COVID-19 short-term forecasts Deaths 2020-10-06


General information

  • Forecasts produced by Jennie Castle, Jurgen Doornik, and David Hendry, researchers at the University of Oxford. These are our forecasts, and should not be considered official forecasts from, or endorsed by, any of: University of Oxford, Oxford Martin School, Nuffield College, or Magdalen College.
  • These forecasts are short term time-series extrapolations of the data. They are not based on epidemiological modelling or simulations. All forecasts are uncertain: their success can only be determined afterwards. Many mitigation strategies are in place, which, if successful, invalidate our forecasts. An explanation of our methods is provided below.
  • A list of notes is below. The most recent note:
    [2020-07-01] Modified the short-term model to allow for (slowly changing) seasonality. Many countries show clear seasonality after the initial period, likely caused by institutional factors regarding data collection. This seasonality was also getting in the way of peak detection. As a consequence estimates of the peak date may have changed for countries with strong seasonality.
    Added forecasts of cumulative confirmed cases for lower tier local authorities of England. The data is available from 2020-07-02 including all tests (pillar one and two). Only authorities with more than 5 cases in the previous week are included.

Peak increase in estimated trend of Deaths in Europe 2020-10-06

UKEUATBEBGBSCZDEDKESFIFRGRHRHUIEITNLPLPTROSENOCH
Peak date (mm-dd)04-1006-1909-0708-1508-2709-24 --04-1508-1006-1904-2109-1810-01 --10-0207-2308-1509-26 --07-05 --09-0108-1406-16
Peak daily increment 964 805 5 9 9 1 226 1 914 30 60 6 14 4 127 30 7 4 3 7
Days since peak 179 109 29 52 40 12 174 57 109 168 18 5 4 75 52 10 93 35 53 112
Last total 42445 150035 822 10092 862 294 794 9566 663 32486 346 32140 420 304 853 1811 36030 6482 2717 2032 5121 5883 275 2081
Last daily increment 76 612 4 14 8 6 36 12 4 261 0 44 3 4 20 1 28 28 58 14 73 -12 0 3
Last week 302 2377 23 76 37 14 139 71 13 695 2 371 29 24 88 7 136 76 204 61 296 -10 1 7
Previous peak date --04-0604-0604-1506-0504-11 -- --04-0403-31 --04-08 -- --04-1904-2403-2904-0404-2404-1505-0204-1204-0704-06
Previous peak daily increment 3095 20 328 5 7 15 946 943 13 167 781 153 26 31 25 98 8 60
Low between peaks -892 0 2 2 -2 0 -1351 7 0 0 6 -6 3 -5 0 1

Peak increase in estimated trend of Deaths 2020-10-06

AustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-DCUS-DEUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NDUS-NEUS-NHUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-SDUS-TNUS-TXUS-UTUS-VAUS-WAUS-WIUS-WV
Peak date (mm-dd)09-0307-2105-0607-1708-2109-1209-23 -- --07-2309-1405-2907-2209-2408-0409-1609-1507-2108-0609-0507-1309-0906-2308-0708-2208-2709-0905-1208-15 --09-0308-0908-2004-2909-0905-2810-0208-26 -- --05-2005-2906-2505-1308-1308-3108-2908-2207-2805-0507-28 -- --07-2710-0209-1508-06 --09-02
Peak daily increment 36 1065 168 785 322 1150 118 2947 168 171 323 68 1077 97 127 78 138 7 9 1 46 175 66 10 20 112 12 9 36 106 56 38 23 23 31 40 25 1566 9 18 26 92 10 5 137 45 386 6 72 13 5
Days since peak 33 77 153 81 46 24 13 75 22 130 76 12 63 20 21 77 61 31 85 27 105 60 45 40 27 147 52 33 58 47 160 27 131 4 41 139 130 103 146 54 36 38 45 70 154 70 71 4 21 61 34
Last total 897 147494 9582 13070 27017 104555 11374 27419 82348 32834 5865 21559 17103 8553 210886 2580 1469 5712 16244 2081 4521 631 646 14767 7055 1413 492 8836 3484 701 1218 5402 9531 3957 7080 2087 2063 3027 3670 280 506 446 16147 894 1629 33192 4947 1066 581 8223 3471 248 2584 16528 399 3288 2161 1399 370
Last daily increment 2 819 22 33 173 986 121 227 471 92 25 184 87 55 705 21 22 6 73 12 4 0 1 55 34 15 5 31 30 3 4 6 7 5 22 4 18 14 33 3 4 3 9 0 6 5 16 11 9 16 15 0 23 91 6 15 8 18 3
Last week 9 3542 236 329 1019 5877 634 1250 4702 438 361 929 369 358 3954 40 100 63 359 30 13 4 10 450 201 55 23 164 79 32 44 81 81 18 77 51 119 58 138 34 28 7 25 17 29 63 143 35 22 93 93 25 161 512 22 83 39 72 15
Previous peak date -- -- -- -- --06-16 --03-20 -- --07-12 -- --04-1504-13 -- -- -- --04-2404-2004-29 -- --04-0705-21 -- --05-02 --04-1404-1404-25 --04-14 --04-30 -- -- -- -- --04-22 --04-1205-1804-2904-17 -- --04-29 -- -- -- --04-2204-0604-1004-23
Previous peak daily increment 1662 150 92 125 2226 72 105 11 44 14 99 10 64 459 137 17 317 10 3573 76 8 24 104 25 12 16
Low between peaks 388 20 16 534 2 3 1 12 3 5 4 12 -1 6 5 52 3 7 15 1 6 9 -17 0

