1 of 22

Do Glasses Help??

​

Two Sample t Tests and Intervals for Independent Samples

2 of 22

theme

3 of 22

Lockdown Browser

4 of 22

Lockdown Browser

Lockdown Browser Practice

5 of 22

Quiz at -20 minutes left in class.

”

6 of 22

Big Ideas - Difference Between Two Means

  • Determine whether the conditions are met for doing inference about a difference between two means.
  • Construct and interpret a confidence interval for a difference between two means.
  • Calculate the standardized test statistic and P-value for a test about a difference between two means.
  • Perform a significance test for the difference between two means.

7 of 22

Intervals and Tests for Two Means

Queue the Ultimate Inference Guide

8 of 22

9 of 22

10 of 22

Never Combine/Pool SD’s

Standard Error:

Unlike proportions we NEVER need to pool these.

Standard deviations are algebraically linked to their proportions, but this is not the case for means.

11 of 22

Finding t*

Finding degrees of freedom

is better left to your calculator.

12 of 22

Independence Assumption

The data in each group must be drawn independently from a homogeneous population

13 of 22

Normal Population Assumption

Make a histogram of the data from each group.

Make sure both are normally distributed.

14 of 22

**NEW Independent Groups Assumption

  • The two groups can not influence each other’s outcomes.
  • No statistical test can verify this assumption. You have to think about how the data were collected.
  • FUN FACT: This test is sometimes called the two independent samples t-test.

15 of 22

CHOOSE

CONDITIONS

CALCULATE

CONCLUDE

Choose the correct inference procedure, set it up, and define variables.

Check the appropriate conditions.

Perform the calculations.

Write a conclusion in context.

16 of 22

Glasses aren't just good for your eyes. They can be a boon to income, too

17 of 22

18 of 22

Research Paper

19 of 22

Wansink, Brian, James E. Painter, and Jill North. 2005. “Bottomless Bowls: Why Visual Cues of Portion Size May Influence Intake.” Obesity 13 (1): 93–100.

20 of 22

Wansink, Brian, James E. Painter, and Jill North. 2005. “Bottomless Bowls: Why Visual Cues of Portion Size May Influence Intake.” Obesity 13 (1): 93–100.

But wait, there’s more!

21 of 22

A Strange Turn of Events!

In 2019 Brian Wansink, the Principal Investigator for this study was let go from Cornell University.

They found he “committed academic misconduct” in this, and at least 14 other studies.

Read more here.

22 of 22

Big Ideas - Difference Between Two Means

  • Determine whether the conditions are met for doing inference about a difference between two means.
  • Construct and interpret a confidence interval for a difference between two means.
  • Calculate the standardized test statistic and P-value for a test about a difference between two means.
  • Perform a significance test for the difference between two means.