SportsTurf provides current, practical and technical content on issues relevant to sports turf managers, including facilities managers. Most readers are athletic field managers from the professional level through parks and recreation, universities.
Issue link: https://read.dmtmag.com/i/282941
Again, it is the randomness of the treatments that will eliminate bias of plot location within each block along with replicating the treatments that will help to increase reliability of the data. Split Plot Designs are a special experimental design when several fac- tors are being evaluated or some constraint (i.e. turfgrass species) prevents you from using a complete randomized block design. A variable could be the application of fungicides to test disease control on these specific turf- 10 SportsTurf | April 2014 www.sportsturfonline.com Facility & Operations Replicate 1 A A A A A B B B B B 5 2 1 4 3 1 3 5 4 2 Replicate 2 B B B B B A A A A A 3 5 1 2 4 4 3 2 1 5 Replicate 3 A A A A A B B B B B 4 3 5 1 2 2 1 3 5 4 Split Plot Design Continued on page 44 grass species. The diagram above demonstrates a split plot design. In many cases you need to fit the experi- ment into existing resources, like an estab- lished stand of grass. You will note that blocks A and B (i.e. two turfgrass species) are planted in blocks as a constraint of the experimental design, but are randomized within each repli- cation. Within each replication, fungicide treatments are then randomized within each species. Treatment 1 may correspond to an untreated control, while treatments 2 through 5 may correspond to four different fungicides. Additional experimental designs are avail- able dependent on the number of factors being looked at; however, the more factors (i.e. species, fertilizers, pesticides, cultural practices, etc.), the more difficult it is to analyze, make comparisons, and draw conclusions. ANALYZING THE DATA After all the data has been collected, the choice of analysis is just as important as the experimental design. This is often considered the black box of statistics. The wrong analysis can lead to wrong conclusions. Researchers need to ask themselves this, "Will I be able to legitimately and correctly answer the ques- tions that I set out to answer after the data has been analyzed?" Regression and Correla- tion can be used to test a cause and effect re- lationship and how well that relationship is correlated. An Analysis of Variance (ANOVA) can be used to test the effective- ness of one product to another and how well that data may fit a regression line. Regression is all about relationships an- swering questions like, "Does nitrogen fertil- izer cause turfgrasses to grow taller?" Here we can relate two variables like fertility and growth and understand that we may observe a positive slope on a graph—turfgrasses will grow taller with increasing rates of nitrogen