NORMSDIST for the TI-89 Calculator

I have an old version of the TI-89 (circa 1997), and it is conveniently missing the stats functions. 

The most painful of these is the Probability function P(x), which is similar to the NORMSDIST function in excel.

If you want to add it to you TI-89, here is how.

Note: this is based on Microsoft's implementation of NORMSDIST, which can be found here.

We are going to define some functions. If you've never done this before, don't worry. Its easy.


First, we define a helper function tt(x). 

  1. From the Home screen, Hit F4.
  2. Select "Define"
  3. Type this:
    Define tt(x)=(1/(1+.2316419*x))
  4. Hit Enter. It should read 'Done'

Next, we define another helper function zz(x).

  1. From the Home screen, Hit F4
  2. Select "Define"
  3. Type this:
    Define zz(x)=(1/(√(2*Π))*e^(-x^2/2)) 

    **These are the Square Root, Pi, and e^ symbols that are native to the TI-89. Also, its a Negative x, not Minus x.

  4. Hit Enter. It should read 'Done'

Finally, we define the probability function prob(x). You can rename this to normsdist, but its to long for my tastes

  1. From the Home screen, Hit F4
  2. Select "Define"
  3. Type this:
    Define prob(x)=(1-zz(x)*(0.31938153*tt(x)+ -0.356563782*(tt(x)^2)+1.781477937*(tt(x)^3)+-1.821255978*(tt(x)^4)+1.330274429*(tt(x)^5))

    **These are negative numbers, not subtraction symbols, so make sure you use the proper key on the TI-89 or it will give you an error

  4. Hit Enter. It should read 'Done'

Check you work on the TI-89

To use a function just type it in like such

tt(.625)  and press Enter.


tt(.625) = .8735

zz(.625) = .3281

prob(.625) =  .734

And in Excel:

=NORMSDIST(.625) = .734 

You never need to use tt(), zz(), they're just helper functions.

Posted by Dustin Hawkins at 16:33 | Comments (0) | Trackbacks (0)

Trackbacks
Trackback specific URI for this entry

No Trackbacks

Comments
Display comments as (Linear | Threaded)

No comments

Add Comment

Enclosing asterisks marks text as bold (*word*), underscore are made via _word_.
E-Mail addresses will not be displayed and will only be used for E-Mail notifications.
You can use [geshi lang=lang_name [,ln={y|n}]][/geshi] tags to embed source code snippets.