A Family of Models Involving Intersecting Straight Lines and Concomitant Experimental Designs Useful in Evaluating Response to Fertilizer Nutrients

摘要: For many cropping situations, especially in developinig countries, quadratic surfaces do not fit the responses of cer tain crops to fertilizer. Use seconid or der designs with stanidard statistical anid econiomic interpretive techniques may result costly biases estimates optimal fertilizer rate. Also, there is a potential pollution problem. A family linear-plateau models, coinsistiing intersecting straight linies, proposed for fitting response data which exhibit plateau effect. The regression coefficients are easily comptuted uisinig desk calcutlator computer, and economic interpretations simple. Techniques fitting, parameter estimation, interpretation described. mtulti-nutrtiienit experiments, complete factorial experiment nulmber levels each nutrient considered be best design foi both evaltuating model theii estimating ntutrient levels. Preliminary information provide basis deciding nutrients apt produce response. In maniy soil-crop only NTP AT experiments required, becatuse other already at adequiate levels; hence, amotunt experimental material redistributed by havinig fewer factors, bult more factor stu.died. Two cutrrently used designs, based on preliminary levels, described; one-factor-at-a-time has disadvantage providing no estimate interaction. Several suggested. We recommend concenitratiing seveial tieatment vicinity aniticipated optimtum. Since sloping phase pattern mole important thani plateatu phase, it shouild receive attention when distributitng treatment