Principles of design of experiments-II: Randomization

-
This blog deals with the basic concept of randomization and its functions along with a suitable example. (reading time 7 min.)
There are three principles of designs of experiments:
1) Replication
2) Randomization
3) Local Control

In a previous blog, we have seen how replication provides an estimate of an experimental error. For a sound experiment, we need to estimate experimental error and that estimate must be an unbiased estimate. Randomization helps us to get an unbiased estimate of experiment error.

Definition

When all the treatments have equal chances (probability) of being allocated to all the experimental units it is called randomization.
Experimental units can be seeds, plants, animals etc. depending on your research. The procedure of randomization varies with the experimental design used.
 
Randomization also allows us to use probability theory and different statistical techniques. The complex statistical techniques can be used only if randomization is used. Randomization also helps us to tackle personal bias towards a any treatment.

Different methods for randomization

  • Chit method
  • Random number table 
  • By using R software
Chit method
Chit method is used when number of treatments are low. It uses chits. The number of chits are equal to number of treatments. On each chit, one treatment is mentioned exclusively. Chits are randomly selected and treatments. Watch video for more details.

Random number table 
Random number tables are specialized table used for selecting random values. In order to see random table click here
 
By using R software
Case: Suppose there are 15 treatments and in a Randomized Complete Block Design there are 3 blocks. Carry out randomization for the above mentioned case.
Run the below lines
#Generate treatment vector of 15 treatments
a<-paste("T",c(1:15),sep="")
#Draw random sample. Repeat the below mentioned line for three times
sample(a,15,replace=F)
Output from R
"T13" "T8"  "T2"  "T7"  "T11" "T5"  "T10" "T9"  "T14" "T12" "T6"  "T15" "T3"  "T4"  "T1"
 
"T1"  "T8"  "T10" "T3"  "T12" "T9"  "T13" "T7"  "T15" "T5"  "T6"  "T14" "T2"  "T4" "T11"
 
"T2"  "T9"  "T15" "T5"  "T11" "T1"  "T12" "T8"  "T14" "T13" "T4"  "T10" "T7"  "T3"  "T6"
 
How arrangement will look like
 
If you find this blog useful please do share.

References:

1) Gupta, S. C., and V. K. Kapoor. Fundamentals of applied statistics. Sulthan Chand & Sons, 2019
2) Rangaswamy, R (2010). A textbook of Agricultural Statistics (2nd Edn). New Age International Publishers, New Delhi.
To learn more about Agricultural Statistics follow my youtube channel

Comments

Post a Comment

Popular posts from this blog

Estimation of Genetic Parameters in Plant Breeding: Theory, Example and Demonstration in AgriAnalyze tool

-
Image
The blog is about estimation of genetic parameters like genotypic variance, phenotypic variance, heritability, genetic advance, genetic advance as a percentage of mean, phenotypic coefficient of variation (PCV), genotypic coefficient of variation (GCV) for the RCBD trails of genotypes. (Reading time 20 mins). 1.      INTRODUCTION      In a general statistical context, a parameter refers to a numerical characteristic or attribute that describes a population. It can be a fixed value or an unknown quantity that helps to describe or summarize a specific aspect of a population. Genetic Parameter is a statistical measure that quantifies the genetic contributions to traits within a population of an organism. Genetic parameter estimation in plant breeding involves quantifying various genetic components that influence traits of interest, such as yield, disease resistance or quality attributes. These parameters provide critical insights into the genetic bas...
Read more

F test: Theory, Solved Example and Demonstration in Agri Analyze

-
Image
 The blog discuss in details about theory of F test, its use cases, solved example (manually) and a demonstration using online tool Agri Analyze (Reading time 10 min)  Introduction The F-test is a statistical method used to compare the variances of two samples or the ratio of variances across multiple samples. It assesses whether the data follow an F-distribution under the null hypothesis, assuming standard conditions for the error term (ε). The test statistic, denoted as F, is commonly used to compare fitted models to determine which best represents the underlying population. F-tests are frequently employed in models fitted using least squares. The test is named after Ronald Fisher, who introduced the concept as the "variance ratio" in the 1920s, with George W. Snedecor later naming the test in Fisher’s honor. Definition An F-test uses the F-statistic to evaluate whether the variances of two samples (or populations) are equal. The test assumes that the population follows an ...
Read more