Question

Capsids are major insect pests of some plantation crops. Control of capsids has been mainly through the use of insecticides. Four varieties with improved resistance to capsids and a standard variety (E) were tested in an experiment at a Research Station. Each plot comprised of 20 trees. Only the upper parts of the trees were sprayed to knock down insects. The following were the counts of capsids per plot after spraying

Row Blocks	Column Blocks
	1	2	3	4	5
1	D        117	B        67	C        25	E        145	A 24
2	C          42	A        27	B        54	D          77	E 147
3	B        149	C        87	E       202	A         38	D           70
4	A          39	E       182	D       161	C         72	B         129
5	E        210	D       143	A         28	B        134	C         115

:

1. What experimental design was used for the study? Explain your answer.

                                                                                                                                           

            (b) State the underlying assumptions of this design and explain why these

       assumptions are necessary.                                                                                                     

            (c) Complete the ANOVA table for the study.                                                    

                                                                                                                                                         

Sources of variation	DF	SS	MS	F	H0: tested
Treatment - Control versus Improved varieties - Among Improved varieties
Total

       (d) Draw conclusions from the results.                                                                                 

Answer 1

The Latin square model assumes that there are no interactions between the blocking variables or between the treatment variable and the blocking variable. Actually, in many cases, Latin squares are necessary because one such combination of levels from two blocking factors can be combined with one treatment, and not all.