Uses data from Britain's Most Admired Companies (http://www.managementtoday.co.uk/go/bmac/).
(means2009 <- ddply(dta2009, .(Industry), function(x) colMeans(x[, -(1:2)])))
## Industry QMan FS QGS AAT VLTI CI QMar CER UCA
## 1 Aero and defence 6.750 6.740 7.200 6.700 6.580 6.640 6.450 6.020 6.410
## 2 Banking 5.410 5.110 5.460 5.110 5.150 5.230 5.170 4.570 4.600
## 3 Building materials 5.920 5.860 6.710 5.560 5.770 5.640 5.310 5.390 5.510
## 4 Chemicals 6.071 5.929 6.171 5.457 5.371 5.443 5.757 5.100 5.586
## 5 Engineering 6.740 6.360 6.330 5.890 6.010 5.770 5.890 5.500 5.870
## 6 Extractive 7.225 6.750 7.562 7.138 7.237 6.588 6.237 5.763 7.525
## 7 Food 6.100 6.090 5.880 5.650 5.380 5.550 5.680 5.920 5.840
## 8 Food and personal retailers 6.600 6.350 6.610 6.310 6.170 6.160 6.420 5.310 5.730
## 9 General retailers 6.120 5.260 5.890 5.100 5.010 5.120 4.950 4.430 4.750
## 10 Health 6.487 7.188 7.037 6.662 6.388 5.987 6.925 5.487 6.250
## 11 Heavy construction 5.960 5.900 6.000 5.800 5.670 5.810 5.520 5.630 5.680
## 12 Home construction 5.330 4.540 5.760 4.610 5.020 5.220 5.030 5.390 4.490
## 13 Insurance 6.200 6.160 5.930 5.870 5.640 5.770 5.410 5.500 5.680
## 14 Leisure 5.860 6.090 5.810 5.220 5.460 5.270 5.260 5.110 5.330
## 15 Media 6.130 5.760 6.570 5.910 5.990 5.870 5.750 5.530 5.740
## 16 Paper 6.213 6.287 6.513 5.700 5.375 5.912 5.562 5.888 5.750
## 17 Property 5.730 5.980 6.060 5.480 5.500 5.350 5.110 5.480 5.630
## 18 Restaurants 6.290 6.200 6.220 5.730 5.740 5.490 5.210 5.290 5.620
## 19 Software 6.400 6.360 6.600 6.050 5.630 6.060 6.050 5.620 6.020
## 20 Specialist retailers 6.263 6.188 6.263 5.862 5.575 6.237 5.987 5.537 6.075
## 21 Specialty finance 5.920 5.740 5.690 5.560 5.560 5.420 5.350 4.860 5.120
## 22 Support services 6.340 6.330 6.240 6.110 6.480 5.770 5.750 5.590 6.370
## 23 Telecoms 5.714 5.629 5.843 5.000 5.157 4.814 4.557 4.786 5.071
## 24 Transport 6.060 5.340 5.700 5.360 5.130 5.550 5.710 5.640 5.850
## 25 Utilities 5.980 6.780 6.080 5.970 6.240 5.800 5.330 5.830 6.200
(sds2009 <- ddply(dta2009, .(Industry), function(x) sapply(x[, -(1:2)], sd)))
## Industry QMan FS QGS AAT VLTI CI QMar CER UCA
## 1 Aero and defence 0.9265 1.0865 0.7102 0.8524 0.9920 0.8343 0.6803 0.5633 0.5724
## 2 Banking 1.2905 1.7546 0.6720 1.4067 1.2826 0.8945 1.1926 1.2320 1.1709
## 3 Building materials 0.7436 1.0102 0.4533 0.7351 0.7484 0.6059 0.6641 0.4932 0.5859
## 4 Chemicals 1.1600 1.3301 1.3086 1.4351 1.4660 1.6461 0.9914 1.2728 1.2402
## 5 Engineering 0.9617 0.9312 0.6961 1.0246 0.8491 0.6651 0.6367 0.8151 0.7573
## 6 Extractive 0.6541 0.7616 0.3503 0.6567 0.6255 0.7338 0.8417 0.7763 0.5751
## 7 Food 1.1025 1.6908 1.0119 1.3243 1.4665 1.0927 1.2621 1.0304 0.5522
## 8 Food and personal retailers 0.9381 1.5160 1.0418 1.2556 1.3225 1.1227 1.3440 1.5617 1.1373
## 9 General retailers 0.8979 1.4439 0.6385 1.0382 1.2697 1.1063 1.2085 0.5229 0.7367
## 10 Health 0.8839 0.9433 0.6989 1.1045 0.7643 0.8167 1.2903 0.6707 0.6803
## 11 Heavy construction 0.9454 1.0274 0.8807 0.9978 0.9056 0.8504 0.7885 0.6395 0.7800
## 12 Home construction 1.4291 1.9540 0.7919 1.0257 0.9163 0.5940 1.1786 0.4254 1.2297
## 13 Insurance 1.2120 1.2747 0.8460 1.0144 1.0679 0.9068 1.2096 0.4028 0.9175
## 14 Leisure 0.9947 0.7795 0.9723 1.2372 1.1345 0.9464 1.0648 0.5238 0.8042
## 15 Media 1.2667 1.5508 1.2962 1.0397 1.0989 1.4166 1.2686 0.7119 0.9119
## 16 Paper 1.1618 0.9687 1.1382 1.1364 0.8664 0.9508 1.1783 0.8967 0.9181
## 17 Property 0.7861 0.8879 0.8383 0.6197 0.7318 0.9312 0.9550 0.5473 0.8525
## 18 Restaurants 0.8647 1.4996 1.1998 1.2266 1.2085 1.3932 1.5438 1.1249 1.2479
## 19 Software 0.6749 0.8592 0.8014 0.7292 0.6767 0.8168 0.6553 0.6647 0.5922
## 20 Specialist retailers 0.7726 0.6468 0.7425 0.5579 1.2338 0.8314 0.7624 0.4438 0.6923
## 21 Specialty finance 0.7510 0.4671 0.5859 0.4904 0.6703 0.6877 0.6754 1.0091 0.6763
## 22 Support services 0.9371 0.9250 0.8475 0.6757 0.7269 0.5982 0.5276 0.2885 0.6945
## 23 Telecoms 1.0637 1.6347 1.5339 1.9983 1.8438 1.3957 1.2895 1.3108 1.0012
## 24 Transport 1.1227 1.8234 0.8615 0.9913 1.4407 1.0113 1.1435 1.0490 1.0341
## 25 Utilities 0.6460 0.8741 0.7239 0.8179 0.7531 0.6037 1.0414 0.7364 0.3972
means2009.m <- melt(means2009)
## Using Industry as id variables
means2009.m <- ddply(means2009.m, .(variable), transform, rescale = rescale(value))
(p <- ggplot(means2009.m, aes(variable, Industry)) + geom_tile(aes(fill = rescale), colour = "white") +
scale_fill_gradient(low = "white", high = "steelblue"))
cols <- c(6, 8, 10, 12, 14, 16, 18, 20, 22)
tot.col <- 4
ind.col <- 3
comp.col <- 2
