MBAStartingSalaries
Kunalika Bagga
20 February 2018
SETTING THE DIRECTORY AND READING THE DATA
setwd("C:/Users/Bagga/Desktop/Internship 2018/Week 4, Day 1")
salary <- read.csv("C:/Users/Bagga/Desktop/Internship 2018/Week 4, Day 1/MBA Starting Salaries Data.csv")
salary## age sex gmat_tot gmat_qpc gmat_vpc gmat_tpc s_avg f_avg quarter
## 1 23 2 620 77 87 87 3.40 3.00 1
## 2 24 1 610 90 71 87 3.50 4.00 1
## 3 24 1 670 99 78 95 3.30 3.25 1
## 4 24 1 570 56 81 75 3.30 2.67 1
## 5 24 2 710 93 98 98 3.60 3.75 1
## 6 24 1 640 82 89 91 3.90 3.75 1
## 7 25 1 610 89 74 87 3.40 3.50 1
## 8 25 2 650 88 89 92 3.30 3.75 1
## 9 25 1 630 79 91 89 3.30 3.25 1
## 10 25 1 680 99 81 96 3.45 3.67 1
## 11 26 1 740 99 98 99 3.56 4.00 1
## 12 26 2 610 75 87 86 3.40 3.75 1
## 13 26 1 710 95 95 98 3.50 3.50 1
## 14 26 1 720 97 97 99 3.40 4.00 1
## 15 26 2 660 84 93 94 3.30 3.25 1
## 16 26 2 640 67 98 92 4.00 4.00 1
## 17 27 2 660 71 99 95 3.50 4.00 1
## 18 27 1 600 77 78 84 3.30 3.50 1
## 19 27 1 630 79 89 89 3.50 4.00 1
## 20 27 1 600 91 58 83 3.40 3.25 1
## 21 27 2 570 65 82 77 3.30 3.25 1
## 22 27 1 740 99 96 99 3.50 3.50 1
## 23 27 1 750 99 98 99 3.40 3.50 1
## 24 28 2 540 75 50 65 3.60 4.00 1
## 25 29 1 580 56 87 78 3.64 3.33 1
## 26 30 1 620 82 84 87 3.40 2.80 1
## 27 31 2 560 60 78 72 3.30 3.75 1
## 28 32 1 760 99 99 99 3.40 3.00 1
## 29 32 1 640 79 91 91 3.60 3.75 1
## 30 32 1 570 71 71 0 3.50 3.50 1
## 31 34 2 620 75 89 87 3.30 3.00 1
## 32 37 2 560 43 87 72 3.40 3.50 1
## 33 42 2 650 75 98 93 3.38 3.00 1
## 34 48 1 590 84 62 81 3.80 4.00 1
## 35 22 2 660 90 92 94 3.50 3.75 1
## 36 27 2 700 94 98 98 3.30 3.25 1
## 37 25 2 680 87 96 96 3.50 2.67 1
## 38 25 2 650 82 91 93 3.40 3.25 1
## 39 27 1 710 96 96 98 3.30 3.50 1
## 40 28 2 620 52 98 87 3.40 3.75 1
## 41 24 1 670 84 96 95 3.30 3.25 1
## 42 25 2 560 52 81 72 3.30 3.50 1
## 43 25 2 530 50 62 61 3.60 3.67 1
## 44 25 1 650 79 93 93 3.30 3.50 1
## 45 26 2 590 56 89 81 3.30 3.25 1
## 46 23 2 650 93 81 93 3.40 3.00 1
## 47 24 1 560 81 50 71 3.40 3.67 1
## 48 27 1 610 72 84 86 3.30 3.50 1
## 49 25 1 650 95 84 93 3.30 3.00 1
## 50 25 1 550 74 50 68 3.50 3.50 1
## 51 26 1 570 68 74 75 3.80 3.50 1
## 52 26 1 580 79 71 78 3.45 3.50 1
## 53 30 1 600 60 91 83 3.30 3.25 1
## 54 31 1 570 72 71 75 3.60 3.50 1
## 55 30 1 620 60 96 87 3.50 3.00 1
## 56 30 2 680 96 87 96 3.70 3.60 1
## 57 27 1 630 93 75 91 3.30 3.25 1
## 58 25 1 600 82 74 83 3.50 3.25 1
## 59 28 2 640 89 81 91 3.60 3.50 1
## 60 39 1 600 72 81 83 3.60 3.50 1
## 61 27 1 570 95 33 75 3.70 4.00 1
## 62 27 1 710 95 98 98 3.60 3.50 1
## 63 33 1 620 72 89 87 3.50 3.50 1
## 64 27 1 600 67 84 83 3.50 3.00 1
## 65 28 1 700 95 95 98 3.80 4.00 1
## 66 30 1 600 77 81 84 3.50 3.25 1
## 67 30 2 670 87 95 95 3.30 3.25 1
## 68 40 1 630 71 95 91 4.00 0.00 1
## 69 25 1 700 98 93 98 3.60 3.75 1
## 70 22 1 600 95 54 83 3.00 3.00 2
## 71 23 1 640 89 87 92 3.00 3.00 2
## 72 24 1 550 73 63 69 3.10 3.00 2
## 73 24 1 570 82 58 75 3.09 3.50 2
## 74 24 1 620 82 84 87 3.10 3.50 2
## 75 25 2 570 61 81 76 3.00 3.25 2
## 76 25 1 660 94 84 94 3.27 3.75 2
## 77 25 1 680 94 92 97 3.17 3.50 2
## 78 25 1 690 87 98 98 3.00 3.00 2
## 79 25 2 670 99 85 96 3.00 3.25 2
## 80 25 1 690 94 95 98 3.00 2.75 2
## 81 25 2 630 83 89 90 3.00 2.75 2
## 82 25 1 670 99 74 96 3.18 3.25 2
## 83 25 