Nonlinear Models for Multi-Factor Plant Nutrition Experiments

Landes, Reid D.; Stroup, Walter W.; Paparozzi, Ellen T.; Conley, M. Elizabeth

doi:10.4148/2475-7772.1263

Cited by 2 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The modeling, analysis, and design issues for the Boron concentration variable used in this example are typical of other elemental concentrations measured in this experiment and of response variables observed in plant nutrition experiments in general. While non-linear models such as the Mitscherlich and Gompertz have intuitive appeal in nutrient-response settings and have been used successfully in past work, such as Landes, et. al.…”

Section: Discussionmentioning

confidence: 99%

“…Among several possible reasons, Mead and Pike suggested that one possibility was that response surface methods do not adequately address researchers' objectives. Landes, et. al.…”

Section: Kansas State Universitymentioning

confidence: 99%

“…Section 5 presents summary and conclusions regarding response surface methods based on suitable models, as opposed to model (1), for plant nutrition experiments. Landes, et. al.…”

Section: Kansas State Universitymentioning

confidence: 99%

“…Because the second order response surface model is inadequate and the augmented polynomial with additional points is impractical, another alternative is needed. Landes et al (1999) and Stroup and Paparozzi (2000) used Gompertz (3) and Mitscherlich (4) models. However, the boron data suggest that these models are inappropriate because of the absence of a rapid increase to plateau response.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Model Building in Multi-Factor Plant Nutrition Experiments

Olson¹,

Stroup²,

Paparozzi³

et al. 2001

Conference on Applied Statistics in Agriculture

Self Cite

View full text Add to dashboard Cite

Often, the goal of plant science experiments is to model plant response as a function of quantitative treatment factors, such as the amount of nutrient applied. As the number of factors increases, modeling the response becomes increasingly challenging, especially since the resources available for such experiments are usually severely limited. Typical methods of analysis, notably second-order response surface regression, often fail to accurately explain the data. Alternatives such as non-linear models and segmented regression have been used successfully with two-factor experiments (Landes, et. aI, 1999). This paper extends previous work to three-and-more factor experiments. Models are assessed to explain the relationship between the levels of nutrients applied and leaf, root, and shoot responses of Poinsettias from an experiment conducted by horticultural researchers at the University of Nebraska-Lincoln. These data illustrate problems that are representative of those that plant researchers typically face. Multiple regression using the Hoed function proved to be especially useful. These analyses suggest a feasible approach to design of experiments suitable for a wide variety of plant science applications with multiple factors and limited resources.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Among several possible reasons, Mead and Pike suggested that one possibility was that response surface methods do not adequately address researchers' objectives. Landes, et. al.…”

Section: Kansas State Universitymentioning

confidence: 99%

“…Section 5 presents summary and conclusions regarding response surface methods based on suitable models, as opposed to model (1), for plant nutrition experiments. Landes, et. al.…”

Section: Kansas State Universitymentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Model Building in Multi-Factor Plant Nutrition Experiments

Olson¹,

Stroup²,

Paparozzi³

et al. 2001

Conference on Applied Statistics in Agriculture

Self Cite

View full text Add to dashboard Cite

show abstract

“…Specifi cally, standard response surface methods assume that responses can be modeled by second order polynomial regression (described in detail in Materials and Methods). Landes et al (2000) using data from Macz (1997) demonstrated that nonlinear models provided descriptions of commonly occurring response-treatment relationships that were superior to second-order polynomial models. Olson et al (2001) compared various approaches that suggested possible adaptations of response surface methods suitable for plant nutrition research.…”

mentioning

confidence: 99%

How to Investigate Four-way Nutrient Interactions in Plants: A New Look at Response Surface Methods

Paparozzi¹,

Stroup²,

Conley³

2005

jashs

View full text Add to dashboard Cite

Response surface methods refer to a set of experimental design and analysis methods to study the effect of quantitative treatments on a response of interest. In theory, these methods have a broad range of applicability. While they have gained widespread acceptance and application in manufacturing and quality improvement research, they have never caught on in the agricultural sciences. We propose that this is because there has not been specific research demonstrating their usage. In this paper, two 34 factorial experiments were performed using 100 poinsettia plants (Euphorbia pulcherrima Willd. ex Klotzsch) to measure nutrient element concentrations in leaves at three rates each of nitrogen (N), sulfur (S), iron (Fe), and manganese (Mn). Three different methods of analysis were compared—the standard analysis of variance with no regression model, the quadratic regression model commonly assumed for most standard response surface methods and the Hoerl model regression, a nonlinear alternative to quadratic response. Actual nutrient element values were compared with the values predicted by each regression model and then also evaluated to see if the visual symptomology of yellowing related to those nutrient concentrations in leaves. The Hoerl model demonstrated better ability to detect biologically relevant nonlinear two-, three-, and four-way nutrient interactions. Though there was minimal replication this model characterized the treatment effects while keeping the size of the experiment manageable both in terms of time (labor) and cost of plant analyses. Additionally, it was shown that when S, Fe, and/or Mn were deficient along with N, their visual deficiency symptoms were masked by the overall yellowing associated with N deficiency. This model is recommended as the initial experiment in a series where scientists are looking to expand information already determined for two factors. Other treatment systems that this can be used with include: levels of irrigation, pesticides, and plant growth regulators.

show abstract

Nonlinear Models for Multi-Factor Plant Nutrition Experiments

Cited by 2 publications

References 3 publications

Model Building in Multi-Factor Plant Nutrition Experiments

Model Building in Multi-Factor Plant Nutrition Experiments

How to Investigate Four-way Nutrient Interactions in Plants: A New Look at Response Surface Methods

Contact Info

Product

Resources

About