# Frequentist

## Definition of Frequentist

Frequentist: A Frequentist is someone who believes that the only valid methods of statistics are those that rely on the law of large numbers, and the principle of population stabilization.

## What do Frequentist do?

Frequentists are data scientists and machine learning specialists who use frequentist statistical methods for their work. Frequentist methods are based on the principle of frequency and assume that a certain probability distribution governs a given set of data points. This means that the results from any given experiment or data analysis can be predicted using probability distributions, making it possible to draw meaningful conclusions from seemingly unrelated datasets. Frequentist methods are widely used in fields such as economics, finance, healthcare, and physics because they provide an efficient way to model complex systems and accurately represent reality.

One example of a frequentist method is the maximum likelihood estimation (MLE). MLE assumes that the parameters of a given dataset can be estimated by finding the values that maximize the log-likelihood function. This allows us to efficiently calculate parameter estimates such as mean, variance, correlation, and more from a set of observations.

Another common frequentist method is hypothesis testing. Hypothesis testing involves making predictions about relationships between variables in order to test whether or not those hypotheses are supported by evidence in the data. For example, if we expect there to be a relationship between two variables, we can use hypothesis testing to determine whether or not that relationship exists and how strong it is statistically.

Finally, Bayesian statistics is another type of frequentist method which uses prior information (which can come from previous experiments) alongside observed data in order to arrive at more accurate conclusions than traditional frequentist approaches. Bayesian methods are often used when dealing with small sample sizes or when making predictions based on uncertain information such as missing or incomplete data points.