# barcode font reporting services Curve Fitting, Regression, and Correlation in Software Generate Quick Response Code in Software Curve Fitting, Regression, and Correlation

CHAPTER 8 Curve Fitting, Regression, and Correlation
Recognize QR Code In None
Using Barcode Control SDK for Software Control to generate, create, read, scan barcode image in Software applications.
Make QR In None
Using Barcode drawer for Software Control to generate, create Denso QR Bar Code image in Software applications.
(a) Plot the points (1, 1), (3, 2), (4, 4), (6, 4), (8, 5), (9, 7), (11, 8), and (14, 9) on a rectangular coordinate system as shown in Fig. 8-6. A straight line approximating the data is drawn freehand in the figure. For a method eliminating the need for individual judgment, see Problem 8.4, which uses the method of least squares. (b) To obtain the equation of the line constructed in (a), choose any two points on the line, such as P and Q. The coordinates of these points as read from the graph are approximately (0, 1) and (12, 7.5). Then from Problem 8.1, y or y 1 0.542x or y 1 0.542x. 1 7.5 12 1 (x 0 0)
Recognizing QR Code ISO/IEC18004 In None
Using Barcode decoder for Software Control to read, scan read, scan image in Software applications.
Paint QR Code ISO/IEC18004 In Visual C#.NET
Using Barcode encoder for .NET Control to generate, create QR image in Visual Studio .NET applications.
8.3. Derive the normal equations (4), page 267, for the least-squares line.
QR Code JIS X 0510 Printer In .NET
Using Barcode printer for ASP.NET Control to generate, create QR image in ASP.NET applications.
Printing QR Code In Visual Studio .NET
Using Barcode printer for Visual Studio .NET Control to generate, create QR Code image in VS .NET applications.
Refer to Fig. 8-7. The values of y on the least-squares line corresponding to x1, x2, . . . , xn are a bx1, a bx2, c, a bxn
Quick Response Code Creation In Visual Basic .NET
Using Barcode encoder for VS .NET Control to generate, create QR Code image in .NET applications.
GS1 - 13 Generator In None
Using Barcode drawer for Software Control to generate, create EAN / UCC - 13 image in Software applications.
Fig. 8-7
Data Matrix ECC200 Printer In None
Using Barcode creation for Software Control to generate, create Data Matrix image in Software applications.
Making UCC-128 In None
Using Barcode printer for Software Control to generate, create GTIN - 128 image in Software applications.
The corresponding vertical deviations are d1 a bx1 c y1, d2 a bx2 y2, c, dn c a bxn yn
Encoding UPC-A In None
Using Barcode generation for Software Control to generate, create UPC Symbol image in Software applications.
Code 3/9 Creator In None
Using Barcode printer for Software Control to generate, create Code 3 of 9 image in Software applications.
Then the sum of the squares of the deviations is d2 1 or d2 2 d2 n (a bx1 ad
USS ITF 2/5 Maker In None
Using Barcode creation for Software Control to generate, create USS ITF 2/5 image in Software applications.
Barcode Decoder In Java
Using Barcode scanner for Java Control to read, scan read, scan image in Java applications.
y1)2 a (a
Generating UPC Symbol In Objective-C
Using Barcode generation for iPad Control to generate, create UPC Symbol image in iPad applications.
Printing Code 128 In .NET Framework
Using Barcode drawer for Reporting Service Control to generate, create ANSI/AIM Code 128 image in Reporting Service applications.
bx2 bx
Barcode Generator In None
Using Barcode creator for Office Excel Control to generate, create bar code image in Excel applications.
Generate Barcode In None
Using Barcode encoder for Online Control to generate, create bar code image in Online applications.
y2)2 y)2
UCC-128 Drawer In C#
Using Barcode generation for .NET Control to generate, create UCC-128 image in Visual Studio .NET applications.
