Your browser doesn't support the features required by impress.js, so you are presented with a simplified version of this presentation.

For the best experience please use the latest Chrome, Safari or Firefox browser.

# Two types of t procedures

• Matched pairs t test
• We measure the same unit twice
• e.g. "before" and "after" for the same person
• 2-sample t test
• We have 2 seperate populations and hence 2 independent samples
• e.g. men vs. women

# How to do in SPSS

• Matched pairs t test
• Create two numeric variables representing the pair
• Variable view:
• Data view:

# How to do in SPSS

• Two-sample t test
• Create one numeric variable containing all the data (both samples), and one string variable labeling the group (e.g. "A" and "B")
• Variable view:
• Data view:

# Remarks

• Always use SPSS to solve t test problems
• In 2-sample comparison of means output, ALWAYS use the bottom row (equal variances NOT assumed)
• In matched pairs, we only have one $\mu$ ($\mu_{diff}$) in the null hypothesis, e.g. $H_0:\mu_{diff}=0$. State what "diff" stands for.
• In 2-sample t test, we have two $\mu$'s, e.g., $\mu_A=\mu_B$. State what "A" and "B" stand for.
• http://statr.me/courses.html