1. Consider the following data on demand (in 10,000) of bars of soap. The independent variables are Time Period (PERIOD), Price, Average Industry Price (AIP), and Advertising (in $1000). We are interested in building different models to forecast demand.

1. Using Excel, construct the correlation matrix and interpret (relation of all variables with demand). Rank variables based on degree of absolute values of correlation with Demand.
2. Using Excel linear regression analysis, find the Trend line to predict demand based on Time Period. Observe R-squared value and Significant F and interpret.
3. Construct multiple linear regression model using all independent variables to predict Demand (Y). Provide the equation and interpretation of R-squared, Significant-F.
4. Based on P-values of independent variables, rank the variables based on degree of contribution to the model. Hint: The lower the P-value, the higher the significance of a given variable.
5. Use the equation in part (c) to forecast demand for September 2023 if Price = $3.90, AIP = $4.25, and

ADV= $7.3.

Copy and paste the data below in an Excel file for analysis.

Month/Yr.	PERIOD	PRICE	AIP	ADV	DEMAND
March 2021	1	3.85	3.8	5.5	7.38
	2	3.75	4	6.75	8.1
	3	3.7	4.3	7.25	9.52
	4	3.7	3.7	7.5	9.2
	5	3.6	3.85	7	9.33
	6	3.6	3.8	6.5	8.28
	7	3.6	3.75	6.75	8.2
	8	3.8	3.85	5.25	7.87
	9	3.8	3.65	5.25	7.1
	10	3.85	4	6	8
Jan. 2022	11	3.9	4.1	6.5	7.89
	12	3.9	4	6.25	8.15
	13	3.7	4.1	7	9.1
	14	3.75	4.2	6.9	9.26
	15	3.75	4.1	6.8	9.5
	16	3.8	4.1	6.8	9.72
	17	3.7	4.2	7.1	9.26
	18	3.8	4.3	7	9
	19	3.7	4.1	6.8	8.75
	20	3.8	3.75	6.5	7.95
	21	3.8	3.75	6.25	7.65
	22	3.75	3.65	6	8.3
Jan. 2023	23	3.7	3.9	6.5	9.2
	24	3.55	3.65	7	9.5
	25	3.6	4.1	6.8	9.75
	26	3.65	4.25	6.8	10.21
	27	3.7	3.65	6.5	9.27
	28	3.75	3.75	5.75	8.67
	29	3.8	3.85	5.8	8.45
Aug. 2023	30	3.7	4.25	6.8	8.2
Sep. 2023	31