Drawing Barcode In .NET
Using Barcode printer for ASP.NET Control to generate, create bar code image in ASP.NET applications.
yn)2
This is a function of a and b, i.e., F(a, b) g(a bx (or a maximum) is that 'F>'a 0, 'F>'b 0. Since 'F 'a 'F 'b we obtain a (a i.e., ay bx an y) b ax 0 ' a 'a (a ' a 'b (a bx bx y)2 y)2
y)2. A necessary condition for this to be a minimum
a 2(a a 2x(a
bx bx
y) y)
a x(a a xy
bx a ax
b a x2
as required. It can be shown that these actually yield a minimum.
8.4. Fit a least-squares line to the data of Problem 8.2 using (a) x as independent variable, (b) x as dependent variable.
(a) The equation of the line is y a bx. The normal equations are ay a xy an a ax b ax b a x2
CHAPTER 8 Curve Fitting, Regression, and Correlation
The work involved in computing the sums can be arranged as in Table 8-2. Although the last column is not needed for this part of the problem, it has been added to the table for use in part (b). Since there are 8 pairs of values of x and y, n 8 and the normal equations become 8a 56a 56b 524b 40 364
7 11 x
6 7 6 Solving simultaneously, a 11 or 0.545, b 11 or 0.636; and the required least-squares line is y 11 y 0.545 0.636x. Note that this is not the line obtained in Problem 8.2 using the freehand method.
Table 8-2 x 1 3 4 6 8 9 11 14 gx 56 gy y 1 2 4 4 5 7 8 9 40 x2 1 9 16 36 64 81 121 196 g x2 524 g xy xy 1 6 16 24 40 63 88 126 364 gy2 y2 1 4 16 16 25 49 64 81 256
Another method
Q a yR Q a x2 R a na n a xy b na x2 Q a xR x2 Q a xR Q a xR Q a xyR
(40)(524) (56)(364) (8)(524) (56)2
6 11
or 0.545
Q a xR Q a yR
(8)(364) (56)(40) (8)(524) (56)2
7 11
or 0.636
(b) If x is considered as the dependent variable and y as the independent variable, the equation of the leastsquares line is x c dy and the normal equations are ax a xy cn c ay d ay d a y2
Then using Table 8-2, the normal equations become 8c 40c
1 from which c 0.50, d 3 or 1.50. 2 or 2 These values can also be obtained from
40d 256d
56 364
Q a xR Q a y2 R c n a y2 n a xy d n a y2
Q a yR Q a xyR Q a yR
(56)(256) (40)(364) (8)(256) (40)2
Q a xR Q a yR Q a yR
(8)(364) (56)(40) (8)(256) (40)2
CHAPTER 8 Curve Fitting, Regression, and Correlation
Therefore, the required equation of the least-squares line is x Note that by solving this equation for y, we obtain y 0.333 obtained in part (a). 0.50 1.50y. 0.667x, which is not the same as the line
8.5. Graph the two lines obtained in Problem 8.4.
0.500 1.50y, are shown in Fig. 8-8. Note that the The graphs of the two lines, y 0.545 0.636x and x two lines in this case are practically coincident, which is an indication that the data are very well described by a linear relationship. The line obtained in part (a) is often called the regression line of y on x and is used for estimating y for given values of x. The line obtained in part (b) is called the regression line of x on y and is used for estimating x for given values of y.
Fig. 8-8
8.6. (a) Show that the two least-squares lines obtained in Problem 8.4 intersect at point (x, y). (b) Estimate the # # value of y when x 12. (c) Estimate the value of x when y 3. x # ax n 56 8 7, y # ay n 40 8 5
Then point (x, y), called the centroid, is (7, 5). # # (a) Point (7, 5) lies on line y Point (7, 5) lies on line x 0.545
1 2 3 2 y,
0.636x or, more exactly, y 1 3 since 7 2 2 (5).
6 11
7 11 x,
Copyright © OnBarcode.com . All rights reserved.