inds2010 <- levels(bmac2010[, ind.col])
dta2010 <- bmac2010[, c(ind.col, comp.col, cols)]
(means2010 <- ddply(dta2010, .(Industry), function(x) colMeans(x[, -(1:2)])))
## Industry QMan QGS QMar FS VLTI CER ATT UCA CI
## 1 Aero and defence 6.410 6.540 5.670 6.470 5.950 5.700 6.190 6.250 6.268
## 2 Banking 6.050 6.160 5.800 6.125 5.640 5.748 5.637 5.490 5.440
## 3 Building materials 6.000 6.573 5.820 5.930 6.070 5.813 6.070 5.983 5.660
## 4 Chemicals 6.170 6.300 5.610 6.310 5.810 5.545 5.922 5.893 5.740
## 5 Extractive 7.110 6.850 6.000 7.216 7.108 5.984 6.791 7.192 6.340
## 6 Food 6.610 6.967 5.881 6.634 6.070 6.233 6.160 6.440 6.181
## 7 Food and personal retailers 6.999 7.006 6.390 7.198 6.897 5.845 6.737 6.350 6.357
## 8 General retailers 6.270 6.050 5.120 6.100 5.700 4.950 5.590 5.450 5.410
## 9 Health 6.140 6.260 5.790 6.040 5.710 5.520 5.890 5.800 5.340
## 10 Heavy construction 5.810 5.920 5.140 5.580 5.200 5.580 5.630 5.450 5.190
## 11 Home construction 5.683 5.880 5.590 5.428 5.383 5.130 5.060 5.360 5.170
## 12 Insurance 6.143 6.170 5.230 6.350 6.010 4.910 5.900 5.340 5.530
## 13 Leisure 6.410 6.683 5.885 6.520 6.196 5.770 6.143 5.830 5.520
## 14 Media 5.940 6.225 5.648 5.840 5.590 5.530 5.754 5.740 5.476
## 15 Property 6.220 6.620 6.060 6.030 5.900 5.480 6.070 5.420 5.650
## 16 Restaurants 6.250 6.260 5.810 5.980 5.850 5.890 6.000 5.750 5.680
## 17 Software 6.510 6.637 5.805 6.530 5.620 5.000 5.900 5.740 6.130
## 18 Specialist retailers 6.050 6.280 5.420 5.780 5.610 5.300 5.640 5.560 5.510
## 19 Specialty finance 6.220 6.700 5.640 6.740 5.860 4.250 6.690 5.940 5.890
## 20 Support services 7.083 6.928 6.588 6.830 6.498 5.980 6.513 6.603 6.280
## 21 Telecoms 6.040 5.710 5.090 5.517 5.140 5.080 5.220 5.380 5.073
## 22 Transport 6.263 5.860 5.740 6.040 5.620 5.730 5.500 5.800 5.540
## 23 Utilities 6.200 6.040 5.920 6.830 6.480 6.140 5.920 5.900 5.660
(sds2010 <- ddply(dta2010, .(Industry), function(x) sapply(x[, -(1:2)], sd)))
## Industry QMan QGS QMar FS VLTI CER ATT UCA CI
## 1 Aero and defence 0.8185 0.7531 0.7602 1.1700 0.9652 0.5457 0.6983 0.6096 0.9047
## 2 Banking 1.1740 0.6275 1.1879 1.5447 1.3235 1.0617 1.6085 1.5329 1.0200
## 3 Building materials 0.9274 0.8390 0.4566 0.9358 1.0144 0.6773 0.8028 0.9047 0.8631
## 4 Chemicals 0.6881 0.8179 0.7824 0.9207 1.0847 0.9136 0.9016 0.8482 1.0058
## 5 Extractive 0.7264 0.5017 0.8537 0.9948 0.6206 1.2466 0.6470 0.5687 0.6328
## 6 Food 1.0857 0.5612 0.7639 1.4705 1.1519 0.5220 1.0648 0.6363 0.7185
## 7 Food and personal retailers 0.8780 0.9709 0.7400 1.0453 1.0300 1.0678 0.8964 0.6468 0.8678
## 8 General retailers 1.1973 0.9812 0.8135 1.4514 1.4236 0.8567 1.0588 1.0876 1.1180
## 9 Health 0.9264 0.6835 1.1484 1.1711 1.1298 0.6579 1.0888 1.0209 0.9442
## 10 Heavy construction 1.1060 0.9163 1.0069 1.3506 1.0562 0.6529 1.0750 0.8835 1.0311
## 11 Home construction 1.6111 0.6779 1.0333 2.1706 1.8108 0.6056 1.0967 1.4924 0.7349
## 12 Insurance 1.3975 0.9322 1.1285 0.7678 0.7593 0.6008 0.8882 0.6004 0.8407
## 13 Leisure 0.9814 0.8526 1.1547 0.9259 0.7934 0.4138 1.0128 0.6567 0.7857
## 14 Media 1.3352 1.2282 1.2483 1.6588 1.3552 0.6717 1.3798 1.0606 1.4393
## 15 Property 1.1419 0.6647 0.7367 0.8577 0.5270 0.5594 0.6684 0.4237 0.7397
## 16 Restaurants 0.5563 0.8695 1.2974 1.0809 0.7619 0.5685 0.8433 0.8528 1.0581
## 17 Software 0.6773 0.8665 1.2950 0.6395 0.6663 0.8969 0.8932 0.7351 0.5908
## 18 Specialist retailers 0.8683 0.7021 1.1708 1.0261 1.3658 0.6992 0.7604 0.8669 0.9134
## 19 Specialty finance 0.7239 0.9933 1.3640 0.7777 0.5147 0.3979 0.6557 0.5929 1.3085
## 20 Support services 0.8912 0.7414 0.7942 0.8551 0.8209 0.5432 0.9687 0.7484 0.7131
## 21 Telecoms 1.0606 1.0311 1.0472 1.2414 1.1286 0.8879 1.1811 0.8430 1.2847
## 22 Transport 1.3595 0.8579 1.1286 1.6507 1.7358 0.7818 1.2092 1.0339 1.2633
## 23 Utilities 0.6782 0.7137 0.8817 0.6183 0.6233 0.6899 0.5789 0.7257 0.8276
means2010.m <- melt(means2010)
## Using Industry as id variables
means2010.m <- ddply(means2010.m, .(variable), transform, rescale = rescale(value))
(p <- ggplot(means2010.m, aes(variable, Industry)) + geom_tile(aes(fill = rescale), colour = "white") +
scale_fill_gradient(low = "white", high = "steelblue"))
cols <- c(3, 5, 7, 9, 11, 13, 15, 17, 19)
tot.col <- 21
ind.col <- 2
comp.col <- 1
inds2011 <- levels(bmac2011[, ind.col])
dta2011 <- bmac2011[, c(ind.col, comp.col, cols)]
(means2011 <- ddply(dta2011, .(Industry), function(x) colMeans(x[, -(1:2)])))
## Industry QMan FS QG.S AAT VLTI CI QMar C.ER UCA
## 1 Aero and defence 6.522 6.667 6.933 6.333 6.211 6.456 6.322 5.244 6.333
## 2 Banking 6.310 6.010 6.020 5.770 5.860 5.850 5.790 5.670 5.890
## 3 Beverages 6.820 7.450 7.160 6.550 6.660 6.710 6.840 7.010 6.990
## 4 Chemicals 6.911 7.400 7.122 6.589 6.589 6.367 5.767 6.033 6.144
## 5 Engineering 6.820 6.540 6.960 6.250 6.890 6.290 5.350 5.280 5.890
## 6 Extractive 6.760 6.630 6.390 6.030 6.500 5.940 5.380 5.150 6.120
## 7 Food 6.622 6.411 6.844 6.200 6.178 6.156 5.456 5.733 6.456
## 8 Food and personal retailers 6.940 6.860 6.680 6.480 6.220 6.430 6.520 6.310 6.700
## 9 Gaming 5.820 6.170 6.110 5.370 5.840 5.870 5.780 4.660 5.500
## 10 Heavy construction 6.290 6.130 6.360 5.790 6.170 5.370 5.660 6.070 6.050
## 11 Home construction 6.971 6.871 6.700 6.586 7.100 6.400 6.500 6.186 6.529
## 12 Home retailers 6.900 5.760 6.170 5.860 5.360 5.700 5.630 5.360 5.910
## 13 Insurance 6.310 6.540 5.770 6.300 6.130 5.430 5.320 5.530 6.010
## 14 Leisure 5.857 5.771 5.971 5.600 5.471 5.186 5.629 5.271 5.829
## 15 Media 6.100 6.090 6.630 5.920 5.900 5.750 5.780 5.160 5.690
## 16 Property 6.980 7.280 7.070 6.800 7.030 6.470 6.380 6.530 7.010
## 17 Restaurants 6.260 5.860 6.210 5.910 5.910 5.820 5.700 5.330 5.750
## 18 Software 6.820 7.100 6.760 6.750 6.820 6.600 6.470 6.110 6.730
## 19 Specialist retailers 6.580 6.610 6.540 6.220 6.140 5.920 5.770 5.270 6.090
## 20 Specialty finance 6.470 6.690 6.550 6.470 6.170 6.140 5.990 5.480 6.060
## 21 Support services 7.240 7.410 7.140 6.870 6.940 6.770 6.630 6.270 6.960
## 22 Telecoms 6.311 6.022 6.378 5.833 5.700 5.822 6.022 5.589 6.300
## 23 Transport 6.650 6.310 6.200 5.910 5.840 5.940 6.020 5.970 6.330
## 24 Transportation services 6.287 5.750 6.037 5.950 5.900 5.513 5.825 5.612 5.525
## 25 Utilities 6.100 6.290 6.290 6.050 5.960 5.730 5.520 6.330 5.890
(sds2011 <- ddply(dta2011, .(Industry), function(x) sapply(x[, -(1:2)], sd)))
## Industry QMan FS QG.S AAT VLTI CI QMar C.ER UCA
## 1 Aero and defence 0.9431 1.0235 0.8944 0.7124 0.8838 0.7055 0.7014 0.6247 0.6856
## 2 Banking 0.5840 0.7295 0.4341 0.7499 0.4402 0.5759 0.5301 0.6308 0.8452
## 3 Beverages 0.5789 0.9144 0.6398 0.9606 0.6501 0.6822 0.7749 0.6691 0.6607
## 4 Chemicals 0.5036 0.9695 1.0895 0.8298 0.7817 0.9434 1.3793 1.3077 0.8676
## 5 Engineering 1.5469 1.3310 1.1530 1.2492 0.9949 0.9871 1.0617 0.9897 1.4098
## 6 Extractive 1.1296 1.3557 1.0713 1.1344 1.2927 1.0741 1.1526 0.9583 1.1173
## 7 Food 1.2607 2.3095 0.5364 1.1292 1.8840 1.1545 1.3049 1.0075 0.8618
## 8 Food and personal retailers 0.8181 1.3986 0.9090 0.9402 0.9426 0.8680 0.7983 0.9374 0.7288
## 9 Gaming 1.4801 2.2301 1.4043 1.5011 1.5342 1.4712 1.4219 0.5060 0.9764
## 10 Heavy construction 0.8020 0.9730 0.5147 0.7894 0.8512 0.7304 0.6720 0.4111 0.3375
## 11 Home construction 1.2842 1.6225 0.7810 0.7946 0.6272 0.7280 1.0770 0.3716 1.0797
## 12 Home retailers 0.8731 1.4516 1.1295 1.4300 1.6181 1.3976 1.3039 1.2624 0.6280
## 13 Insurance 0.9689 0.6995 0.6684 0.8246 0.8367 0.6308 0.6680 0.5658 0.9666
## 14 Leisure 2.0181 2.0014 1.1265 1.4844 1.5381 0.9155 0.9534 0.9340 1.4840
## 15 Media 1.0306 1.1100 0.9166 0.9496 1.0077 1.0384 1.0518 0.7306 0.7355
## 16 Property 1.1203 0.8677 0.6913 0.8692 0.8420 0.9274 0.9601 0.7804 0.7608
## 17 Restaurants 0.9958 1.4953 1.1484 0.9608 1.3153 1.1400 1.4636 0.8551 1.1683
## 18 Software 0.6070 0.9177 0.5522 0.7059 0.7927 0.6429 0.5250 0.5626 0.6617
## 19 Specialist retailers 0.5865 0.8239 0.7820 0.6286 0.6786 0.6374 0.8870 0.4990 0.5065
## 20 Specialty finance 0.8166 0.8925 0.7075 0.8028 0.7181 0.8343 0.7400 0.2616 0.5758
## 21 Support services 0.8449 0.8711 1.1078 0.7514 0.9857 0.8667 0.6413 0.2359 0.8959
## 22 Telecoms 1.6465 1.5048 1.0462 1.3793 1.4491 1.2367 1.4140 1.1363 1.3115
## 23 Transport 0.9312 1.0525 0.7888 0.6790 1.0002 0.7351 1.0507 0.8327 0.6038
## 24 Transportation services 1.1205 1.5278 1.0405 1.1402 1.2398 1.2438 1.1449 0.7473 1.1145
## 25 Utilities 0.9080 0.8762 0.5384 0.6900 0.8276 0.6881 1.0983 0.6038 0.4332
means2011.m <- melt(means2011)
## Using Industry as id variables
means2011.m <- ddply(means2011.m, .(variable), transform, rescale = rescale(value))
(p <- ggplot(means2011.m, aes(variable, Industry)) + geom_tile(aes(fill = rescale), colour = "white") +
scale_fill_gradient(low = "white", high = "steelblue"))
Find the industries that are in all three years
print("2009")
## [1] "2009"
inds2009
## [1] "Aero and defence" "Banking" "Building materials"
## [4] "Chemicals" "Engineering" "Extractive"
## [7] "Food" "Food and personal retailers" "General retailers"
## [10] "Health" "Heavy construction" "Home construction"
## [13] "Insurance" "Leisure" "Media"
## [16] "Paper" "Property" "Restaurants"
## [19] "Software" "Specialist retailers" "Specialty finance"
## [22] "Support services" "Telecoms" "Transport"
## [25] "Utilities"
print("\n2010")
