Normal Distribution Quick Reference Card
Module 4: The Normal Distribution
KEY PROPERTIES: Bell-shaped • Symmetric • Mean = Median = Mode • Total area = 1
Essential Formulas
z-score: z = (x − μ) / σ
Converts to standard normal
Inverse: x = μ + zσ
Converts z-score to x-value
Notation
- X ~ N(μ, σ) – normal distribution
- Z ~ N(0, 1) – standard normal
- z > 0 → above mean
- z < 0 → below mean
Empirical Rule (68-95-99.7)
| Range | % of Data |
|---|---|
| μ ± 1σ | ~68% |
| μ ± 2σ | ~95% |
| μ ± 3σ | ~99.7% |
Use for QUICK estimates without z-table!
Common z-values
| Percentile | z-value | Area Left |
|---|---|---|
| 50th | 0.00 | 0.5000 |
| 90th | 1.645 | 0.9000 |
| 95th | 1.96 | 0.9500 |
| 97.5th | 1.96 | 0.9750 |
| 99th | 2.576 | 0.9900 |
Memorize these for faster work!
Checking Normality
Visual Methods
- Histogram: Bell-shaped? Symmetric?
- Q-Q Plot: Points on straight line?
Range Check
If normal, expect:
- ~68% in [x̄ − s, x̄ + s]
- ~95% in [x̄ − 2s, x̄ + 2s]
Finding Probabilities
Type 1: P(X < a)
- Calculate z = (a − μ) / σ
- Look up z in table → answer
Type 2: P(X > a)
- Calculate z = (a − μ) / σ
- Look up z → get P(Z < z)
- Answer = 1 − P(Z < z)
Type 3: P(a < X < b)
- z₁ = (a − μ) / σ, z₂ = (b − μ) / σ
- Look up both z-values
- Answer = P(Z < z₂) − P(Z < z₁)
Type 4: Finding Percentiles
- Find probability inside table → z
- x = μ + zσ
z-table Usage Guide
Standard z-table gives:
- Area to the LEFT of z
- This equals P(Z < z)
- For z = 1.5 → 0.9332 means 93.32% below
Reading the table:
- Row = first two digits (e.g., 1.2)
- Column = second decimal (e.g., 0.05)
- Example: z = 1.25 → row 1.2, col 0.05
Decision Tree
Problem Type?
- Given x, find P? → x to z, use table
- Given P, find x? → table to z, z to x
- "Less than"? → Direct table lookup
- "Greater than"? → 1 − table value
- "Between"? → Subtract two table values
- Percentile? → Inverse lookup
Common Mistakes
- Forgetting to convert x to z first
- Wrong formula: (μ − x)/σ instead of (x − μ)/σ
- Not subtracting from 1 for P(X > a)
- Assuming all data is normal
- Sign errors: negative z = below mean
- Using σ² instead of σ in formula
Quick Tips for Success
- Always draw a picture and shade the area
- Check: probabilities must be 0 to 1
- Memorize Empirical Rule (68-95-99.7)
- |z| > 2 is unusual (< 5%)
- |z| > 3 is very unusual (< 0.3%)
- For continuous: P(X < a) = P(X ≤ a)
- Check normality before using methods
- Practice reading z-table both ways
Example Walkthrough
Problem: IQ ~ N(100, 15). Find P(IQ > 120).
Step 1: z = (120 − 100) / 15 = 20/15 = 1.33
Step 2: Table: P(Z < 1.33) = 0.9082
Step 3: P(Z > 1.33) = 1 − 0.9082 = 0.0918
Answer: 9.18% of people have IQ > 120
Step 1: z = (120 − 100) / 15 = 20/15 = 1.33
Step 2: Table: P(Z < 1.33) = 0.9082
Step 3: P(Z > 1.33) = 1 − 0.9082 = 0.0918
Answer: 9.18% of people have IQ > 120
Free Statistics Learning Platform • Safaa Dabagh • sdabagh.github.io • © 2025