Kurtosis and measures of kurtosis

Kurtosis is a statistical measure that defines how heavily the tails of a distribution differ from the tails of a normal distribution. In other words, kurtosis identifies whether the tails of a given distribution contain extreme values.
The above formula are given by prof.karl Pearson which are known as 'covexity of frequency curve' or simply kurtosis. These formula will give us idea about flatness or peakedness.It is measured by above  coefficients.If value of gamma2 is more  than zero then the curve is leptokurtic,if value equals to zero then it is mesokurtic or normal curve and if value of gamma 2 is less than zero than curve said to be platykurtic.
1)Mesokurtic
Data that follows a mesokurtic distribution shows an excess kurtosis of zero or close to zero. This means that if the data follows a normal distribution, it follows a mesokurtic distribution.

2. Leptokurtic
Leptokurtic indicates a positive excess kurtosis. The leptokurtic distribution shows heavy tails on either side, indicating large outliers.
  
3. Platykurtic
A platykurtic distribution shows a negative excess kurtosis. The kurtosis reveals a distribution with flat tails. The flat tails indicate the small outliers in a distribution.

Let us consider following example.

Thanks for reading...
Share the blog to support us
Content created by - Chandrashekhar Awate and Priyanka Pawar

Thanks for your positive feedback to our blog,we will definitely work on our weak points and your precious suggestions...

Comments

Post a Comment

Popular posts from this blog

Median

Image
  Median Median is the value of the variable that divides the ordered set of values into two equal parts. In another words,median is the middle most value of ordered( ascending or descending)set of values.50% of values are to the left side of the median and 50% values are on right side of the median. let us consider there are N values in the data set. I)when N is odd,then  Median=size of(N+1/2) th item(Arranging values in ascending or descending order) Example:  values =1,2,3,4,5 here,Median is 3 II) when N is even , median is the average of size of (N/2)th item and (N+2/2) th item. Example: Heights (in cm) = {180, 167, 154, 122, 181, 135, 123, 145, 166, 145} Rearranged Heights= {122, 123, 135, 145, 145, 154, 166, 167, 180, 181} Median = (145+154)/2 = 149.5= 149.5 Median is preferable measure of location for asymmetric distribution.Median is best measure of central tendency as it is least affected by extreme values.Median can be visually located for discrete values....
Read more

Mode

Image
Mode : Mode is an important measure of central tendency.Ya Lun Chou statement about the mode is ,"Mode is that values of series which appears most frequently than any other." In simple  words,"The mode is a value which has highest frequency." The mode may not be unique .that is there are several values or classes with the same highest frequency. I) Mode for discrete data:      Mode of sample is the observation with highest frequency. Example: A sample is 4,8,3,8,3,9,3,7,11,3,12,11 Here number 3 has maximum frequency(4). Hence given sample has mode 3. II)Mode for grouped data:      Mode of grouped data is the class centre of the modal class,while the modal class is a class which has highest frequency. Example Here 10-20 class has maximum frequency (15). Hence 10-20 is modal class. Here L=10,f1=15,fo=5,f2=8,h=20-10= 10 Mode=10+[(15-5)/(30-5-8)]×10 Mode=10+(10/17)×10 Mode=10+5.88 Mode=15.88 For example,In clothing Store,they operate their business to incl...
Read more

Sample space and event in probability

Image
  Sample space and Event Sample space:  A collection of all possible outcomes of an experiment is called sample space.It is denoted by  Ω. Example: A coin is tossed   Ω ={H,T} Where H=head, T=tail.   Event: The collection of all outcomes favorable to phenomenon is called an event. It is denoted by capital letters A,B,C.. Example: Event A is containing at least one head,if two coins are tossed.   Ω ={HH,HT,TH,TT} A={HH,HT,TH} (1) Elementary event: An event containing only one element is called as elementary or simple event. Example: Event A is getting both heads ,if two coins are tossed.   Ω ={HH,HT,TH,TT} A={HH} (2) Compound event: An event which contains more then one sample point of sample space is called a compound event. Example: Event A is containing both head and tail,if two coins are tossed. Ω ={HH,HT,TH,TT} A={HT,TH} (3)Sure event or certain event: An event containing all the points of sample space is called sure event. Example:  In an exp...
Read more