Application of Factorial Experiments with Asymmetric Responses for Determine Important Factors Affecting on Production of Dates
The factorial of experiments assume that the response variable is a distributed one with normal distribution, thus, the dependence of the technique of analysis of variance (ANOVA), assumes the response variable are normally distributed. However, there are many situations where the response variable is non-normal. There are many methods that help us process this problem, the log transformation method for the responses due to the fact that distribution of this responses is non- normal. In this paper we are studying the most important factors affecting the production of the Iraqi dates using factorial experiments. The five factors have been described as the following: (Fertilizers, Dates Type, Number of times vaccinate, Watering the Palm, Pesticides) and each factor has two levels. The ways used to determinate the most important factors are the traditional methods (ANOVA) and adaptive Lasso method for determine important factors. We used program R to analyse the data.
 Dong W., Zhang X., Wang H., Dai X., Sun X., Qiu, W., & Yang F. Effect of different fertilizer application on the soil fertility of paddy soils in red soil region of southern China. PloS one. 2012. 7(9) pp. 444-504
 Douglas C. M. Design and Analysis of Experiments., New York, USA: John Wiley & Sons. 2001
 Efron B., Hastie T., Johnstone I., & Tibshirani R. Least angle regression. The Annals of statistics. 2004. 32(2). pp. 407-499
 Eghball B. & Power J. F., "Composted and Noncomposed Manure Application to Convantional and No-Tillage System: Corn Yield and Nitrogen Uptake", Published in Agron. 1999. J. 91. pp. 819-825
 Fan J., & Li R. Variable selection via nonconcave penalized likelihood and its oracle properties. Journal of the American statistical Association, 2001. 96 b(456) pp. 1348-1360
 Fisher R. A. The arrangement of field experiments. Journal of Ministry of Agriculture, 33, 1926. pp. 503-513
 Kane A., & Mandal, A. A new analysis strategy for designs with complex aliasing. Submitted to The American Statistican in March. 2016
 Keene O. N. The log transformation is special. Statistics in medicine. 1995. 14(8). pp. 811-819
 Kraemer N., Schaefer J. & Boulesteix A.-L. Regularized Estimation of Large-Scale Gene Regulatory Networks with Gaussian Graphical Models BMC Bioinformatics. 2009
 Massey Jr., & Frank J. "The Kolmogorov-Smirnov test for goodness of fit."Journal of the American statistical Association 46.25.1951. pp. 68-78
 Morrison M. J., Voldeng H. D. & Cober E. R. "Agronomic Changes from 58 Years of Genetic Improvement of Short-Season Soybean Cultivars in Canada", Published in Agron J. 92. 2000. pp. 780-784
 Patil S. C., & Kulkarni, H. V. Analysis of 2n Factorial Experiments with Exponentially Distributed Response Variable. Applied Mathematical Sciences, 5(10). 2011. pp. 459-476
 RealSoft. Experiment Design and Analysis Reference, ReliaSoft Corporation, Tucson. 2015
 Tarakanovas P. & Ruzag V. "Additive main effect and multiplicative interaction analysis of grain yield of wheat varieties in Lithuania", Agronomy research. 2006. 4(1). pp. 91-98
 Tibshirani R. Regression shrinkage and selection via the Lasso. Journal of the Royal Statistical Society, Series B 58. 1996. pp. 267–288
 www.zeraa.gov.iq. Ministry of Agriculture, Iraq
 Yates F. The design and analysis of factorial experiments. Technical communication 1937. p. 35
 Zou, H. The adaptive lasso and its oracle properties. Journal of the American Statistical Association 101. 2006. pp. 1418–1429
Copyright (c) 2018 LUMEN Proceedings
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Selection and peer-review under responsibility of the Organizing Committee of the conference.
This is an Open Access article distributed under the terms of the Creative Commons Attribution-Noncommercial 4.0 Unported License, permitting all non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited