統計数理研究所

Lecture given by Professor Terrence Speed

Date
November 6th, 2012 (Tuesday)  16:00-17:00
Admission Free, No Booking Necessary
Place
D313 (seminar room 5) ,The Institute of Statistical Mathematics
Speaker
Terrence Speed (Bioinformatics division, The Walter and Eliza Hall institute of medical research, Department of Statistics, UC Berkeley), jointly with Johann Gagnon-Bartsch and Laurent Jacob
Title
Removing unwanted variation from high--‐dimensional data using negative control
Abstract

High dimensional data suffer from unwanted variation, such as the batch effects common in microarray data. Unwanted variation complicates the analysis of high dimensional data, leading to high rates of false discoveries, high rates of missed discoveries, or both.

In many cases the factors causing the unwanted variation are unknown and must be inferred from the data. In such cases, negative controls may be used to identify the unwanted variation and separate it from the wanted variation. In a paper published in 2012 in Biostatistics, we presented a method called RUV--‐2 for doing so. In this talk I’ll describe a new method, RUV--‐4, to adjust for unwanted variation in high dimensional data with negative controls. RUV--‐4 may be used when the goal of the analysis is to determine which of the features are truly associated with a given factor of interest. One nice property of RUV--‐4 is that it is relatively insensitive to the number of unwanted factors included in the model; this makes estimating the number of factors less critical. I’ll also present a novel method for estimating the features’ variances that may be used even when a large number of unwanted factors are included in the model and the design matrix is full rank. We named this the “inverse method for estimating variances.” By combining RUV--‐4 with the inverse method, it is no longer necessary to estimate the number of unwanted factors at all.

Using both real and simulated data I’ll compare the performance of
RUV--‐4 with that of other adjustment methods such as SVA, LEAPP, ICE, and RUV--‐2. We find that RUV--‐4 and its variants perform as well or better than other methods.

Note
This lecture is organised by the risk analysis research center. We also plan to have a mixer from 17:30 at the west lounge in the 6th floor. If you want to make an appointment to discuss with him, please let me know at smanoism.ac.jp. He will also give the keynote speech at the ROIS symposium: http://www.rois.ac.jp/sympo/2012/index.html.
▲ このページのトップへ