BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250625T140816EDT-8274NuMf2u@132.216.98.100
DTSTAMP:20250625T180816Z
DESCRIPTION:Excess False Positives in Negative-Binomial Based Analysis of D
 ata from RNA-Seq Experiments \n\nDavid M. Rocke1\,2\, PhD and Yilun Zhang\
 , MS1\n	\n	1Division of Biostatistics\, Department of Public Health Sciences
 \, UC Davis\n	 2Department of Biomedical Engineering\, UC Davis\n	\n	Key Word
 s: RNA-Seq\, Gene Expression\, Negative Binomial\, DESeq\, edgeR\, limma-v
 oom\n\n \n\nRNA-Seq data are increasingly used for whole-genome differenti
 al mRNA expression analysis in lieu of gene expression arrays such as thos
 e from Affymetrix and Illumina. Because the raw data in RNA-Seq consist of
  counts of fragments mapping to each gene or exon\, and because the counts
  are over-dispersed\, it is common to model the distribution as negative b
 inomial. Yet empirically methods based on the negative binomial generate o
 ften massively inflated false positives whether real data are used or simu
 lated negative binomial data. This appears to be a consequence of the fact
  that the negative binomial with unknown scale is not an exponential famil
 y distribution\, and that as a quasi-likelihood\, the link function\, and 
 thus the natural parameter\, are functions of the scale parameter. Consequ
 ently also\, a linear model with negative binomial quasi-likelihood is not
  a proper generalized linear model unless the scale is known. We demonstra
 te that\, even when the data are truly negative binomial\, it is better to
  use transformation or weighting followed by standard linear models than i
 t is to fit a version of a generalized linear model with estimated scale.
 \n
DTSTART:20170928T160000Z
DTEND:20170928T170000Z
LOCATION:room 908\, McIntyre Medical Building\, CA\, QC\, Montreal\, H3G 1Y
 6\, 3655 promenade Sir William Osler
SUMMARY:QLS Featured Seminar - David Rocke
URL:/qls/channels/event/qls-featured-seminar-david-roc
 ke-270489
END:VEVENT
END:VCALENDAR