Estimation of correlation between various types of pixel intensities in a single spot

Kalesh M. Karun, V. S. Binu, N. Sreekumaran Nair, K. Manjunatha Prasad, Kala M. Karun, Keerthana Prasad, K. M. Girisha

Research output: Contribution to journalArticlepeer-review


In complementary DNA (cDNA) microarray experiments, the measurement of interest is signal intensity ratio of spots. Each spot have four types of pixel intensities namely red foreground, green foreground, red background and green background. The uncertainty associated with the intensity ratio of a spot depends on the correlations between intensities of these pixels. In this article, we propose a method to estimate correlations between various types of pixel intensities within a spot using a modied form of Moran's I spatial autocorrelation. We estimate these correlations for eight selected spots from image les downloaded from the Gene Expression Omnibus (GEO) database. These estimated correlations are used for ending the uncertainty associated with each of the selected eight spots using the theory of error propagation. We observed that the estimated uncertainty associated with intensity ratio of a spot is less if we consider the correlation between various pixel intensities compared to assuming zero correlation.

Original languageEnglish
Pages (from-to)58-67
Number of pages10
JournalElectronic Journal of Applied Statistical Analysis
Issue number1
Publication statusPublished - 2016

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modelling and Simulation


Dive into the research topics of 'Estimation of correlation between various types of pixel intensities in a single spot'. Together they form a unique fingerprint.

Cite this