Systematic Analysis of Experiment Precision Measures and Methods for Experiments Comparison

TL;DR

This paper introduces a systematic framework for comparing the precision of subjective experiments in multimedia quality assessment, using three measures and three comparison methods validated through simulations and real-world data.

Contribution

It proposes a novel framework with measures and methods for assessing and comparing experiment precision in subjective multimedia quality experiments.

Findings

Proposed measures effectively capture experiment precision.

Comparison methods reliably differentiate experiment quality.

Framework works well on both simulated and real data.

Abstract

The notion of experiment precision quantifies the variance of user ratings in a subjective experiment. Although there exist measures that assess subjective experiment precision, there are no systematic analyses of these measures available in the literature. To the best of our knowledge, there is also no systematic framework in the Multimedia Quality Assessment field for comparing subjective experiments in terms of their precision. Therefore, the main idea of this paper is to propose a framework for comparing subjective experiments in the field of MQA based on appropriate experiment precision measures. We present three experiment precision measures and three related experiment precision comparison methods. We systematically analyse the performance of the measures and methods proposed. We do so both through a simulation study (varying user rating variance and bias) and by using data from four real-world Quality of Experience (QoE) subjective experiments. In the simulation study we focus on crowdsourcing QoE experiments, since they are known to generate ratings with higher variance and bias, when compared to traditional subjective experiment methodologies. We conclude that our proposed measures and related comparison methods properly capture experiment precision (both when tested on simulated and real-world data). One of the measures also proves capable of dealing with even significantly biased responses. We believe our experiment precision assessment framework will help compare different subjective experiment methodologies. For example, it may help decide which methodology results in more precise user ratings. This may potentially inform future standardisation activities.