1 680 91 95 97 3.00 3.00 2
## 84 25 1 690 96 89 97 3.00 3.00 2
## 85 25 1 670 97 81 95 3.10 3.25 2
## 86 25 1 580 79 71 78 3.10 2.33 2
## 87 26 1 680 92 93 97 3.00 3.00 2
## 88 26 2 560 64 71 72 3.20 3.25 2
## 89 26 1 560 87 41 72 3.00 3.00 2
## 90 26 1 530 68 54 62 3.09 3.17 2
## 91 27 1 740 99 98 99 3.10 3.50 2
## 92 27 1 720 99 95 99 3.10 3.25 2
## 93 27 1 590 60 87 81 3.00 2.75 2
## 94 27 1 630 87 84 89 3.20 3.00 2
## 95 27 1 560 60 71 72 3.20 3.00 2
## 96 28 2 450 49 22 44 3.10 3.75 2
## 97 28 1 620 81 90 89 3.20 3.00 2
## 98 28 2 610 85 78 86 3.10 3.00 2
## 99 28 1 660 95 85 96 3.10 3.25 2
## 100 29 1 660 94 87 94 3.00 3.00 2
## 101 29 1 580 91 50 80 3.10 2.67 2
## 102 29 1 510 57 50 55 3.27 3.40 2
## 103 29 2 640 90 84 92 3.20 3.00 2
## 104 29 1 610 91 62 86 3.10 3.67 2
## 105 29 1 590 68 84 81 3.10 3.00 2
## 106 29 1 580 79 67 78 3.00 3.25 2
## 107 30 1 680 97 87 96 3.00 3.00 2
## 108 31 1 670 83 98 96 3.20 3.40 2
## 109 32 2 610 64 89 86 3.25 0.00 2
## 110 35 1 540 43 78 65 3.20 3.25 2
## 111 35 1 630 66 95 90 3.08 3.25 2
## 112 36 2 530 48 71 62 3.00 2.50 2
## 113 36 1 650 87 89 93 3.00 3.20 2
## 114 43 1 630 82 87 89 3.10 3.00 2
## 115 26 2 670 87 95 95 3.10 3.33 2
## 116 25 2 620 89 74 87 3.10 3.50 2
## 117 31 1 540 60 62 65 3.10 3.00 2
## 118 25 1 670 95 89 95 3.20 3.50 2
## 119 25 1 610 87 71 86 3.27 3.25 2
## 120 24 1 560 52 81 72 3.20 3.25 2
## 121 24 1 500 78 30 52 3.00 2.75 2
## 122 23 1 590 72 81 81 3.20 3.25 2
## 123 24 1 570 82 58 75 3.20 3.25 2
## 124 26 2 570 93 37 75 3.00 2.75 2
## 125 28 2 580 83 58 79 3.10 3.00 2
## 126 24 2 580 72 71 78 3.00 3.25 2
## 127 31 1 560 68 67 72 3.09 3.00 2
## 128 25 2 620 89 74 87 3.10 3.50 2
## 129 27 1 620 97 63 88 3.20 3.00 2
## 130 28 1 560 75 58 72 3.20 3.25 2
## 131 26 1 680 84 96 96 3.20 3.25 2
## 132 27 1 620 81 87 89 3.00 3.00 2
## 133 34 1 550 72 58 69 3.00 3.00 2
## 134 26 1 600 84 67 83 3.09 3.50 2
## 135 29 1 670 91 93 95 3.10 3.00 2
## 136 24 1 620 84 81 87 3.00 3.25 2
## 137 27 1 630 72 95 89 3.20 3.00 2
## 138 26 1 650 89 87 93 3.20 3.25 2
## 139 24 1 620 88 74 87 3.10 3.00 2
## 140 23 1 720 95 98 99 2.80 2.50 3
## 141 24 2 640 94 78 92 2.90 3.25 3
## 142 24 1 710 96 97 99 2.80 2.75 3
## 143 24 1 670 94 89 96 2.70 3.00 3
## 144 24 2 710 97 97 99 2.80 3.00 3
## 145 24 1 650 89 84 93 2.70 3.25 3
## 146 24 1 600 89 62 83 2.90 3.00 3
## 147 24 2 640 96 71 91 2.70 2.50 3
## 148 25 1 600 89 62 83 2.70 3.25 3
## 149 25 1 630 79 91 89 2.70 2.75 3
## 150 25 1 550 72 58 69 2.90 3.00 3
## 151 25 1 710 99 91 98 2.90 3.25 3
## 152 25 1 660 95 84 94 2.70 3.00 3
## 153 25 1 630 93 71 89 2.90 3.25 3
## 154 25 1 560 79 58 72 2.73 3.17 3
## 155 26 1 670 97 81 96 2.70 2.50 3
## 156 26 1 660 88 93 94 2.90 2.75 3
## 157 26 1 630 83 87 90 2.70 3.00 3
## 158 26 1 640 87 84 91 2.70 3.20 3
## 159 26 1 560 56 81 72 2.80 3.25 3
## 160 26 1 540 52 71 65 2.70 2.75 3
## 161 26 1 600 97 45 83 2.70 3.00 3
## 162 26 2 570 48 89 75 2.82 2.50 3
## 163 26 1 610 82 81 86 2.90 2.75 3
## 164 27 1 650 89 84 93 2.90 3.00 3
## 165 27 2 550 66 63 69 2.90 3.00 3
## 166 27 1 730 95 99 99 2.90 3.33 3
## 167 27 1 610 97 45 86 2.70 2.50 3
## 168 27 2 630 82 89 89 2.70 3.25 3
## 169 27 2 560 61 74 73 2.80 3.25 3
## 170 27 2 620 97 54 87 2.70 2.75 3
## 171 27 1 600 68 87 83 2.90 3.25 3
## 172 27 1 650 79 