Scribd
Upload
3 views

L1 Principles of Experimentation

The document outlines the principles of experimentation, focusing on randomization, replication, and blocking. Randomization protects against confounding and systematic bias, while replication allows for the estimation of experimental error and increases precision. Blocking helps to reduce experimental error by grouping homogeneous units, enhancing the efficiency of treatment comparisons.

Uploaded by

Cliff Boogië
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

L1 Principles of Experimentation

The document outlines the principles of experimentation, focusing on randomization, replication, and blocking. Randomization protects against confounding and systematic bias, while replication allows for the estimation of experimental error and increases precision. Blocking helps to reduce experimental error by grouping homogeneous units, enhancing the efficiency of treatment comparisons.

Uploaded by

Cliff Boogië
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

PRINCIPLES OF EXPERIMENTATION

1. Randomization
2. Replication
3. Blocking
1. Randomization
An experiment is randomized if the method for assigning treatments to experimental units
involves a known, well-understood probabilistic scheme. The probabilistic scheme is called
randomization.
Advantages
 Protects against confounding.
It helps in distributing the unknown variation due to confounded variables throughout the
experiment thus breaking the confounding influence.
 Avoids systematic bias
Systematic bias occurs when treatments differ with respect to a nuisance variable. If so, it
becomes a confounding variable that randomization eliminates.
Example: Two varieties (A, B) are to be compared with respect to crop yield. Suppose a
crop row consisting of 100 plants is divided into plots of 10 plants. The two varieties are
assigned to plots such that variety A come before variety B (A A A A A B B B B B). Suppose
there is a fertility gradient along this row. Then even if the varieties are equivalent, we will
observe better yield in variety B.
 Ensures valid results
 Can be used as a basis for inference

2. Replication
Replication is the repetition of each treatment on multiple independent experimental units.
Example: Suppose we randomize 10 plots in a crop row to two treatments A and B:
A B B B A B A A A B
Then we have 5 replicates per treatment.
Advantages
1. Allows estimation of the experimental error.
The experimental error is the variation which exists among observations on experimental
units that are treated alike.
When there is no method of estimating experimental error, there is no way to
determine whether observed differences indicate real differences or the differences
observed are due to inherent variation (biological variations occurring in all species).
2. Increases the precision of the experiment.
Increasing the number of observations per treatment increases precision by reducing the
standard deviation of the treatment mean [variance of sample mean 𝑥̅ based on n
𝜎2
observation is , so, as n increases, var(𝑥̅ ) decreases].
𝑛
3. Increases the scope of inference of the experiment.
This is achieved by selection and appropriate use of more variable experimental units.
Example: replication in time and space in yield trials.

What determines number of replicates?


• Available resources. These include; limitations on cost, labor, time, experimental material,
etc.
• Sources of variability in design and their magnitudes.
• Size of the difference to be detected.
• Required significance level (𝛼 = 5%?, 1%?)
• Number of treatments

3. Blocking
(Also called Local Control/Error Control)
A block of experimental units is a set of units that are homogeneous in some sense.
The idea of blocking is to divide experimental units into homogeneous subgroups (or
blocks) within which all treatments are observed so that treatment comparisons can then
be made between similar units in the same block.
Examples; field plots located in the same general area, or region.
Advantages
1. Increases precision with which comparisons among the factors/treatments of
interest are made.
2. Reduces experimental error.
Since the experimental units are divided into different groups such that they are
homogeneous within the blocks, then the variation among the blocks is eliminated and
ideally the error component will contain the variation due to the treatments only. This will
in turn increase the efficiency.
3. Used to reduce or eliminate the variability transmitted from nuisance factors.
Typically, each level of the nuisance factor becomes a block.

Examples of factors that often create heterogeneity in the experimental units and should
form the basis of blocks:
• Region.
• Time (season, year, day).
• Facility (multiple greenhouses are to be used/multiple labs to take measurements/
patients recruited from multiple clinics).
• Personnel to conduct the experiment.

Examples of experimental designs


1 CRD-Completely Randomized Designs
2 RBD-Randomized Block Designs
3 Factorial Designs
4 Latin Square Designs
5 Graeco-Latin Square Designs
6 BIBD-Balanced Incomplete Block Designs
7 Split-Plot Design

Considerations when Designing an Experiment


1. Experimental design should give unambiguous answers to questions of interest.
2. Experimental design should be “optimal”. That is, it should have more power
(sensitivity) and estimate quantities of interest more precisely than other designs.
3. Experiment should be of a manageable size. Not too big to perform, analyze, or
interpret.
4. Objectives of the experiment should be clearly defined.
– What questions are we trying to answer?
– Which questions are most important?
– What populations are we interested in generalizing to?
5. Appropriate response and explanatory variables must be determined and nuisance
variables should be identified.
– What levels of the treatment factors will be examined?
– Should there be a control group?
– Which nuisance variables will be measured?
6. The practical constraints of the experiment should be identified.
– How much time, money, personnel, raw material will it take, and how much do I have?
– Is it practical to assign and apply the experimental conditions to experimental units as
called for by the experimental design.
7. Identify blocking factors.
– In what respects that can be expected to be relevant to the response variable are
experimental units dissimilar?
– Will the experiment be conducted over several days (weeks, seasons, years)? Then block
by day (week/season/year).
– Will the experiment involve several experimenters? (e.g., several different crews to
measure trees, lab technicians, etc.). Then block by experimenter.
– Will the experiment involve units from different locations, or units that dispersed
geographically/spatially? Then form blocks by location, or as groups of units that are near
one another.
8. Statistical analysis of the experiment should be planned in detail to meet the objectives
of the experiment.
– What model will be used?
– How will nuisance variables be accounted for?
– What hypotheses will be tested?
– What “effects” will be estimated?
9. Experimental design should be economical, practical, timely.

You might also like