Random Block Design in Experiments
Translated by
ScribdTranslationsRandom Block Design in Experiments
Translated by
ScribdTranslationspreparation d e l o s principals
Experimental designs
y
FACTORIAL ARRANGEMENTS
BY: HECTOR M. DELGADO
simple experiments
Design
Random Blocks
(DBA)
simple experiments
random block design (RBD)
In this section, the most outstanding traits for working with the DBA will be presented.
Design characteristics
It is used when in the place
where it will be developed
It is the most used in The area of the experiment is
agricultural experimentation and research is identified
divide into blocks
a gradient of
forestry homogeneous
variability defined in a
only sense.
The units In each block each
experimental ones treatment must appear
The treatments are assigned
distributed in groups or only once; it is
randomly to the units
blocks, in such a way that recommended to place the
experimental of each
the experimental units length of the unit
block
inside a block are experimental parallel to the
relatively homogeneous variability gradient.
simple experiments
random block design (RBD)
In this section, the most outstanding features for working with the DBA will be addressed.
Modalities
Balanced:
When all treatments have the same number of
repetitions.
Unbalanced:
When not all treatments have the same number of
repetitions.
simple experiments
random block design (RBD)
In this section, the most notable traits for working with the DBA will be presented.
Advantages
By using a random block
Any can be included
results are obtained
number of treatments and
more precise than when Easy statistical analysis.
repetitions up to where
it is used completely
it is practically possible
at random.
If a treatment is lost In the event that it is
If units are lost complete is analyzed as
lose a treatment, the
experimental (up to 3) one treatment less; yes
statistical analysis is
statistical analysis it is a complete block,
you can do with a
it is still easy like a repetition
less treatment
less.
simple experiments
random block design (RBD)
In this section, the most outstanding features for working with the DBA will be outlined.
Disadvantages
There are fewer number of
degrees of freedom for
the experimental error
regarding the design
completely at random.
simple experiments
random block design (RBD)
This section will address the most outstanding features for working with the DBA.
Statistical model
Yij = μ + τi + βj + εij
i = 1, 2, ...t
j = 1, 2, ... r
Where:
Yij = Response variable of the ij-th experimental unit
μ = Effect of the overall mean
Effect of the i-th treatment
βj = Effect of the j-th block
εij = Effect of the experimental error associated with the ij-th experimental unit
simpleexperiments
random block design (RBD)
This section will present the most prominent features for working with the DBA.
Determination of the number of experimental units
glee = (t–1) (r-1)
In this example, it t1: Caldo sulfocálcico
will evaluate the Formula for degrees of freedom of
effectiveness of the experimental error for DBA
Biofertilizer
application of 6
preparations in the t3: Sulfocalcium solution + Where:
damping control biofertilizer t= Número de tratamientos
openPinus caribaea r = Number of repetitions
Fungicide-bactericide
Morelet Python 24
glee = (t-1) (r-1)
Bordeaux broth
So:
Witness (no application 12 = (6-1) (r-1)
of treatments).
simple experiments
random block design (RBD)
In this section, the most notable traits for working with the DBA will be discussed.
Determination of the number of experimental units
Number of treatments 01 02 03 04 05 06
t=6
Number of repetitions
07 08 09 10 11 12
r=4
Determination of
13 14 15 16 17 18
Number of Units
Experimental:
ue = t×r = 6×4 = 24 19 20 21 22 23 24
simple experiments
random block design (RBD)
Gradient of variability
Randomization
t1: Caldo sulfocálcico
Repetition 1 = Block I 01 02 03 04 05 06
Biofertilizer
Repetition 2 = Block II 07 08 09 10 11 12 Calcium sulfacalcium +
biofertilizer
Fungicide-bactericide
Python 24
Repetition 3 = Block III 13 14 15 16 17 18
Brothel broth
Repetition 4 = Block IV 19 20 21 t6: Witness (null application
22 23 24 of treatments).
simple experiments
random block design (RBD)
Gradient of variability
Randomization
t1: Caldo sulfocálcico
Repetition 1 = Block I 3 1 6 4 2 5
Biofertilizer
Repetition 2 = Block II 5 3 2 4 6 1 Calcium sulfanilate +
biofertilizer
Fungicide-bactericide
Repetition 3 = Block III Python 24
1 3 6 5 2 4
Bordeaux broth
Repetition 4 = Block IV 2 3 1 5 4 6 t6: Witness (no application)
of treatments).
simple experiments
random block design (RBD)
Gradient of variability
Randomization
t1: Caldo sulfocálcico
Repetition 1 = Block I 31 11 61 41 21 51
Biofertilizer
Repetition 2 = Block II 52 32 22 42 62 12 Calcium sulfide solution +
biofertilizer
Fungicide-bactericide
Repetition 3 = Block III 13 33 63 53 23 43 Python 24
Bordel broth
Repetition 4 = Block IV 24 34 14 54 44 64 t6: Witness (null application
of treatments).
simple experiments
random block design (RBD)
Direction of the gradient of variability t1: Caldo sulfocálcico
↓
Biofertilizer
311161412151
sulfur calcium broth +
biofertilizer
52322242 6212
Fungicide-bactericide
Python 24
133363 532343
Bordeaux broth
witness (null
2434 14 544464 application of
treatments).
preparation d e l o s principals
EXPERIMENTAL DESIGNS AND
FACTORIAL ARRANGEMENTS