Scribd
Upload
57 views

Minitab Manual Graphs

This document describes an assignment involving regression analysis of a dataset to determine the best fitting equation for the relationship between variables Y and X. Seven different equation forms are tested and the best fitting one is identified based on having the highest R-squared value above 50%. Plots of the data and regression lines for each equation are presented.

Uploaded by

oblex99
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
57 views

Minitab Manual Graphs

This document describes an assignment involving regression analysis of a dataset to determine the best fitting equation for the relationship between variables Y and X. Seven different equation forms are tested and the best fitting one is identified based on having the highest R-squared value above 50%. Plots of the data and regression lines for each equation are presented.

Uploaded by

oblex99
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 8

APS ASSIGNMENT

MTB > LET C2 = C2/1E6


MTB > LET C3= LOGE(C1)
MTB > LET C4= LOGE(C2)
MTB > LET C5=1/C1
MTB > LET C6 = 1/C2
MTB > LET C7=C1**2
MTB > LET C8=C1**3

1. Y=A +BX
MTB > REGRESS C2 1 C1

Regression Analysis: Y versus X

The regression equation is


Y = 287659 - 7566 X
A= 287659
B=-7566

R-Sq = 5.2%

Analysis of Variance

SSR 1.85382E+11
SSE 3.39854E+12
SST 3.58392E+12

Since the R-sq value is smaller than 50% so the given equation is not suitable
for data.

MTB > LET C9=287659 - 7566*C1

Scatterplot of Y, Y1 vs X
Variable
2000000 Y
Y1

1500000
Y-Data

1000000

500000

0 10 20 30 40 50 60
X
APS ASSIGNMENT

2. Y= A + BX+ CX^2
MTB > REGRESS C2 2 C1 C7

Regression Analysis: Y versus X, X^2


The regression equation is
Y = 401315 - 37559 X + 524 X^2
A 401315
B -37559
C 524.1

R-Sq = 12.0%

Analysis of Variance
SSR 4.30187E+11
SSE 3.15373E+12
SST 3.58392E+12

Since the R-sq value is smaller than 50% so the given equation is not suitable
for data.
MTB > LET C10= 401315 - 37559*C1 + 524*C7

Scatterplot of Y, Y2 vs X
Variable
2000000 Y
Y2

1500000
Y-Data

1000000

500000

0 10 20 30 40 50 60
X
APS ASSIGNMENT

3.Y= A + BX + CX^2 + DX^3


MTB > REGRESS C2 3 C1 C7 C8

Regression Analysis: Y versus X, X^2, X^3

The regression equation is


Y = 545187 - 128618 X + 6259 X^2 - 71.1 X^3

A 545187
B -128618
C 6259
D -71.15

R-Sq = 20.2%

Analysis of Variance
SSR 7.22744E+11
SSE 2.86117E+12
SST 3.58392E+12

Since the R-sq value is smaller than 50% so the given equation is not suitable
for data.

MTB > LET C11=545187 - 128618*C1 + 6259*C7 - 71.1*C8


*C8

Scatterplot of Y3 vs X
600000

500000

400000

300000

200000
Y3

100000

-100000

-200000

-300000
0 10 20 30 40 50 60
X
APS ASSIGNMENT

4. Y=AB^X
LNY= LNA+XLNB

MTB > REGRESS C4 1 C1


Regression Analysis: LNY versus X

The regression equation is


LNY = 8.37 - 0.166 X
LNA 8.366 A 4298.407998
LNB -0.16561 B 0.847377

R-Sq = 43.4%

Analysis of Variance
SSR 88.82
SSE 115.93
SST 204.74

Since the R-sq value is smaller than 50% so the given equation is not suitable
for data.

MTB > LET C12= 4298.407998*0.847377**C1

Scatterplot of Y4 vs X

4000

3000
Y4

2000

1000

0 10 20 30 40 50 60
X
APS ASSIGNMENT

5. Y = AX^B
LNY = LNA + BLNX

MTB > REGRESS C4 1 C3

Regression Analysis: LNY versus LNX

The regression equation is


LNY = 9.10 - 2.33 LNX
LNA 9.1009 A 8963.3561
B -2.3251

R-Sq = 95.5% R-Sq(adj) = 95.0%

Analysis of Variance
SSR 195.48
SSE 9.26
SST 204.74

Since the R-sq value is larger than 50% so the given equation is best fitted for data.
LET C13=8963.3561*C1**(-2.3251)

Scatterplot of Y5 vs X
2000000

1500000

1000000
Y5

500000

0 10 20 30 40 50 60
X
APS ASSIGNMENT

6. Y= AEXP(BX)
LNY = LNA + BX

MTB > REGRESS C4 1 C1

Regression Analysis: LNY versus X

The regression equation is


LNY = 22.2 - 0.166 X
LNA 22.182 A 8.86402
B -0.16561

R-Sq = 43.4% R-Sq(adj) = 37.1%

Analysis of Variance

SSR 88.82
SSE 115.93
SST 204.74

Since the R-sq value is smaller than 50% so the given equation is not suitable
for data.

MTB > LET C14= 8.86402*EXP(-0.16561*C1)

Scatterplot of Y6 vs X
9

5
Y6

0 10 20 30 40 50 60
X
APS ASSIGNMENT

7. Y =X/(A+BX)
1/Y = A/X +B

MTB > REGRESS C6 1 C5

Regression Analysis: 1/Y versus 1/X

The regression equation is


1/Y = 0.0694 - 0.0099 1/X
B 0.06939
A -0.00993

R-Sq = 9.7%

Analysis of Variance
SSR 0.008359
SSE 0.077799
SST 0.086158

Since the R-sq value is smaller than 50% so the given equation is not suitable
for data.

MTB > LET C15= C1/(-0.00993 + 0.06939*C1)

Scatterplot of Y7 vs X

20

10

0
Y7

-10

-20

-30

-40
0 10 20 30 40 50 60
X
APS ASSIGNMENT

Scatterplot of Y, Y1, Y2, Y3, Y4, Y5, Y6, Y7 vs X

MTB > PLOT C2*C1 C9*C1 C10*C1 C11*C1 C12*C1 C13*C1 C14*C1 C15*C1;
SUBC> LINE C1 C9;
SUBC> LINE C1 C10;
SUBC> LINE C1 C11;
SUBC> LINE C1 C12;
SUBC> LINE C1 C13;
SUBC> LINE C1 C14;
SUBC> LINE C1 C15;
SUBC> OVERLAY.

Scatterplot of Y, Y1, Y2, Y3, Y4, Y5, Y6, Y7 vs X


Variable
2000000 Y
Y1
Y2
Y3
1500000 Y4
Y5
Y6
Y7
Y-Data

1000000

500000

0 10 20 30 40 50 60
X

You might also like