## [1] "\n2010"
inds2010
## [1] "Aero and defence" "Banking" "Building materials"
## [4] "Chemicals" "Extractive" "Food"
## [7] "Food and personal retailers" "General retailers" "Health"
## [10] "Heavy construction" "Home construction" "Insurance"
## [13] "Leisure" "Media" "Property"
## [16] "Restaurants" "Software" "Specialist retailers"
## [19] "Specialty finance" "Support services" "Telecoms"
## [22] "Transport" "Utilities"
print("\n2011")
## [1] "\n2011"
inds2011
## [1] "Aero and defence" "Banking" "Beverages"
## [4] "Chemicals" "Engineering" "Extractive"
## [7] "Food" "Food and personal retailers" "Gaming"
## [10] "Heavy construction" "Home construction" "Home retailers"
## [13] "Insurance" "Leisure" "Media"
## [16] "Property" "Restaurants" "Software"
## [19] "Specialist retailers" "Specialty finance" "Support services"
## [22] "Telecoms" "Transport" "Transportation services"
## [25] "Utilities"
indsall <- intersect(inds2011, intersect(inds2009, inds2010))
(meansag <- ddply(dta, .(Industry), function(x) colMeans(x[, -c(1:2, 12, 13)])))
## Industry QMan FS QGS ATT VLTI CI QMar CER UCA
## 1 Aero and defence 6.562 6.624 6.890 6.410 6.248 6.454 6.141 5.669 6.331
## 2 Banking 5.923 5.748 5.880 5.506 5.550 5.507 5.587 5.329 5.327
## 3 Chemicals 6.400 6.585 6.550 6.028 5.962 5.877 5.704 5.594 5.897
## 4 Extractive 7.018 6.874 6.889 6.618 6.928 6.268 5.846 5.623 6.904
## 5 Food 6.438 6.377 6.554 5.997 5.866 5.956 5.680 5.970 6.238
## 6 Food and personal retailers 6.846 6.803 6.765 6.509 6.429 6.316 6.443 5.822 6.260
## 7 Heavy construction 6.020 5.870 6.093 5.740 5.680 5.457 5.440 5.760 5.727
## 8 Home construction 5.886 5.473 6.048 5.289 5.694 5.507 5.619 5.500 5.341
## 9 Insurance 6.218 6.350 5.957 6.023 5.927 5.577 5.320 5.313 5.677
## 10 Leisure 6.063 6.167 6.175 5.660 5.736 5.341 5.587 5.396 5.644
## 11 Media 6.057 5.897 6.475 5.861 5.827 5.699 5.726 5.407 5.723
## 12 Property 6.310 6.430 6.583 6.117 6.143 5.823 5.850 5.830 6.020
## 13 Restaurants 6.267 6.013 6.230 5.880 5.833 5.663 5.573 5.503 5.707
## 14 Software 6.577 6.663 6.666 6.233 6.023 6.263 6.108 5.577 6.163
## 15 Specialist retailers 6.300 6.193 6.368 5.911 5.789 5.864 5.707 5.357 5.896
## 16 Specialty finance 6.203 6.390 6.313 6.240 5.863 5.817 5.660 4.863 5.707
## 17 Support services 6.888 6.857 6.769 6.498 6.639 6.273 6.323 5.947 6.644
## 18 Telecoms 6.046 5.722 5.977 5.373 5.338 5.263 5.269 5.177 5.615
## 19 Transport 6.324 5.897 5.920 5.590 5.530 5.677 5.823 5.780 5.993
## 20 Utilities 6.093 6.633 6.137 5.980 6.227 5.730 5.590 6.100 5.997
(sdsag <- ddply(dta, .(Industry), function(x) sapply(x[, -c(1:2, 12, 13)], sd)))
## Industry QMan FS QGS ATT VLTI CI QMar CER UCA
## 1 Aero and defence 0.8756 1.0642 0.8073 0.7645 0.9542 0.8085 0.7739 0.6415 0.6030
## 2 Banking 1.0947 1.4402 0.6446 1.2945 1.0979 0.8618 1.0278 1.1152 1.2951
## 3 Chemicals 0.8485 1.1919 1.1021 1.1028 1.1761 1.2024 1.0348 1.1727 0.9582
## 4 Extractive 0.8675 1.0783 0.8517 0.9483 0.9461 0.8542 1.0020 1.0570 0.9911
## 5 Food 1.1340 1.7864 0.8734 1.1654 1.5041 1.0101 1.1030 0.8732 0.7258
## 6 Food and personal retailers 0.8672 1.3361 0.9574 1.0222 1.1232 0.9339 0.9651 1.2475 0.9287
## 7 Heavy construction 0.9477 1.1136 0.7882 0.9313 0.9939 0.8889 0.8353 0.6015 0.7277
## 8 Home construction 1.5614 2.1029 0.8211 1.2556 1.5035 0.8494 1.2086 0.6367 1.4905
## 9 Insurance 1.1654 0.9295 0.8114 0.9027 0.8917 0.7868 0.9967 0.5882 0.8605
## 10 Leisure 1.2997 1.2344 1.0166 1.2484 1.1571 0.8590 1.0675 0.6671 0.9705
## 11 Media 1.1782 1.4153 1.1328 1.1010 1.1359 1.2761 1.1531 0.7032 0.8807
## 12 Property 1.1223 1.0396 0.8247 0.8910 0.9522 0.9684 1.0190 0.7953 0.9876
## 13 Restaurants 0.7976 1.3323 1.0446 0.9936 1.0842 1.1713 1.4132 0.8931 1.0661
## 14 Software 0.6564 0.8491 0.7292 0.8421 0.8962 0.7093 0.9040 0.8357 0.7695
## 15 Specialist retailers 0.7572 0.9018 0.7268 0.6844 1.1140 0.8256 0.9618 0.5574 0.7249
## 16 Specialty finance 0.7726 0.8495 0.8792 0.8097 0.6677 0.9931 0.9797 0.8045 0.7311
## 17 Support services 0.9487 0.9641 0.9628 0.8413 0.8494 0.8212 0.7614 0.4637 0.7959
## 18 Telecoms 1.2650 1.4045 1.1786 1.4812 1.4207 1.3170 1.3389 1.1032 1.1492
## 19 Transport 1.1383 1.5473 0.8348 0.9789 1.4074 1.0081 1.0789 0.8755 0.9142
## 20 Utilities 0.7325 0.8096 0.6505 0.6800 0.7455 0.6899 1.0073 0.6878 0.5404
meansag.m <- melt(meansag)
## Using Industry as id variables
meansag.m <- ddply(meansag.m, .(variable), transform, rescale = rescale(value))
