Submitted to: Agronomy Journal
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 4/14/2005
Publication Date: 9/1/2005
Citation: Wu, J., Jenkins, J.N., McCarty Jr., J.C., Watson, C.E. 2005. Comparisons of two statistical models for evaluating boll retention in cotton. Agronomy Journal. 97:1291-1294.
Interpretive Summary: In the normal pattern of fruiting in cotton different numbers of bolls are retained and matured at various fruiting sites on the cotton plant. In conventional analysis of variance this variable is considered as a normally distributed value. We consider boll retention at each fruiting site as a binomial distribution. In this manuscript we compare the mixed linear model of analysis of variance (using four structures of the model, heterogeneous compound symmetry, heterogeneous autoregressive, unstructured and compound symmetry) with the logistic regression method to study boll set and maturation at the first position across nodes. SAS version 8 was used for all analyses. All models provide similar estimates for the mean; however, the logistic model provides a smaller (better) estimate of the standard error. Thus, statistical precision was greater with the logistic regression model and it is more appropriate for evaluating boll retention across nodes and other binominal traits.
Technical Abstract: Boll number is one of the most important traits related to yield of upland cotton (Gossypium hirsutum L.). Evaluation of boll retention properties at different fruiting sites would provide useful information for cotton breeding and cotton growth management. The presence or absence of a boll at each fruiting position, can be considered as binomially distributed. In this study, 188 upland cotton recombinant inbred (RI) lines, two parental lines, and a control cultivar, Stoneville 474, were used. These lines were planted at Mississippi State, MS, in 1999. The data set was analyzed by the mixed linear model and logistic regression model. The results showed that the boll retention for the first position was significantly different among nodes but expressed similar total numbers from the first position among RI lines. Estimates for boll retention were similar for both models; however, the logistic regression model gave higher precision for the estimation than the mixed linear model. Two-year data from box mapping of nine cotton cultivars were also analyzed by the two models, and the statistical conclusions were in good agreement with the one-year data on the RI lines. Since statistical precisions were greater with the logistic regression model it is more appropriate for evaluating boll retention on different nodes.