Quality of Experience is a parameter used to express the relationship between Quality of Service and the satisfaction of network service subscribers. The modeling of Quality of Experience demands for solving a multidimensional problem. In this paper, we present a Quality of Experience analysis of streaming videos. Related to this, we show that we can reduce the dimensions of the Quality of Experience modeling with the help of Principle Component Analysis techniques. We demonstrate that for our data set the Zero Throughput Time and the Packet Delay Variation are enough to get a picture of the state of the network. We further calculate the Mahalanobis distance to analyze the outliers in the data set. We illustrate that for our data set the 97.5% quantile for the Mahalanobis distance is a good threshold that indicates low user perception. We also advocate the use of robust statistics in the analysis of Quality of Experience as we are dealing with contaminated data sets.