BLUPF90

User Tools

Site Tools

Trace:
readme.thrgibbs1

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
Next revisionBoth sides next revision
readme.thrgibbs1 [2012/05/29 13:02] – shogoreadme.thrgibbs1 [2013/09/30 17:04] – shogo
Line 1: Line 1:
-=====THRGIBBS1F90===== +====== THRGIBBS1F90 ======
-// +
-Gibbs sampler for threshold-linear mixed models+
  
 =====Summary===== =====Summary=====
-Based on THRGIBBSF90 written by DeukHwan Lee at the University of Georgia, 2001 rerived from  GIBBS2F90 by I. Misztal (2001). +Gibbs sampler for threshold-linear mixed models. The original program (THRGIBBSF90) was written by DeukHwan Lee in 2001 based on GIBBS2F90. Rewritten by Shogo Tsuruta in 2004. See PREGSF90 with genotypes (SNP) for options. 
-Rewritten by Shogo Tsuruta, 2004 +\\ 
-last modified 09/05/2007 +THRGIBBS1F90 implements Gibbs sampler for mixed threshold-linear models involving multiple categorical and linear variables. Thresholds and variances can be estimated or assumed. Another version of thrgibbs1f90b for binary responses is available. 
- +\\ 
- +See PREGSF90 with genotypes (SNP) for options.
-=====Functionality===== +
-THRGIBBS1F90  implements Gibbs sampler for mixed threshold-linear models +
-involving multiple categorical and linear variables. Thresholds and variances +
-can be computed or assumed. Another version of thrgibbs1f90b for binary responses is available. The followong options are available:+
  
 =====Parameters===== =====Parameters=====
Line 21: Line 15:
 OPTION cat 0 0 2 5 OPTION cat 0 0 2 5
 </file> </file>
-0s indicate that the first and second traits are linear. +"0" indicate that the first and second traits are linear. 
-2 and 5 indicate that the third and fourth traits are categorical with 2 and 5 categories.+"2" and "5" indicate that the third and fourth traits are categorical with 2 (binary) and 5 categories.
 <file> <file>
 OPTION fixed_var all OPTION fixed_var all
 </file> </file>
-Store all samples for solutions in "all_solutions" and posterior means and SD for all effects in "final_solutions" +Store all samples for solutions in "all_solutions" and posterior means and SD for all effects in "final_solutions", assuming that (co)variances in the parameter file are known.
-assuming that (co)variances set in the parameter file are known.+
 <file> <file>
 OPTION fixed_var all 1 2 3 OPTION fixed_var all 1 2 3
 +</file>
 Store all samples for solutions in "all_solutions" and posterior means and SD for 1, 2, and 3 effects in "final_solutions". Store all samples for solutions in "all_solutions" and posterior means and SD for 1, 2, and 3 effects in "final_solutions".
-</file> 
 <file> <file>
 OPTION fixed_var mean OPTION fixed_var mean
Line 43: Line 36:
 OPTION solution all OPTION solution all
 </file> </file>
-Store all samples for solutions in "all_solutions" and posterior means and SD for all effects.+Store all samples for solutions in "all_solutions" and posterior means and SD for all effects. The file "all_solutions" could be very large.
 <file> <file>
 OPTION solution all 1 2 3 OPTION solution all 1 2 3
 </file> </file>
-Store all samples for solutions in "all_solutions" and posterior means and SD for 1, 2, and 3 effects.+Store all samples for solutions in "all_solutions" and posterior means and SD for 1, 2, and 3 effects. The file "all_solutions" could be very large.
 <file> <file>
 OPTION solution mean OPTION solution mean
Line 59: Line 52:
 OPTION cont 10000 OPTION cont 10000
 </file> </file>
-10000 is the number of samples run previously. +"10000" is the number of samples run previously. The user can restart the program from the last run.
-The user can restart the program from the last run.+
 <file> <file>
-OPTION prior 10+OPTION prior 5 2 -1 5 
 </file> </file>
-10 is the degree of belief for the priors specified in the parameter file.+The (co)variance  priors are specified in the parameter file.\\ 
 +Degree of belief for all random effects should be specified using the following structure:\\ 
 +OPTION prior eff1 db1    eff2 db2 ...    effn dbn    -1 dbres\\ 
 +effx correspond to the effect number and dbx to the degree of belief for this random effect, -1 corresponds to the degree of belief of the residual variance.\\ 
 +In this example 2 is the degree of belief for the 5th effect, and 5 is the degree of belief for the residual.\\
 <file> <file>
 OPTION seed 123 -432 OPTION seed 123 -432
Line 72: Line 68:
 OPTION thresholds 0.0 1.0 2.0 OPTION thresholds 0.0 1.0 2.0
 </file> </file>
-Set the fixed the thresholds +Set the fixed thresholds. No need to set 0 for binary traits.
-No need to set 0 for binary traits+
 <file> <file>
-OPTION residual 1+OPTION residual 1.
 </file> </file>
-Set the residual variance = 1+Set the residual variance = 1.
 <file> <file>
-OPTION censored xx+OPTION censored xx.
 </file> </file>
 Negative values of the last category in the data set indicate censored records. "xx" determines the lower and upper limit of the category + xx when sampling from the distribution. Negative values of the last category in the data set indicate censored records. "xx" determines the lower and upper limit of the category + xx when sampling from the distribution.
-<file> +OPTION SNP_file snp
-OPTION missing -1+
 </file> </file>
-Change the missing value for a continuous trait (default 0). This is not tested yet. +Specify the SNP file name to use genotype data.
readme.thrgibbs1.txt · Last modified: 2024/03/25 18:22 by 127.0.0.1
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki