? Q1: Apply and evaluate quadratic discriminant analysis on the diabetes dataset.

? Q2 : Apply and evaluate linear discriminant analysis on the diabetes dataset. If the last digit of your student number is: (i) 0- 3: Use a full but common/shared covariance matrix for each class. (ii) 4- 6: Use a diagonal common/shared covariance matrix for each class. (iii) 7- 9: Use a diagonal common/shared covariance matrix w ith equal variances for all dimensions, for each class. Details/hints : ? Split the data into training (the first 500 points) and test (the remaining points) sets. ? Fit the model using the training set. ? Report (a) the training classification error; (b) the te st classification error; (c) the model parameters (mean vectors and covariance matrices). To calculate the classification error, assume a decision threshold of 0.5 on the posterior probability values and then calculate the percentage correct for the data set in question. Note this corresponds to a 0/1 loss function after the decision threshold converts the prediction to a 0/1 output. ? For Q2, you will need to pool the data to estimate the covariance matrix (see Alpaydin, Sec.5.5 for how to do this).

1 2 3 4 5 6 7 8 9 6 148 72 35 0 33.6 0.627 50 pos 1 85 66 29 0 26.6 0.351 31 neg 8 183 64 0 0 23.3 0.672 32 pos 1 89 66 23 94 28.1 0.167 21 neg 0 137 40 35 168 43.1 2.288 33 pos 5 116 74 0 0 25.6 0.201 30 neg 3 78 50 32 88 31 0.248 26 pos 10 115 0 0 0 35.3 0.134 29 neg 2 197 70 45 543 30.5 0.158 53 pos 8 125 96 0 0 0 0.232 54 pos 4 110 92 0 0 37.6 0.191 30 neg 10 168 74 0 0 38 0.537 34 pos 10 139 80 0 0 27.1 1.441 57 neg 1 189 60 23 846 30.1 0.398 59 pos 5 166 72 19 175 25.8 0.587 51 pos 7 100 0 0 0 30 0.484 32 pos 0 118 84 47 230 45.8 0.551 31 pos

Note: The language to be used is MATLAB, cheers!