Question

We have a lot of data and information. If you want to forecast something, find data for it from the library. Let us call this data Dependent variable . Also find data for variables,( let us call them Independent Variables) that influence dependent variables.

Your task is to find data for one dependent variable and more than one independent variables. The independent variables must be related to the dependent variable.

Using your data,  run the regression on Excel and comment on how good and robust is the relationship between the dependent variable and the independent variables.

Important: You must indicate the source of data.(failure to indicate this gets automatic zero).  Data should be original. No data from the text books or data that has been already used for regression may be used.

Answer 1

For the purpose ofthis problem, i am taking a dataset of GPA scores (dependent variables) with Gender, GMAT score and work experience (independent variables)

The dataset is as follows.

GPA	Gender	Work	GMAT
4.15	0	0	680
3.76	1	4	630
3.02	0	8	650
2.9	0	3	590
2.96	0	9	660
4.22	0	1	610
3.17	0	1	590
3.73	1	5	700
3.21	0	4	680
3.43	1	4	610
3.28	1	7	700
2.79	0	7	630
3.02	0	5	590
2.96	0	7	580
3.24	1	3	690
3.33	1	2	620
2.95	1	5	530
3.39	0	1	620
3.44	0	5	700
3.3	0	6	690
2.87	0	4	600
3.62	0	1	620
2.89	1	7	650
3.18	0	2	680
3.06	0	8	570
3.05	1	5	690
2.99	1	9	580
3.23	1	5	570
3.22	0	9	620
2.2	0	8	610
2.91	0	7	730
2.63	1	2	600
2.28	0	4	590
3.01	0	6	580
2.56	0	4	670
3.31	0	5	730
3.39	0	0	590
2.54	0	7	590
3.06	0	4	580
3.64	0	5	640
2.93	0	7	600
4.18	1	2	690
3.64	0	4	670
3.62	0	5	660
3.33	1	3	620
3.5	0	9	650
4.21	0	3	660
3.67	0	7	650
4.11	1	4	580
3.69	1	1	690
2.54	0	6	610
2.76	0	9	600
3.23	0	1	640
2.43	1	8	570
3.43	0	5	560
4.41	1	6	550
4.27	0	9	650
3.21	0	5	620
2.83	0	5	630
3.59	0	4	580
2.34	0	4	650
3.8	1	5	600
4.08	1	1	620
3.92	0	2	620
2.9	0	2	600
3.18	0	7	640
3.81	0	0	680
2.92	0	7	640
3	1	4	680
2.7	0	5	670
2.44	0	9	560
3.67	0	5	560
2.98	0	4	690
3.58	1	2	610
2.97	0	5	540
3.06	0	0	650
3.45	1	9	730
4.22	1	4	690
2.53	0	6	660
3.24	0	8	560
3.01	0	1	640
3.1	0	7	650
3.74	0	6	640
3.63	0	7	580
3.7	0	5	570
3.4	0	6	660
2.54	0	7	600
3.39	1	7	620
3.71	0	6	610
2.99	1	4	570
3.95	1	1	670
3.14	0	7	590
4.12	1	4	560
3.63	0	9	670
3.33	0	4	660
3.01	0	9	630
3.2	0	6	630
2.86	0	8	500
3.28	0	2	590
3.34	0	5	640
3.34	0	5	620
3.23	0	1	590
3.4	0	4	720
3.16	0	5	720
2.57	0	3	510
3.88	0	2	620
3.94	1	0	660
3.3	0	6	660
3.69	0	4	670
2.55	0	9	600
3.83	0	7	550
3.15	0	7	580
4.64	1	4	720
3.16	0	4	640
3.96	1	5	610
2.37	0	5	580
3.08	0	7	670
3.81	0	4	550
3.27	0	4	600
3.47	0	1	680
2.73	0	8	540
2.79	0	6	670
3.56	1	6	660
2.62	0	7	600
3.58	0	2	620
3.48	0	1	630
3.62	0	7	670
3.3	0	4	650
3.38	0	3	670
3.08	0	4	760
3.28	0	6	610
2.99	0	6	660
3.72	1	2	690
2.94	0	1	650
3.09	0	7	670
3.44	1	9	590
3.27	0	5	630
2.34	0	4	560
3.41	1	5	620
3.38	0	3	630
4.03	0	7	680
3.5	0	5	620
3.38	0	9	730
2.94	0	5	600
2.93	0	7	550
3.39	1	1	540
3.44	0	5	650
3.31	0	6	640
2.88	1	2	610
2.79	1	7	650

The source of the data is Cornell university website related to resources and study materials.

Now, based on the dataset we shall do the regression analysis and try to find out the strength of relation between various independent variables and the dependenet variables.

The result obtained from the regression analysis is as follows

Clearly from the regression analysis we can see that:-

1. The F statistic is statistically significant (<0.05) . Hence the regression equation is significant

2. All the independent variables are significently related to the dependent variable since p value of all the independent variables are less than 0.05.

3. The constant is also significent (p<0.05)

The regression equation is given by

y( GPA)=2.282+0.256*(Gender)-0.0478(work)+0.002*(GMAT)