Strip Plot Analysis with Agri Analyze: From Basics to Solved Examples

Summary

The blog explains the concept and application of Strip Plot Design (SPD) for two-factor experiments where precise estimation of interaction effects is required. It describes the layout, randomization procedure, ANOVA model, and calculation of degrees of freedom and mean squares using a solved example on irrigation and fertilizer treatments. The analysis shows significant effects of both irrigation and fertilizer levels on crop yield, while their interaction was found to be non-significant. A complete ANOVA table is presented to support the findings with statistical evidence. The blog also demonstrates how to perform strip plot analysis using the Agri Analyze tool through a step-by-step procedure. Overall, it serves as a practical guide combining theory, calculations, and software-based implementation for researchers and students.

1.Introduction

The Strip Plot Design (SPD) is particularly suitable for two-factor experiments where higher precision is needed for measuring the interaction effect between the factors compared to measuring the main effects of either factor individually. This design is also ideal when both sets of treatments require large plots. For instance, in experiments involving spacing and ploughing treatments, cultural convenience necessitates larger plots. Ploughing strips can be arranged in one direction, and spacing strips can be laid out perpendicular to the ploughing strips. This arrangement is achieved using:

  • Vertical strip plot for the first factor (the vertical factor)
  • strip plot for the second factor (the horizontal factor)
  • Interaction plot for the interaction between the two factors.
  • The vertical and horizontal strip plots are always perpendicular to each other. However, their sizes are unrelated, unlike the main plot and subplot in the split plot design. The interaction plot is the smallest. In a strip plot design, the precision of the main effects of both factors is sacrificed to improve the precision of the interaction effect.

    2. Randomization and Layout Planning for Strip Plot Design

    Step 1:Assign horizontal plots by dividing the experimental area into r blocks, then dividing each block into horizontal strips. Follow the randomization procedure used in RBD, and randomly assign the levels of the first factor to the horizontal strips within each of the r blocks, separately and independently.

    Step 2:Assign vertical plots by dividing each block into b vertical strips. Follow the randomization procedure used in RBD with b treatments and r replications, and randomly assign the b levels to the vertical strips within each block, separately and independently.

    3. Layout Example:

    A sample layout of strip-plot design with six varieties (V1, V2, V3, V4, V5 and V6) as a horizontal factor and three nitrogen rates (N1, N2 and N3) as a vertical factor in three replications.

    Replication I Replication II Replication III
    N1 N3 N2 N3 N2 N1 N3 N1 N2
    V6 V4 V5
    V5 V2 V2
    V3 V6 V3
    V2 V3 V4
    V4 V1 V6
    V1 V5 V1

    Statistical Model of Strip Plot Design

    $$ Y_{ijk} = \mu + \gamma_i + A_j + \varepsilon_{ij} + B_k + \beta_{ik} + (AB)_{jk} + \delta_{ijk} $$

    Where,

    \( Y_{ijk} \) = The response of yield from the ith unit receiving the jth main plot factor and kth sub-plot factor

    \( \mu \) = General mean

    \( \gamma_i \) = Effect of ith replication

    \( A_j \) = Effect of jth main plot factor

    \( \varepsilon_{ij} \) = Uncontrolled variation associated with the jth main plot factor in the ith replication

    \( B_k \) = Effect of kth sub-plot factor

    \( (AB)_{jk} \) = Interaction effect between the jth main plot factor and kth sub-plot factor

    \( \delta_{ijk} \) = Uncontrolled variation associated with the jth main plot factor and kth sub-plot factor in the ith replication

    Analysis of Variance for Strip Plot Design

    Source DF SS MS Cal F
    Replication r-1 $$ \sum_{i=1}^{r} Y_{i..}^2 - \frac{(\sum Y_{ijk})^2}{rab} $$ $$ \frac{RSS}{r-1} $$ $$ \frac{RMS}{E(a)MS} $$
    Horizontal Factor (A) a-1 $$ \sum_{j=1}^{a} Y_{.j.}^2 - \frac{(\sum Y_{ijk})^2}{rab} $$ $$ \frac{ASS}{a-1} $$ $$ \frac{AMS}{E(a)MS} $$
    Error (a) (r-1)(a-1) $$ \sum_{i=1}^{r}\sum_{j=1}^{a} \frac{Y_{ij.}^2}{b} - \frac{(\sum Y_{ijk})^2}{rab} - RSS - ASS $$ $$ \frac{E(a)SS}{(r-1)(a-1)} $$
    Vertical Factor (B) b-1 $$ \sum_{k=1}^{b} Y_{..k}^2 - \frac{(\sum Y_{ijk})^2}{rab} $$ $$ \frac{BSS}{b-1} $$ $$ \frac{BMS}{E(b)MS} $$
    Error (b) (r-1)(b-1) $$ \sum_{i=1}^{r}\sum_{k=1}^{b} \frac{Y_{i.k}^2}{a} - \frac{(\sum Y_{ijk})^2}{rab} - RSS - BSS $$ $$ \frac{E(b)SS}{(r-1)(b-1)} $$
    A × B (a-1)(b-1) $$ \sum_{j=1}^{a}\sum_{k=1}^{b} \frac{Y_{.jk}^2}{r} - \frac{(\sum Y_{ijk})^2}{rab} - ASS - BSS $$ $$ \frac{ABSS}{(a-1)(b-1)} $$ $$ \frac{ABMS}{E(c)MS} $$
    Error (c) (r-1)(a-1)(b-1) By subtraction $$ \frac{E(c)SS}{(r-1)(a-1)(b-1)} $$
    Total rab-1 $$ \sum_{i=1}^{r}\sum_{j=1}^{a}\sum_{k=1}^{b} Y_{ijk}^2 - \frac{(\sum Y_{ijk})^2}{rab} $$

