[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
David Airey <david.airey@vanderbilt.edu> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
st: comparing tables of ranks |

Date |
Sun, 14 Aug 2005 17:27:34 -0500 |

.

I'm trying to get,

1) a p value for a set of rankings occurring by chance, and

2) a p value for the correspondence between two sets of rankings.

The first data set has rankings of 3 molecular measures (relative abundance of protein isoforms) from 3 inbred (isogenic) mouse strains. In the table below, the 3 strains of mice are c57, dba, and balb.

strain ranks

--------------------

isoform c57 dba balb

------------------------------

1 1 3 2

2 1 3 2

3 1 2 3

The second data set has ranking of strains for 5 measures of behavior.

strain ranks

--------------------

behavior c57 dba balb

------------------------------

1 1 3 2

2 1 3 2

3 1 2 3

4 1 3 2

5 1 2 3

For example, regarding the p value for (1) above, I'd think that I could directly say that the probability of observing c57 being ranked "1" across 5 behavior measures would be, because there are 6 permutations for 3 objects,

(1,2,3 or 1,3,2)^5 = (1/6 + 1/6)^5 = 0.004

and for the top table,

(1,2,3 or 1,3,2)^3 = (1/6 + 1/6)^3 = 0.04

Is their a simple Stata command to get a p value for the correspondence between isoform and behavior for the strain ranks or should I develop a randomization test?

The ranks are based on the means of 10 different animals measured per strain, and different animals are in the two data sets.

Cheers,

Dave

*

* For searches and help try:

* http://www.stata.com/support/faqs/res/findit.html

* http://www.stata.com/support/statalist/faq

* http://www.ats.ucla.edu/stat/stata/

- Prev by Date:
**st: bootstrap with stata** - Next by Date:
**st: stset for conditional risk set (multiple failure) models** - Previous by thread:
**st: bootstrap with stata** - Next by thread:
**re: st: comparing tables of ranks** - Index(es):

© Copyright 1996–2016 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |