Question

Good day. I am struggling with a stats problem, it is NOT my strength. How do you change the slope in a regression analysis to evaluate a change in a particular variable and its impact to the other?

Thanks in advance for you help!

Ela

Yes, this is the question in it's entirety. "As a baseline, construct a time series forecast. Then for each condition, manipulate the variable (s) that would be affected. For example, to address economic growth, you might change the slope value in the regression analysis. You might run a correlation between price and demand or temperature and demand to see whether the relationship is statistically significant. If so, you might consider a catastrophic event such as a drastic change in weather patterns."

I've constructed the baseline, deseasonalized it, and the conditions in the data are average temp, price per unit, demand, and quarterly sales for 10 years. I've extended my forecast for sales an additional three years.

			Yt					Baseline	Yt/CMA		Yt/St
t	Yr	Q	Quarterly Sales	Demand (000)	Price/Unit	Avg Temp	MA(4)	CMA(4)	St, It	St	deseasonalize	Tt	Forecast
1	1	1	12645.60	26.4	479.00	47.3				1.035	12217.97	11871.304	12286.8
2		2	10298.50	21.5	479.00	69.1				0.972	10595.16	11956.999	11622.2
3		3	9723.70	20.3	479.00	85.4	11400.20	11388.23	0.85	0.943	10311.45	12042.694	11356.26
4		4	12933.00	27.0	479.00	51.3	11376.25	11519.26	1.12	1.044	12387.93	12128.388	12662.04
5	2	1	12549.80	26.2	479.00	47.9	11662.28	11761.00	1.07	1.035	12125.41	12214.083	12641.58
6		2	11442.60	23.4	489.00	69.3	11859.73	11972.94	0.96	0.972	11772.22	12299.778	11955.38
7		3	10513.50	21.5	489.00	85.6	12086.15	12320.61	0.85	0.943	11148.99	12385.473	11679.5
8		4	13838.70	28.3	489.00	50.1	12555.08	12758.98	1.08	1.044	13255.46	12471.167	13019.9
9	3	1	14425.50	29.5	489.00	46.9	12962.88	13295.39	1.09	1.035	13937.68	12556.862	12996.35
10		2	13073.80	26.2	499.00	69.9	13627.90	13775.55	0.95	0.972	13450.41	12642.557	12288.57
11		3	13173.60	26.4	499.00	88.0	13923.20	14003.74	0.94	0.943	13969.88	12728.252	12002.74
12		4	15019.90	30.1	499.00	51.4	14084.28	14235.43	1.06	1.044	14386.88	12813.946	13377.76
13	4	1	15069.80	30.2	499.00	47.2	14386.58	14465.74	1.04	1.035	14560.19	12899.641	13351.13
14		2	14283.00	27.0	529.00	69.1	14544.90	14671.00	0.97	0.972	14694.44	12985.336	12621.75
15		3	13806.90	26.1	529.00	85.4	14797.10	14864.06	0.93	0.943	14641.46	13071.031	12325.98
16		4	16028.70	30.3	529.00	51.3	14931.03	14916.74	1.07	1.044	15353.16	13156.725	13735.62
17	5	1	15605.50	29.5	529.00	47.5	14902.45	14928.21	1.05	1.035	15077.78	13242.420	13705.9
18		2	14168.70	27.3	519.00	69.1	14953.98	14894.46	0.95	0.972	14576.85	13328.115	12954.93
19		3	14013.00	27.0	519.00	85.4	14834.95	14629.96	0.96	0.943	14860.02	13413.809	12649.22
20		4	15552.60	29.4	529.00	51.3	14424.98	14101.88	1.10	1.044	14897.13	13499.504	14093.48
21	6	1	13965.60	26.4	529.00	48.0	13778.78	13420.24	1.04	1.035	13493.33	13585.199	14060.68
22		2	11583.90	21.1	549.00	69.1	13061.70	12833.25	0.90	0.972	11917.59	13670.894	13288.11
23		3	11144.70	20.3	549.00	85.4	12604.80	12530.00	0.89	0.943	11818.35	13756.588	12972.46
24		4	13725.00	25.0	549.00	52.0	12455.20	12408.61	1.11	1.044	13146.55	13842.283	14451.34
25	7	1	13367.20	24.8	539.00	47.3	12362.03	12245.15	1.09	1.035	12915.17	13927.978	14415.46
26		2	11211.20	20.8	539.00	69.1	12128.28	11801.28	0.95	0.972	11534.16	14013.673	13621.29
27		3	10209.70	19.3	529.00	85.4	11474.28	11165.55	0.91	0.943	10826.83	14099.367	13295.7
28		4	11109.00	21.0	529.00	51.7	10856.83	10810.99	1.03	1.044	10640.8	14185.062	14809.2
29	8	1	10897.40	20.6	529.00	47.3	10765.15	11201.64	0.97	1.035	10528.89	14270.757	14770.23
30		2	10844.50	20.5	529.00	69.1	11638.13	11644.31	0.93	0.972	11156.89	14356.452	13954.47
31		3	13701.60	26.4	519.00	85.4	11650.50	11630.66	1.18	0.943	14529.8	14442.146	13618.94
32		4	11158.50	21.5	519.00	51.6	11610.83	12040.64	0.93	1.044	10688.22	14527.841	15167.07
33	9	1	10738.70	20.3	529.00	47.3	12470.45	12490.23	0.86	1.035	10375.56	14613.536	15125.01
34		2	14283.00	27.0	529.00	69.1	12510.00	12893.89	1.11	0.972	14694.44	14699.231	14287.65
35		3	13859.80	26.2	529.00	85.4	13277.78	14313.78	0.97	0.943	14697.56	14784.925	13942.18
36		4	14229.60	26.4	539.00	52.4	15349.78	15929.26	0.89	1.044	13629.89	14870.620	15524.93
37	10	1	19026.70	35.3	539.00	47.9	16508.75	17120.93	1.11	1.035	18383.29	14956.315	15479.79
38		2	18918.90	35.1	539.00	68.1	17733.10	18452.35	1.03	0.972	19463.89	15042.010	14620.83
39		3	18757.20	34.8	539.00	87.2	19171.60			0.943	19890.99	15127.704	14265.43
40		4	19983.60	36.4	549.00	52.5				1.044	19141.38	15213.399	15882.79
41	11	1								1.035		15299.094	15834.56
42		2								0.972		15384.789	14954.01
43		3								0.943		15470.483	14588.67
44		4								1.044		15556.178	16240.65
45	12	1								1.035		15641.873	16189.34
46		2								0.972		15727.567	15287.2
47		3								0.943		15813.262	14911.91
48		4								1.044		15898.957	16598.51
49	13	1								1.035		15984.652	16544.11
50		2								0.972		16070.346	15620.38
51		3								0.943		16156.041	15235.15
52		4								1.044		16241.736	16956.37

Answer 1

Time series is the series of data belonging to a variable with respect to time

It is useful for under standing the behavior of the data with respect to time

Trend line is useful for predicting the value of a dependent variable at a particular time period

to construct the trend line we have to calculate the slope and intercept of the line

slope is also called incremental value in the dependent variable and regression coefficient in case of regression line

slope is the ratio of successive difference in the trend values to the successive difference in the time period