1 / 15

Sequential Multiple Decision Procedures (SMDP) For PGRN mini-GAW Data

Sequential Multiple Decision Procedures (SMDP) For PGRN mini-GAW Data. Q. Zhang and M.A. Province Division of Biostatistics Washington University School of Medicine PGRN AWSII, Chicago April 28, 2005. Brief History of SMDP. Sequential Probability Ratio Test (SPRT), Wald 1947

liluye
Download Presentation

Sequential Multiple Decision Procedures (SMDP) For PGRN mini-GAW Data

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Sequential Multiple Decision Procedures (SMDP)For PGRN mini-GAW Data Q. Zhang and M.A. Province Division of BiostatisticsWashington University School of Medicine PGRN AWSII, ChicagoApril 28, 2005

  2. Brief History of SMDP Sequential Probability Ratio Test (SPRT), Wald 1947 SMDP, Bechhoffer, Kiefer, Sobel, 1968 SMDP Haseman-Elston Method (ASP), Province 2000

  3. Idea 1: Sequential Start from a small sample size Increase sample size one by one Use sequential information Do analysis at each time Stop when conclusion is reached n0+1 n0+2 … n0 n0+i … Plan experiments in next stage and save resources Use residual/extra data to do validation

  4. SNP1 SNP2 SNP2 SNP3 SNP3 SNP4 SNP4 SNP5 SNP5 SNP6 SNP6 … … SNPn SNPn Independent Test Multiple Decision Idea 2: Multiple Decision Test 1 Test 2 Test 3 Test 4 Test 5 Test 6 Test n SMDP divides populations into two groups and guarantees that there is a real difference (D) between the two groups with probability P*. SNP1 Tradeoff between false positive rate and false negative rate.

  5. Y =α+ βX +Є SNP x Drug/Treatment 11 => 0 ALCOHOL 12 => 1 X OR 22 => 2 IVY SNP Main effects SNP-Drug interactions Model: Regression Model SNP Genotypes 11 => 0 12 => 1 22 => 2 Phenotypes NPUBS NDRIVEL PCTDRIVEL RIVALSIDE GOTGRANTS

  6. Methods Regular P value Bonferroni corrected P value FDR corrected P value Fixed sample Regression (Entire data) n0 Q[h]1 Q[h]2 Q[h]3 Q[h]4 Q[h]5 … … P Probability that a real difference (D) between two groups exists n0+1 Stopping rule SMDP (Sequential) n0+2 … n0+h Sequential sum of squares of regression errors …

  7. Region 3 (86 SNPs), GOTGRANTS

  8. Region 2 (28 SNPs, IVY-SNP), RIVALSIDE

  9. Region 1 (74 SNPs, ALCOHOL-SNP), PCTDRIVEL

  10. SMDP Summary • Test, identify all signals simultaneously No multiple comparisons • Tight control statistical errors (Type I, II) • Efficient, Sequential information “Minimal” N to find significant signals • Reliable, Save rest of N for validation

  11. Thanks !

  12. Fixed sample regression Region 3 (86 SNPs), GOTGRANTS

  13. Fixed sample regressionRegion 2 (28 SNPs, IVY-SNP), RIVALSIDE

  14. Fixed sample regressionRegion 1 (74 SNPs, ALCOHOL-SNP), PCTDRIVEL

  15. Fixed sample regression of 5 phenotypes on genotypes of 188 SNPs

More Related