# How to calculate t-values from percent ranks?

A norm-table from a psychological test is giving percent ranks (PR).

How can I transform those into t-values by calculation? (Assuming normal distribution.)

I found a lot of references on how to transform z --> t, but none on PR --> t.

Way back in university, we had tables with the bell-curve, to look up PR, z-values, t-values and stanines - but how to calculate?

If Excel is available to you, you can use the t.inv and norm.invfunctions. For the other direction (to get the probability from the t- or z-value), then use the t.dist and norm.dist functions. You'll get the same figures as with the tables.

Edit:

In PHP, this looks right:

• stats_cdf_normal (p, mean, sd, 1): returns float x which bounds cumulative probalility $p$
• stats_dens_normal (x , mean, sd): returns float cumulative probability

and

• stats_cdf_t (par1, par2, which): calculates any one parameter of the T distribution given values for the others.
• stats_dens_t (x, dfr)

This is all from http://php.net/manual/en/ref.stats.php

• thanks for your advice! I do have excel, but would like to code a php-solution to be able to do this online. Feb 24, 2013 at 9:20
• If you don't get an answer here, you could ask to close this question (I'm told it's very important), and migrate it on another SE site... Maybe stackoverflow: stackoverflow.com/questions/tagged/php Feb 24, 2013 at 14:09
• thanks, I'd like to leave it open, though, I still hope :-) Feb 24, 2013 at 14:26
• Do the functions from my last edit work? Can you try them? Feb 24, 2013 at 14:53
• wow!!! didn't think about that, thanks!!! Feb 24, 2013 at 15:28