    Calculation of Standard Error of Mean and Critical Difference (CD)

    1. Standard error of mean for Horizontal factor (A)
    $$ S.Em.(A) = \sqrt{\frac{E(a)MS}{rb}} $$

    2. Standard error of mean for Vertical factor (B)
    $$ S.Em.(B) = \sqrt{\frac{E(b)MS}{ra}} $$

    3. Standard error of mean for interaction (A × B)
    $$ S.Em.(A \times B) = \sqrt{\frac{E(c)MS}{r}} $$

    4. Critical difference for main factor (A)
    $$ CD_{0.05}(A) = S.Em.(A) \times \sqrt{2} \times t_{0.05,ne(a)} $$

    5. Critical difference for sub factor (B)
    $$ CD_{0.05}(B) = S.Em.(B) \times \sqrt{2} \times t_{0.05,ne(b)} $$

    6. Critical difference for interaction (A × B)
    $$ CD_{0.05}(A \times B) = S.Em.(A \times B) \times \sqrt{2} \times t_{0.05,ne(c)} $$


    Calculation of Coefficient of Variation (CV%)

    1. CV for Horizontal factor (A)
    $$ CV\%(A) = \frac{\sqrt{E(a)MS}}{\bar{Y}} \times 100 $$

    2. CV for Vertical factor (B)
    $$ CV\%(B) = \frac{\sqrt{E(b)MS}}{\bar{Y}} \times 100 $$

    3. CV for interaction (A × B)
    $$ CV\%(AB) = \frac{\sqrt{E(c)MS}}{\bar{Y}} \times 100 $$

    Example of Strip Plot Design

    In the previous chapter, this dataset was used for a split-plot design and now the same dataset will be used to illustrate a strip plot design.

    A strip plot design was used to investigate the effects of irrigation levels (Horizontal factor) and fertilizer types (Vertical factor) on the yield of a particular crop. The experiment was conducted over four replicates (R1, R2, R3, R4).

    Factors:

    Horizontal Factor (A - Irrigation Levels):

    A1: Low Irrigation
    A2: Medium Irrigation
    A3: High Irrigation

    Vertical Factor (B - Fertilizer Types):

    B1: Organic Fertilizer
    B2: Inorganic Fertilizer
    B3: Mixed Fertilizer

    Treatments

    Treatment R1 R2 R3 R4
    A1B1 386 396 298 387
    A1B2 496 549 469 513
    A1B3 476 492 436 476
    A2B1 376 406 280 347
    A2B2 480 540 436 500
    A2B3 455 512 398 468
    A3B1 355 388 201 337
    A3B2 446 533 413 482
    A3B3 433 482 334 435

    Solution:

    Treatments R1 R2 R3 R4 Treatment total Treatment means
    A1B1 386 396 298 387 1467 366.75
    A1B2 496 549 469 513 2027 506.75
    A1B3 476 492 436 476 1880 470.00
    A2B1 376 406 280 347 1409 352.25
    A2B2 480 540 436 500 1956 489.00
    A2B3 455 512 398 468 1833 458.25
    A3B1 355 388 201 337 1281 320.25
    A3B2 446 533 413 482 1874 468.50
    A3B3 433 482 334 435 1684 421.00
    Total 3903 4298 3265 3945 15411

    1. Correction factor (CF):

    $$ CF = \frac{(\sum Y_{ijk})^2}{rab} $$ $$ CF = \frac{(15411)^2}{4 \times 3 \times 3} = 6597192 $$