(p <- ggplot(meansag.m, aes(variable, Industry)) + geom_tile(aes(fill = rescale), colour = "white") +
scale_fill_gradient(low = "white", high = "steelblue"))
indag <- dlply(dta, .(Industry))
for (i in 1:length(indag)) {
x.m <- melt(indag[[i]], "Company.Year", 3:11)
x.m <- ddply(x.m, .(variable), transform, rescale = rescale(value))
print(ggplot(x.m, aes(variable, Company.Year)) + geom_tile(aes(fill = value), colour = "white") +
scale_fill_gradient(high = "tomato", low = "cyan") + ggtitle(indsall[i]) + geom_text(aes(label = value),
size = 3))
}
pcindag <- dlply(dta, .(Industry), function(x) {
pctmp <- prcomp(x[, -c(1, 2, 12, 13)], scale. = TRUE)
# plot(pctmp$x[,1],pctmp$x[,2])
biplot(pctmp, xlabs = abbreviate(x$Company), main = x$Industry[1])
print(summary(pctmp))
# screeplot(pctmp)
})
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.571 1.012 0.664 0.5920 0.455 0.3861 0.3021 0.27219 0.2285
## Proportion of Variance 0.735 0.114 0.049 0.0389 0.023 0.0166 0.0101 0.00823 0.0058
## Cumulative Proportion 0.735 0.848 0.897 0.9363 0.959 0.9758 0.9860 0.99420 1.0000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.67 0.9013 0.7137 0.4209 0.368 0.328 0.26809 0.2183 0.17449
## Proportion of Variance 0.79 0.0903 0.0566 0.0197 0.015 0.012 0.00799 0.0053 0.00338
## Cumulative Proportion 0.79 0.8800 0.9366 0.9563 0.971 0.983 0.99132 0.9966 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.776 0.7454 0.465 0.4501 0.3572 0.29739 0.23802 0.1967 0.09303
## Proportion of Variance 0.856 0.0617 0.024 0.0225 0.0142 0.00983 0.00629 0.0043 0.00096
## Cumulative Proportion 0.856 0.9179 0.942 0.9644 0.9786 0.98845 0.99474 0.9990 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.622 0.7966 0.6491 0.5714 0.4956 0.4361 0.3596 0.3009 0.29339
## Proportion of Variance 0.764 0.0705 0.0468 0.0363 0.0273 0.0211 0.0144 0.0101 0.00956
## Cumulative Proportion 0.764 0.8345 0.8813 0.9176 0.9449 0.9660 0.9804 0.9904 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.538 0.954 0.8524 0.5513 0.4968 0.4409 0.27530 0.25394 0.19119
## Proportion of Variance 0.716 0.101 0.0807 0.0338 0.0274 0.0216 0.00842 0.00716 0.00406
## Cumulative Proportion 0.716 0.817 0.8975 0.9313 0.9587 0.9804 0.98877 0.99594 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.47 1.073 0.8314 0.5837 0.4752 0.4463 0.3768 0.3011 0.19146
## Proportion of Variance 0.68 0.128 0.0768 0.0379 0.0251 0.0221 0.0158 0.0101 0.00407
## Cumulative Proportion 0.68 0.808 0.8850 0.9228 0.9479 0.9701 0.9859 0.9959 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.691 0.8751 0.6390 0.4505 0.3694 0.3224 0.26369 0.21339 0.16512
## Proportion of Variance 0.804 0.0851 0.0454 0.0226 0.0152 0.0115 0.00773 0.00506 0.00303
## Cumulative Proportion 0.804 0.8895 0.9349 0.9575 0.9726 0.9842 0.99191 0.99697 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.650 1.08 0.511 0.4492 0.3633 0.29732 0.24659 0.20237 0.14485
## Proportion of Variance 0.781 0.13 0.029 0.0224 0.0147 0.00982 0.00676 0.00455 0.00233
## Cumulative Proportion 0.781 0.91 0.939 0.9619 0.9765 0.98636 0.99312 0.99767 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.406 1.058 0.9118 0.5860 0.5410 0.511 0.3969 0.3368 0.3012
## Proportion of Variance 0.643 0.124 0.0924 0.0382 0.0325 0.029 0.0175 0.0126 0.0101
## Cumulative Proportion 0.643 0.768 0.8601 0.8983 0.9308 0.960 0.9773 0.9899 1.0000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.761 0.6274 0.5893 0.4598 0.3703 0.3394 0.27282 0.25384 0.1849
## Proportion of Variance 0.847 0.0437 0.0386 0.0235 0.0152 0.0128 0.00827 0.00716 0.0038
## Cumulative Proportion 0.847 0.8907 0.9293 0.9527 0.9680 0.9808 0.98904 0.99620 1.0000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.764 0.6564 0.5526 0.4508 0.3772 0.3395 0.28563 0.23221 0.16077
## Proportion of Variance 0.849 0.0479 0.0339 0.0226 0.0158 0.0128 0.00906 0.00599 0.00287
## Cumulative Proportion 0.849 0.8970 0.9309 0.9535 0.9693 0.9821 0.99114 0.99713 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.583 0.984 0.7962 0.4906 0.4328 0.3440 0.29386 0.2419 0.19083
## Proportion of Variance 0.741 0.108 0.0704 0.0267 0.0208 0.0132 0.00959 0.0065 0.00405
## Cumulative Proportion 0.741 0.849 0.9192 0.9459 0.9667 0.9799 0.98945 0.9960 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.801 0.6199 0.4792 0.403 0.3563 0.29444 0.26655 0.24254 0.19148
## Proportion of Variance 0.872 0.0427 0.0255 0.018 0.0141 0.00963 0.00789 0.00654 0.00407
## Cumulative Proportion 0.872 0.9142 0.9397 0.958 0.9719 0.98150 0.98939 0.99593 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.359 