When to Use a One-Sample t-Test
You'll learn when to apply a one-sample t-test to compare a sample mean against a known population value.
The Core Scenario
A one-sample t-test is your go-to tool when you have:
- One sample of data
- A known population mean (or target value) you want to compare against
- An unknown population standard deviation (you only have your sample's standard deviation)
Think of it like checking if your batch of products meets a quality standard. You know the target weight should be 500 grams, but you don't know the natural variability in the manufacturing process. You take a sample of 30 products, weigh them, and want to know: "Is our actual average significantly different from 500 grams?"
Real-World Examples
- Quality control: Does the average diameter of manufactured bolts differ from the specification of 10mm?
- Health standards: Is the average blood pressure of patients in a clinic different from the national average of 120 mmHg?
- Education: Does the average test score in your classroom differ from the district standard of 75?
Why the t-Test (Not z-Test)?
You use the t-distribution instead of the z-distribution because you're estimating the population standard deviation from your sample. This introduces extra uncertainty, especially with smaller samples, which the t-distribution accounts for through degrees of freedom.
Key Takeaway: Use a one-sample t-test when comparing your sample mean to a known benchmark value and you don't know the true population variance—the most common situation in real-world data analysis.