Advertisement
Guest User

Untitled

a guest
Jan 16th, 2019
78
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 2.16 KB | None | 0 0
  1. %Kamil Sosna
  2. %Task 1
  3. d = matfile('d14.mat');
  4. x_vect = d(:,1);
  5. y_vect = d(:,2);
  6.  
  7. mean_x = mean(x_vect);
  8. mean_y = mean(y_vect);
  9. r_value = 0;
  10. std_x = std(x_vect);
  11. std_y = std(y_vect);
  12.  
  13. for i = 1:15
  14. r_value = r_value + (x_vect(i)-mean_x)*(y_vect(i)-mean_y);
  15. end
  16.  
  17. r_value = r_value/(std_x*std_y*(14));
  18. disp(r_value)
  19. %concludions : stample is corelated with nither strong nor weak
  20. %correlation for growing trend
  21. X = ((length(x_vect)-2)/1-r_value*r_value);
  22. value = r_value*(sqrt(X));
  23. disp(value)
  24. tinv(0.025, length(x_vect)-1)
  25. b_1 = ((r_value*std_y)/std_x) ;
  26. b0 = mean_y- mean_x*b_1;
  27. disp(b_1); % a coeff
  28. disp(b0); % intercept
  29. value_of_regression_model = b_1* 58 + b0;
  30. disp(value_of_regression_model) %value for x=48
  31. residuals = zeros(length(x_vect),1);
  32. for i = 1:length(x_vect)
  33. residuals(i) = y_vect(i) - (b0+(b_1*x_vect(i)));
  34. end
  35.  
  36. %y_val = zeros(500);
  37. %x_val2 = zeros(500);
  38. iterator2 = 1;
  39. x_val=[40:0.1:90];
  40. %for x_val = 40:0.1:90
  41. % x_val2(iterator2) = x_val;
  42. % y_val(iterator2) = b_1*x_val2(iterator2) + b0;
  43. %iterator2 = iterator2 + 1;
  44. %end
  45. y_val = b_1*x_val+b0;
  46. scatter(x_vect,y_vect)
  47. hold on
  48. scatter(x_val,y_val)
  49. %plotmatrix(x_vect,residuals)
  50. %////////////////////////////////////////////////////////////////
  51. %Task 2
  52. X=d7(:,1);
  53. Y=d7(:,2);
  54. plotmatrix(X,Y);
  55. %Yes, we can see there will be linear relation between points.
  56. %using power_transform
  57. YY = power_transform(Y,0);
  58. Y12 = power_transform(Y, 1/2);
  59. YYY = power_transform(Y,1);
  60. Y2 = power_transform(Y,2);
  61. Y3=power_transform(Y,3);
  62. Y5= power_transform(Y,5);
  63. Y10=power_transform(Y,10);
  64. %diplaying figures
  65. plotmatrix(X,Y);
  66. figure;
  67. plotmatrix(X,YY);
  68. figure;
  69. plotmatrix(X,Y12);
  70. figure;
  71. plotmatrix(X,YYY);
  72. figure;
  73. plotmatrix(X,Y2);
  74. figure;
  75. plotmatrix(X,Y5);
  76. figure;
  77. plotmatrix(X,Y10);
  78. figure;
  79. plotmatrix(X,Y3);
  80.  
  81. %Calculating correlation coefficient
  82. R=corrcoef(X,Y);
  83. R0=corrcoef(X,YY);
  84. R12=corrcoef(X,Y12);
  85. R1=corrcoef(X,YYY);
  86. R2=corrcoef(X,Y2);
  87. R3=corrcoef(X,Y3);
  88. R5=corrcoef(X,Y5);
  89. R10=corrcoef(X,Y10);
  90.  
  91. %For us the best parameter p would be 3, because its sample correlation
  92. %coefficient is equal to 0.9077. If its closer to 1 or -1, its better.
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement