Some New Dimensions to Construct Economical Circular Weakly Balanced Neighbor Robust Designs

Noreen, Khadija; Rasheed, Muhammad; Rasheed, H. M. Kashif; Jamal, Farrukh; Ahmed, Rashid; Onyango, Ronald

doi:https://doi.org/10.1155/2022/8473332

Mathematical Problems in Engineering

On this page

Abstract Introduction Conclusions Data Availability Conflicts of Interest Authors’ Contributions References Copyright Related Articles

Special Issue

Robust Statistical Modeling and Machine Learning with Applications in Data Science

View this Special Issue

Research Article | Open Access

Volume 2022 | Article ID 8473332 | https://doi.org/10.1155/2022/8473332

Some New Dimensions to Construct Economical Circular Weakly Balanced Neighbor Robust Designs

Khadija Noreen,¹Muhammad Rasheed,¹H. M. Kashif Rasheed,¹Farrukh Jamal,¹Rashid Ahmed,¹and Ronald Onyango²

Academic Editor: Firdous Khan

Received15 Oct 2021

Revised22 Feb 2022

Accepted25 Apr 2022

Published30 May 2022

Abstract

Neighbor-balanced designs are used in the experiments where the performance of a treatment is affected by the treatments applied to its neighboring units. These are well-known designs to balance the neighbor effects. Among these designs, minimal neighbor-balanced designs are economical; therefore, these are preferred by the experimenters. For even, minimal neighbor balanced designs in circular blocks cannot be constructed for most of the cases, where is number of treatments. In such situations, experimenters would like to relax the neighbor balance property up to some extent and consider the minimal circular weakly balanced neighbor designs as the better alternates to the minimal circular neighbor-balanced designs. In this article, some generators are developed to obtain minimal circular weakly balanced neighbor designs in blocks of equal, two and three different sizes.

1. Introduction

Neighbor-balanced designs (NBDs) are used in the experiments where performance of a treatment is influenced by the treatments applied to its neighboring units. NBDs are well-known designs to balance the neighbor effects. Among the NBDs, minimal NBDs are economical; therefore, these are preferred by the experimenters. If each pair of distinct treatments appears once in adjacent plots, then, the design is called minimal NBD. A block formed in a cycle in such a way that its first and last units are considered as adjacent neighbors is called a circular block. In circular blocks, each unit has one left-neighbor and one right-neighbor. Williams [1] suggested nearest neighbor-balanced designs (NBDs) in linear blocks for first-order autoregressive model. Rees [2] introduced neighbor designs in a technique used in virus research and constructed these designs for odd number of treatments (). Lawless [3] gave a note on different types of balanced incomplete designs balanced for residual effects. Hwang and Lin [4,5] constructed four classes of NBDs for [6] discussed that the bias due to neighbor effects can be minimized through NBDs. Azais et al. [6] suggested that NBDs should be used to deal with neighbor effects and if a NBD requires large number of experimental units, a partially NBD is used. Jacroux [7] constructed equineighbored designs in blocks of sizes three. Kunert [8] showed that the bias due to neighbor effects can be minimized through NBDs or partially NBDs. Ahmed and Akhtar [9] constructed some series of NBDs which are not minimal. Akhtar and Ahmed [10] constructed some second-order NBDs for some cases of [11] constructed some all-order NBDs for odd. Ahmed and Akhtar [12] constructed some NBDs in circular blocks of sizes six which are not minimal. Akhtar et al. [13] constructed some NBDs in circular blocks of sizes five. Misra and Nutan [14,15] constructed circular generalized neighbor designs (CGNDs) by relaxing the neighbor balance property. The CGNDs will become more economical and better alternate to the minimal CNBDs if most of the unordered pairs appear (i) once as neighbor while other appear no time, or (ii) once as neighbor while other appear twice. GNDs possessing this property are also called minimal circular weakly balanced neighbor designs (CWBNDs). Mishra [16] presented some families of proper GNDs. Ahmed et al. [17] constructed economical GNDs in use of serology. Zafaryab et al. and Shehzad et al. [18,19] developed some generators to obtain the minimal CWBNDs (MCWBNDs) for some cases. Iqbal et al. [20] presented GNDs for k (block size) = 3. This review shows that MCWBNDs-II (MCWBNDs in which 3 /2 unordered pairs do not appear as neighbors while all other appear once) are not available in the literature. In this study, therefore, some generators are presented to generate MCWBNDs-II for all k > 2. These designs are economical and efficient to balance the neighbor effects.

