Microarrays are part of a new class of biotechnologies which allow the monitoring of expression levels four thousands of genes simultaneously. The problem is now to make sense of the resulting massive data set. In this thesis the results from five different methods for differential analysis of oligonucleotide microarray data are evaluated. The methods are simple classic t-test and Mann-Whitney U test, the software GeneSpring and Significance Analysis of Microarrays (SAM) and the use of Affymetrix software in combination with a scoring system. The methods are used to analyse two different microarray data sets with different number of replicates. These data sets are further divided in different ways to examine different questions that still are unsolved problems in the microarray technology. The aim of the evaluation is to examine the reliability of the results obtained from differential analysis of microarray data.