95 93 2.70 3.25 3
## 173 27 1 560 52 81 72 2.70 2.75 3
## 174 27 1 610 48 98 86 2.70 3.00 3
## 175 27 1 600 77 81 84 2.70 3.00 3
## 176 28 1 460 66 16 37 2.70 2.50 3
## 177 28 1 650 99 63 93 2.90 3.00 3
## 178 28 2 610 64 93 86 2.80 3.25 3
## 179 28 1 500 46 54 52 2.90 2.75 3
## 180 29 1 590 92 58 81 2.80 2.75 3
## 181 29 1 560 57 74 73 2.80 3.00 3
## 182 32 1 550 52 78 71 2.70 2.75 3
## 183 34 1 610 79 81 86 2.80 3.00 3
## 184 34 1 610 82 78 86 2.70 3.00 3
## 185 43 1 480 49 41 45 2.90 3.25 3
## 186 23 2 520 43 67 58 2.90 2.75 3
## 187 27 1 620 87 74 87 2.70 2.75 3
## 188 25 1 580 78 67 80 2.90 3.25 3
## 189 25 1 630 75 93 89 2.70 2.50 3
## 190 25 1 610 89 74 87 2.70 2.75 3
## 191 29 2 560 64 71 72 2.90 3.00 3
## 192 27 1 620 79 87 88 2.90 2.75 3
## 193 28 1 580 72 71 78 2.80 3.00 3
## 194 24 2 670 83 98 96 2.90 3.25 3
## 195 25 2 560 39 91 72 2.90 3.00 3
## 196 25 2 580 72 71 78 2.80 3.25 3
## 197 27 1 680 97 90 97 2.90 2.75 3
## 198 28 1 610 89 67 86 2.70 3.00 3
## 199 29 1 710 93 98 99 2.90 3.25 3
## 200 24 1 710 99 92 99 2.90 3.00 3
## 201 25 2 630 84 87 89 2.80 2.75 3
## 202 24 2 600 89 67 85 2.80 3.00 3
## 203 29 1 660 91 90 95 2.80 3.00 3
## 204 30 1 670 83 97 96 2.80 2.75 3
## 205 24 1 580 89 54 78 2.91 2.83 3
## 206 29 1 680 79 99 96 2.90 3.00 3
## 207 32 1 660 83 95 94 2.90 3.50 3
## 208 28 1 570 56 84 75 2.90 3.00 3
## 209 24 1 680 96 87 97 2.80 2.75 3
## 210 24 1 610 82 81 86 2.50 2.75 4
## 211 24 1 640 93 78 91 2.40 2.50 4
## 212 25 1 600 53 95 84 2.50 3.00 4
## 213 25 1 730 98 96 99 2.40 2.75 4
## 214 25 2 650 87 91 93 2.50 2.50 4
## 215 25 1 640 79 93 91 2.67 0.00 4
## 216 25 1 590 68 81 81 2.60 2.75 4
## 217 25 1 590 97 41 81 2.50 2.75 4
## 218 25 1 700 99 87 98 2.00 2.00 4
## 219 26 1 660 93 87 95 2.60 2.00 4
## 220 26 1 450 28 46 34 2.10 2.00 4
## 221 26 1 560 87 45 72 2.60 3.00 4
## 222 26 1 600 75 78 83 2.20 2.25 4
## 223 26 1 570 82 58 75 2.50 2.75 4
## 224 26 1 590 89 58 81 2.50 2.25 4
## 225 26 2 670 98 81 95 2.60 2.50 4
## 226 27 1 660 97 81 94 2.50 2.50 4
## 227 27 2 560 59 74 73 2.40 2.50 4
## 228 27 1 790 99 99 99 2.40 2.50 4
## 229 27 1 630 93 78 91 2.10 2.50 4
## 230 27 1 580 84 58 78 2.70 2.75 4
## 231 27 1 620 85 85 89 3.30 3.00 4
## 232 27 1 670 89 91 95 3.60 3.25 4
## 233 27 1 580 74 70 78 3.40 3.25 4
## 234 28 1 560 74 67 73 3.60 3.60 4
## 235 28 1 620 93 71 87 2.40 2.75 4
## 236 28 1 710 94 98 99 3.40 3.75 4
## 237 28 1 570 69 71 0 2.30 2.50 4
## 238 29 1 530 35 81 62 3.30 2.75 4
## 239 29 1 690 99 87 97 2.30 2.25 4
## 240 29 1 630 87 84 89 2.90 2.80 4
## 241 29 1 670 91 91 95 3.30 3.25 4
## 242 29 1 630 99 50 89 2.90 3.25 4
## 243 29 2 680 89 96 96 2.80 3.00 4
## 244 30 1 650 88 92 93 3.45 3.83 4
## 245 30 1 550 79 45 69 2.45 2.75 4
## 246 30 2 600 99 46 86 2.80 3.00 4
## 247 30 1 630 82 87 89 3.80 3.50 4
## 248 31 1 580 83 67 79 3.00 3.25 4
## 249 31 1 740 99 98 99 2.20 3.00 4
## 250 31 1 570 75 62 75 2.80 3.00 4
## 251 31 1 640 79 92 92 2.70 2.75 4
## 252 32 1 570 89 41 75 2.60 2.50 4
## 253 32 1 510 79 22 54 2.30 2.25 4
## 254 35 1 570 72 71 75 3.30 4.00 4
## 255 39 2 700 89 98 98 3.30 3.25 4
## 256 24 2 560 55 78 71 3.50 3.25 4
## 257 23 1 660 81 98 95 2.50 3.00 4
## 258 25 2 720 96 98 99 3.50 3.60 4
## 259 26 1 620 78 87 89 2.40 2.00 4
## 260 26 2 630 85 81 90 2.90 3.25 4
## 261 27 1 