1. Linear Regression

Apply the following steps on this wind quality dataset (attached is the google document link)

https://docs.google.com/spreadsheets/d/1QrX9fEceQlfSOY-nG1dUYSLwEvV7RrdNYcj2J4zVbDI/edit?usp=sharing

• step 1: In excel regression, use "quality" as Y variable, and use all other columns as X variables by selecting the whole block as the input x range, click on label, output the results starting from O1, and generating NO plots.
• step 2: Copy the winequality-red sheet to create a duplicate worksheet,
• step 3: In the duplicated sheet, from the excel output, identify variables with p-value greater than 0.05, which means the corresponding variables are not predictive. (Btw, 8.37E-06 means 0.000000837). Remove those variables by deleting those colums. Also delete the excel output portion.
• Repeat Step 1- 3, until all variables remaining are significantly predictive, i.e., with p-value less than 0.05. This might or might not require more than two iterations.

a. In your final model, what factors have positive influence on quality and what factors have negative influence on quality?

b. use your final model to predict the quality of this wine with the profile below:

Fixed volatile citric residual chlorides free total density pH sulphates alcohol

acidity acidity acid sugar sulfer sulfer

dioxide dioxide

7.0 0.88 0 2 0.071 15 32 0.9978 3.31 0.46 9.8