In data science, we usually classify variables into two big types: Continuous(age), Categorical(sex).
What about the variables in clinical trials/statistics? How many different types do we have?
Little goal:
Today we will learn the six common types of variable in statistics?
How to use and present them in clinical trials?
- Continuous variable: Numerical numbers that have an infinite number of values between any two values.
Ex: Age, weight, height, BMI
Numerical: summary of stats (mean, median, sd, variance, min,max, q1,q3)
Graphics: Histogram, box plot - Binary/dichotomous variables: only take two values, either yes or no
Ex: death flag, AE flag, Inclusion/Exclusion
Numerical: Proportion tabulate
Graphics: Bar plot - Nomial/categorical variables: More than 2 categories without order
Ex: Race
Numerical: Frequency Count
Graphics: Bar plot/ Pie chart - Ordinal variables: Categories with order.
Ex: AE grade(mild, moderate, severe, life-threatening, death)
Pain score(1,2,3,4,5)
Numerical: Frequency Count
Graphics: Bar plot/ Pie chart - Count/Discrete Variables: occurrences are countable infinitely
Ex: Number of Leision
Numerical: Frequency Count
Graphics: Bar plot/ Pie chart - Time to Event Variable: Time from the origin to a specified event happens.
Ex: Time to death
Numerical: Median, Pvalue, 95%CI
Graphics: Kaplan Meier Curve.
* TTE, survival analysis is a unique analysis in the clinical trials.
bonus: Measure of locations is a fancy way of saying mean, sd, median.
Happy studying!
Special thanks to 77 for sharing the Havard catalyst classes!