650 89 89 93 2.40 2.25 4
## 262 25 1 660 99 71 95 3.40 3.25 4
## 263 25 1 610 83 81 86 2.40 2.75 4
## 264 26 1 600 87 62 83 2.50 2.50 4
## 265 24 1 570 75 62 75 2.30 2.50 4
## 266 24 2 600 77 78 84 2.60 3.00 4
## 267 26 2 650 91 84 93 2.60 3.00 4
## 268 29 1 630 72 95 89 2.60 2.50 4
## 269 26 1 630 96 71 91 2.60 2.75 4
## 270 31 1 530 75 45 62 2.40 2.75 4
## 271 23 1 580 64 81 78 2.20 2.00 4
## 272 25 1 540 79 45 65 2.60 2.50 4
## 273 26 1 550 72 58 69 2.60 2.75 4
## 274 40 2 500 60 45 51 2.50 2.75 4
## work_yrs frstlang salary satis
## 1 2 1 0 7
## 2 2 1 0 6
## 3 2 1 0 6
## 4 1 1 0 7
## 5 2 1 999 5
## 6 2 1 0 6
## 7 2 1 0 5
## 8 2 1 0 6
## 9 2 2 999 4
## 10 2 1 998 998
## 11 2 1 998 998
## 12 2 1 998 998
## 13 3 1 998 998
## 14 2 1 998 998
## 15 4 1 998 998
## 16 2 1 998 998
## 17 4 1 998 998
## 18 3 2 998 998
## 19 2 1 998 998
## 20 4 1 998 998
## 21 4 1 999 4
## 22 3 1 0 6
## 23 1 2 0 5
## 24 5 1 0 5
## 25 3 1 0 5
## 26 5 1 999 6
## 27 10 1 0 7
## 28 5 1 0 5
## 29 7 1 0 6
## 30 4 1 999 4
## 31 7 1 0 6
## 32 9 1 0 6
## 33 13 1 0 5
## 34 22 1 0 6
## 35 1 1 85000 5
## 36 2 1 85000 6
## 37 2 1 86000 5
## 38 3 1 88000 7
## 39 2 1 92000 6
## 40 5 1 93000 5
## 41 0 1 95000 4
## 42 1 1 95000 5
## 43 3 1 95000 3
## 44 1 1 96000 7
## 45 4 1 96000 5
## 46 2 1 100000 7
## 47 2 1 100000 6
## 48 6 1 100000 6
## 49 2 1 105000 7
## 50 3 1 105000 6
## 51 3 1 105000 6
## 52 2 1 105000 5
## 53 5 1 105000 6
## 54 6 1 105000 6
## 55 8 1 106000 7
## 56 6 1 106000 6
## 57 3 1 107500 5
## 58 3 1 108000 6
## 59 6 1 110000 5
## 60 16 1 112000 7
## 61 4 1 115000 5
## 62 1 1 115000 5
## 63 10 2 118000 7
## 64 3 1 120000 5
## 65 5 1 120000 5
## 66 5 1 120000 6
## 67 8 1 120000 6
## 68 15 1 146000 6
## 69 1 1 162000 5
## 70 1 1 0 5
## 71 2 1 0 7
## 72 0 2 0 5
## 73 2 1 0 6
## 74 1 1 0 5
## 75 3 1 0 4
## 76 2 1 0 5
## 77 2 1 0 6
## 78 3 1 999 5
## 79 2 2 998 998
## 80 2 1 998 998
## 81 3 1 998 998
## 82 2 2 998 998
## 83 2 1 998 998
## 84 3 1 998 998
## 85 2 1 998 998
## 86 2 1 998 998
## 87 3 1 999 1
## 88 3 1 0 6
## 89 3 1 0 6
## 90 4 2 0 5
## 91 2 1 999 4
## 92 5 1 0 5
## 93 3 1 0 6
## 94 4 1 998 998
## 95 4 1 998 998
## 96 4 2 998 998
## 97 4 1 0 6
## 98 5 1 0 6
## 99 4 1 999 3
## 100 1 1 0 6
## 101 4 2 999 4
## 102 5 1 0 5
## 103 3 1 0 5
## 104 7 1 0 5
## 105 6 1 999 5
## 106 4 1 0 6
## 107 4 1 0 5
## 108 4 1 999 6
## 109 11 1 0 7
## 110 8 1 0 5
## 111 12 1 0 5
## 112 7 1 0 5
## 113 18 1 0 6
## 114 16 1 0 5
## 115 1 1 82000 7
## 116 2 1 92000 5
## 117 8 1 93000 6
## 118 2 1 95000 6
## 119 3 1 95000 6
## 120 2 1 96000 7
## 121 2 1 96500 6
## 122 2 1 98000 6
## 123 2 1 98000 6
## 124 3 2 98000 5
## 125 5 2 99000 6
## 126 2 1 100000 5
## 127 4 1 100000 6
## 128 2 1 101000 5
## 129 3 1 103000 6
## 130 4 1 104000 5
## 131 3 1 105000 6
## 132 3 1 105000 5
## 133 16 1 105000 5
## 134 2 1 107000 5
## 135 6 1 112000 6
## 136 1 1 115000 6
## 137 4 1 115000 6
## 138 4 1 130000 7
## 139 2 1 145800 6
## 140 1 1 0 5
## 141 2 2 0 4
## 142 2 1 0 7
## 143 2 1 0 7
## 144 2 1 0 7
## 145 1 1 999 5
## 146 1 1 0 6
## 147 2 1 0 6
## 148 4 1 998 998
## 149 2 1 998 998
## 150 3 1 0 6
## 151 1 1 0 6
## 152 3 1 999 6
## 153 3 2 998 998
## 154 2 2 998 998
## 155 4 1 998 998
## 156 3 2 998 998
## 157 3 1 998 998
## 158 4 1 999 5
## 159 4 1 0 6
## 160 2 1 0 6
## 161 4 2 999 6
## 