Non-statistically Significant Interactions
between Treatments and an Approach for
Dealing with these Statuses
Zakaria M Sawan*
Cotton Research Institute, Agricultural Research Center, Ministry of Agriculture, Egypt
Submission: May 28, 2020; Published: August 10, 2020
*Corresponding author: Zakaria M Sawan, Cotton Research Institute, Agricultural Research Center, Ministry of Agriculture and Land Reclamation, 9 Gamaa Street, 12619, Giza, Egypt
How to cite this article: Zakaria M S. Non-statistically Significant Interactions between Treatments and an Approach for Dealing with
these Statuses. JOJ Wildl Biodivers. 2020: 2(5): 555596 DOI: 10.19080/JOJWB.2020.02.555596
A field experiment on cotton yield resulted in a non-statistically significant interaction. An approach for follow-up examination between treatments based on least significant difference values was suggested to identify the effect regardless of insignificance. It was found that the classical formula used in calculating the significance of interactions suffers a possible shortage that can be eliminated by applying a suggested revision.
Managing the balance of vegetative and reproductive growth is the essence of managing a cotton crop. It is known from numerous fertilizer experiments that the yield of field crop is strongly dependent on the supply of mineral nutrients [1-3]. Several approaches have been used in an attempt to break this yield plateau; among them the application of plant growth regulators (PGR’s), particularly Mepiquat Chloride (MC) has received much attention recent years [4,5]. Also, a statistical approach for dealing with the non-significant interactions between treatments depending on least significant differences, regardless of statistical insignificance is suggested .
Seed cotton yield per plant, as well as seed cotton and lint yield per hectare, were increased by as much as 12.8, 12.8, and 12.3 %, respectively, when the nitrogen rate was increased . N is an important nutrient for control of new growth and preventing abscission of squares and bolls and is also essential for photosynthetic activity [7,8]. When K was applied at all three rates (319, 638 and 957 g K per hectare), seed cotton yield per plant and seed cotton and lint yield per hectare also increased .
These increases could be attributed to the favorable effects of K on yield components, that is, the number of opened bolls per plant and boll weight leading consequently to higher cotton yield [9,10]. Mepiquat Chloride (MC) significantly increased seed cotton yield per plant, as well as seed cotton and lint yield per hectare (by 9.5, 9.6 and 9.3%, respectively), compared to the untreated control  that lead to yield enhancements of both boll retention and boll weight .
No significant interactions were identified among the variables in this study (N rates, K rates and MC) with respect to the characters under investigation. Generally, interactions indicated that the favorable effects accompanied the application of N; spraying cotton plants with K combined with MC on cotton productivity was more obvious by applying N at 143 kg per hectare and combined with spraying cotton plants with K at 957 g per hectare and also with MC at 48 + 24 g active ingredient per hectare .
Regarding the non-significant interaction effects, increases were observed in seed cotton yield per hectare (about 40%) as a result of applying the same combination . Differences were observed between the interactions in this study, that is, the first order and the second order; however, these interactions were not
statistically significance. Because it is possible that experimental
error could mask the pronounced effects of the interactions
 a statistical approach for dealing with the non-significant
interactions between treatments is suggested.
Differences between treatment combinations regardless of
the non-significance of the interaction effects from the ANOVA.
Results show that, if no significant differences are identified
between the different levels of any main factor (N, K or MC)
when the LSD is calculated, then the significance does not exist.
Conversely, if the significance of the interactions between the main
factors (first and second order interactions) is not identified, then
the estimation of the LSD of the interactions between the main
factors could provide a significant result . For these reasons, the
formula used in calculating the significance of interactions suffers
a possible shortage.
Study results indicate that it could be useful to modify or add
to the original formula used for calculating F values of interactions
F = Mean Square for Interaction / Mean Square for Error
In this connection, calculating the significance of interactions
could proceed as:
F = Mean square for interaction × n / Root of mean square for
Where n = number of main factors in the interaction.
Based on findings from this study, it may be concluded that the
use of the suggested formula could secure the disclosure of any
significant effects among interactions regardless of experimental
Nuti RC, Witten TK, Jost PH, Cothren JT (2000) Comparisons of Pix Plus and additional foliar Bacillus cereus in cotton. In Proceedings Beltwide Cotton Production Research Conference, San Antonio, TX, USA, January 4-8, Memphis, USA; Natl. Cotton Council pp. 684-687.
Kumar KAK, Patil BC, Chetti MB (2004) Effect of plant growth regulators on biophysical, biochemical parameters and yield of hybrid cotton. Karnataka Journal of Agricultural Science, 16: 591-594.