Detailed Explanation
Mean deviation measures how spread out the data is from a central value. Here we measure spread about the median. For discrete frequency data, we first arrange the values in increasing order and build a cumulative frequency (c.f.) table. The median is the value of the observation for which the cumulative frequency first reaches or exceeds \( \frac{N}{2} \), where \( N = \sum f_i \) is the total frequency. Once we know the median \( M \), we compute the absolute deviation \( |x_i - M| \) of each value from the median, weight each by its frequency, add them up, and divide by \( N \). Using absolute values ensures deviations do not cancel out.
Formula Used
\[ \text{M.D.}(M) = \frac{1}{N} \sum_{i=1}^{n} f_i \, |x_i - M| \] where \( N = \sum f_i \) and \( M \) is the median.
Solution
- Step 1: Arrange the data in increasing order (already done) and find the total frequency. \[ N = 8 + 6 + 2 + 2 + 2 + 6 = 26 \] Since \( N = 26 \), we have \( \frac{N}{2} = 13 \).
- Step 2: Build the cumulative frequency (c.f.) table by adding frequencies as we move through the ordered values: for \( x_i = 5 \), c.f. \( = 8 \); for \( x_i = 7 \), c.f. \( = 14 \); for \( x_i = 9 \), c.f. \( = 16 \); for \( x_i = 10 \), c.f. \( = 18 \); for \( x_i = 12 \), c.f. \( = 20 \); for \( x_i = 15 \), c.f. \( = 26 \).
- Step 3: Locate the median. We need the value where the cumulative frequency first reaches or crosses \( \frac{N}{2} = 13 \). The c.f. is \( 8 \) at \( x = 5 \) (less than 13) and jumps to \( 14 \) at \( x = 7 \) (which is \( \ge 13 \)). So the median is \[ M = 7. \]
- Step 4: Compute the absolute deviations \( |x_i - M| \) from the median \( M = 7 \): for \( 5 \), \( |5-7| = 2 \); for \( 7 \), \( |7-7| = 0 \); for \( 9 \), \( |9-7| = 2 \); for \( 10 \), \( |10-7| = 3 \); for \( 12 \), \( |12-7| = 5 \); for \( 15 \), \( |15-7| = 8 \).
- Step 5: Multiply each absolute deviation by its frequency \( f_i \, |x_i - M| \): \( 8 \times 2 = 16 \); \( 6 \times 0 = 0 \); \( 2 \times 2 = 4 \); \( 2 \times 3 = 6 \); \( 2 \times 5 = 10 \); \( 6 \times 8 = 48 \).
- Step 6: Add these products to get the total weighted deviation. \[ \sum f_i |x_i - M| = 16 + 0 + 4 + 6 + 10 + 48 = 84 \]
- Step 7: Apply the mean deviation formula by dividing by \( N \). \[ \text{M.D.}(M) = \frac{1}{N} \sum f_i |x_i - M| = \frac{84}{26} \] \[ \text{M.D.}(M) \approx 3.23 \]
Final Answer
The median is \( M = 7 \) and the mean deviation about the median is \[ \text{M.D.}(M) = \frac{84}{26} \approx 3.23. \]
Common Mistake
A common mistake is to take the median as simply the middle value \( \frac{9+10}{2} \) or the average of the two middle x-values without using the cumulative frequency. For frequency data you must use the c.f. table and the \( \frac{N}{2} \) rule; here the correct median is \( 7 \), not \( 9.5 \).