Deaths count forecast Europe (bold red line in graphs) 2020-10-07 to 2020-10-13

DateUKEUATBEBGCZDEESFRGRHRHUITNLPLPTRO
2020-10-06 42445 150035 822 10092 862 794 9566 32486 32140 420 304 853 36030 6482 2717 2032 5121
2020-10-07 42550 150400 825 10110 868 824 9566 32610 32200 425 313 858 36050 6507 2749 2040 5148
2020-10-08 42610 150800 828 10120 870 855 9577 32720 32260 430 319 862 36070 6526 2779 2047 5187
2020-10-09 42670 151100 831 10130 880 883 9587 32820 32310 435 327 867 36090 6542 2810 2054 5239
2020-10-10 42730 151400 834 10140 882 905 9597 32920 32370 440 331 871 36110 6558 2841 2061 5281
2020-10-11 42780 151700 837 10160 886 926 9604 33020 32430 444 338 876 36130 6570 2873 2068 5323
2020-10-12 42800 152100 840 10170 895 959 9619 33110 32480 449 341 880 36140 6577 2905 2075 5361
2020-10-13 42870 152400 843 10180 901 995 9628 33210 32540 454 344 885 36160 6597 2938 2081 5424

Deaths count forecast (bold red line in graphs) 2020-10-07 to 2020-10-13

DateBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MIUS-MNUS-MOUS-MSUS-NCUS-NDUS-NEUS-NJUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-SDUS-TNUS-TXUS-UTUS-VAUS-WAUS-WI
2020-10-06 147494 9582 13070 27017 104555 11374 27419 82348 32834 5865 21559 17103 8553 210886 2580 1469 5712 16244 2081 14767 7055 1413 492 8836 3484 701 1218 5402 9531 7080 2087 2063 3027 3670 280 506 16147 1629 33192 4947 1066 581 8223 3471 248 2584 16528 399 3288 2161 1399
2020-10-07 148300 9603 13090 27200 106000 11480 27610 82350 32940 5897 21620 17200 8611 211800 2604 1491 5752 16390 2081 14930 7110 1418 495 8846 3487 717 1221 5419 9546 7087 2093 2082 3057 3708 288 506 16160 1644 33200 4974 1077 582 8250 3497 248 2593 16630 401 3308 2172 1399
2020-10-08 149200 9624 13180 27370 107000 11590 27750 83050 33040 5934 21780 17300 8669 212600 2613 1512 5775 16460 2084 15060 7150 1424 497 8872 3501 718 1236 5427 9561 7095 2103 2101 3066 3750 297 516 16160 1647 33210 4991 1082 583 8263 3514 258 2630 16720 404 3328 2176 1413
2020-10-09 149400 9644 13230 27530 108000 11700 27870 83760 33140 5971 21940 17340 8726 213400 2614 1532 5794 16540 2087 15160 7190 1435 500 8910 3515 732 1243 5451 9576 7104 2112 2118 3081 3780 305 517 16170 1653 33220 5055 1091 585 8280 3525 261 2652 16810 406 3346 2188 1418