Neutrosophic statistics is the extension of classical statistics and is applied when the data are coming from a complex process or from an uncertain environment. The proposed study can be extended for neutrosophic statistics. Few researchers [21–23] constructed designs of (i) sampling plan for exponential distribution under the neutrosophic statistical interval method, (ii) a new attribute control chart under neutrosophic statistics, and (iii) variable sampling plan for Pareto distribution using the neutrosophic statistical interval method.

2. Method of Cyclic Shifts

This method was introduced by Iqbal [24] which is simplified here for CBNDs and MCWBNDs-II.

Let S_j = [, ,…, ] be i sets of shifts, j = 1,2, …, i, u = 1,2, …, k-1, and 1 ≤ ≤ -1. (i) If all from 1 to -1 appears exactly once in S, then designs will be MCBND. (ii) If all from 1 to -1 appears once in S except any three elements which do not appear, then designs will be MCWBND-II.where S contains(i)Each element of all S_j.(ii)Sum (mod ) of all elements in each S_j.(iii)Complements of all elements in (i) and (ii), here complement of ‘a’ is ‘-a’.

Logic behind Rule I of this method expresses that

If m = (-2)/2 for, even then, S = [1, 2, …, m-1] or S = [1, 2, …, m-2, m] will provide MCWBNDs-II if sum of S is divisible by v. Otherwise, for this, elements with their complements have to be replaced.

Example 1. S₁ = [4, 6, 7] and S₂ = [2, 3] generate following MCWBND-II for = 18, k₁ = 4, and k₂ = 3.
For S₁, get Blocks and assign 0, 1, …, -1 to first units of each block, respectively. Add 4 (mod 18) to the first unit element of each block for second unit elements. Similarly, add 6 (mod 18) and so on (see Table 1).
Take more blocks for S₂ and obtain the design (see Table 2).
Table 1 and Table 2 jointly present the MCWBND-II for = 18, k₁ = 4, and k₂ = 3. In this design, 27 unordered pairs do not appear as neighbors while all other appear once.

2.1. Logic behind Rule I

Using the logic behind Rule I, following theorems are developed for MCWBNDs-II.

Theorem 1. If m = 4u, i sets obtained from S = [1, 2, …, (m/2), (m+4)/2, (m+6)/2,…, (m-1), (3m + 2)/2] will provide MCWBNDs-II for = 2ik+4, where m = (-2)/2.

Proof. Let Sum = [1 + 2, …+(m/2)+((m+4)/2)+((m+6)/2)+ …+(m-1)+(3m + 2)/2]
= 2(m+1)m/4 = (m/4) Since = 2(m+1).
m/4 will be integer for m = 4u.
Sum will be divisible of if m/4 is integer. Hence proved.

Theorem 2. If m = 4u+1, then sets derived from S = [1, 2, …, (3m + 1)/4, (3m + 9)/4, (3m + 13)/4, …, (m-1), (5m + 3)/4] will provide MCWBNDs-II for = 2ik+4.

Proof. Let Sum = [1 + 2, …+(3m + 1)/4+(3m + 9)/4+(3m + 13)/4+…+(m-1)+(5m + 3)/4]
= 2(m+1) (m-1)/4 = (m-1)/4 Since = 2(m+1).
(m-1)/4 will be integer for m = 4u+1.
Sum will be divisible of if (m-1)/4 is integer. Hence proved.

Theorem 3. If m = 4u+2, i sets obtained from S = [2, 3, …, m-2, m, 2m + 1] will provide MCWBNDs-II for = 2ik+4.

Proof. Let Sum = 2 + 3+,…+(m-2)+m+(2m + 1)
= 2(m+1) (m+2)/4 = (m+2)/4 Since = 2(m+1).
(m+2)/4 will be integer for m = 4u+2.
Sum will be divisible of if (m+2)/4 is integer. Hence proved.

Theorem 4. If m = 4u+3, then i sets obtained from S = [1, 2, …, (m+1)/4, (m+9)/4, (m+13)/4, m-2, m, (7m + 3)/4] produce MCWBNDs-II for = 2ik+4.

Proof. Let Sum = [1 + 2, …+(m+1)/4+(m+9)/4+(m+13)/4+(m-2)+m+(7m + 3)/4]
= 2(m+1) (m+1)/4 = (m+1)/4 Since = 2(m+1).
(m+1)/4 will be integer for m = 4u+3.
Sum will be divisible of if (m+1)/4 is integer. Hence proved.

2.2. Efficiency of Neighbor Effects

The efficiency factor for neighbor effect (residual effect) is the harmonic mean of nonzero Eigen values of their respective information matrix (see [25]). The high value of E_n shows that design is suitable for the estimation of neighbor effects. Our developed generators provide the designs with high values of E_n for even; therefore, these designs are suitable for the estimation of neighbor effects. Table 3 shows the the E_n of some existing MCBNDs and proposed designs for comparison.

3. Construction of MCWBNDs-II

Here, minimal CWBNDs-II are generated through Rule I. To generate required MCWBNDs-I, sets of shifts will be obtained from the elements of selected S, see Theorem 2–Theorem 4. Here, m = (-2)/2, and i, u, and are integers.(i)If m = 4u, then, S = [1, 2, …, (m/2), (m+4)/2, (m+6)/2,…, (m-1), (3m + 2)/2](ii)If m = 4u+1, then, S = [1, 2, …, (3m + 1)/4, (3m + 9)/4, (3m + 13)/4,…, (m-1), (5m + 3)/4](iii)If m = 4u+2, then, S = [2, 3, …, m-2, m, 2m + 1](iv)If m = 4u+3, then, S = [1, 2, …, (m+1)/4, (m+9)/4, (m+13)/4, m-2, m, (7m + 3)/4].

3.1. MCWBNDs-II in Blocks of Equal Sizes

Here, MCWBNDs-II are generated in equal block sizes from i sets which will be generated in the following manner.

Divide the elements of selected S in i groups of size k in such a way that is the factor of sum of each group; then, discard one element from each group.

3.1.1. Generator 3.1.1

MCWBNDs-II can be generated for = 2ik+4 and(i)k = 4l, i and l integer and m = 4u+1,(ii)k = 4l + 2, i odd, l integer and m = 4u+3.(iii)k = 4l + 2, i even, l integer and m = 4u+1.(iv)k (odd) > 3, i = 4j and m = 4u+1.(v)k (odd) > 3, i = 4j+2 and m (mod 4) ≡ 3.(vi)k = 4 + 1, k > 1, i = 4j+3 and m = 4u.(vii)k = 4 + 1, k > 1, i = 4j+1 and m = 4u+2.(viii)k = 4 + 3, k > 3, i = 4j+1 and m = 4u.(ix)k = 4 + 3, k > 3, i = 4j+3 and m = 4u+2.

Example 2. MCWBND-II is generated for = 18 and k = 7.
S₁ = [2,3,4,6,7,13].

Example 3. MCWBND-II is generated for = 28 and k = 5.
S₁ = [3,4,5,6,8], S₂ = [7,9,10,12,17].

3.2. MCWBNDs-II in Blocks of Two Different Sizes

Here, MCWBNDs-II are constructed in two different block sizes from (i+1) sets which will be generated in the following manner.

Divide the elements of selected S in i groups of size k₁ and one of k₂ in such a way that is the factor of sum of each group; then, discard one element from each group.

3.2.1. Generator 3.2.1

MCWBNDs-II can be generated for = 2(i+1)k₁+2, k₂ = k₁-1, and (i) k₁ = 4l, i and l integer and m = 4u. (ii) k₁ = 4l + 2, i odd and m = 4u. (iii) k₁ = 4l + 2, i even and m = 4u+2. (iv) k₁ (odd) > 3, i = 4j+3 and m = 4u. (v) k₁ (odd) > 3, i = 4j+1 and m = 4u+2. (vi) k₁ = 4 + 1, k₁ > 1, i = 4j+2 and m = 4u+3. (vii) k₁ = 4 + 1, k₁ > 1, i = 4j and m = 4u+1. (viii) k₁ = 4 + 3, k₁ > 3, i = 4j and m = 4u+3. (ix) k₁ = 4 + 3, k₁ > 3, i = 4j+2 and m = 4u+1.

Example 4. MCWBND-II is generated for = 44, k₁ = 7, and k₂ = 6.
S₁ = [3, 4, 5, 67, 18], S₂ = [9, 10, 11, 12, 13, 14, 19], S₃ = [8, 15, 16, 20, 27].