    2. General mean ($\bar{Y}$):

    $$ \bar{Y} = \frac{15411}{4 \times 3 \times 3} = 428.08 $$

    3. Replication SS (RSS):

    $$ RSS = \frac{\sum Y_{i..}^2}{ab} - \frac{(\sum Y_{ijk})^2}{rab} $$ $$ = \frac{3903^2 + 4298^2 + 3265^2 + 3945^2}{3 \times 3} - 6597192 $$ $$ = 61636.97 $$

    Horizontal factor (A) × Replication table:

    R1 R2 R3 R4
    A1 1358 1437 1203 1376
    A2 1311 1458 1114 1315
    A3 1234 1403 948 1254

    4. Horizontal factor SS (ASS):

    $$ ASS = \frac{\sum Y_{.j.}^2}{rb} - \frac{(\sum Y_{ijk})^2}{rab} $$ $$ = \frac{5374^2 + 5198^2 + 4839^2}{4 \times 3} - 6597192 $$ $$ = 12391.17 $$

    5. Error associated with horizontal factor ($E(a)SS$):

    $$ E(a)SS = \frac{\sum \sum Y_{ij.}^2}{b} - \frac{(\sum Y_{ijk})^2}{rab} - RSS - ASS $$ $$ = 4382.61 $$

    6. Vertical factor SS (BSS):

    $$ BSS = \frac{\sum Y_{..k}^2}{ra} - \frac{(\sum Y_{ijk})^2}{rab} $$ $$ = 128866.70 $$

    Vertical factor (B) × Replication table:

    R1 R2 R3 R4
    B1 1117 1190 779 1071
    B2 1422 1622 1318 1495
    B3 1364 1486 1168 1379

    7. Error associated with vertical factor ($E(b)SS$):

    $$ E(b)SS = \frac{\sum \sum Y_{i.k}^2}{a} - \frac{(\sum Y_{ijk})^2}{rab} - RSS - BSS $$ $$ = 4752.44 $$

    A × B table:

    B1 B2 B3 Total A
    A1 1467 2027 1880 5374
    A2 1409 1956 1833 5198
    A3 1281 1874 1684 4839
    Total B 4157 5857 5397

    8. A × B SS (ABSS):

    $$ ABSS = \frac{\sum \sum Y_{.jk}^2}{r} - \frac{(\sum Y_{ijk})^2}{rab} - ASS - BSS $$ $$ = 304.16 $$

    9. Total SS (TSS):

    $$ TSS = \sum \sum \sum Y_{ijk}^2 - \frac{(\sum Y_{ijk})^2}{rab} $$ $$ = 213796.80 $$

    10. Main Error ($E(c)SS$):

    $$ E(c)SS = TSS - RSS - ASS - E(a)SS - E(b)SS - BSS - ABSS $$ $$ = 1462.72 $$

    Final ANOVA Table for Crop Yield Analysis Using Strip Plot Design with Irrigation and Fertilizer Treatments

    TABLE F

    SV DF SS MS CAL F 5% 1%
    Replication 3 61636.97 20545.66 28.12 3.49 10.80
    Horizontal plot (A) 2 12391.17 6195.58 8.48 5.14 10.92
    Error (A) 6 4382.61 730.44
    Vertical plot (B) 2 128866.67 64433.33 81.35 5.14 10.92
    Error (B) 6 4752.44 792.07
    $A \times B$ 4 304.17 76.04 0.62 3.26 5.41
    Error (C) 12 1462.72 121.89
    Total 35 213796.75

    Calculation of degrees of freedom:

    Replication DF: r-1 = 4-1=3

    Main plot (A): a-1=3-1=2

    Error (A):(r-1)*(a-1)=3*2=6

    Main plot (B): b-1=3-1=2

    Error (B): (r-1)*(b-1)=3*2=6

    $A \times B$: (a-1)*(b-1)=2*2=4

    Error (C): (r-1)*(a-1)*(b-1)=3*2*2=12

    Total: rab-1=4*3*3-1=35


    Calculation of MS:

    Replication: 61636.97/3=20545.66

    Main plot (A): 12391.17/2=6195.58

    Error (A): 4382.61/6=730.44

    Main plot (B): 128866.67/2=64433.33

    Error (B): 4752.44/6=792.07.