162 3 1 0 5
## 163 3 1 0 6
## 164 2 1 0 6
## 165 3 1 0 4
## 166 0 1 999 5
## 167 4 2 0 5
## 168 5 1 0 6
## 169 5 1 0 6
## 170 2 2 999 2
## 171 3 1 998 998
## 172 3 1 998 998
## 173 2 1 998 998
## 174 4 1 998 998
## 175 3 1 998 998
## 176 4 1 998 998
## 177 4 2 998 998
## 178 4 1 998 998
## 179 9 1 999 6
## 180 3 2 0 5
## 181 4 1 999 5
## 182 7 1 0 6
## 183 11 1 0 6
## 184 12 1 0 5
## 185 22 1 0 5
## 186 1 1 78256 5
## 187 3 1 88500 6
## 188 2 1 90000 7
## 189 2 1 90000 5
## 190 4 1 93000 6
## 191 5 1 95000 7
## 192 4 1 97000 7
## 193 3 1 97000 6
## 194 2 1 98000 7
## 195 2 1 98000 7
## 196 2 1 98000 6
## 197 2 2 98000 6
## 198 4 1 98000 7
## 199 7 1 98000 5
## 200 3 1 100000 6
## 201 2 1 100000 6
## 202 2 1 101000 6
## 203 8 1 101100 6
## 204 6 1 102500 5
## 205 2 1 105000 5
## 206 6 1 106000 6
## 207 2 2 107300 7
## 208 4 1 108000 6
## 209 2 1 112000 6
## 210 2 1 998 998
## 211 1 1 998 998
## 212 2 1 999 4
## 213 2 1 0 6
## 214 3 1 999 7
## 215 1 1 998 998
## 216 3 1 998 998
## 217 2 2 999 4
## 218 1 1 0 7
## 219 2 1 0 5
## 220 4 1 0 6
## 221 3 2 999 3
## 222 2 1 0 6
## 223 3 1 999 6
## 224 3 1 998 998
## 225 3 1 998 998
## 226 4 1 999 4
## 227 2 1 0 5
## 228 4 1 999 6
## 229 4 1 0 5
## 230 1 1 0 5
## 231 1 1 999 5
## 232 5 1 0 6
## 233 3 1 0 6
## 234 5 1 0 5
## 235 3 1 999 4
## 236 6 1 0 6
## 237 5 1 0 5
## 238 6 1 0 7
## 239 7 1 999 5
## 240 3 1 999 4
## 241 3 1 0 5
## 242 1 2 0 4
## 243 4 1 0 5
## 244 2 1 0 6
## 245 5 2 999 4
## 246 6 2 999 4
## 247 7 1 998 998
## 248 6 1 998 998
## 249 8 1 998 998
## 250 1 1 0 6
## 251 7 1 999 3
## 252 4 2 999 3
## 253 5 2 0 5
## 254 8 1 0 6
## 255 5 1 0 5
## 256 2 1 64000 7
## 257 2 1 77000 6
## 258 3 1 85000 6
## 259 2 1 85000 6
## 260 3 1 86000 5
## 261 5 1 90000 5
## 262 2 1 92000 7
## 263 2 1 95000 7
## 264 2 1 96000 6
## 265 2 1 98000 6
## 266 2 1 100000 6
## 267 2 1 100000 7
## 268 3 1 100400 7
## 269 3 1 101600 6
## 270 4 2 104000 6
## 271 2 1 105000 6
## 272 3 1 115000 5
## 273 3 1 126710 6
## 274 15 2 220000 6SUMMARY OF THE DATA
summary(salary)## age sex gmat_tot gmat_qpc
## Min. :22.00 Min. :1.000 Min. :450.0 Min. :28.00
## 1st Qu.:25.00 1st Qu.:1.000 1st Qu.:580.0 1st Qu.:72.00
## Median :27.00 Median :1.000 Median :620.0 Median :83.00
## Mean :27.36 Mean :1.248 Mean :619.5 Mean :80.64
## 3rd Qu.:29.00 3rd Qu.:1.000 3rd Qu.:660.0 3rd Qu.:93.00
## Max. :48.00 Max. :2.000 Max. :790.0 Max. :99.00
## gmat_vpc gmat_tpc s_avg f_avg
## Min. :16.00 Min. : 0.0 Min. :2.000 Min. :0.000
## 1st Qu.:71.00 1st Qu.:78.0 1st Qu.:2.708 1st Qu.:2.750
## Median :81.00 Median :87.0 Median :3.000 Median :3.000
## Mean :78.32 Mean :84.2 Mean :3.025 Mean :3.062
## 3rd Qu.:91.00 3rd Qu.:94.0 3rd Qu.:3.300 3rd Qu.:3.250
## Max. :99.00 Max. :99.0 Max. :4.000 Max. :4.000
## quarter work_yrs frstlang salary
## Min. :1.000 Min. : 0.000 Min. :1.000 Min. : 0
## 1st Qu.:1.250 1st Qu.: 2.000 1st Qu.:1.000 1st Qu.: 0
## Median :2.000 Median : 3.000 Median :1.000 Median : 999
## Mean :2.478 Mean : 3.872 Mean :1.117 Mean : 39026
## 3rd Qu.:3.000 3rd Qu.: 4.000 3rd Qu.:1.000 3rd Qu.: 97000
## Max. :4.000 Max. :22.000 Max. :2.000 Max. :220000
## satis
## Min. : 1.0
## 1st Qu.: 5.0
## Median : 6.0
## Mean :172.2
## 3rd Qu.: 7.0
## Max. :998.0STRUCTURE OF THE DATA
str(salary)## 'data.frame': 274 obs. of 13 variables:
## $ age : int 23 24 24 24 24 24 25 25 25 25 ...
## $ sex : int 2 1 1 1 2 1 1 2 1 1 ...
## $ gmat_tot: int 620 610 670 570 710 640 610 650 630 680 ...
## $ gmat_qpc: int 77 90 99 56 93 82 89 88 79 99 ...
## $ gmat_vpc: int 87 71 78 81 98 89 74 89 91 81 ...
## $ gmat_tpc: int 87 87 95 75 98 91 87 92 89 96 ...
## $ s_avg : num 3.4 3.5 3.3 3.3 3.6 3.9 3.4 3.3 3.3 3.45 ...
## $ f_avg : num 3 4 3.25 2.67 3.75 3.75 3.5 3.75 3.25 3.67 ...
## $ quarter : int 1 1 1 1 1 1 1 1 1 1 ...
## $ work_yrs: int 2 2 2 1 2 2 2 2 2 2 ...
## $ frstlang: int 1 1 1 1 1 1 1 1 2 1 ...
## $ salary : int 0 0 0 0 999 0 0 0 999 998 ...
## $ satis : int 7 6 6 7 5 6 5 6 4 998 ...MEAN, MEDIAN AND STANDARD DEVIATION OF EACH VARIABLE
library(psych)
describe(salary)[,c(2,3,4,5,8,9)]## n mean sd median min max
## age 274 27.36 3.71 27 22 48
## sex 274 1.25 0.43 1 1 2
## gmat_tot 274 619.45 57.54 620 450 790
## gmat_qpc 274 80.64 14.87 83 28 99
## gmat_vpc 274 78.32 16.86 81 16 99
## gmat_tpc 274 84.20 14.02 87 0 99
## s_avg 274 3.03 0.38 3 2 4
## f_avg 274 3.06 0.53 3 0 4
## quarter 274 2.48 1.11 2 1 4
## work_yrs 274 3.87 3.23 3 0 22
## frstlang 274 1.12 0.32 1 1 2
## salary 274 39025.69 50951.56 999 0 220000
## satis 274 172.18 371.61 6 1 998NUMBER OF PLACED STUDENTS
Placed <- salary[ which(salary$salary > 999), c(1,2,12,13)]VISUALISATION OF PLACED STUDENTS
#hist(Placed)NUMBER OF UNPLACED STUDENTS
NotPlaced <- salary[ which(salary$salary == 0),c(1,2,11,12,13)]
NotPlaced## age sex frstlang salary satis
## 1 23 2 1 0 7
## 2 24 1 1 0 6
## 3 24 1 1 0 6
## 4 24 1 1 0 7
## 6 24 1 1 0 6
## 7 25 1 1 0 5
## 8 25 2 1 0 6
## 22 27 1 1 0 6
## 23 27 1 2 0 5
## 24 28 2 1 0 5
## 25 29 1 1 0 5
## 27 31 2 1 0 7
## 28 32 1 1 0 5
## 29 32 1 1 0 6
## 31 34 2 1 0 6
## 32 37 2 1 0 6
## 33 42 2 1 0 5
## 34 48 1 1 0 6
## 70 22 1 1 0 5
## 71 23 1 1 0 7
## 72 24 1 2 0 5
## 73 24 1 1 0 6
## 74 24 1 1 0 5
## 75 25 2 1 0 4
## 76 25 1 1 0 5
## 77 25 1 1 0 6
## 88 26 2 1 0 6
## 89 26 1 1 0 6
## 90 26 1 2 0 5
## 92 27 1 1 0 5
## 93 27 1 1 0 6
## 97 28 1 1 0 6
## 98 28 2 1 0 6
## 100 29 1 1 0 6
## 102 29 1 1 0 5
## 103 29 2 1 0 5
## 104 29 1 1 0 5
## 106 29 1 1 0 6
## 107 30 1 1 0 5
## 109 32 2 1 0 7
## 110 35 1 1 0 5
## 111 35 1 1 0 5
## 112 36 2 1 0 5
## 113 36 1 1 0 6
## 114 43 1 1 0 5
## 140 23 1 1 0 5
## 141 24 2 2 0 4
## 142 24 1 1 0 7
## 143 24 1 1 0 7
## 144 24 2 1 0 7
## 146 24 1 1 0 6
## 147 24 2 1 0 6
## 150 25 1 1 0 6
## 151 25 1 1 0 6
## 159 26 1 1 0 6
## 160 26 1 1 0 6
## 162 26 2 1 0 5
## 163 26 1 1 0 6
## 164 27 1 1 0 6
## 165 27 2 1 0 4
## 167 27 1 2 0 5
## 168 27 2 1 0 6
## 169 27 2 1 0 6
## 180 29 1 2 0 5
## 182 32 1 1 0 6
## 183 34 1 1 0 6
## 184 34 1 1 0 5
## 185 43 1 1 0 5
## 213 25 1 1 0 6
## 218 25 1 1 0 7
## 219 26 1 1 0 5
## 220 26 1 1 0 6
## 222 26 1 1 0 6
## 227 27 2 1 0 5
## 229 27 1 1 0 5
## 230 27 1 1 0 5
## 232 27 1 1 0 6
## 233 27 1 1 0 6
## 234 28 1 1 0 5
## 236 28 1 1 0 6
## 237 28 1 1 0 5
## 238 29 1 1 0 7
## 241 29 1 1 0 5
## 242 29 1 2 0 4
## 243 29 2 1 0 5
## 244 30 1 1 0 6
## 250 31 1 1 0 6
## 253 32 1 2 0 5
## 254 35 1 1 0 6
## 255 39 2 1 0 5VISUALISATION OF UNPLACED STUDENTS
#hist(NotPlaced)H1 - AGE DEPENDS ON THE STARTING SALARY OF A MBA STUDENT
my_table <- xtabs(~ age + salary, data = salary)
chisq.test(my_table)##
## Pearson's Chi-squared test
##
## data: my_table
## X-squared = 1114.2, df = 880, p-value = 1.178e-07H2 - SEX DEPENDS ON THE STARTING SALARY OF A MBA STUDENT
my_table1 <- xtabs(~ sex + salary, data = salary)
chisq.test(my_table1)##
## Pearson's Chi-squared test
##
## data: my_table1
## X-squared = 63.727, df = 44, p-value = 0.0274PLOT OF AGE VS SALARY
boxplot(salary ~ age, data = salary)
PLOT OF GENDER VS SALARY
library("lattice")
histogram( ~ salary | sex, data = salary)
PLOT OF TOTAL SCORE OF GMAT VS FIRST LANGUAGE
library(lattice)