1.132 0.8234 0.6944 0.6044 0.5049 0.4373 0.3364 0.26271
## Proportion of Variance 0.618 0.142 0.0753 0.0536 0.0406 0.0283 0.0213 0.0126 0.00767
## Cumulative Proportion 0.618 0.761 0.8360 0.8896 0.9302 0.9585 0.9798 0.9923 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.445 1.019 0.9160 0.6438 0.5305 0.3983 0.3399 0.3195 0.26805
## Proportion of Variance 0.664 0.115 0.0932 0.0461 0.0313 0.0176 0.0128 0.0113 0.00798
## Cumulative Proportion 0.664 0.780 0.8729 0.9189 0.9502 0.9678 0.9807 0.9920 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.274 1.082 0.8410 0.7857 0.7461 0.5498 0.4716 0.4146 0.28647
## Proportion of Variance 0.574 0.130 0.0786 0.0686 0.0619 0.0336 0.0247 0.0191 0.00912
## Cumulative Proportion 0.574 0.704 0.7830 0.8516 0.9135 0.9471 0.9718 0.9909 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.597 0.9009 0.6269 0.5400 0.5153 0.4260 0.3775 0.3533 0.21027
## Proportion of Variance 0.749 0.0902 0.0437 0.0324 0.0295 0.0202 0.0158 0.0139 0.00491
## Cumulative Proportion 0.749 0.8396 0.8833 0.9157 0.9452 0.9654 0.9812 0.9951 1.00000
## Warning: abbreviate used with non-ASCII chars
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.665 0.8139 0.6761 0.5136 0.4289 0.4012 0.3048 0.20503 0.18324
## Proportion of Variance 0.789 0.0736 0.0508 0.0293 0.0204 0.0179 0.0103 0.00467 0.00373
## Cumulative Proportion 0.789 0.8628 0.9136 0.9429 0.9634 0.9813 0.9916 0.99627 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.44 1.096 0.969 0.5571 0.5298 0.3601 0.3206 0.22878 0.20731
## Proportion of Variance 0.66 0.134 0.104 0.0345 0.0312 0.0144 0.0114 0.00582 0.00478
## Cumulative Proportion 0.66 0.794 0.898 0.9324 0.9636 0.9780 0.9894 0.99522 1.00000
## Importance of components:
## PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
## Standard deviation 2.235 1.085 1.004 0.8530 0.6585 0.5007 0.4404 0.3662 0.27924
## Proportion of Variance 0.555 0.131 0.112 0.0809 0.0482 0.0278 0.0215 0.0149 0.00866
## Cumulative Proportion 0.555 0.686 0.798 0.8789 0.9270 0.9549 0.9764 0.9913 1.00000
mdsindag <- dlply(dta, .(Industry), function(z) {
tmpd <- dist(z[, -c(1, 2, 12, 13)])
mdstmp <- cmdscale(tmpd, eig = TRUE)
plot(mdstmp$points, main = z$Industry[1], type = "n")
text(mdstmp$points, abbreviate(z$Company), cex = 0.8)
print(mdstmp$GOF)
# print(mdstmp)
})
## [1] 0.8492 0.8492
## [1] 0.8985 0.8985
## [1] 0.9177 0.9177
## [1] 0.8393 0.8393
## [1] 0.8673 0.8673
## [1] 0.8053 0.8053
## [1] 0.9049 0.9049
## [1] 0.9329 0.9329
## [1] 0.7958 0.7958
## [1] 0.9086 0.9086
## [1] 0.9019 0.9019
## [1] 0.8481 0.8481
## [1] 0.9253 0.9253
## [1] 0.7639 0.7639
## [1] 0.8133 0.8133
## [1] 0.7149 0.7149
## [1] 0.8454 0.8454
## Warning: abbreviate used with non-ASCII chars
## [1] 0.8674 0.8674
## [1] 0.8209 0.8209
## [1] 0.7046 0.7046
### Add performance data
## Linear mixed model fit by REML
## Formula: ROA ~ Total + (1 | Company) + (1 | Industry) + (1 | Year)
## Data: dta.merge
## AIC BIC logLik deviance REMLdev
## 3875 3901 -1932 3861 3863
## Random effects:
## Groups Name Variance Std.Dev.
## Company (Intercept) 30.97 5.56
## Industry (Intercept) 6.60 2.57
## Year (Intercept) 1.21 1.10
## Residual 45.09 6.71
## Number of obs: 545, groups: Company, 237; Industry, 20; Year, 3
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) -12.2470 3.0278 -4.04
## Total 0.3416 0.0533 6.41
##
## Correlation of Fixed Effects:
## (Intr)
## Total -0.946
library(influence.ME)
## Attaching package: 'influence.ME'
## The following object(s) are masked from 'package:arm':
##
## se.fixef
## The following object(s) are masked from 'package:stats':
##
## influence
me.inf <- influence(m1, "Company", gf = "all")
rot <- 2/sqrt(230)
dfb <- dfbetas(me.inf)
ggplot(data = data.frame(dfb)) + geom_dotplot(aes(x = Total)) + coord_flip() + geom_vline(xintercept = c(-rot,
rot), colour = "red")
## stat_bindot: binwidth defaulted to range/30. Use 'binwidth = x' to adjust this.
ix <- dfb[, 2] > rot | dfb[, 2] < -rot
dfb[ix, 2]
## Alternative Networks Ashmore Group Cadbury
## -0.2454 -0.4616 0.2555
## IG Group McInerney Homes UK Mothercare
## -0.1448 0.4385 0.1888
## Mucklow (A&J) QinetiQ Group Redrow
## 0.2362 -0.1522 0.1330
## Sports Direct St James Place Capital Victrex
## -0.2353 0.2298 0.1833
## Cable & Wireless Worldwide Cairn Energy Punch Taverns
## 0.1980 0.3045 0.1413
## Telecom plus
## -0.1812
cd <- cooks.distance(me.inf, parameter = 2, sort = TRUE)
rot.cd <- 4/237
colnames(cd) <- "Cook"
ggplot(data = data.frame(cd)) + geom_dotplot(aes(x = Cook)) + coord_flip() + geom_vline(xintercept = rot.cd,
colour = "red")
