Professional Documents
Culture Documents
Eshika
Eshika
Eshika
An assignment on
GRAPHICAL REPRESENTATION OF DATA
BUSINESS STATISTICS, 3rd SEMESTER
Measure of Kurtosis………………………………………………………………………………………………………………………………1
Types of Kurtosis……………………………………………………………………………………………………………………………………1
Measure of Kurtosis
Measure of kurtosis is a descriptive statistical measure used to measure the peakedness or
flatness of the curve drawn from frequency table. This is useful to access whether the given
frequency is normally distributed or not.
Traditionally, kurtosis has been explained in terms of the central peak where we can see, higher
values indicate a higher, sharper peak; lower values indicate a lower, less distinct peak.
However, “higher kurtosis means more of the variance is the result of infrequent extreme
deviations, as opposed to frequent modestly sized deviations.” In other words, it’s the tails that
mostly account for kurtosis, not the central peak.
Types of Kurtosis:
Mesokurtic Curve (Normal Curve)
Leptokurtic Curve (Peaked Curve)
Platykurtic Curve (Flat Curve
Mesokurtic Curve (Normal Curve)
The normal curve is called Mesokurtic Curve. It is also one of the three categories of curve
found in Kurtosis analysis. A curve is said to be mesokurtic if the curve drawn from the
frequency distribution is more peaked than platykurtic curve and flatter than leptokurtic curve.
According to Kelly’s measure based on percentiles, if K =0.263 then the distribution is
mesokurtic. And according to Karl Pearson’s measure, if β2 =3, then the curve is said to be
mesokurtic.
Interpretation:
1) If K = 0.263 then Mesokurtic or Normal
2) If K > 0.263 then Leptokurtic
3) If K < 0.263 then Platykurtic