Part 1 obgyn notes Sri Lanka
    NOTES for part 1
    /
    statistics
    /
    MEAN, MODE,SD

    MEAN, MODE,SD

    Owner
    U
    Untitled
    Verification
    Tags

    ✅ 1. Percentages

    (From Medical Statistics Made Easy, pages 7–8)

    What it means

    “Percent” means “per 100.”

    A percentage tells you how many out of 100 are in a group.

    How to calculate

    Percentage = (number in the category ÷ total number) × 100

    Example from the book

    14 patients out of 80 were in the 30–39 age band.

    Percentage = (14 ÷ 80) × 100 = 17.5%

    Key point

    Percentages help compare groups, but they can hide small sample sizes.

    ✅ 2. Mean (Average)xˉ

    (From pages 9–11)

    What it means

    Mean = total of all values divided by the number of values.

    When to use

    Use the mean when the data are evenly spread (normal distribution).

    Example from the book

    Ages: 52, 55, 56, 58, 59

    Sum = 280

    Mean = 280 ÷ 5 = 56

    Warning

    A very large or very small value can pull the mean in one direction.

    If the data are skewed, use the median instead.

    ✅ 3. Median

    (From pages 12–13)

    What it means

    The median is the middle value when numbers are arranged from smallest to largest.

    When to use

    Use the median when the data are skewed or have outliers.

    Example from the book

    Data: 52, 55, 56, 58, 59 → median is 56

    Add a new age 92: data becomes 52, 55, 56, 58, 59, 92

    Middle values are 56 and 58 → median is 57

    This represents the data better than the mean.

    Extra

    The median is often reported with the interquartile range (IQR), which shows the middle half of the data.

    ✅ 4. Mode

    (From pages 14–15)

    What it means

    The mode is the value or category that appears most often.

    When to use

    Useful for categorical data (like eye colour).

    Book example

    In a clinic:

    Brown eyes = most common → Mode = “brown”

    Extra

    A distribution can be “bimodal” (two peaks), meaning two common groups exist.

    ✅ 5. Standard Deviation (SD)

    image

    (From pages 16–19)

    What it means

    Standard deviation describes how spread out the values are around the mean.

    When to use

    Use SD only when the data are normally distributed.

    Key numbers to remember

    In a normal (bell-shaped) distribution:

    • 68.2% of values lie within 1 standard deviation of the mean
    • 95.4% lie within 2 standard deviations
    • 99.7% lie within 3 standard deviations

    Book example

    Mean weight = 80 kg

    SD = 5 kg

    This means:

    • Most people (68%) weigh between 75 and 85 kg

    • Almost all (95%) weigh between 70 and 90 kg

    • Nearly everyone (99.7%) weighs between 65 and 95 kg

    Warning

    If the mean minus 2 SD gives an impossible number (like negative days in hospital), the data are not normally distributed, so SD should not be used.

    Here is the same standard deviation example, now with x clearly defined inside it.

    Example: Standard Deviation (Sample)

    Data (observations = x values):

    x = 2, 4, 6

    Step 1: Find the mean (x̄)

    x̄ = (2 + 4 + 6) / 3 = 4

    Step 2: Calculate deviations (x − x̄)

    x (individual value)
    x − x̄
    2
    2 − 4 = −2
    4
    4 − 4 = 0
    6
    6 − 4 = +2

    Step 3: Square the deviations

    x − x̄
    (x − x̄)²
    −2
    4
    0
    0
    +2
    4

    Sum of squared deviations = 8

    Step 4: Divide by (n − 1)

    n = number of x values = 3

    Variance = 8 / (3 − 1) = 4

    Step 5: Square root

    Standard deviation = √4 = 2

    Final exam-ready statement:

    • x = individual observation
    • x̄ = mean of observations
    • n = total number of observations
    • SD = 2

    ⭐ Quick Comparison Table

    Concept
    What it represents
    Best used when
    Percentages
    Proportion out of 100
    Comparing groups
    Mean
    Average value
    Normal data
    Median
    Middle value
    Skewed data or outliers
    Mode
    Most common value
    Categories
    Standard deviation
    Spread around the mean
    Normal data