    A x B: 304.17/4=76.04

    Error (C): 1462.72/12=121.89

    Calculation of Standard Error of Mean and Critical Difference (CD)

    1. Standard error of mean for horizontal factor (A)
      \[ \text{S.Em. (A)} = \sqrt{\frac{E(a)\,MS}{rb}} = \sqrt{\frac{730.44}{4 \times 3}} = 7.80 \]
    2. Standard error of mean for vertical factor (B)
      \[ \text{S.Em. (B)} = \sqrt{\frac{E(b)\,MS}{ra}} = \sqrt{\frac{792.07}{4 \times 3}} = 8.12 \]
    3. Standard error of mean for interaction (A × B)
      \[ \text{S.Em. (A \times B)} = \sqrt{\frac{E(b)\,MS}{r}} = \sqrt{\frac{121.89}{4}} = 5.52 \]
    4. Critical difference of mean for horizontal factor (A)
      \[ \text{CD}_{0.05} = \text{S.Em. (A)} \times \sqrt{2} \times t_{0.05,\;ne(a)} \] \[ = 7.80 \times \sqrt{2} \times 2.44 = 26.99 \]
    5. Critical difference of mean for vertical factor (B)
      \[ \text{CD}_{0.05} = \text{S.Em. (B)} \times \sqrt{2} \times t_{0.05,\;ne(b)} \] \[ = 8.12 \times \sqrt{2} \times 2.44 = 28.11 \]
    6. Critical difference of mean for interaction (A × B)
      \[ \text{CD}_{0.05} = \text{S.Em. (A \times B)} \times \sqrt{2} \times t_{0.05,\;ne(c)} \] \[ = 5.52 \times \sqrt{2} \times 2.17 = 17.00 \]

    Calculation of Coefficient of Variation (CV%)

    1. Coefficient of variation for horizontal factor (A)
      \[ \text{CV % (A)} = \frac{\sqrt{E(a)\,MS}}{\bar{Y}} \times 100 = \frac{\sqrt{730.44}}{428.08} \times 100 = 6.31 \]
    2. Coefficient of variation for vertical factor (B)
      \[ \text{CV % (B)} = \frac{\sqrt{E(b)\,MS}}{\bar{Y}} \times 100 = \frac{\sqrt{792.07}}{428.08} \times 100 = 6.57 \]
    3. Coefficient of variation (Interaction)
      \[ \text{CV % (C)} = \frac{\sqrt{E(c)\,MS}}{\bar{Y}} \times 100 = \frac{\sqrt{121.89}}{428.08} \times 100 = 2.57 \]

    Conclusion

    • The calculated F-value (28.12) is much greater than the critical F-values at both 5% (3.49) and 1% (10.80) significance levels. Therefore, there is strong evidence to suggest that there are significant differences between the replicates.
    • The calculated F-value (8.48) for the horizontal factor exceeds the critical F-value at the 5% (5.14) significance level. This indicates that there are significant differences among the irrigation levels.
    • The calculated F-value (81.35) for the vertical factor exceeds the critical F-value at the 1% (10.92) significance level. This indicates that there is highly significant variation among fertilizer levels.
    • The calculated F-value (0.62) for the interaction between the main factor and sub-factor (A × B) is less than the critical F-value at the 5% (2.93) significance level. This indicates that there is a non-significant interaction between irrigation and fertilizer.
    • For irrigation, the highest yield was observed for A1, and A2 was found to be statistically at par with it based on the critical difference.
    • For fertilizer, the highest yield was observed for B2, and none of the fertilizer levels were found to be at par with it based on the critical difference.
    • For the interaction (A × B), the highest yield was observed for A1 × B2, and none of the combinations of the two factors were found to be at par with it.

    Steps to perform analysis of split plot design in Agri Analyze

    Step 1: To create a CSV file with columns for replication, main factor (A), sub factor (B) and Yield.

    Horizontal Vertical Replication Yield
    A1 B1 R1 386
    A1 B2 R1 496
    A1 B3 R1 476
    A2 B1 R1 376
    A2 B2 R1 480
    A2 B3 R1 455
    A3 B1 R1 355
    A3 B2 R1 446
    A3 B3 R1 433
    A1 B1 R2 396
    A1 B2 R2 549
    A1 B3 R2 492
    A2 B1 R2 406
    A2 B2 R2 540

    Step 2: Click on ANALYTICAL TOOL ->DESIGN OF EXPERIMENT ->STRIP PLOT DESIGN ANALYSIS

    Step 3: Open link https://www.agrianalyze.com/StripPlot.aspx (For first time users free registration is mandatory)

    Step 4: Link Here to download sample file Sample File Download

    Step 5: Select Replication, Horizontal factor (A), Vertical factor (B) and Dependent variable (Yield)

    Step 6: Select a test for multiple comparisons, such as Least Significant Difference (LSD) test or Tuckey's test or Duncan's New Multiple Range Test (DNMRT test) for grouping of treatment means.

    Step 7: Click submit, pay a nominal fee, and download the output report with detailed interpretation.

    Output Report: Link of the output report

    Video Tutorial: Link of the Youtube Tutorial

    Reference

    Gomez, K. A., & Gomez, A. A. (1984). Statistical Procedures for Agricultural Research. John wiley & sons. 108-120.

    The blog is written by:
    Darshan Kothiya, PhD Scholar, Department of Agricultural Statistics, BACA, AAU, Anand