Single-Sample t Test


	Psychology Home

	Statistics and Research Methods Workshops Home



	Statistics Workshops

	Research Methods Workshops

	Videos




	Why Is This Important

	The Big Idea

	How Does It Work

	Example

	Things to Know

	Bottom Line

	Summary

	Workshop Quiz

How Does It Work?		< back		3 of 9		next >

First, you will calculate the mean and standard deviation for your group. You might use a computer to do all of this for you.
		Let me introduce some notation. The sample mean is usually noted as
	The population mean is noted as m. You are testing to see whether or not is different from m.
Next, you will use the t-test formula to compute the t-value. Let’s look at our chart again.

			You pull an infinite set of sample means and make a distribution of these means (Sampling Distribution of the Mean). The mean of this distribution is m if the Null Hypothesis is true. Its width is measured by the standard error of the mean (dark gray arrow from mean to curve). You calculate a t-value and see if it is in the tail. If the t-score is far away: Reject the Null Hypothesis
The *t-score is like a z-score and* tells you if the sample mean is far away from the population mean (m). You will use the sampling distribution of the mean to do this. If the t-value is big enough (you look it up in a t-table), you will reject the Null Hypothesis and say you have a difference. If the t-value is not big enough, you will say that you have not found a difference and fail to reject the Null Hypothesis.**