1 5 3 Perform a thorough analysis of the Ski Sales data in Table 5 11 using the ideas presented in Section 5 6 Table 5 11 Disposable Income and Ski Sales for Years 1964 1973 Row Date Sales PDI Row Date Sales PDI Q1 64 37 0 109 21 Q1 69 44 9 153 Q2 64 33 5 115 22 Q2 69 41 6 156 3 Q3 64 30 8 113 23 Q3 69 44 0 160 4 Q4 64 37 9 116 24 Q4 69 48 1 163 Q1 65 37 4 118 25 Q1 70 49 7 166 Q2 65 31 6 120 26 Q2 70 43 9 171 Q3 65 34 0 122 27 Q3 70 41 6 174 8 Q4 65 38 1 124 28 Q4 70 51 0 175 9 Q1 66 40 0 126 29 Q1 71 52 0 180 10 Q2 66 35 0 128 30 Q2 71 46 2 184 11 Q3 66 34 9 130 31 Q3 71 47 1 187 12 Q4 66 40 2 132 32 Q4 71 52 7 13 189 Q1 67 41 9 133 33 Q1 72 52 2 191 14 Q2 67 34 7 135 34 Q2 72 47 0 15 193 Q3 67 38 8 138 35 Q3 72 47 8 194 16 Q4 67 43 7 140 36 Q4 72 52 8 196 17 Q1 68 44 2 143 37 Q1 73 54 1 18 199 Q2 68 40 4 147 38 Q2 73 49 5 201 19 Q3 68 38 4 148 39 Q3 73 49 5 202 20 Q4 68 45 4 151 40 Q4 73 54 3 2045 6 SEASONALITY The data set we use as an example here, referred to as the Ski Sales data, is shown in Table 5 11 and can be obtained from the book's Website The data consist of two variables the sales, S, in millions for a firm that manufactures skis and relatedequipment for the years 1964 1973, and personal disposable income, PDI Each of these variables is measured quarterly We use these data in Chapter 8 to illustrate the problem of correlated errors The model is an equation that relates S to PDI, that is, St Po 1PDIt Et, where St is sales in millions in the tth period and PDI, is the corresponding personal disposable income Our approach here is to assume the existence of a seasonal effect on sales that is determined on a quarterly basis To measure this effect we may define indicator variables to characterize the seasonality Since we have four quarters, we define three indicator variables, Z1, Z2, and Za, where 1, if the tth period is a first quarter, 0, otherwise, 1, if the tth period is a second quarter, 0, otherwise, 1, if the tth period is a third quarter, Z 3 0, otherwise Aggregate measure of purchasing potential The analysis and interpretation of this data set are left to the reader The authors have analyzed these data and found that there are actually only two seasons (See the discussion of these sales data in Chapter 8 for an analysis using only one indicator variable, two seasons ) See Kmenta (1986) for further discussion on using indicator variables for analyzing seasonality

Question

1  5 3 Perform a thorough analysis of the Ski Sales data in Table 5 11 using the ideas presented in Section 5 6 Table 5 11 Disposable Income and Ski Sales for Years 1964 1973 Row Date Sales PDI Row Date Sales PDI Q1 64 37 0 109 21 Q1 69 44 9 153 Q2 64 33 5 115 22 Q2 69 41 6 156 3 Q3 64 30 8 113 23 Q3 69 44 0 160 4 Q4 64 37 9 116 24 Q4 69 48 1 163 Q1 65 37 4 118 25 Q1 70 49 7 166 Q2 65 31 6 120 26 Q2 70 43 9 171 Q3 65 34 0 122 27 Q3 70 41 6 174 8 Q4 65 38 1 124 28 Q4 70 51 0 175 9 Q1 66 40 0 126 29 Q1 71 52 0 180 10 Q2 66 35 0 128 30 Q2 71 46 2 184 11 Q3 66 34 9 130 31 Q3 71 47 1 187 12 Q4 66 40 2 132 32 Q4 71 52 7 13 189 Q1 67 41 9 133 33 Q1 72 52 2 191 14 Q2 67 34 7 135 34 Q2 72 47 0 15 193 Q3 67 38 8 138 35 Q3 72 47 8 194 16 Q4 67 43 7 140 36 Q4 72 52 8 196 17 Q1 68 44 2 143 37 Q1 73 54 1 18 199 Q2 68 40 4 147 38 Q2 73 49 5 201 19 Q3 68 38 4 148 39 Q3 73 49 5 202 20 Q4 68 45 4 151 40 Q4 73 54 3 2045 6 SEASONALITY The data set we use as an example here, referred to as the Ski Sales data, is shown in Table 5 11 and can be obtained from the book's Website  The data consist of two variables  the sales, S, in millions for a firm that manufactures skis and relatedequipment for the years 1964 1973, and personal disposable income, PDI  Each of these variables is measured quarterly  We use these data in Chapter 8 to illustrate the problem of correlated errors  The model is an equation that relates S to PDI, that is, St   Po   1PDIt   Et, where St is sales in millions in the tth period and PDI, is the corresponding personal disposable income  Our approach here is to assume the existence of a seasonal effect on sales that is determined on a quarterly basis  To measure this effect we may define indicator variables to characterize the seasonality  Since we have four quarters, we define three indicator variables, Z1, Z2, and Za, where 1, if the tth period is a first quarter, 0, otherwise, 1, if the tth period is a second quarter, 0, otherwise, 1, if the tth period is a third quarter, Z 3   0, otherwise  Aggregate measure of purchasing potential The analysis and interpretation of this data set are left to the reader  The authors have analyzed these data and found that there are actually only two seasons  (See the discussion of these sales data in Chapter 8 for an analysis using only one indicator variable, two seasons ) See Kmenta (1986) for further discussion on using indicator variables for analyzing seasonality

Accepted Answer

The Answer is in the image, click to view ...

Question

1. 5.3 Perform a thorough analysis of the Ski Sales data in Table 5.11 using the ideas presented in Section 5.6.Table 5.11 Disposable Income and

Step by Step Solution

Step: 1

Get Instant Access to Expert-Tailored Solutions

Step: 2

Step: 3

Ace Your Homework with AI

Recommended Textbook for

Geometry, Structure And Randomness In Combinatorics

Students also viewed these Mathematics questions

Question

Question

Question

Question

Question

Question

Question

Question

Question

Question

Question

Question

Question

Question

Question