3.2.2. Generator 3.2.2

MCWBNDs-II can be generated for = 2(i+1)k₁, k₂ = k₁-2, and (i) k₁ = 4l, l > 1, i and l integer and m = 4u+3. (ii) k₁ = 4l + 2, i odd, l integer and m = 4u+3. (iii) k₁ = 4l + 2, i even, l integer and m = 4u+1. (iv) k₁ (odd) > 3, i = 4j+1, and m = 4u+1. (v) k₁ (odd) > 3, i = 4j+3, and m = 4u+3. (vi) k₁ = 4 + 1, k₁ > 1, i = 4j, and m = 4u. (vii) k₁ = 4 + 1, k₁ > 1, i = 4j+2, and m = 4u+2. (viii) k₁ = 4 + 3, k₁ > 3, i = 4j, and m = 4u+2. (ix) k₁ = 4 + 3, k₁ > 3, i = 4j+2, and m = 4u.

Example 5. MCWBND-II is generated for = 20, k₁ = 5, and k₂ = 3.
S₁ = [3, 4, 5, 6], S₂ = [7, 12].

3.3. MCWBNDs-II in Blocks of Three Different Sizes

Here, MCWBNDs-II are constructed in three different block sizes using (i+2) sets which will be generated in the following manner.

Divide the elements of selected S in i groups of size k₁ and one each of k₂ and k₃ in such a way that is factor of sum of each group; then, discard one element from each group.

3.3.1. Generator 3.3.1

MCWBNDs-II can be generated for = 2ik₁+2k₂+2k₃+4, k₂ = k₁-1, k₃ = k₁-2, and (i) k₁ = 4l, l > 1, i and l integer and m = 4u+2. (ii) k₁ = 4l + 2, i odd, l integer and m = 4u. (iii) k₁ = 4l + 2, i even, l integer and m = 4u+2. (iv) k₁ (odd) > 3, i = 4j, and m = 4u. (v) k₁ (odd) > 3, i = 4j+2, and m = 4u+2. (vi) k₁ = 4 + 1, k₁ > 1, i = 4j+1, and m = 4u+1. (vii) k₁ = 4 + 1, k₁ > 1, i = 4j+3, and m = 4u+3. (viii) k₁ = 4 + 3, k₁ > 3, i = 4j+1, and m = 4u+3. (ix) k₁ = 4 + 3, k₁ > 3, i = 4j+3, and m = 4u+1.

Example 6. MCWBND-II is generated for = 28, k₁ = 5, k₂ = 4, and k₃ = 3.
S₁ = [2, 3, 5, 17], S₂ = [7, 8, 9], S₃ = [10, 12].

Example 7. MCWBND-II is generated for = 34, k₁ = 6, k₂ = 5, and k₃ = 4.
S₁ = [3, 4, 5, 6, 14], S₂ = [10, 11, 15, 25], S₃ = [8, 12, 13].

3.3.2. Generator 3.3.2

MCWBNDs-II can be generated for = 2(i+2)k₁-4, k₂ = k₁-1, k₃ = k₁-3, and (i) k₁ = 4l, l > 1, i and l integer and m = 4u+1. (ii) k₁ = 4l + 2, l integer, i odd and m = 4u+3. (iii) k₁ = 4l + 2, l integer, i even, and m = 4u+1. (iv) k₁ (odd) > 5, i = 4j, and m = 4u+3. (v) k₁ (odd) > 5, i = 4j+2, and m = 4u+1. (vi) k₁ = 4 + 1, k₁ > 5, i = 4j+1, and m = 4u. (vii) k₁ = 4 + 1, k₁ > 5, i = 4j+3, and m = 4u+2. (viii) k₁ = 4 + 3, k₁ > 3, i = 4j+1, and m = 4u+2. (ix) k₁ = 4 + 3, k₁ > 3, i = 4j+3, and m = 4u.

Example 8. MCWBND-II is generated for = 44, k₁ = 8, k₂ = 7, and k₃ = 5.
S₁ = [3, 4, 5, 6, 7, 8, 10], S₂ = [11, 12, 13, 14, 16, 20], S₃ = [15, 18, 19, 27].

Example 9. MCWBND-II is generated for = 50, k₁ = 9, k₂ = 8, and k₃ = 6.
S₁ = [2, 5, 4, 6, 7, 8, 9, 10], S₂ = [12, 15, 16, 17, 19, 23, 379], S₃ = [14, 18, 20, 21, 22].

