AIM • STEP 10
4th Year MBBS
Community Medicine
4th Year MBBS
Community Medicine
Student Memory Support
Descriptive Biostatistics and Data Distribution
High-yield memory reinforcement for central tendency, dispersion, normal distribution, percentiles and interquartile range.
1. High-Yield Flashcards
Tap each question to reveal the answer.
Q: What are the three principal measures of central tendency?
A: Mean, median and mode.
Q: Which measure of central tendency uses every numerical observation?
A: Arithmetic mean.
Q: Why is the median useful in markedly skewed data?
A: It depends on ranked position and is less affected by extreme values.
Q: Which measure identifies the most frequently occurring value or category?
A: Mode.
Q: How is the range calculated?
A: Maximum value − minimum value.
Q: What is the main limitation of the range?
A: It uses only the minimum and maximum values and ignores observations between them.
Q: What does variance measure?
A: The average squared deviation of observations from the mean.
Q: What is the relationship between standard deviation and variance?
A: Standard deviation is the square root of variance.
Q: What does a larger standard deviation indicate?
A: Greater dispersion of observations around the mean.
Q: Which measure expresses standard deviation relative to the mean?
A: Coefficient of variation.
Q: Which three measures coincide at the centre of an ideal normal distribution?
A: Mean, median and mode.
Q: Approximately what proportion of a normal distribution lies within ±2 standard deviations of the mean?
A: Approximately 95%.
Q: Which percentile corresponds to the median?
A: The 50th percentile.
Q: How is the interquartile range calculated?
A: IQR = Q3 − Q1 = P75 − P25.
2. Mnemonics
Mnemonic Title: Central Tendency
MMM
Meaning: Mean → mathematical average; Median → middle ranked value; Mode → most frequent value.
Mnemonic Title: Normal Distribution SD Rule
68–95–99.7
Meaning: Approximately 68% lie within ±1 SD, 95% within ±2 SD and 99.7% within ±3 SD.
Mnemonic Title: Quartile Percentile Positions
25–50–75
Meaning: Q1 = P25; Q2 = P50 = median; Q3 = P75.
3. Memory Tables
Mean vs Median vs Mode
| Feature | Mean | Median | Mode |
|---|---|---|---|
| Basis | All values | Ranked position | Frequency |
| Extreme values | Strongly affected | Less affected | Usually little affected |
| Best use | Symmetrical quantitative data | Skewed or ordered data | Most frequent value/category |
Choosing a Measure of Dispersion
| Situation | Preferred Measure | Memory Link |
|---|---|---|
| Quick total spread | Range | Maximum − minimum |
| Symmetrical quantitative data | Standard deviation | Spread around mean |
| Skewed data/outliers | Interquartile range | Middle 50% |
| Relative variability | Coefficient of variation | SD relative to mean |
4. Rapid Revision Points — Last-Minute Revision
- Mean uses every numerical observation and is sensitive to extreme values.
- Median divides ordered observations into two halves and resists extreme values.
- Mode identifies the most frequent value or category and may be absent or multiple.
- Range is simple but depends only on the minimum and maximum observations.
- Variance is based on squared deviations; SD is its square root.
- Coefficient of variation describes variability relative to the mean.
- Normal distribution is symmetrical and unimodal with mean = median = mode.
- Approximately 68%, 95% and 99.7% lie within ±1, ±2 and ±3 SD respectively.
- IQR = Q3 − Q1 and represents the spread of the middle 50%.
- Mean + SD suit symmetrical data; median + IQR suit markedly skewed data.
Common KMU Trap: A familiar measure is not automatically the correct measure. Distribution shape determines whether mean/SD or median/IQR provides the better summary.
5. Clinical Memory Hooks
Very high outlier in a clinical dataset → arithmetic mean shifts toward the extreme value → median may better represent the typical observation.
Measurements tightly clustered around their average → small standard deviation → low dispersion.
Broad, flatter normal curve → greater spread around the same centre → larger standard deviation.
Observation reported at the 75th percentile → approximately three-quarters of the reference observations lie at or below that value → this position is Q3.
6. Starred High-Yield Exam Points
- ⭐ Mean is sensitive to outliers; median is relatively resistant to them.
- ⭐ Standard deviation = √variance and is expressed in the original measurement unit.
- ⭐ Normal distribution: mean = median = mode at the centre.
- ⭐ 68–95–99.7 rule: approximately ±1, ±2 and ±3 SD respectively.
- ⭐ P25 = Q1, P50 = median, P75 = Q3.
- ⭐ IQR = Q3 − Q1; median + IQR is the high-yield descriptive pair for markedly skewed data.