Random Variable Basics ​​​​(SOA Exam P – Probability – Univariate Random Variables Module)

Uppercase letters (like $N$) denote the random variable itself, which is a function or rule before observation. Lowercase letters (like $n$) denote a specific realized value or observation of that variable after the experiment is conducted.

Conditions: The context involves probability notation.; Distinguishing between the theoretical variable and empirical data.

A discrete counting model is appropriate when the variable represents a count of items within a finite or countable set, such as the number of people in a family. A continuous measurement model is appropriate for idealized quantities that can take any value in an interval, such as time or unrounded monetary amounts.

Conditions: The variable is a count of distinct entities.; The variable is a measurement of a continuous quantity.

A discrete counting model is defined by a finite set of possible values that the random variable can take. For example, counting items within a fixed group results in integer values ranging from zero to the total number of items in that group.

Conditions: The random variable represents a count.; The population or group size being counted is finite.

Modeling money in whole cents restricts the possible values to a discrete set (multiples of 0.01). This creates a countably infinite set of possible outcomes, which differs from an idealized continuous model where amounts can take any real value within an interval before rounding.

Conditions: The monetary amount is constrained to whole cents.; Comparing discrete cent-based models with idealized continuous models.