You are on page 1of 20

PRESENTATION ON LOG-NORMAL DISTRIBUTION

Presented by: YOG KUNWAR(2243) SHIVANI(2237) KIRANPAL(2217) KIRANARANI(2218)

INTRODUCTION
Most of the data does not exhibit symmetry & instead skew towards either very large positive or very large negative values. If the data is positively skewed, one common choice is a log-normal distribution .

LOGNORMAL DISTRIBUTION
In probability theory, lognormal distribution is a continuous probability distribution of random variable whose algorithm is normally distributed. Or A statistical distribution of random variables which have normally distributed logarithm. i.e. If the random variable Y is log-normally distributed, then X=log(Y) has a normal distribution. Likewise, if X has a normal distribution, then Y=exp(X) has a log-normal distribution. A variable X is log-normally distributed if Y = LN(X) is normally distributed with "LN" denoting the natural logarithm.

LOGNORMAL DISTRIBUTION contd.


A random variable which is log-normally distributed takes only positive real values.
i.e. log-normal distribution is applicable when quantity of interest must be positive , since log(X) exists when X is positive. Log-normal distribution is used to model continuous random quantities.

GRAPH OF LOG-NORMAL & NORMAL DISTRIBUTION f

BRIEF HISTORY
GALTON and MCALISTER initiated the study of the distribution in papers published together, relating it to the use of the geometric mean as an estimate of location in 1897. KAPTEYN (1903) discussed the genesis of the distribution, KAPTEYN and VAN UVEN (1916) gave a graphical method of estimating the parameters. The distribution is occasionally referred to as the GALTON distribution, after FRANCIS GALTON. The lognormal distribution was found to be accurately representing the distribution of critical dose for a number of drugs; this is also the first time that lognormal distribution applied in real life.

PARAMETERS OF LOG-NORMAL DISTRIBUTION


Log Mean: Also called Location Parameter or arithmetic mean or expected value. Denoted by E(X) or M .

where m = mean of normal distribution v = variance of normal distribution

PARAMETERS OF LOG-NORMAL DISTRIBUTION contd. Standard deviation: Also called Scale Parameter.
Denoted by .
= Now log-normal distribution X, in terms of mean and standard deviation.

Where Z=standard normal variable

Variance: Square of standard deviation. Denoted by Var(X).

Probability Density Function(PDF):

GRAPHS FOR PDF


Keeping constant

Cumulative distribution function(CDF):

where erf= error function that occurs in probability statistics. erfc= complementary error function. = cumulative distribution function of standard normal distribution.

GRAPHS FOR CDF


Keeping constant

Mode: Mode is the point of global maximum of probability density function.

Median: Median is a point where Fx =

Cofficient of variation: It is the ratio of standard deviation over mean( / )


Cofficient of variation =

RELATON WITH OTHER DISTRIBUTIONS


The log-normal distribution is closely related to normal distribution . If X is distributed log-normally with parameters and , then log(X) is distributed normally with mean and standard deviation . i.e. If is a normal distribution, then If is distributed log-normally, then is a normal random variable. If are n independent log-normally distributed variables and , then Y is also distributed log-normally:

When = 0 and

0 , the graph looks like normal distribution.

DIFFERENCE BETWEEN NORMAL & LOG-NORMAL DISTRIBUTION Log-normal distribution is applicable when quantity of interest must be positive , since log(X) exists when X is positive. i.e. a random variable which is log-normally distributed takes only positive real values. Whereas normal distribution is applicable to quantity of interest that can be positive or negative , i.e. a random variable which is normally distributed take positive or negative real values.

DIFFERENCE BETWEEN NORMAL & LOG-NORMAL DISTRIBUTION (GRAPH WISE)

Log-normal distribution graph is skewed towards right. But normal distribution graph is uniformly distributed over the scale.

APPLICATIONS OF LOG-NORMAL DISTRIBUTION


The log-normal distribution is important in the description of natural phenomena. As time series creates random variables. By taking the natural log of each random variable, the resulting set of numbers will be log-normally distributed. Can model instances such as : Change in price distribution of a stock or commodity position. Survival rate of cancer patients. Can also be used in scientific fields such as : Agriculture Biology Hydrology Photographic emulsion Also extensively used in reliability application to model failure times.

MATLAB FUNCTION FOR LOG-NORMAL DISTRIBUTION


lognstat function [M,V] = lognstat(mu,sigma) Where mu = mean sigma = standard deviation M & V are variables to store result.

You might also like