Chapter Contents |
Previous |
Next |

The INBREED Procedure |

The OUTCOV= data set has the following variables:

- a list of BY variables, if there is a BY statement
- the generation variable, if there is a CLASS statement
- the gender variable, if there is a GENDER statement
- _Type_, a variable indicating the type of observation. The valid values of the _Type_ variable are `COV' for covariance estimates and `INBREED' for inbreeding coefficients.
- _Panel_, a variable indicating the panel
number used when populations delimited by BY
groups contain different numbers of individuals.
If there are
*n*individuals in the first BY group and if any subsequent BY group contains a larger population, then its covariance/inbreeding matrix is divided into panels, with each panel containing*n*columns of data. If you put these panels side by side in increasing _Panel_ number order, then you can reconstruct the covariance or inbreeding matrix. - _Col_, a variable used to name columns
of the inbreeding or covariance matrix.
The values of this variable start with `COL',
followed by a number indicating the column number.
The names of the individuals corresponding to any given
column
*i*can be found by reading the individual's name across the row that has a _Col_ value of `COL*i*'. When the inbreeding or covariance matrix is divided into panels, all the rows repeat for the first*n*columns, all the rows repeat for the next*n*columns, and so on. - the variable containing the names of the individuals, that is, the first variable listed in the VAR statement
- the variable containing the names of the first parents, that is, the second variable listed in the VAR statement
- the variable containing the names of the second parents, that is, the third variable listed in the VAR statement
- a list of covariance variables Col1-Col
*n*, where*n*is the maximum number of individuals in the first population

The functions of the variables _Panel_ and _Col_ can best be demonstrated by an example. Assume that there are three individuals in the first BY group and that, in the current BY group (Byvar=2), there are five individuals with the following covariance matrix.

COV |
1 |
2 |
3 |
4 |
5 |

1 | Cov(1,1) | Cov(1,2) | Cov(1,3) | Cov(1,4) | Cov(1,5) |

2 | Cov(2,1) | Cov(2,2) | Cov(2,3) | Cov(2,4) | Cov(2,5) |

3 | Cov(3,1) | Cov(3,2) | Cov(3,3) | Cov(3,4) | Cov(3,5) |

4 | Cov(4,1) | Cov(4,2) | Cov(4,3) | Cov(4,4) | Cov(4,5) |

5 | Cov(5,1) | Cov(5,2) | Cov(5,3) | Cov(5,4) | Cov(5,5) |

Panel 1 | Panel 2 |

Then the OUTCOV= data set appears as follows.

Byvar |
_Panel_ |
_Col_ |
Individual |
Parent |
Parent2 |
Col1 |
Col2 |
Col3 |

2 | 1 | COL1 | 1 | Cov(1,1) | Cov(1,2) | Cov(1,3) | ||

2 | 1 | COL2 | 2 | Cov(2,1) | Cov(2,2) | Cov(2,3) | ||

2 | 1 | COL3 | 3 | Cov(3,1) | Cov(3,2) | Cov(3,3) | ||

2 | 1 | 4 | Cov(4,1) | Cov(4,2) | Cov(4,3) | |||

2 | 1 | 5 | Cov(5,1) | Cov(5,2) | Cov(5,3) | |||

2 | 2 | 1 | Cov(1,4) | Cov(1,5) | . | |||

2 | 2 | 2 | Cov(2,4) | Cov(2,5) | . | |||

2 | 2 | 3 | Cov(3,4) | Cov(3,5) | . | |||

2 | 2 | COL1 | 4 | Cov(4,4) | Cov(4,5) | . | ||

2 | 2 | COL2 | 5 | Cov(5,4) | Cov(5,5) | . |

Notice that the first three columns go to the first panel (_Panel_=1), and the remaining two go to the second panel (_Panel_=2). Therefore, in the first panel, `COL1', `COL2', and `COL3' correspond to individuals 1, 2, and 3, respectively, while in the second panel, `COL1' and `COL2' correspond to individuals 4 and 5, respectively.

Chapter Contents |
Previous |
Next |
Top |

Copyright © 1999 by SAS Institute Inc., Cary, NC, USA. All rights reserved.