boxplot(gmat_tot ~ frstlang, data = salary)
CORRELATIONS
library(car)
scatterplotMatrix(formula = ~ salary + age + sex + gmat_tot + frstlang , cex = 0.6,data= salary, diagonal = "histogram")
Correlation matirx
cor(salary) ## age sex gmat_tot gmat_qpc gmat_vpc
## age 1.00000000 -0.028106442 -0.14593840 -0.21616985 -0.04417547
## sex -0.02810644 1.000000000 -0.05336820 -0.16377435 0.07488782
## gmat_tot -0.14593840 -0.053368202 1.00000000 0.72473781 0.74839187
## gmat_qpc -0.21616985 -0.163774346 0.72473781 1.00000000 0.15218014
## gmat_vpc -0.04417547 0.074887816 0.74839187 0.15218014 1.00000000
## gmat_tpc -0.16990307 -0.008090213 0.84779965 0.65137754 0.66621604
## s_avg 0.14970402 0.127115144 0.11311702 -0.02984873 0.20445365
## f_avg -0.01744806 0.091663891 0.10442409 0.07370455 0.07592225
## quarter -0.04967221 -0.133533171 -0.09223903 0.03636638 -0.17460736
## work_yrs 0.85829810 -0.011296374 -0.18235434 -0.23660827 -0.06639049
## frstlang 0.05692649 0.001536205 -0.13503402 0.13892774 -0.38980465
## salary -0.06257355 0.068858628 -0.05497188 -0.04403293 -0.00613934
## satis -0.12788825 -0.054602220 0.08255770 0.06060004 0.06262375
## gmat_tpc s_avg f_avg quarter work_yrs
## age -0.169903066 0.14970402 -0.01744806 -4.967221e-02 0.858298096
## sex -0.008090213 0.12711514 0.09166389 -1.335332e-01 -0.011296374
## gmat_tot 0.847799647 0.11311702 0.10442409 -9.223903e-02 -0.182354339
## gmat_qpc 0.651377538 -0.02984873 0.07370455 3.636638e-02 -0.236608270
## gmat_vpc 0.666216035 0.20445365 0.07592225 -1.746074e-01 -0.066390490
## gmat_tpc 1.000000000 0.11736245 0.07973210 -8.303535e-02 -0.173361859
## s_avg 0.117362449 1.00000000 0.55062139 -7.621166e-01 0.129292714
## f_avg 0.079732099 0.55062139 1.00000000 -4.475064e-01 -0.039056921
## quarter -0.083035351 -0.76211664 -0.44750637 1.000000e+00 -0.086026406
## work_yrs -0.173361859 0.12929271 -0.03905692 -8.602641e-02 1.000000000
## frstlang -0.103362747 -0.13631308 -0.03705695 9.949226e-02 -0.027866747
## salary 0.004930901 0.14583606 0.02944303 -1.643699e-01 0.009023407
## satis 0.092934266 -0.03268664 0.01089273 -1.267198e-05 -0.109255286
## frstlang salary satis
## age 0.056926486 -0.062573547 -1.278882e-01
## sex 0.001536205 0.068858628 -5.460222e-02
## gmat_tot -0.135034017 -0.054971880 8.255770e-02
## gmat_qpc 0.138927742 -0.044032933 6.060004e-02
## gmat_vpc -0.389804653 -0.006139340 6.262375e-02
## gmat_tpc -0.103362747 0.004930901 9.293427e-02
## s_avg -0.136313080 0.145836062 -3.268664e-02
## f_avg -0.037056954 0.029443027 1.089273e-02
## quarter 0.099492259 -0.164369865 -1.267198e-05
## work_yrs -0.027866747 0.009023407 -1.092553e-01
## frstlang 1.000000000 -0.086592096 7.932264e-02
## salary -0.086592096 1.000000000 -3.352171e-01
## satis 0.079322637 -0.335217114 1.000000e+00CORRELATION TEST
library(corrplot)
library(gplots)
library(Hmisc)
colsalary <- c( "salary","age","sex","gmat_tot","frstlang")
corMatrix <- rcorr(as.matrix(salary[,colsalary]))
corMatrix## salary age sex gmat_tot frstlang
## salary 1.00 -0.06 0.07 -0.05 -0.09
## age -0.06 1.00 -0.03 -0.15 0.06
## sex 0.07 -0.03 1.00 -0.05 0.00
## gmat_tot -0.05 -0.15 -0.05 1.00 -0.14
## frstlang -0.09 0.06 0.00 -0.14 1.00
##
## n= 274
##
##
## P
## salary age sex gmat_tot frstlang
## salary 0.3020 0.2560 0.3647 0.1529
## age 0.3020 0.6432 0.0156 0.3479
## sex 0.2560 0.6432 0.3789 0.9798
## gmat_tot 0.3647 0.0156 0.3789 0.0254
## frstlang 0.1529 0.3479 0.9798 0.0254CORRGRAM PLOT
library(car)
library(corrgram)
library(Hmisc)
corrgram(salary[,colsalary], order = TRUE,
main = "SALARY OF MALE AND FEMALE",
lower.panel = panel.pts,upper.panel = panel.pie,
diag.panel = panel.minmax, text.panel = panel.txt)
T-TEST OF FIRST LAGUAGE AND TOTAL GMAT SCORE
t.test(salary$frstlang,salary$gmat_tot)##
