Question: This dataset is from the Duke University Cardiovascular Disease Databank and consists of 3504 pat...
This dataset is from the Duke University Cardiovascular Disease Databank and consists of 3504 patients and 6 variables. The patients were referred to Duke University Medical Center for chest pain. Some interesting analyses include predicting the probability of significant (>= 75% diameter narrowing in at least one important coronary artery) coronary disease, and predicting the probability of severe coronary disease given that some significant disease is "ruled in." The first analysis would use sigdz as a response variable, and the second would use tvdlm on the subset of patients having sigdz=1. Severe coronary disease is defined as three-vessel or left main disease and is denoted by tvdlm=1. sex=0 for males, 1 for females.
sex age cad.dur choleste sigdz tvdlm
0 73 132 268 1 1
0 68 85 120 1 1
0 54 45 1 0
1 58 86 245 0 0
1 56 7 269 0 0
0 64 0 1 0
0 65 76 1 1
0 41 15 247 1 0
0 68 30 1 1
0 52 1 1 0
0 48 1 1 1
0 35 44 257 0 0
1 69 10 0 0
0 58 7 168 1 0
0 81 2 246 1 1
0 58 79 221 1 1
0 59 36 1 1
0 47 6 272 1 0
0 66 8 257 1 0
0 48 69 236 1 1
1 52 30 240 0 0
0 67 48 274 1 1
0 59 1 0 0
1 57 30 261 0 0
0 53 25 273 1 1
0 68 11 1 1
1 65 2 1 0
0 62 87 255 1 0
1 68 1 1 0
0 48 22 187 1 1
0 49 12 252 1 0
1 59 3 200 1 0
0 69 128 1 1
1 58 1 246 1 1
1 67 58 1 1
1 53 120 250 0 0
0 55 213 241 1 1
1 57 122 346 1 1
0 69 1 184 1 1
0 65 100 195 1 1
1 52 36 0 0
1 46 133 0 0
0 57 0 1 0
0 54 3 195 1 0
0 53 60 278 1 1
0 37 12 190 1 0
1 63 180 263 0 0
1 32 42 174 0 0
1 70 125 228 1 1
0 59 2 245 1 1
0 59 51 194 1 0
0 42 1 313 1 0
0 72 0 1 0
1 63 24 288 1 1
0 68 118 1 1
1 58 36 222 0 0
0 63 1 1 0
1 68 1 245 1 0
0 53 120 290 1 1
1 65 147 209 0 0
1 53 5 220 1 1
1 53 8 282 1 1
1 62 86 260 0 0
0 56 216 251 1 1
0 69 86 1 1
1 49 3 242 0 0
0 59 4 1 1
0 64 1 105 1 0
0 67 36 195 1 1
0 49 41 220 0 0
1 57 4 333 1 0
0 73 2 1 0
0 67 22 1 0
1 46 34 318 1 0
0 68 157 192 1 0
0 65 306 1 1
0 61 121 1 0
1 53 28 195 0 0
1 54 2 280 1 0
1 74 41 1 1
1 58 44 210 0 0
0 64 95 1 1
0 44 12 197 1 0
0 39 0 0 0
0 54 41 214 0 0
0 65 240 192 0 0
0 66 39 172 1 1
0 39 65 1 0
0 64 56 210 1 1
0 48 4 1 0
1 62 8 188 0 0
0 69 16 1 0
0 49 69 210 0 0
0 58 1 1 1
1 65 83 1 0
1 65 0 1 0
1 63 45 192 0 0
0 62 22 222 1 1
0 56 96 224 1 1
1. Identify the number of classes and class width, and construct a frequency distribution table for your data.
2. Construct a histogram and a frequency polygon for the data (separately).
(Note: computer generated charts are not acceptable) (8 Marks)