Raynner-Okpara Raynner
SOFTWARE ENGINEERING
GROUP E
DESCRIPTIVE STATISTICS
ASSINGMENT 3
25/0162
Class Interval Frequency (f) Class Boundary Class Cumulative Cumulative
Mark Frequency Frequency
(CFL) (CFL)
3.50 – 3.54 2 3.495 – 3.545 3.52 2 40
3.55 – 3.59 4 3.545 – 3.595 3.57 6 38
3.60 – 3.64 4 3.595 – 3.645 3.62 10 34
3.65 – 3.69 8 3.645 – 3.695 3.67 18 30
3.70 – 3.74 10 3.695 – 3.745 3.72 28 22
3.75 – 3.79 5 3.745 – 3.795 3.77 33 12
3.80 – 3.84 4 3.795 – 3.845 3.82 37 7
3.85 – 3.89 3 3.845 – 3.895 3.87 40 3
A. Median Using the General Approximating Formula
The formula for the median is given by:
Where: N=40, therefore N/2=20, Median class = 3.70 –
3.74, L=3.695, CFB=18, F=10, h=0.05
[Link] Quartile (Q₁)
QUESTION 2
(i) Concept of Skewness
Skewness measures the degree of asymmetry in a
distribution.
Positive skewness → Positive skewness (or right-
skew) occurs when a data distribution has a long, thin tail
extending to the right, with most data points clustered on
the left.
Negative skewness → Negative skewness, or left-skewed
distribution, occurs when a dataset's tail extends toward
lower values (left) and most data points cluster on the
higher side.
Zero skewness → Zero skewness indicates a perfectly
symmetrical probability distribution where the left and
right sides are mirror images, and the mean, median, and
mode are equal.
(ii) Important Measures of Skewness
1. Karl Pearson’s coefficient: Karl Pearson’s coefficient
measures skewness based on the mean, median, and
standard deviation of a dataset.
Formula:
If the mean > median, the distribution is positively
skewed (long tail on the right).
If the mean < median, the distribution is negatively
skewed (long tail on the left).
If mean ≈ median, the distribution is approximately
symmetric.
Range: Usually between -3 and +3, but can go beyond in
extreme cases.
2. Bowley’s coefficient: Bowley’s coefficient is based on
quartiles instead of mean or median, so it’s less affected by
extreme values.
Formula:
Where:
Q1 = first quartile (25th percentile)
Q2 = median (50th percentile)
Q3 = third quartile (75th percentile)
NOTE:
Positive value → right skew
Negative value → left skew
Zero → symmetric distribution
3. Kelly’s coefficient: Kelly’s coefficient is another quartile-
based measure, but it focuses on the relative distances
between the median and the quartiles.
Formula:
Measures difference in spread between the upper half and
lower half of data.
. Positive → longer upper tail (right skew)
. Negative → longer lower tail (left skew)
4. Moment coefficient of skewness: This uses statistical
moments (mean, variance, third central moment) to quantify
skewness mathematically.
(iii) Role of Skewness and Kurtosis
Skewness shows direction and extent of asymmetry:
Skewness refers to the degree to which a distribution
departs from symmetry. It shows the direction in which the
data are skewed and the extent or amount of that skewness.
Kurtosis measures peakedness or flatness: Kurtosis
describes the degree of peakedness or flatness of a
distribution when compared to a normal distribution. A
high kurtosis value indicates a sharply peaked distribution
with heavy tails, meaning more values are concentrated
near the mean.
Both help interpret shape, spread, and reliability of
data: Skewness and kurtosis together help in understanding
the overall shape of a data distribution by showing whether
the data are symmetrical, skewed, sharply peaked, or flat.
Interpretation
The distribution is slightly positively skewed.