Question

Basic Least-Squares Regression 0 solutions submitted (max: Unlimited) Sample data is contained in the "SampleData.xlsx" spreadsheet on Canvas. 1) Load in the data using readmatrix(). 2) Use fit() and any necessary postprocessing commands to fit a 1st order polynomial in the form of: y = a?x + a? to the data. 3) Compute R² (there are many hard ways and one easy way). 4) Use the regression line to predict y ($y_{eval}$) given a random x-value ($x_{eval}$). 5) Generate a well-labeled plot of the data (including ($x_{eval}$, $y_{eval}$)) and the best-fit line in your function. Do not use polyfit() or polyval()! NOTE: You need to have the Curve Fitting Toolbox installed on your local MATLAB. If you don't know if you have it or no Function 1 function [a1,a2,R2,y_fit] = linearRegression(x_eval) % Input: 2 % x_eval: value of x for which to evaluate curve for y (scalar). % Outputs: 5 6 a1: slope of best straight line through data [ND] (scalar) 7 a2: y-intercept of best straight line through data [ND] (scalar) 8 R2: Coefficient of determination [ND] (scalar) 9 y_fit: Fitted value of y for x_eval value [ND] (scalar) 10 % Write your code below: 12 13 14 15 16 17 18 19 20 end 21

          Basic Least-Squares Regression
0 solutions submitted (max: Unlimited)
Sample data is contained in the "SampleData.xlsx" spreadsheet on Canvas.
1) Load in the data using readmatrix().
2) Use fit() and any necessary postprocessing commands to fit a 1st order polynomial in the form of:
y = a?x + a?
to the data.
3) Compute R² (there are many hard ways and one easy way).
4) Use the regression line to predict y ($y_{eval}$) given a random x-value ($x_{eval}$).
5) Generate a well-labeled plot of the data (including ($x_{eval}$, $y_{eval}$)) and the best-fit line in your function.
Do not use polyfit() or polyval()!
NOTE: You need to have the Curve Fitting Toolbox installed on your local MATLAB. If you don't know if you have it or no
Function
1 function [a1,a2,R2,y_fit] = linearRegression(x_eval)
% Input:
2
% x_eval: value of x for which to evaluate curve for y (scalar).
% Outputs:
5
6 a1: slope of best straight line through data [ND] (scalar)
7 a2: y-intercept of best straight line through data [ND] (scalar)
8 R2: Coefficient of determination [ND] (scalar)
9 y_fit: Fitted value of y for x_eval value [ND] (scalar)
10
% Write your code below:
12
13
14
15
16
17
18
19
20 end
21

Basic Least-Squares Regression
0 solutions submitted (max: Unlimited)
Sample data is contained in the "SampleData.xlsx" spreadsheet on Canvas.
1) Load in the data using readmatrix().
2) Use fit() and any necessary postprocessing commands to fit a 1st order polynomial in the form of:
y = a?x + a?
to the data.
3) Compute R² (there are many hard ways and one easy way).
4) Use the regression line to predict y (yeval) given a random x-value (xeval).
5) Generate a well-labeled plot of the data (including (xeval, yeval)) and the best-fit line in your function.
Do not use polyfit() or polyval()!
NOTE: You need to have the Curve Fitting Toolbox installed on your local MATLAB. If you don't know if you have it or no
Function
1 function [a1,a2,R2,yfit] = linearRegression(xeval)
% Input:
2
% xeval: value of x for which to evaluate curve for y (scalar).
% Outputs:
5
6 a1: slope of best straight line through data [ND] (scalar)
7 a2: y-intercept of best straight line through data [ND] (scalar)
8 R2: Coefficient of determination [ND] (scalar)
9 yfit: Fitted value of y for xeval value [ND] (scalar)
10
% Write your code below:
12
13
14
15
16
17
18
19
20 end
21

Added by Ivan B.

Question

Please give Ace some feedback