Scribd
Upload
41 views12 pages

ISE 500 Fall 2018 Assignment 6: Submitted By: Ananth Ramesh

The document contains regression analysis results from two datasets. The first dataset shows a moderate correlation between variables X and Y, with X explaining 36.27% of the variation in Y. The second dataset shows a weaker correlation, with X explaining only 20% of the variation in Y. A third dataset shows a very strong correlation between X and Y, with X explaining 97.07% of the variation in Y. The correlation coefficient of 0.985 indicates that as X increases, Y also tends to increase.

Uploaded by

Ananth Ramesh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as XLSX, PDF, TXT or read online on Scribd
41 views12 pages

ISE 500 Fall 2018 Assignment 6: Submitted By: Ananth Ramesh

The document contains regression analysis results from two datasets. The first dataset shows a moderate correlation between variables X and Y, with X explaining 36.27% of the variation in Y. The second dataset shows a weaker correlation, with X explaining only 20% of the variation in Y. A third dataset shows a very strong correlation between X and Y, with X explaining 97.07% of the variation in Y. The correlation coefficient of 0.985 indicates that as X increases, Y also tends to increase.

Uploaded by

Ananth Ramesh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as XLSX, PDF, TXT or read online on Scribd
You are on page 1/ 12

ISE 500 Fall 2018 Assignment 6

Submitted by: Ananth Ramesh

Due: 10/01/2018

X Y SUMMARY OUTPUT
6.8 32.46
12.6 32.59 Regression Statistics
19.6 36.94 Multiple R 0.602285
26.8 38.22 R Square 0.362747
31.8 38.5 Adjusted R Square 0.327344
35.2 35.06 Standard Error 5.301615
37.6 33.59 Observations 20
44.6 43.06
47 41.72 ANOVA
50.6 38.08 df SS MS F Significance F
54.6 47.54 Regression 1 287.9923 287.9923 10.24624 0.004952
61.8 35.41 Residual 18 505.9281 28.10712
66.4 34.47 Total 19 793.9204
72.6 39.53
78.8 49.39 Coefficients
Standard Error t Stat P-value Lower 95%
83.6 44.7 Intercept 32.44823 2.654275 12.22489 3.74E-10 26.8718
87.6 45.36 X 0.138289 0.043202 3.200975 0.004952 0.047525
91 38.77
93.8 37.44 From the regression tool, we can calculate the slope, the y intercept and the percentage of y va
96.6 58.17 (Marked in Red)

36.27% of the dependent y values are directly related to any increase or decrease in the indepe
70

60

50

40 f(x) = 0.1382894814x + 32.4482272099


R² = 0.3627470338
Y
30

20

10

Significance F 0
0 20 40 60 80 100 120

Upper 95%
Lower 95.0%
Upper 95.0%
38.02465 26.8718 38.02465
0.229054 0.047525 0.229054

cept and the percentage of y values (r square) that are dependent on x values.

crease or decrease in the independent x values.


Source: "National Diabetes Statistics Report" - https://www.cdc.gov/diabetes/data/statistics/statistics-report.html

X (ages) Y (diabetes level)


53 112 140
38 95
120
27 131 f(x) = 0.7779443553x + 72.671013179
24 71 100 R² = 0.2005762797
28 83
80
35 129
Y
39 88 60
23 79
40
52 122
36 126 20
51 99
0
31 91 15 20 25 30 35 40 45 50 5
60 133 X
28 99
25 90
28 96
38 89 SUMMARY OUTPUT
21 110 Only 20% of the y values ar
20 73 Regression Statistics
41 72 Multiple R 0.447857432
30 100 R Square 0.20057628
32 102 Adjusted R Square 0.160605094
Standard Error 17.73334399
Observations 22

ANOVA
df SS MS
Regression 1 1578.025 1578.025
Residual 20 6289.43 314.4715
Total 21 7867.455

CoefficientsStandard Error t Stat


Intercept 72.67101318 12.57865 5.777329
X (ages) 0.777944355 0.347282 2.240094
stics/statistics-report.html

71013179

40 45 50 55 60 65

Only 20% of the y values are dependent on the x values which means that only 20% of the people fall into the pattern of diabetes occurin

F Significance F
5.018022 0.036601

P-value Lower 95%Upper 95%


Lower 95.0%
Upper 95.0%
1.18E-05 46.4324 98.90962 46.4324 98.90962
0.036601 0.053527 1.502362 0.053527 1.502362
o the pattern of diabetes occuring as expected determined by their age. Since this is a basic data set, it does not consider other factors such
s not consider other factors such as general health and lifestyle, hence this cannot be a conclusive evidence of a person being diabetic dep
e of a person being diabetic depending on his age.
x y
47 38
62 62 Regression
65 53 250
70 67
200 f(x) = 1.0013683317x - 0.9624893863
70 84 R² = 0.9706903319
78 79
150
95 93
Y
100 106 100
114 117
118 116 50

124 127
0
127 114 0 50 100 150 200
140 134 X
140 139
140 142
150 170
152 149 Correlation Coefficient 0.985236
164 154
198 200 The correlation coefficient indicates that if the value of the independent variable increases, th
221 215
Hence 0.985236 dependent values increase with an increase in independent (x) values.

SUMMARY OUTPUT

Regression Statistics
Multiple R 0.9852361808
R Square 0.9706903319 97.07% of the data plots show a re
Adjusted R Square 0.969062017
Standard Error 8.2969986991
Observations 20

ANOVA
df SS MS F
Regression 1 41037.82662657 41037.83 596.1318
Residual 18 1239.123373426 68.84019
Total 19 42276.95

Coefficients Standard Error t Stat P-value


Intercept -0.962489386 5.2117077188 -0.18468 0.855546
x 1.0013683317 0.0410131096 24.41581 3E-15
200 250

nt variable increases, then the value of the dependent variable also increases.

endent (x) values.

f the data plots show a relation between each other. Hence, it can be concluded that they appear to be measuring roughly the same quanti
Significance F
3E-15

Lower 95%Upper 95%


Lower 95.0%
Upper 95.0%
-11.9119 9.986902 -11.9119 9.986902
0.915203 1.087534 0.915203 1.087534
easuring roughly the same quantity

You might also like