## Welch Two Sample t-test
##
## data: salary$frstlang and salary$gmat_tot
## t = -177.88, df = 273.02, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -625.1791 -611.4924
## sample estimates:
## mean of x mean of y
## 1.116788 619.452555T-TEST OF SALARY AND AGE
t.test(salary$salary,salary$age)##
## Welch Two Sample t-test
##
## data: salary$salary and salary$age
## t = 12.67, df = 273, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 32938.51 45058.15
## sample estimates:
## mean of x mean of y
## 39025.68978 27.35766T-TEST OF SALARY AND SEX
t.test(salary$salary,salary$sex)##
## Welch Two Sample t-test
##
## data: salary$salary and salary$sex
## t = 12.678, df = 273, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 32964.62 45084.26
## sample estimates:
## mean of x mean of y
## 39025.689781 1.248175FORMULATING MULTIVARIATE LINEAR REGRESSION MODEL TO FIT SALARY WITH RESPECT TO OTHER VARAIBLES
Model <- salary ~ .
fit <- lm(Model, data = salary)
summary(fit)##
## Call:
## lm(formula = Model, data = salary)
##
## Residuals:
## Min 1Q Median 3Q Max
## -77353 -42055 -4193 43432 204537
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 215476.47 74731.74 2.883 0.00426 **
## age -3841.82 1578.26 -2.434 0.01560 *
## sex 1810.69 6853.24 0.264 0.79183
## gmat_tot -278.09 209.44 -1.328 0.18540
## gmat_qpc 334.82 578.64 0.579 0.56333
## gmat_vpc 294.13 550.38 0.534 0.59351
## gmat_tpc 512.59 417.03 1.229 0.22012
## s_avg 12836.84 12919.75 0.994 0.32135
## f_avg -6371.67 6636.87 -0.960 0.33792
## quarter -5443.82 4050.86 -1.344 0.18016
## work_yrs 2881.46 1784.27 1.615 0.10753
## frstlang -3058.63 10365.65 -0.295 0.76817
## satis -47.17 7.84 -6.016 6.01e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 47130 on 261 degrees of freedom
## Multiple R-squared: 0.1818, Adjusted R-squared: 0.1442
## F-statistic: 4.834 on 12 and 261 DF, p-value: 3.555e-07FINDING THE BEST PREDICTORS
library(leaps)
leap1 <- regsubsets(Model,data = salary, nbest = 1)
plot(leap1, scale = "adjr2")
## REVISING THE MODEL
Model1 <- salary ~ age + gmat_tot + gmat_tpc + quarter + work_yrs + satis
fit1 <- lm(Model1, data = salary)
summary(fit1)##
## Call:
## lm(formula = Model1, data = salary)
##
## Residuals:
## Min 1Q Median 3Q Max
## -70813 -41036 -4206 43065 199904
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 212040.118 49365.781 4.295 2.45e-05 ***
## age -3778.530 1501.671 -2.516 0.01245 *
## gmat_tot -174.240 93.673 -1.860 0.06397 .
## gmat_tpc 640.571 383.667 1.670 0.09617 .
## quarter -7593.684 2579.792 -2.944 0.00353 **
## work_yrs 2954.050 1731.271 1.706 0.08912 .
## satis -47.998 7.705 -6.230 1.81e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 46790 on 267 degrees of freedom
## Multiple R-squared: 0.1751, Adjusted R-squared: 0.1566
## F-statistic: 9.448 on 6 and 267 DF, p-value: 2.059e-09VISUALISING THE BETA COEFFICIENTS AND THEIR CONFIDENCE INTERVALS FROM MODEL1
library(coefplot)
coefplot(fit,intercept = FALSE,outerCI = 1.96,coefficients = c("age","gmat_tot" ,"gmat_tpc", "quarter","work_yrs" , "satis"))
MODEL 1 FITS BETTER THAN MODEL, AS INDICATED BY ADJUSTED R SQUARE
summary(fit)$adj.r.squared## [1] 0.1442077summary(fit1)$adj.r.squared## [1] 0.1566027INTERACTION PLOTS BETWEEN AGE, SEX AND SALARY
interaction.plot(salary$age,salary$sex,salary$salary, type = "b",
col = c("red","blue"),pch = c(16,18),
main = "Interaction between gender and salary")
INTERACTION PLOTS BETWEEN FIRST LANGUAGE, SATIFACTION RATING AND SALARY
interaction.plot(salary$satis,salary$frstlang,salary$salary, type = "b",
col = c("red","blue"),pch = c(16,18),
main = "Interaction between gender and salary")
## RESULT INTERPRETATION ## THE COEFFICIENTS, “age”,“gmat_tot” ,“gmat_tpc”, “quarter”,“work_yrs” , “satis” ARE STATISTICALLY SIGNIFICANT WITH THE CHANGE IN STARTING SALARIES.