Monday

In Class

Learning Targets:

I can explain why Correlation does not imply Causation

I can discuss Lurking Variables: Confounding:Common Response situations + the Diagrams

Finishing up your Spurious Correlation posts in Canvas

Tuesday

In Class

Learning Target:

• I can use a LSRE for prediction.
• I can find a residual and I know why the Least Squares Regression (LSRE) equation has that name.
• I can explain what extrapolation is and the problems with using a LSRE to make a prediction that is an extrapolation situation.

We’ll do some exploration with this data <link> and this web page <link>

Exit ticket

Wednesday

In Class:

Same learning targets

Now that you have some background, let’s see an application: <link>

Learning Target: I can describe what the slope and y-intercept of the LSRE means in the context of the situation.

Learning Target: I can find r2 and describe what it means in the context.

We’ll look at some of those situations in the spreadsheet

Thursday

Learning Targets:

I can

Here is the assessment:

Regression Analysis:

Part 1

Choose two quantitative variables that you think may be associated. You can collect some data yourself or find lists on the Internet.

Before you conduct any analysis, What association ( Shape, Strength, Direction) do you expect to see between the two variables? Which variable is the explanatory variable and which variable is the response variable?

Part 2

I’ll be looking to see if the following is present and correct.

• Table of Your two quantitative variables.
• Well labeled scatterplot (Axes with units)
• Correlation coefficient (r)
• Coefficient of Determination (r2 ) expressed either as a proportion/percentage and you explain what it means in the context of this situation.
• Least Square Regression Equation for predicting your Response Variable from your Explanatory Variable.
• An analysis of your results. You must relate your results back to part 1. This must include a discussion about r and r2
• You use your model to make a prediction for two values that are not part of the original data. One of these values must be an example of extrapolation. Identify this prediction.
• Discuss what the slope and y-intercept of your model means in the context of the situation.
• You suggest possible sources of confounding influences.