Key Takeaways
- The normal distribution is symmetric and bell-shaped, centered around the mean (μ)
- 68-95-99.7 Rule: 68% of data falls within 1σ, 95% within 2σ, 99.7% within 3σ
- Z-score tells you how many standard deviations a value is from the mean
- For a standard normal distribution: mean = 0 and standard deviation = 1
- The total area under the normal curve equals 1 (or 100%)
What Is Normal Distribution?
| Range | % of Data | z-score Range |
|---|---|---|
| Within 1 standard deviation | 68.27% | −1 to +1 |
| Within 2 standard deviations | 95.45% | −2 to +2 |
| Within 3 standard deviations | 99.73% | −3 to +3 |
| Beyond 3 standard deviations | 0.27% | < −3 or > +3 |
| Upper half (above mean) | 50% | z > 0 |
| Lower 2.5% | 2.5% | z < −1.96 |
| Upper 2.5% | 2.5% | z > +1.96 |
| Confidence Level | α (two-tailed) | z* (critical value) |
|---|---|---|
| 80% | 0.20 | ±1.282 |
| 85% | 0.15 | ±1.440 |
| 90% | 0.10 | ±1.645 |
| 95% | 0.05 | ±1.960 |
| 99% | 0.01 | ±2.576 |
| 99.5% | 0.005 | ±2.807 |
| 99.9% | 0.001 | ±3.291 |
| Variable | Mean (μ) | Std Dev (σ) | Notes |
|---|---|---|---|
| Adult male height (US) | 5′9″ (175 cm) | 3 in (7.6 cm) | Well-approximated by normal |
| IQ scores | 100 | 15 | Normed to normal by design |
| SAT total score | ~1060 | ~210 | Approximately normal |
| Blood pressure (systolic) | ~120 mmHg | ~15 mmHg | Clinical reference |
| Measurement errors | 0 | Instrument-dependent | Central limit theorem |
| Daily stock returns | ~0% | 1–2% | Approximately normal, fat tails |
The normal distribution (also called Gaussian distribution or bell curve) is the most important probability distribution in statistics. It describes how data is distributed around a central value (the mean) with a specific spread (standard deviation). Many natural phenomena follow this pattern: heights, test scores, measurement errors, and more.
The distribution is characterized by two parameters: the mean (μ) which determines the center of the distribution, and the standard deviation (σ) which determines the spread or width of the curve.
Z-Score Formula Explained
z = (x - μ) / σ
The z-score tells you how many standard deviations away from the mean a particular value lies. A z-score of 0 means the value equals the mean, while a z-score of 2 means the value is 2 standard deviations above the mean.
Common Z-Score Reference Values
| Z-Score | Left Tail P(Z ≤ z) | Right Tail P(Z ≥ z) | Common Use |
|---|---|---|---|
| -2.576 | 0.0050 | 0.9950 | 99% CI lower |
| -1.96 | 0.0250 | 0.9750 | 95% CI lower |
| -1.645 | 0.0500 | 0.9500 | 90% CI lower |
| 0 | 0.5000 | 0.5000 | Mean (50th percentile) |
| 1.645 | 0.9500 | 0.0500 | 90% CI upper |
| 1.96 | 0.9750 | 0.0250 | 95% CI upper |
| 2.576 | 0.9950 | 0.0050 | 99% CI upper |
The 68-95-99.7 Rule (Empirical Rule)
The empirical rule is a quick way to estimate probabilities for normal distributions:
- 68% of data falls within 1 standard deviation of the mean (μ ± 1σ)
- 95% of data falls within 2 standard deviations of the mean (μ ± 2σ)
- 99.7% of data falls within 3 standard deviations of the mean (μ ± 3σ)
Pro Tip: Using the Empirical Rule
If you know a dataset is approximately normal, you can quickly estimate probabilities without a calculator. For example, if test scores have a mean of 75 and standard deviation of 10, about 95% of students scored between 55 and 95 (75 ± 20).
Practical Applications
Quality Control
Manufacturing uses normal distribution to set tolerance limits. If a product dimension should be 10mm with σ = 0.1mm, items outside μ ± 3σ (9.7mm to 10.3mm) might be rejected - this captures only 0.3% of defects.
Test Scores & Grading
Standardized tests like SAT and IQ are designed to follow normal distributions. A z-score lets you compare scores across different tests or years.
Finance & Risk
Stock returns are often modeled (approximately) as normal distributions. Value at Risk (VaR) calculations use z-scores to estimate potential losses at specific confidence levels.
Medical Research
Clinical trials use normal distribution assumptions to determine if treatments are effective. Statistical significance often uses z-scores to calculate p-values.