06-18-2015 11:43 PM
I need some help to decide which experimental design should I consider to analyze an experiment with Mahogany (Swietenia macrophylla) regeneration tree.
The main objective is to investigate the density of mahogany regeneration around the mother-tree in Amazonia forest. Was selected 20 trees (not randomized trees) and from each tree four oriented-strips (North, South, East, West) was installed with 5 meters x 40 meters long each. Into each plot the number of Mahogany regeneration was counted at sub-plot 5 meter away of each other (5-10; 15-20; 25-30; 35-40).
The idea is to investigate if theres a specific orientation where occur more regeneration and until wich distance they reach.
To consider the variation between trees I put the DBH into the statistical model as a covariate. Each tree has 16 treatments (four orientation x four distance).
I run a Poisson in Glimmix of SAS (I had to sum 1 to each value because SAS was did not converge with zero values!)
PROC GLIMMIX DATA=MAHOGANY;
CLASS TREE ORIENT DIST;
MODEL NREG= ORIENT|DIST / DIST=POISSON LINK=LOG;
RANDOM TREE DIST(TREE) ORIENT(TREE);
However, I should consider the factor distance (DIST) as an dependent factor. So, I need to consider Spatial Correlation during the analysis.
I add the line:
RANDOM INTERCEPT / SUBJECT=TREE TYPE=SP(EXP)(DIST);
But SAS does not converge!
There is some suggestion for analyzes?
Which experimental design should I follow when analysing Mahogany tree regeneration? - ResearchGate. Available from: https://www.researchgate.net/post/Which_experimental_design_should_I_follow_when_analysing_Mahogany_... [accessed Jun 18, 2015].