Two axioms for evaluation measures in information retrieval
Proc. of the third joint BCS and ACM symposium on Research and development in information retrieval
Information Retrieval Experiment
Information Retrieval Experiment
Measurement-theoretical investigation of the MZ-metric
SIGIR '80 Proceedings of the 3rd annual ACM conference on Research and development in information retrieval
The LIVE-project: retrieval experiments based on evaluation viewpoints
SIGIR '85 Proceedings of the 8th annual international ACM SIGIR conference on Research and development in information retrieval
Hi-index | 0.00 |
Retrieval tests are often performed with an inhomogeneous query collection, that means certain properties of queries vary within the collection. This paper investigates under which conditions this inhomogeneity may lead to a loss of measurement precision and validity and should be controlled by an experimental design. In particular, interrelationships between the design of a retrieval test, inhomogeneity of the query collection and measurement theoretical properties of the evaluation measure will be discussed. Based on these results, some recommendations for experimental design of retrieval tests are presented.