3.3.3. Generator 3.3.3

MCWBNDs-II can be generated for = 2ik₁+2k₂+2k₃+4, k₂ = k₁-2, k₃ = k₁-3, and (i) k₁ = 4l, l > 1, i and l integer and m = 4u+1. (ii) k₁ = 4l + 2, l integer, i odd, and m = 4u+2. (iii) k₁ = 4l + 2, l integer, i even, and m = 4u+1. (iv) k₁ (odd) > 5, i = 4j, and m = 4u+2. (v) k1 (odd) > 5, i = 4j+2, and m = 4u. (vi) k₁ = 4 + 1, k₁ > 5, i = 4j+1, and m = 4u+3. (vii) k₁ = 4 + 1, k₁ > 5, i = 4j+3, and m = 4u+1. (viii) k₁ = 4 + 3, k₁ > 3, i = 4j+1, and m = 4u+1. (ix) k₁ = 4 + 3, k₁ > 3, i = 4j+3, and m = 4u+3.

Example 10. MCWBND-II is generated for = 42, k₁ = 8, k₂ = 6, and k₃ = 5.
S₁ = [2, 4, 5, 6, 7, 8, 9], S₂ = [10, 12, 13, 15, 31], S₃ = [16, 17, 18, 19].
Catalogues of MCWBNDs-II generated from these generators are presented in blocks of equal, two different and three different sizes as Table 4–6, respectively, in Appendix.

4. Conclusions and Future Research

Neighbor effects may arise in experiments of serology for virus research and in agriculture experiments, due to nature of plots, etc. In the presence of neighbor effects, misleading conclusions may be drawn in the variety competition experiments. Minimal NBDs are available in the literature to neutralize these effects economically for odd. To overcome this problem for even, complete solution is given in this article to construct proposed MCWBNDs-I for each and every k > 2. At least (-1) experimental units are required to satisfy the neighbor balance property for even. MCWBND-II requires (-4)/2 units. Hence, we lose []% neighbor balance and save at least []% experimental units. Our proposed designs save more than 50% of experimental material for even at the cost of losing at most 3% efficiency of neighbour effects, therefore, are efficient to reduce the bias due to neighbor effects.

As a future research, (i) an algorithm coded with R-language can be developed to generate the proposed designs, (ii) the proposed new designs can be applied in experiments of serology and agriculture to obtain the real data for comparison, and (iii) the current study can be extended using neutrosophic statistics [26].

Data Availability

The data used in the article are included within the article.

Conflicts of Interest

The authors declare no conflicts of interest.

Authors’ Contributions

All authors contributed equally.

