Generic selectors
Exact matches only
Search in title
Search in content
Search in posts
Search in pages
Filter by Categories
CBAB 19(4) 2019
Editions
CBAB 19(3) 2019
Uncategorized
CBAB 19(2) 2019
CBAB 19(1) 2019
CBAB 18(4) 2018
CBAB 18(3) 2018
CBAB 18(2) 2018
CBAB 18(1) 2018
CBAB 17(4) 2017
CBAB 17(3) 2017
CBAB 17(2) 2017
CBAB 17(1) 2017
CBAB 16(4) 2016
CBAB 16(3) 2016
CBAB 16(2) 2016
CBAB 16(1) 2016
CBAB 15(4) 2015
CBAB 15(3) 2015
CBAB 15(2) 2015
CBAB 15(1) 2015
CBAB 14(4) 2014
CBAB 14(3) 2014
CBAB 14(2) 2014
CBAB 14(1) 2014
CBAB 13(4) 2013
CBAB 13(3) 2013
CBAB 13(2) 2013
CBAB 13(1) 2013
CBAB 12(S2) 2012 Special Edition
CBAB 12(4) 2012
CBAB 12(3) 2012
CBAB 12(2) 2012
CBAB 12(1) 2012
CBAB 11(S1) 2011 Special Edition
CBAB 11(4) 2011
CBAB 11(3) 2011
CBAB 11(2) 2011
CBAB 11(1) 2011
CBAB 10(4) 2010
CBAB 10(3) 2010
CBAB 10(2) 2010
CBAB 10(1) 2010
CBAB 09(4) 2009
CBAB 09(3) 2009
CBAB 09(2) 2009
CBAB 09(1) 2009
CBAB 08(4) 2008
CBAB 08(3) 2008
CBAB 08(2) 2008
CBAB 08(1) 2008
CBAB 07(4) 2007
CBAB 07(3) 2007
CBAB 07(2) 2007
CBAB 07(1) 2007
CBAB 06(4) 2006
CBAB 06(3) 2006
CBAB 06(2) 2006
CBAB 06(1) 2006
CBAB 05(4) 2005
CBAB 05(3) 2005
CBAB 05(2) 2005
CBAB 05(1) 2005
CBAB 04(4) 2004
CBAB 04(3) 2004
CBAB 04(1) 2004
CBAB 03(4) 2003
CBAB 03(3) 2003
CBAB 03(2) 2003
CBAB 03(1) 2003
CBAB 02(4) 2002
CBAB 02(3) 2002
CBAB 02(2) 2002
CBAB 02(1) 2002
CBAB 01 (4) 2001
CBAB 01 (3) 2001
CBAB 01 (2) 2001
CBAB 01 (1) 2001
CBAB News
+55 31 3612-4490
cbabjournal@gmail.com
Close

Thiago Vincenzi Conrado, Daniel Furtado Ferreira, Carlos Alberto Scapim and Wilson Roberto Maluf

Abstract: The Scott-Knott cluster analysis is an alternative approach to mean comparisons with high power and no subset overlapping. It is well suited for the statistical challenges in agronomy associated with testing new cultivars, crop treatments, or methods. The original Scott-Knott test was developed to be used under balanced designs; therefore, the loss of a single plot can significantly increase the rate of type I error. In order to avoid type I error inflation from missing plots, we propose an adjustment that maintains power similar to the original test while adding error protection. The proposed adjustment was validated from more than 40 million simulated experiments following the Monte Carlo method. The results indicate a minimal loss of power with a satisfactory type I error control, while keeping the features of the original procedure. A user-friendly SAS macro is provided for this analysis.

Get the article here. (PDF)

Add Your Comment

Your email address will not be published. Required fields are marked *