I am using SAS 9.4. I have a factorial design for my experiment to try and establish common milkweed into a landscape using two main effects of: mowed plots vs unmowed plots, each of the main plots is divided into three sub-plots using three different rates of herbicide to suppress the grass in the landscape: a control rate, a low rate, and a high rate of glyphosate, and within the subplots I have four sub-subplots each with different milkweed seed densities: a control, a low density, a low density + mid-june mowing, and a high density. I am wanting to analyze the presence of common milkweed seedlings based seedlings being present or absent only. It runs fine up through the proc print data code; however once I try to run the Proc glimmix portion of the code it does not converge and I am needing help with trying to fix this so it converges. I attached my data excel file if that is useful in trying to help me.
Here is the code I have been trying to run:
* Import the data;
proc import out = seedling_counts
datafile = '/folders/myfolders/AES Consulting/Lizotte-Hall, Sydney/Data/Aug2016counts.xlsx'
dbms = xlsx
replace;
getnames = yes;
datarow = 2;
run;
* Create a absense/presense variable for seedlings;
data seedling_counts;
set seedling_counts;
if seedling_counts > 0 then seedling_present = 1;
else seedling_present = 0;
run;
* Print the data;
proc print data = seedling_counts;
run;
proc glimmix data = seedling_counts plots = residualpanel;
class mowing herb seed rep;
model seedling_present = mowing herb seed rep / dist = binary link = logit;
random rep*mowing*herb;
lsmeans herb / diff;
run;
I wonder if you can re-state the Random statement to make it more efficient. This paper by the SAS/STAT statisticians may provide tips on how to improve the specification of the model: https://support.sas.com/resources/papers/proceedings16/SAS6403-2016.pdf
Join us for SAS Innovate April 16-19 at the Aria in Las Vegas. Bring the team and save big with our group pricing for a limited time only.
Pre-conference courses and tutorials are filling up fast and are always a sellout. Register today to reserve your seat.
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.