## stat_bindot: binwidth defaulted to range/30. Use 'binwidth = x' to adjust this.
ix <- cd[, 1] > rot.cd
cd[ix, ]
## Redrow Punch Taverns IG Group
## 0.01769 0.01998 0.02095
## QinetiQ Group Telecom plus Victrex
## 0.02317 0.03283 0.03361
## Mothercare Cable & Wireless Worldwide St James Place Capital
## 0.03565 0.03920 0.05280
## Sports Direct Mucklow (A&J) Alternative Networks
## 0.05536 0.05579 0.06024
## Cadbury Cairn Energy McInerney Homes UK
## 0.06530 0.09273 0.19231
## Ashmore Group
## 0.21309
st <- sigtest(me.inf, test = 1.96)
any(st$Total[, 3])
## [1] FALSE
obs.inf <- influence(m1.ss, obs = TRUE)
obs.cd <- cooks.distance(obs.inf)
ix <- (obs.cd > 4/528)
m1.ss@frame[ix, c("Company", "Year")]
## Company Year
## 3 3i 2010
## 4 3i 2011
## 5 Aberdeen Asset Management 2009
## 6 Aberdeen Asset Management 2010
## 7 Aberdeen Asset Management 2011
## 8 Admiral 2009
## 9 Admiral 2010
## 10 Admiral 2011
## 11 Aegis 2009
## 12 Aegis 2010
## 13 Aer Lingus 2009
## 14 Aer Lingus 2010
## 15 Aggreko 2009
## 16 Aggreko 2010
## 17 Aggreko 2011
## 18 Allied Irish Bank (GB) 2009
## 19 Allied Irish Bank (GB) 2010
## 21 Amlin 2009
## 22 Amlin 2010
## 23 Amlin 2011
## 24 Anglo American 2009
## 25 Anglo American 2010
## 32 Associated British Foods 2009
## 33 Associated British Foods 2010
## 34 Associated British Foods 2011
## 35 Autonomy 2009
## 36 Autonomy 2010
## 38 Aveva Group 2009
## 39 Aveva Group 2010
## 40 Aveva Group 2011
## 41 Avis Europe 2009
## 42 Avis Europe 2010
## 44 Aviva 2009
## 45 Aviva 2010
## 46 Aviva 2011
## 47 Babcock International 2009
## 48 Babcock International 2010
## 49 Babcock International 2011
## 50 BAE Systems 2009
## 51 BAE Systems 2010
## 52 BAE Systems 2011
## 53 Balfour Beatty 2009
## 54 Balfour Beatty 2010
## 55 Balfour Beatty 2011
## 56 Banco Santander 2009
## 57 Banco Santander 2010
## 58 Banco Santander 2011
## 60 Bank of Ireland 2010
## 61 Barclays 2009
## 62 Barclays 2010
## 63 Barclays 2011
## 64 Barratt Developments 2009
## 65 Barratt Developments 2010
## 66 Barratt Developments 2011
## 67 Bellway 2009
## 68 Bellway 2010
## 69 Bellway 2011
## 70 Berkeley Group 2009
## 71 Berkeley Group 2010
## 72 Berkeley Group 2011
## 73 BG Group 2009
## 74 BG Group 2010
## 75 BG Group 2011
## 76 BHP Billiton 2009
## 77 BHP Billiton 2010
## 78 Big Yellow Company. 2009
## 79 Big Yellow Company. 2010
## 80 Boot (Henry) 2009
## 81 Boot (Henry) 2010
## 82 Boot (Henry) 2011
## 83 Bovis Homes 2009
## 84 Bovis Homes 2010
## 85 Bovis Homes 2011
## 86 BP 2009
## 87 BP 2010
## 88 BP 2011
## 89 British Airways 2009
## 90 British Airways 2010
## 91 British Land Company 2009
## 92 British Land Company 2010
## 93 British Land Company 2011
## 94 Britvic 2009
## 95 Britvic 2010
## 96 Brown (N) 2009
## 97 Brown (N) 2010
## 98 BSkyB 2009
## 99 BSkyB 2010
## 100 BSkyB 2011
## 101 BT Group 2009
## 102 BT Group 2010
## 103 BT Group 2011
## 104 Bunzl 2009
## 105 Bunzl 2010
## 106 Bunzl 2011
## 107 Burberry 2009
## 108 Burberry 2010
## 109 Cable & Wireless Communications 2009
## 110 Cable & Wireless Communications 2010
## 111 Cable & Wireless Communications 2011
## 113 Capita Group 2009
## 114 Capita Group 2010
## 115 Capita Group 2011
## 116 Carillion 2009
## 117 Carillion 2011
## 118 Carnival 2009
## 119 Carnival 2010
## 120 Carnival 2011
## 121 Carphone Warehouse 2009
## 122 Carphone Warehouse 2010
## 123 Carphone Warehouse 2011
## 124 Centrica 2009
## 125 Centrica 2010
## 126 Centrica 2011
## 127 Chemring Group 2009
## 128 Chemring Group 2010
## 129 Chemring Group 2011
## 130 Cineworld Group 2009
## 131 Clarke (T) 2009
## 132 Clarke (T) 2010
## 133 Close Brothers 2009
## 134 Co-operative Bank 2009
## 135 Co-operative Bank 2010
## 136 Co-operative Bank 2011
## 137 Cobham 2009
## 138 Cobham 2010
## 139 Cobham 2011
## 140 COLT Telecom 2009
## 141 COLT Telecom 2010
## 143 Compass 2009
## 144 Compass 2010
## 145 Costain Group 2009
## 146 Costain Group 2010
## 147 Costain Group 2011
## 148 Cranswick 2009
## 149 Cranswick 2010
## 153 Daily Mail & General Trust 2009
## 154 Daily Mail & General Trust 2010
## 155 Daily Mail & General Trust 2011
## 156 Dairy Crest 2009
## 157 Dairy Crest 2010
## 158 Debenhams 2009
## 159 Debenhams 2010
## 160 Derwent London 2009
## 161 Derwent London 2010
## 162 Derwent London 2011
## 163 Diageo 2009
## 164 Diageo 2010
## 165 Dimension Data 2009
## 166 Dimension Data 2010
## 167 Drax 2009
## 168 easyJet 2009
## 169 easyJet 2010
## 170 easyJet 2011
## 171 Elementis 2009
## 172 Elementis 2010
## 173 Elementis 2011
## 174 Enterprise Inns 2009
## 175 Enterprise Inns 2010
## 176 Enterprise Inns 2011
## 177 Experian 2009
## 178 Experian 2010
## 179 Experian 2011
## 180 Fidessa 2009
## 181 Fidessa 2010
## 182 Fidessa 2011
## 183 FirstGroup 2009
## 184 FirstGroup 2010
## 185 FirstGroup 2011
## 186 Friends Provident 2009
## 187 G4S 2009
## 188 G4S 2010
## 189 G4S 