![[Pasted image 20240629141535.png|300]]
# Random Variables
**Randomness** can be described as the *presence of uncertainty* (or the absence of predictability).
A random variable is a mathematical object takes in an element in a sample space and outputs a number
The relationship between these two is described through a [[Probability Distributions 1|probability distribution]]
A **random variable** will always have an associated probability distribution that represents the likelihood that any of the possible values would occur
Random variables are known as *stochastic processes*. The term “stochastic” refers to the property of being well-described by a random [[Probability Distributions 1|probability distribution]].
- An *uppercase* random variable *has not been observed* yet and a *lowercase* random variable is associated with an observed value and is *no longer random*.
> [!NOTE]+ Random Variables vs Events
>
> Random varaibles and events are two different concepts.
>
> An event is an outcome, or more often a set of outcomes, to an experiment. A random variable is more like an experiment
---
Once a value has actually been determined for a random variable, we say that it has been **realized** (or observed). The value produced is known as a *realization* (or observation/observed value).
## Discrete vs Continuous Variables
> See also:
> - [[Probability Distributions 1]]
### Discrete Random Variables
- [ ] Probability Mass Functions
### Continuous Random Variables
In the case of **continuous random variables**, we can no longer talk about the probability that we observed $O$ given $\theta$, because at any given $O$, $P(O|\theta)=0$.
This occurs because there are now an *infinite amount of possible outcomes* due to the nature of continuous functions.
> [!summary] **Definition:** Continuous Random Variables
> a
> a
>
---
The distinction between continuous and discrete variables is blurred/nonexistant when viewed from the field of [[Measure Theory]].
## Marginal Probabilities
> See also:
> - [[Joint Probability Distributions]]
Given some subset of random variables from a larger collection, the marginal distribution
The marginal distribution of a subset of a collection of random variables
**Marginal Probability Mass Function**
A marginal distribution gives the proba
It contrasts with the