Scribd
Upload
140 views

EDA - Formula

This document provides formulas and definitions for analysis of variance (ANOVA) for completely randomized designs, randomized complete block designs, and factorial designs. It includes formulas to calculate total sum of squares, treatment sum of squares, error sum of squares, mean sum of squares, mean square error, and F-critical values. It also provides definitions and formulas for standard error, least significant difference, Student-Newman-Keuls test, Tukey's honest significant difference test, and Scheffe's S test to compare treatment means.

Uploaded by

Lyka Mae Mancol
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
140 views

EDA - Formula

This document provides formulas and definitions for analysis of variance (ANOVA) for completely randomized designs, randomized complete block designs, and factorial designs. It includes formulas to calculate total sum of squares, treatment sum of squares, error sum of squares, mean sum of squares, mean square error, and F-critical values. It also provides definitions and formulas for standard error, least significant difference, Student-Newman-Keuls test, Tukey's honest significant difference test, and Scheffe's S test to compare treatment means.

Uploaded by

Lyka Mae Mancol
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

COMPLETELY RANDOMIZED DESIGN (CRD) RANDOMIZED COMPLETELY BLOCK DESIGN

(RCBD)
(𝑌. . )2
𝐶𝐹 = (𝑌. . )2
𝑛
𝐶𝐹 =
𝑛

𝑡 𝑟𝑗 𝑡 𝑟𝑗

𝑇𝑆𝑆 = ∑ ∑ 𝑌𝑖𝑗 2 − 𝐶𝐹 𝑇𝑆𝑆 = ∑ ∑ 𝑌𝑖𝑗 2 − 𝐶𝐹


𝑖=𝑗 𝑗=1 𝑖=𝑗 𝑗=1

𝑡 𝑡
𝑌𝑡 2 𝑌𝑡 2
𝑇𝑟𝑆𝑆 = ∑ − 𝐶𝐹 𝑇𝑟𝑆𝑆 = ∑ − 𝐶𝐹
𝑟𝑡 𝑟𝑡
𝑖=1 𝑖=1

𝐸𝑆𝑆 = 𝑇𝑆𝑆 − 𝑇𝑟𝑆𝑆 ∑𝑡𝑖=1 𝑌𝑡 2


𝑅𝑆𝑆 = − 𝐶𝐹
𝑡

𝑀𝑆𝑇𝑟 = 𝑇𝑟𝑆𝑆 /(𝑡 − 1)


𝐸𝑆𝑆 = 𝑇𝑆𝑆 − 𝑇𝑟𝑆𝑆 − 𝑅𝑆𝑆

𝑀𝑆𝐸 = 𝐸𝑆𝑆/(𝑛 − 𝑡)
𝑀𝑆𝑇𝑟 = 𝑇𝑟𝑆𝑆 /(𝑡 − 1)

𝑀𝑆𝑇𝑟
𝐹𝑐 =
𝑀𝑆𝐸 𝑀𝑆𝑅 = 𝑅𝑆𝑆 /(𝑟 − 1)

√𝑀𝑆𝐸 𝑀𝑆𝐸 = 𝐸𝑆𝑆/(𝑟 − 1)(𝑡 − 1)


𝐶𝑉(%) = ̅̅̅̅ 𝑥100%
𝑌. .

𝑀𝑆𝑅
𝐹𝑐 =
𝑀𝑆𝐸

𝑀𝑆𝑇𝑟
𝐹𝑐 =
𝑀𝑆𝐸

√𝑀𝑆𝐸
𝐶𝑉(%) = ̅̅̅̅ 𝑥100%
𝑌. .
Factorial Design COMPARISON OF MEANS

(𝑌. . )2
𝐶𝐹 = 𝑀𝑆𝐸
𝑁 ̅̅̅̅
𝑠. 𝑒. (𝑌 𝑖) = √
𝑛𝑜. 𝑜𝑓 𝑟𝑒𝑝𝑙𝑖𝑐𝑎𝑡𝑖𝑜𝑛𝑠

∑( ∑ 𝑎 𝑖 ) 2 1 1
𝑠𝑠𝐴 = − 𝐶𝐹 ̅𝑖 ′ ) 𝑜𝑟 𝑠. 𝑒. (𝑑) = √𝑀𝑆𝐸 ( + )
̅𝑖 − 𝑌
𝑆. 𝐸. (𝑌
(𝑏)(𝑛) 𝑛𝑎 𝑛𝑏

∑(∑ 𝑏𝑖 )2 Least significant difference (LSD) test


𝑠𝑠𝐵 = − 𝐶𝐹
(𝑎)(𝑛)
𝐿𝑆𝐷 = 𝑡 𝑥 𝑠𝑒(𝑑)

∑(∑ 𝑎𝑖 𝑏𝑖 )2 ∑(∑ 𝑎𝑖 )2 ∑(∑ 𝑏𝑖 )2


𝑠𝑠𝐴𝐵 = − − − 𝐶𝐹 Student-Newmann-Keuls (SNK) Test
(𝑛) (𝑏)(𝑛) (𝑎)(𝑛)
𝑊𝑝 = 𝑞𝑝 𝑥 𝑠𝑒 (𝑌̃𝑖 . )

𝑠𝑠𝑡𝑜𝑡𝑎𝑙 = ∑ 𝑌 2 − 𝐶𝐹
Tukey’s Honest Significant Difference (HSD) Test

𝑠𝑠𝑒𝑟𝑟𝑜𝑟 = 𝑠𝑠𝑡𝑜𝑡𝑎𝑙 − 𝑠𝑠𝐴 − 𝑠𝑠𝐵 − 𝑠𝑠𝐴𝐵 HSD = 𝑞𝑝 𝑥 𝑠𝑒 (𝑌̃𝑖 . )

Scheffe’s S Test
𝑀𝑆𝑆𝐴 = 𝑆𝑆𝐴 /(𝑎 − 1)
𝑆 = √(𝑡 − 1)𝐹𝑡 𝑥 𝑠𝑒 (𝑑)

𝑀𝑆𝑆𝐵 = 𝑆𝑆𝐵 /(𝑏 − 1)

𝑀𝑆𝑆𝐴𝐵 = 𝑆𝑆𝐴𝐵 /(𝑎 − 1)(𝑏 − 1)

𝑀𝑆𝐸 = 𝑆𝑆𝐸/(𝑁 − 𝑎𝑏)

𝐹𝑐𝐴 = 𝑀𝑆𝑆𝐴 /𝑀𝑆𝐸

𝐹𝑐𝐵 = 𝑀𝑆𝑆𝐵 /𝑀𝑆𝐸

𝐹𝑐𝐴𝐵 = 𝑀𝑆𝑆𝐴𝐵 /𝑀𝑆𝐸

√𝑀𝑆𝐸
𝐶𝑉(%) = ̅̅̅̅ 𝑥100%
𝑌. .

You might also like