Brian Dunning's FileMaker Custom Functions

_Normdist ( z ; mu ; sigma )

FileMaker implementation of NORMDIST Excel function

  Average rating: 4.7 (31 votes) Log in to vote

Mislav Kos   Mislav Kos
Soliant Consulting
http://www.soliantconsulting.com

Share on Facebook Share on Twitter

  Sample input:
( 100; 100; 15 )
( 90 ; 100; 15 )
( 70 ; 100; 15 )
( 130; 100; 15 )
  Sample output:
0.500000001
0.252492467
0.022750062
0.977249938

Compare to Excel
0.500000000
0.252492538
0.022750132
0.977249868

  Function definition: (Copy & paste into FileMaker's Edit Custom Function window)

PURPOSE:
To provide a near equivalent of the NORMDIST Excel function, for when its "cumulative" parameter is set to true.

RESULT:
The cumulative probability that the observed value of a normal random variable with mean mu and standard deviation sigma will be less than or equal to parameter z.

DEPENDENCIES:
This custom function requires the _Normsdist ( z ) custom function.

NOTES:
This custom function is a FileMaker implementation of the NORMDIST function in Excel.
Caution: This custom function is ONLY AN APPROXIMATION of the Excel function;
i.e. it will calculate an approximate answer rather than the exact answer.
(Note: The same is true of the Excel function.)
The results are accurate to several decimal places, which is typically sufficient for most uses.

Also see the custom function _Normsdist ( z ).

The difference between NORMDIST and NORMSDIST:
- NORMSDIST applies to standard normal distribution.
- NORMDIST applies to any normal distribution.
- A standard normal distribution has a mean of 0 and a standard deviation of 1.

The calculation was adapted from http://www.wilmott.com/messageview.cfm?catid=8&threadid=78622.

Here are some notes on the NORMDIST Excel function from http://support.microsoft.com/kb/827371:
- The normal distribution is a continuous probability distribution whose shape is determined by its mean, mu, and standard deviation, sigma.
- The normal distribution with mean mu and standard deviation sigma is centered at mu and has half of its probability to the left of mu and half to the right.
- The /standard/ normal distribution is the special case where mu = 0 and sigma = 1.
- The probability is distributed according to the familiar bell-shaped curve with the total area under the curve equal to 1.
- The probability that a value that is less than or equal to z will occur (also called cumulative probability up to z) is the area under this curve to the left of z.
- In NORMDIST, when the last argument is set to TRUE, NORMDIST returns the cumulative probability that the observed value of a Normal random variable with mean mu and standard deviation sigma will be less than or equal to z.

 

Comments

Log in to post comments.

 

Note: these functions are not guaranteed or supported by BrianDunning.com. Please contact the individual developer with any questions or problems.

Under construction. Email me your wish list for improvements.