2011
## 190 Galliford Try 2009
## 191 Galliford Try 2010
## 192 Galliford Try 2011
## 193 Game Group 2009
## 194 Game Group 2010
## 195 Game Group 2011
## 196 GKN 2009
## 197 GKN 2010
## 198 GKN 2011
## 199 Gleeson (M.J.) Group 2009
## 200 Gleeson (M.J.) Group 2010
## 201 Go-Ahead Gp 2009
## 202 Go-Ahead Gp 2010
## 203 Go-Ahead Gp 2011
## 204 Great Portland Estates 2009
## 205 Great Portland Estates 2010
## 206 Great Portland Estates 2011
## 207 Greencore 2009
## 208 Greencore 2011
## 209 Greene King 2009
## 210 Greene King 2010
## 211 Greene King 2011
## 212 Halfords 2009
## 213 Halfords 2010
## 214 Halfords 2011
## 215 Hammerson 2009
## 216 Hammerson 2010
## 217 Hammerson 2011
## 218 HMV 2009
## 219 HMV 2010
## 220 HSBC 2009
## 221 HSBC 2010
## 222 HSBC 2011
## 223 ICAP 2009
## 224 ICAP 2010
## 225 ICAP 2011
## 226 IG Group 2009
## 227 IG Group 2010
## 228 IG Group 2011
## 229 Inchcape 2009
## 230 Inchcape 2010
## 231 Inchcape 2011
## 232 Informa 2009
## 233 Informa 2010
## 238 Inmarsat 2009
## 239 Inmarsat 2010
## 240 Inmarsat 2011
## 241 InterContinental Hotels 2009
## 242 InterContinental Hotels 2010
## 243 InterContinental Hotels 2011
## 244 International Power 2009
## 245 International Power 2010
## 246 International Power 2011
## 247 Intertek 2009
## 248 Intertek 2010
## 249 Intertek 2011
## 250 Invensys 2009
## 251 Invensys 2010
## 252 Invensys 2011
## 253 Investec 2009
## 254 Investec 2010
## 255 Investec 2011
## 256 ITV 2009
## 257 ITV 2010
## 258 ITV 2011
## 259 Johnson Matthey 2009
## 260 Johnson Matthey 2010
## 261 Johnson Matthey 2011
## 262 KCOM Group 2009
## 263 KCOM Group 2010
## 264 Keller Group 2009
## 265 Keller Group 2010
## 266 Keller Group 2011
## 267 Kier Group 2009
## 268 Kier Group 2010
## 269 Kier Group 2011
## 270 KSK Power Ventur 2009
## 271 Ladbrokes 2009
## 272 Ladbrokes 2010
## 273 Land Securities 2009
## 274 Land Securities 2010
## 275 Land Securities 2011
## 276 Legal & General Group 2009
## 277 Legal & General Group 2010
## 278 Legal & General Group 2011
## 279 Liberty International 2009
## 280 Liberty International 2010
## 281 Lloyds Banking Group 2009
## 282 Lloyds Banking Group 2010
## 283 Lloyds Banking Group 2011
## 284 Logica 2009
## 285 Logica 2010
## 286 Logica 2011
## 287 Majestic Wine 2009
## 288 Man 2009
## 289 Man 2010
## 290 Man 2011
## 291 Marks & Spencer 2009
## 292 Marks & Spencer 2010
## 293 Marstons 2009
## 294 Marstons 2010
## 295 Marstons 2011
## 298 Meggitt 2009
## 299 Meggitt 2010
## 300 Meggitt 2011
## 301 Micro Focus International 2009
## 302 Micro Focus International 2010
## 303 Millennium & Copthorne 2009
## 304 Millennium & Copthorne 2010
## 305 Millennium & Copthorne 2011
## 306 Misys 2009
## 307 Misys 2010
## 308 Misys 2011
## 309 Mitchells & Butlers 2009
## 310 Mitchells & Butlers 2010
## 311 Mitchells & Butlers 2011
## 312 Morgan Sindall 2009
## 313 Morgan Sindall 2010
## 314 Morgan Sindall 2011
## 315 Morrison (Wm) 2009
## 316 Morrison (Wm) 2010
## 317 Morrison (Wm) 2011
## 318 Mothercare 2009
## 319 Mothercare 2010
## 321 Mucklow (A&J) 2009
## 358 QinetiQ Group 2009
## 360 QinetiQ Group 2011
## 362 Redrow 2009
## 375 Rolls-Royce 2009
## 416 Sports Direct 2009
## 433 Taylor Wimpey 2009
## 454 Ultra Electronics 2009
## 500 AMEC 2010
## 501 AMEC 2011
## 502 ASDA 2010
## 503 ASDA 2011
## 504 BASF 2010
## 505 BASF 2011
## 507 Cable & Wireless Worldwide 2010
## 508 Cable & Wireless Worldwide 2011
## 509 Cairn Energy 2010
## 510 Cairn Energy 2011
## 511 Co-operative Group 2010
## 513 E.on UK 2010
## 514 E.on UK 2011
## 515 EDF Energy 2010
## 516 EDF Energy 2011
## 517 Gala Coral 2010
## 518 Glanbia 2010
## 519 Glanbia 2011
## 522 Ineos 2010
## 523 Ineos 2011
## 524 John Lewis Partnership 2010
## 525 Kerry Group 2010
## 526 Kerry Group 2011
## 527 npower 2010
## 528 npower 2011
## 529 Punch Taverns 2010
## 530 Punch Taverns 2011
## 533 ROK 2010
## 534 Savills 2010
## 535 Syngenta 2010
## 536 Syngenta 2011
## 537 Talk Talk 2010
## 538 Talk Talk 2011
## 552 Essar Energy 2011
## 553 Euromoney Institutional Inv. 2011
## 554 Filtrona 2011
## 559 Iceland 2011
Use the mean return on assests in the industry as a measure of how competitive it is. The higher the ROA, the less competitive. The hypothesis is that reputation more important in the most competitive industries (ie, those with lowest mean ROA). That implies a negative interation between the effect of reputation score (Total) and meanROA.
meanROA <- ddply(dta.merge, .(Industry), summarize, meanROA = mean(ROA, na.rm = TRUE))
dta.merge2 <- merge(dta.merge, meanROA, by = "Industry", all = TRUE)
m2 <- lmer(ROA ~ Total * meanROA + (1 + Total | Industry) + (1 | Company) + (1 | Year), data = dta.merge2)
m2.ss <- lmer(ROA ~ Total * meanROA + (1 + Total | Industry) + (1 | Company) + (1 | Year), data = dta.merge2,
subset = ss)
ef2 <- effect("Total:meanROA", m2)
plot(ef2)
