Academic Research Journal of Agricultural Science and Research
 

Academic Research Journal of Agricultural Science and Research 

Vol. 6(7), pp. 370-379. September, 2018.

ISSN: 2360-7874 

 DOI: 10.14662/ARJASRD2018.049

Full Length Research

Longitudinal Analysis of Arabica Coffee Bean Yield: Application of Linear Mixed Model for Clustered Longitudinal Data

Tarekegn Argaw¹, Girma Taye², Dechasa Bedada³, Ashenafi Ayano⁴

¹Biometrics, Ethiopian Institute of Agricultural Research, P. O. Box 2003, Addis Ababa, Ethiopia

²Associate Professor, School of Public Health, Addis Ababa University, P. O. Box 9086, Addis Ababa, Ethiopia

³Department of Statistics, College of Natural Science, Jimma University, P.O. Box 378, Jimma, Ethiopia

⁴ Ethiopian Institute of Agricultural Research ,Jimma Agricultural Research Center, P.O. Box, 192, Jimma, Ethiopia

Corresponding author’s E-mail: tare.aragaw@gmail.com

Accepted 26 September 2018

The study aimed to do longitudinal analysis to investigate the effect of time, biennial, and correlation on Arabica coffee bean yield by using Exploratory Data Analysis (EDA) and Linear Mixed Model (LMM). The data for this study came from coffee variety field trials conducted by Jimma Agricultural Research Center (JARC) over 7 years during 2005-2011 in south west Ethiopia across 3 coffee growing areas (Jimma, Agaro, and Metu). The experimental design of the trial was RCBD with 4 replications and 17 Arabica coffee genotypes. The LMM results revealed that the heterogeneous variance function (varIdent) and autoregressive order three (AR3) were, respectively, found to give better fit to the variance and correlation structure among measurements of coffee bean yield. Biennial interacts significantly with location and genotype. The estimated variance of random effect of block associated with intercept and biennial were σ ̂^2 (b0j) = (221.81)2 and σ ̂^2 (b3j) = 145.242, respectively. The result also showed significant location by linear and quadratic time effect interactions. Estimates of quadratic time effects for Jimma, Agaro, and Mutu were, respectively, -151.51, -66.05, and -4, whereas estimates of linear time effects for these locations were 158.92, 158.92, and 31.08, respectively. It was observed that the measurements of coffee bean yield obtained from Arabica coffee tree over time induced an autocorrelation which is known as serial correlation. There was initially an increasing andgradually a decreasing trend in Arabica coffee bean yield over time/years with linear rate of growth. There was also a differential response of genotypes and environments in the presence and absence of biennially. The effects of correlation among measurements, time, and biennial have to be considered in Arabica coffee breeding research to improve the precision and accuracy of research outcomes by using advanced statistical models.

Key Words: Arabica Coffee, Biennial , Clustered Longitudinal Data

 

How to cite this article (APA Style): Argaw, T., Taye, G., Bedada, D., Ayano, A. (2018). Longitudinal Analysis of Arabica Coffee Bean Yield: Application of Linear Mixed Model for Clustered Longitudinal Data. Acad. Res. J. Agri. Sci. Res. 6(7): 370-379