b×c). The 95% confidence interval helps determine statistical significance.
Example 1: Probability to Odds
Example 2: Odds to Probability
Example 3: Odds Ratio (Case-Control Study)
Probability is the chance of an event (0-1 scale, e.g., 0.25 = 25%). Odds is the ratio of favorable to unfavorable outcomes (e.g., 1:3). Both represent the same likelihood. Probability is more intuitive; odds are used in betting and logistic regression.
OR > 1: higher odds in exposed/treatment group (positive association). OR < 1: lower odds in exposed group (protective effect). OR = 1: no association. OR = 2 means exposed group has 2× the odds. OR = 0.5 means exposed group has half the odds.
A table organizing data by two binary factors. a = both present, b = factor 1 only, c = factor 2 only, d = neither. Common in epidemiology: rows are exposure (yes/no), columns are outcome (disease/healthy). OR measures association strength.
Confidence interval for the odds ratio. If CI doesn't contain 1, the association is statistically significant (p<0.05). Wider CI = less precision (small sample). Narrower CI = more precision (large sample). Example: CI=[2.0, 8.5] excludes 1, so significant.
Yes! Odds can be any positive number. Odds = 1 means 50% probability (equal likelihood). Odds = 2 means 2:1 for (67% probability). Odds = 0.5 means 1:2 for (33% probability). As odds increase, probability approaches 100%.
Probability: intuitive for general communication, direct interpretation. Odds: betting contexts, logistic regression (log odds), case-control studies. Odds ratio: comparing groups in epidemiology, measuring association strength in research.
Not statistically significant at α=0.05 level. The true OR could plausibly be 1 (no association). This doesn't prove no effect - just insufficient evidence. May need larger sample size. Report as 'not statistically significant'.
Both measure association. Relative Risk (RR) = ratio of probabilities, used in cohort studies with incidence data. Odds Ratio = ratio of odds, used in case-control studies and logistic regression. When outcome is rare (<10%), OR ≈ RR.
Related Tools
Basic probability calculations.
P(A|B) calculations.
P(A and B) calculations.
Three event probabilities.
Conditional probability.
Probability-weighted average.