Should data ever be thrown away? Pooling interval-censored data sets with different precision

Data quality is an important consideration in many engineering applications and projects. collection procedures do not always involve careful utilization of the most precise instruments strictest protocols. As a consequence, data are invariably affected by imprecision sometimes sharply varying levels data. Different mathematical representations have been suggested, including classical approach to censored which considered optimal when proposed error model correct, weaker called interval statistics based on partial identification that makes fewer assumptions. Maximizing statistical results often crucial success projects, natural question arises whether differing qualities should be pooled together or we include only measurements disregard imprecise Some worry combining can depreciate overall fear excluding lesser precision increase their uncertainty about because lower sample size implies more sampling uncertainty. This paper explores these concerns describes simulation show it advisable combine fairly with rather comparing analyses using different imprecision. Pooling sets preferred low-quality set does exceed certain level However, so long as random, may legitimate reject if its reduction counterbalance effect