Skip to main content

t distribution

t Distribution

Probability Density FunctionThe formula for the probability density function of the t distribution isf(x) = (1 + x**2/nu)**(-(nu+1)/2)/[B(0.5,0.5*nu)*SQRT(nu)]
where B is the beta function and nu is a positive integer shape parameter. The formula for the beta function is
B(alpha,beta) = INTEGRAL(t**(alpha-1)*(1-t)**(beta-1)dt) where the integration is from 0 to 1
In a testing context, the t distribution is treated as a "standardized distribution" (i.e., no location or scale parameters). However, in a distributional modeling context (as with other probability distributions), the t distribution itself can be transformed with alocation parameter, mu, and a scale parameter, sigma.
The following is the plot of the t probability density function for 4 different values of the shape parameter.
plot of the t probability density function for 4 different values of the shape parameter
These plots all have a similar shape. The difference is in the heaviness of the tails. In fact, the t distribution with nu equal to 1 is aCauchy distribution. The t distribution approaches a normaldistribution as nu becomes large. The approximation is quite good for values of nu > 30.
Cumulative Distribution FunctionThe formula for the cumulative distribution function of the tdistribution is complicated and is not included here. It is given in theEvans, Hastings, and Peacock book.The following are the plots of the t cumulative distribution function with the same values of nu as the pdf plots above.
plot of the t cumulative distribution function with the same values of nu as the pdf plots above
Percent Point FunctionThe formula for the percent point function of the t distribution does not exist in a simple closed form. It is computed numerically.The following are the plots of the t percent point function with the same values of nu as the pdf plots above.
plot of the t percent point function with the same values of nu as the pdf plots above
Other Probability FunctionsSince the t distribution is typically used to develop hypothesis tests and confidence intervals and rarely for modeling applications, we omit the formulas and plots for the hazard, cumulative hazard, survival, and inverse survival probability functions.
Common Statistics
Mean0 (It is undefined for nu equal to 1.)
Median0
Mode0
RangeInfinity in both directions.
Standard DeviationSQRT(nu/(nu-2))It is undefined for nu equal to 1 or 2.
Coefficient of VariationUndefined
Skewness0. It is undefined for nu less than or equal to 3. However, the t distribution is symmetric in all cases.
Kurtosis3*(nu-2)/(nu-4)It is undefined for nu less than or equal to 4.
Parameter EstimationSince the t distribution is typically used to develop hypothesis tests and confidence intervals and rarely for modeling applications, we omit any discussion of parameter estimation.
CommentsThe t distribution is used in many cases for the critical regions for hypothesis tests and in determining confidence intervals. The most common example is testing if data are consistent with the assumed process mean.
SoftwareMost general purpose statistical software programs support at least some of the probability functions for the t distribution.

Comments

Post a Comment

Popular posts from this blog

Runs Test for Detecting Non-randomness

Runs Test for Detecting Non-randomness Purpose: Detect Non-Randomness The runs test ( Bradley, 1968 ) can be used to decide if a data set is from a random process. A run is defined as a series of increasing values or a series of decreasing values. The number of increasing, or decreasing, values is the length of the run. In a random data set, the probability that the ( I +1)th value is larger or smaller than the I th value follows a binomial distribution , which forms the basis of the runs test. Typical Analysis and Test Statistics The first step in the runs test is to count the number of runs in the data sequence. There are several ways to define runs in the literature, however, in all cases the formulation must produce a dichotomous sequence of values. For example, a series of 20 coin tosses might produce the f...
Post a Comment
Read more

Lognormal distribution

Lognormal Distribution Probability Density Function A variable X is lognormally distributed if Y = LN(X) is normally distributed with "LN" denoting the natural logarithm. The general formula for the  probability density function  of the lognormal distribution is where   is the  shape parameter ,   is the  location parameter  and  m is the  scale parameter . The case where   = 0 and  m  = 1 is called the  standard lognormal distribution . The case where   equals zero is called the 2-parameter lognormal distribution. The equation for the standard lognormal distribution is Since the general form of probability functions can be  expressed in terms of the standard distribution , all subsequent formulas in this section are given for the standard form of the function. The following is the plot of the lognormal probability density function for four values of  . There are several commo...
Post a Comment
Read more

Poisson distribution

Poisson Distribution Probability Mass Function The Poisson distribution is used to model the number of events occurring within a given time interval.The formula for the Poisson probability mass function is  is the shape parameter which indicates the average number of events in the given time interval. The following is the plot of the Poisson probability density function for four values of  . Cumulative Distribution Function The formula for the Poisson cumulative probability function is The following is the plot of the Poisson cumulative distribution function with the same values of   as the pdf plots above. Percent Point Function The Poisson percent point function does not exist in simple closed form. It is computed numerically. Note that because this is a discrete distribution that is only defined for integer values of  x , the percent point function is not smooth in the way the percent point function typically is for a continuous distribution....
Post a Comment
Read more