# Kaiser’s rule

## What is Kaiser’s rule ?

Kaiser’s rule is a statistical concept that states that the number of factors that can be extracted from a data set is equal to the number of eigenvalues greater than 1. This rule is also known as the Kaiser criterion and is often used in factor analysis, which is a statistical method used to identify the underlying structure of a large and complex data set.
One example of Kaiser’s rule in action is in the analysis of consumer behavior data. Imagine a company wants to understand the factors that drive consumer purchasing decisions, and they have collected data on a variety of factors such as age, income, education level, and purchasing history. Using factor analysis, they can extract the underlying factors that influence consumer behavior and determine how many of these factors are significant.
Using Kaiser’s rule, the company would first calculate the eigenvalues for each factor, which are a measure of the amount of variance explained by each factor. If the eigenvalues for all factors are greater than 1, it indicates that all of the factors are significant and can be extracted from the data. If some of the eigenvalues are less than 1, it indicates that those factors are not significant and should be discarded.
For example, let’s say the company calculates the eigenvalues for each factor and finds that the eigenvalues for age, income, and education level are all greater than 1, but the eigenvalue for purchasing history is less than 1. This indicates that the factors of age, income, and education level are significant and can be extracted from the data, but the factor of purchasing history is not significant and should be discarded.
Another example of Kaiser’s rule in action is in the analysis of psychological data. Imagine a researcher is studying the factors that influence an individual’s personality, and they have collected data on a variety of factors such as agreeableness, openness, conscientiousness, and neuroticism. Using factor analysis, they can extract the underlying factors that influence personality and determine how many of these factors are significant.
Using Kaiser’s rule, the researcher would first calculate the eigenvalues for each factor, which are a measure of the amount of variance explained by each factor. If the eigenvalues for all factors are greater than 1, it indicates that all of the factors are significant and can be extracted from the data. If some of the eigenvalues are less than 1, it indicates that those factors are not significant and should be discarded.
For example, let’s say the researcher calculates the eigenvalues for each factor and finds that the eigenvalues for agreeableness, openness, and conscientiousness are all greater than 1, but the eigenvalue for neuroticism is less than 1. This indicates that the factors of agreeableness, openness, and conscientiousness are significant and can be extracted from the data, but the factor of neuroticism is not significant and should be discarded.
Overall, Kaiser’s rule is a valuable tool in factor analysis, allowing researchers and analysts to identify the significant factors in a data set and discard those that are not significant. By understanding the underlying structure of a data set, researchers and analysts can gain valuable insights and make informed decisions.