References

R. M. Williams, “Experimental designs for serially correlated observations,” Biometrika, vol. 39, no. 1/2, pp. 151–167, 1952.
View at: Publisher Site | Google Scholar
D. H. Rees, “Some designs of use in serology,” Biometrics, vol. 23, no. 4, pp. 779–791, 1967.
View at: Publisher Site | Google Scholar
J. F. Lawless, “A note on certain types of BIBD’s balanced for residual effects,” Ann. Math. Statist., vol. 42, no. 4, pp. 1439–1441, 1971.
View at: Publisher Site | Google Scholar
F. K. Hwang, “Constructions for some classes of neighbor designs,” Ann. Statist., vol. 1, no. 4, pp. 786–790, 1973.
View at: Publisher Site | Google Scholar
F. K. Hwang and S. Lin, “Neighbor designs,” Journal of Combinatorial Theory - Series A, vol. 23, no. 3, pp. 302–313, 1977.
View at: Publisher Site | Google Scholar
J. M. Azaïs, R. A. Bailey, and H. Monod, “A catalogue of efficient neighbour-designs with Border plots,” Biometrics, vol. 49, no. 4, pp. 1252–1261, 1993.
View at: Publisher Site | Google Scholar
M. Jacroux, “On the construction of efficient equineighbored incomplete block designs having block size 3,” Sankhya Series B, vol. 60, no. 3, pp. 488–495, 1998.
View at: Google Scholar
J. Kunert, “Randomization of neighbour balanced designs,” Biometrical Journal, vol. 42, no. 1, pp. 111–118, 2000.
View at: Publisher Site | Google Scholar
R. Ahmed and M. Akhtar, “Construction of neighbor balanced block designs,” Journal of Statistical Theory and Practice, vol. 2, no. 4, pp. 551–558, 2008.
View at: Publisher Site | Google Scholar
M. Akhtar and R. Ahmed, “Circular binary block second and higher order neighbor designs,” Communications in Statistics - Simulation and Computation, vol. 38, no. 4, pp. 821–828, 2009.
View at: Publisher Site | Google Scholar
R. Ahmed and M. Akhtar, “Construction of one-dimensional all order neighbor balanced designs by cyclic shifts,” Pakistan J. Statist., vol. 25, no. 2, pp. 121–126, 2009.
View at: Google Scholar
R. Ahmed and M. Akhtar, “Designs balanced for neighbor effects in circular blocks of size six,” Journal of Statistical Planning and Inference, vol. 141, no. 2, pp. 687–691, 2011.
View at: Publisher Site | Google Scholar
M. Akhtar, R. Ahmed, and F. Yasmin, “A catalogue of nearest neighbor balanced designs in circular blocks of size five,” Pakistan J. Statist, vol. 26, no. 2, pp. 397–405, 2010.
View at: Google Scholar
B. L. Misra and B. Nutan, “Families of neighbour designs and their analysis,” Communications in Statistics - Simulation and Computation, vol. 20, no. 2-3, pp. 427–436, 1991.
View at: Publisher Site | Google Scholar
K. Chaure and B. L. Misra, “On construction of generalized neighbor designs,” Sankhya Series B, vol. 58, pp. 245–253, 1996.
View at: Google Scholar
N. S. Mishra, “Families of proper generalized neighbor designs,” Journal of Statistical Planning and Inference, vol. 137, no. 5, pp. 1681–1686, 2007.
View at: Publisher Site | Google Scholar
R. Ahmed, M. Akhtar, and M. H. Tahir, “Economical generalized neighbor designs for use in Serology,” Computational Statistics & Data Analysis, vol. 53, no. 12, pp. 4584–4589, 2009.
View at: Publisher Site | Google Scholar
M. Zafaryab, F. Shehzad, and R. Ahmed, “Proper generalized neighbor designs in circular blocks,” Journal of Statistical Planning and Inference, vol. 140, no. 11, pp. 3498–3504, 2010.
View at: Publisher Site | Google Scholar
F. Shehzad, M. Zafaryab, and R. Ahmed, “Some series of proper generalized neighbor designs,” Journal of Statistical Planning and Inference, vol. 141, no. 12, pp. 3808–3813, 2011.
View at: Publisher Site | Google Scholar
I. Iqbal, M. H. Tahir, M. L. Aggarwal, A. Ali, and I. Ahmed, “Generalized neighbor designs with block size 3,” Journal of Statistical Planning and Inference, vol. 142, pp. 626–632, 2012.
View at: Publisher Site | Google Scholar
M. Aslam, “Design of sampling plan for exponential distribution under neutrosophic statistical interval method,” IEEE Access, vol. 6, pp. 64153–64158, 2018.
View at: Publisher Site | Google Scholar
M. Aslam, R. A. R. Bantan, and N. Khan, “Design of a new attribute control chart under neutrosophic statistics,” International Journal of Fuzzy Systems, vol. 21, no. 2, pp. 433–440, 2019.
View at: Publisher Site | Google Scholar
M. Aslam, N. Khan, and A. H. Al-Marshadi, “Design of variable sampling plan for Pareto distribution using neutrosophic statistical interval method,” Symmetry, vol. 11, no. 1, p. 80, 2019.
View at: Publisher Site | Google Scholar
I. Iqbal, “Construction of Experimental Design Using Cyclic Shifts,” University of Kent at Canterbury, England, U.K, UK, 1991, Ph.D. Thesis.
View at: Google Scholar
A. T. James and G. N. Wilkinson, “Factorization of the residual operator and canonical decomposition of non-orthogonal factors in the analysis of variance,” Biometrika, vol. 58, no. 2, pp. 279–294, 1971.
View at: Publisher Site | Google Scholar
J. M. Azais, “Design of experiments for studying intergenotypic competition,” Journal of the Royal Statistical Society: Series B, vol. 49, no. 3, pp. 334–345, 1987.
View at: Publisher Site | Google Scholar

Copyright

Copyright © 2022 Khadija Noreen et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

PDF Download Citation

Download other formats

Order printed copies

Views

136

Downloads

219

Citations