Details
| Original language | English |
|---|---|
| Pages (from-to) | 69-79 |
| Number of pages | 11 |
| Journal | Journal of Agronomy and Crop Science |
| Volume | 201 |
| Issue number | 1 |
| Early online date | 19 May 2014 |
| Publication status | Published - 1 Feb 2015 |
Abstract
Two or higher-order factorial designs are very common in agricultural and horticultural experiments. The evaluation of such trials by analysis of variance (anova) and the corresponding F-tests for the interaction effects covers only a global decision concerning the presence of interactions. This study presents a straightforward method, which provides a more detailed analysis of interactions via multiple contrast tests. The presented approach takes both the structure of each factor and the research question into account by building user-defined product-type contrasts. Simultaneous inference for these user-specified interaction contrasts that controls the overall error rate is available. In addition to adjusted P-values, it is recommended to use simultaneous confidence intervals to present the magnitude, direction and the biological relevance of the interaction effects. The proposed method is demonstrated using two horticultural trials. Furthermore, the authors provide a collection of worked examples using the R (A Language and Environment for Statistical Computing, 2013, R Foundation for Statistical Computing, Vienna, Austria) add-on package statint stored on github (https://github.com/AKitsche/statint).
Keywords
- Adjusted P-values, Analysis of variance, Interaction effect, Simultaneous confidence intervals
ASJC Scopus subject areas
- Agricultural and Biological Sciences(all)
- Agronomy and Crop Science
- Agricultural and Biological Sciences(all)
- Plant Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Journal of Agronomy and Crop Science, Vol. 201, No. 1, 01.02.2015, p. 69-79.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Analysis of Statistical Interactions in Factorial Experiments
AU - Kitsche, Andreas
AU - Schaarschmidt, Frank
N1 - Funding information: We thank members of the Miura laboratory, especially Vicente Gapuz III, Kayla Andrada, and Dr. Zhiping Zhang, for providing feedback and technical assistance with the project. We also thank Dr. Minkyung Kim for experimental advice and Dr. Brian Perrino and Dr. Brad Ferguson for sharing reagents. Funding was provided to P.M. and W.Y. from National Institute of General Medical Sciences grant P30 GM110767; G.S.M. was supported by R01 EY025205 (National Eye Institute; P.M. was supported by R35 GM138319 (National Institute of General Medical Sciences). Core facilities at the University of Nevada, Reno campus were supported by NIGMS COBRE P30 GM103650.
PY - 2015/2/1
Y1 - 2015/2/1
N2 - Two or higher-order factorial designs are very common in agricultural and horticultural experiments. The evaluation of such trials by analysis of variance (anova) and the corresponding F-tests for the interaction effects covers only a global decision concerning the presence of interactions. This study presents a straightforward method, which provides a more detailed analysis of interactions via multiple contrast tests. The presented approach takes both the structure of each factor and the research question into account by building user-defined product-type contrasts. Simultaneous inference for these user-specified interaction contrasts that controls the overall error rate is available. In addition to adjusted P-values, it is recommended to use simultaneous confidence intervals to present the magnitude, direction and the biological relevance of the interaction effects. The proposed method is demonstrated using two horticultural trials. Furthermore, the authors provide a collection of worked examples using the R (A Language and Environment for Statistical Computing, 2013, R Foundation for Statistical Computing, Vienna, Austria) add-on package statint stored on github (https://github.com/AKitsche/statint).
AB - Two or higher-order factorial designs are very common in agricultural and horticultural experiments. The evaluation of such trials by analysis of variance (anova) and the corresponding F-tests for the interaction effects covers only a global decision concerning the presence of interactions. This study presents a straightforward method, which provides a more detailed analysis of interactions via multiple contrast tests. The presented approach takes both the structure of each factor and the research question into account by building user-defined product-type contrasts. Simultaneous inference for these user-specified interaction contrasts that controls the overall error rate is available. In addition to adjusted P-values, it is recommended to use simultaneous confidence intervals to present the magnitude, direction and the biological relevance of the interaction effects. The proposed method is demonstrated using two horticultural trials. Furthermore, the authors provide a collection of worked examples using the R (A Language and Environment for Statistical Computing, 2013, R Foundation for Statistical Computing, Vienna, Austria) add-on package statint stored on github (https://github.com/AKitsche/statint).
KW - Adjusted P-values
KW - Analysis of variance
KW - Interaction effect
KW - Simultaneous confidence intervals
UR - http://www.scopus.com/inward/record.url?scp=84920509661&partnerID=8YFLogxK
U2 - 10.1111/jac.12076
DO - 10.1111/jac.12076
M3 - Article
AN - SCOPUS:84920509661
VL - 201
SP - 69
EP - 79
JO - Journal of Agronomy and Crop Science
JF - Journal of Agronomy and Crop Science
SN - 0931-2250
IS - 1
ER -