Conditional analysis for mixed covariates, with application to feed intake of lactating sows

摘要: We propose a novel modeling framework to study the effect of covariates various types on conditional distribution response. The methodology accommodates flexible model structure, allows for joint estimation quantiles at all levels, and involves computationally efficient algorithm. Extensive numerical investigation confirms good performance proposed method. is motivated by applied lactating sow study, where primary interest understand how dynamic change minute-by-minute temperature in farrowing rooms within day (functional covariate) associated with low feed intake sows, while accounting other sow-specific information (vector covariate).