@article{Fajriyah_2016, title={A Study of Convolution Models for Background Correction of BeadArrays}, volume={45}, url={https://ajs.or.at/index.php/ajs/article/view/vol45-2-2}, DOI={10.17713/ajs.v45i2.92}, abstractNote={<p>The robust multi-array average (RMA), since its introduction in Irizarry, Bolstad,<br />Collin, Cope, Hobbs, and Speed (2003a); Irizarry, Hobbs, Collin, Beazer-Barclay, An-<br />tonellis, Scherf, and Speed (2003b); Irizarry, Wu, and Jaee (2006), has gained popularity<br />among bioinformaticians. It has evolved from the exponential-normal convolution to the<br />gamma-normal convolution, from single to two channels and from the Aymetrix to the<br />Illumina platform.<br />The Illumina design provides two probe types: the regular and the control probes.<br />This design is very suitable for studying the probability distribution of both and one can<br />apply a convolution model to compute the true intensity estimator.<br />In this paper, we study the existing convolution models for background correction of<br />Illumina BeadArrays in the literature and give a new estimator for the true intensity,<br />assuming that the intensity value is exponentially or gamma distributed and the noise has<br />lognormal distribution.<br />Our study shows that one of our proposed models, the gamma-lognormal with the<br />method of moments for parameters estimation, is the optimal one for the benchmark-<br />ing data set with benchmarking criteria, while the gamma-normal model has the best<br />performance for the benchmarking data set with simulation criteria.<br />For the publicly available data sets, the gamma-normal and the exponential-gamma<br />models with maximum likelihood estimation method can not be used and our proposed<br />models exponential-lognormal and gamma-lognormal have the best performance, showing<br />a moderate error in background correction and in the parametrization.</p>}, number={2}, journal={Austrian Journal of Statistics}, author={Fajriyah, Rohmatul}, year={2016}, month={Feb.}, pages={15–33} }