2020-10-10 150400 9664 13290 27680 108900 11810 27950 84260 33240 6010 22100 17380 8783 214000 2628 1552 5809 16600 2091 15230 7220 1437 503 8936 3526 732 1249 5451 9590 7112 2123 2137 3092 3799 314 520 16180 1660 33230 5066 1098 591 8296 3549 268 2684 16880 408 3366 2188 1427
2020-10-11 150800 9684 13340 27840 109800 11910 28050 84420 33340 6048 22190 17410 8840 214300 2629 1572 5809 16620 2096 15250 7242 1440 506 8949 3530 732 1252 5475 9605 7121 2128 2155 3094 3804 322 521 16180 1663 33240 5066 1099 592 8307 3557 268 2695 16890 410 3386 2188 1437
2020-10-12 151000 9704 13390 28000 110600 12020 28150 87410 33440 6088 22280 17470 8897 214600 2630 1592 5809 16630 2098 15260 7257 1451 508 8960 3538 738 1255 5483 9620 7130 2132 2174 3094 3804 331 524 16190 1663 33240 5067 1101 593 8318 3560 268 2712 16960 413 3405 2197 1441
2020-10-13 151800 9724 13430 28160 111600 12130 28260 87590 33540 6127 22450 17560 8955 215400 2648 1612 5814 16730 2107 15340 7293 1466 511 8988 3563 744 1260 5488 9635 7139 2136 2192 3112 3843 341 529 16200 1668 33250 5092 1112 601 8331 3577 268 2736 17050 415 3425 2210 1456

Deaths count average forecast Europe (bold black line in graphs) 2020-10-07 to 2020-10-13

DateUKEUATBEBGCZDEESFRGRHRHUITNLPLPTRO
2020-10-06 42445 150035 822 10092 862 794 9566 32486 32140 420 304 853 36030 6482 2717 2032 5121
2020-10-07 42500 150500 826 10110 871 823 9578 32630 32200 425 309 866 36050 6500 2753 2042 5170
2020-10-08 42550 150900 829 10120 875 845 9590 32730 32250 429 313 877 36070 6515 2782 2049 5206
2020-10-09 42600 151200 832 10130 883 868 9600 32830 32300 434 319 888 36090 6529 2810 2056 5248
2020-10-10 42640 151500 835 10130 887 889 9609 32920 32360 440 321 899 36110 6545 2839 2063 5285
2020-10-11 42690 151800 839 10140 892 908 9616 33020 32410 444 326 910 36130 6556 2869 2070 5322
2020-10-12 42730 152200 842 10150 899 932 9625 33120 32460 450 327 922 36150 6564 2899 2077 5353
2020-10-13 42790 152500 845 10160 905 958 9635 33210 32510 455 329 934 36170 6578 2929 2084 5395

Deaths count average forecast (bold black line in graphs) 2020-10-07 to 2020-10-13

DateBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MIUS-MNUS-MOUS-MSUS-NCUS-NDUS-NEUS-NJUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-SDUS-TNUS-TXUS-UTUS-VAUS-WAUS-WI
2020-10-06 147494 9582 13070 27017 104555 11374 27419 82348 32834 5865 21559 17103 8553 210886 2580 1469 5712 16244 2081 14767 7055 1413 492 8836 3484 701 1218 5402 9531 7080 2087 2063 3027 3670 280 506 16147 1629 33192 4947 1066 581 8223 3471 248 2584 16528 399 3288 2161 1399
2020-10-07 148200 9607 13110 27210 105600 11490 27600 83280 32930 5917 21720 17170 8611 211700 2598 1490 5726 16320 2086 14910 7087 1426 496 8868 3503 712 1223 5411 9544 7092 2099 2078 3039 3702 286 509 16150 1634 33200 4971 1076 585 8246 3485 249 2609 16640 402 3301 2165 1417
2020-10-08 148900 9630 13180 27360 106500 11600 27720 83880 33030 5970 21870 17250 8673 212300 2606 1509 5746 16390 2089 15050 7125 1432 499 8893 3516 716 1233 5421 9558 7102 2109 2098 3049 3741 294 515 16160 1637 33210 4985 1081 587 8260 3502 256 2639 16730 404 3317 2168 1432
2020-10-09 149300 9658 13230 27550 107500 11700 27810 84490 33120 6022 22010 17300 8735 212900 2611 1527 5764 16470 2093 15150 7163 1442 502 8926 3529 728 1240 5439 9573 7111 2118 2119 3064 3772 301 518 16160 1643 33220 5046 1090 589 8276 3515 259 2662 16820 407 3333 2178 1439
2020-10-10 150200 9680 13290 27730 108500 11800 27890 85010 33210 6079 22160 17360 8797 213300 2621 1546 5780 16530 2096 15230 7193 1446 505 8953 3540 732 1246 5445 9587 7121 2130 2139 3075 3794 308 521 16160 1650 33230 5055 1097 594 8291 3535 264 2690 16890 409 3348 2178 1450
2020-10-11 150600 9700 13340 27890 109400 11900 27970 85380 33310 6136 22270 17410 8859 213500 2627 1566 5792 16550 2100 15260 7223 1451 508 8967 3544 735 1251 5463 9602 7131 2134 2160 3080 3804 313 523 16170 1653 33230 5056 1101 596 8303 3546 266 2706 16930 411 3364 2178 1456
2020-10-12 151000 9721 13390 28060 110400 12000 28070 86390 33410 6188 22370 17480 8923 213700 2632 1585 5803 16590 2103 15300 7249 1458 511 8980 3551 743 1255 5473 9617 7141 2136 2181 3083 3816 318 526 16170 1656 33240 5056 1104 597 8316 3556 268 2724 16990 413 3380 2182 1461
2020-10-13 151800 9744 13440 28210 111400 12120 28160 86970 33500 6241 22510 17560 8986 214300 2644 1605 5819 16720 2107 15400 7286 1469 514 9001 3570 751 1261 5483 9632 7150 2140 2203 3108 3856 325 530 16170 1663 33250 5072 1114 602 8329 3574 269 2746 17080 415 3395 2195 1472

Deaths count scenario forecast (bold purple line in graphs) 2020-10-07 to 2020-10-15

DateUKEUATBEBGCZDEESFRGRHRHUITNLPLPTROBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MIUS-MNUS-MOUS-MSUS-NCUS-NDUS-NEUS-NJUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-SDUS-TNUS-TXUS-UTUS-VAUS-WAUS-WI
2020-10-06 42445 150035 822 10092 862 794 9566 32486 32140 420 304 853 36030 6482 2717 2032 5121 147494 9582 13070 27017 104555 11374 27419 82348 32834 5865 21559 17103 8553 210886 2580 1469 5712 16244 2081 14767 7055 1413 492 8836 3484 701 1218 5402 9531 7080 2087 2063 3027 3670 280 506 16147 1629 33192 4947 1066 581 8223 3471 248 2584 16528 399 3288 2161 1399
2020-10-07 42500 150300 824 10100 864 816 9569 32520 32180 426 307 856 36040 6482 2722 2033 5128 148100 9586 13120 27190 105400 11470 27530 82440 32910 5914 21600 17170 8613 211600 2587 1485 5738 16330 2081 14890 7085 1413 493 8861 3484 714 1225 5416 9547 7080 2095 2094 3038 3707 290 511 16150 1633 33200 4966 1072 581 8240 3487 251 2591 16610 402 3301 2166 1404
2020-10-08 42550 150700 826 10120 870 838 9574 32650 32230 430 310 868 36050 6483 2739 2040 5176 148600 9614 13170 27340 106300 11570 27690 82860 32990 5959 21750 17230 8667 212500 2593 1501 5753 16390 2081 14990 7112 1415 496 8883 3495 725 1230 5426 9556 7088 2103 2116 3047 3732 296 516 16160 1637 33220 4983 1076 582 8251 3502 255 2608 16680 406 3312 2171 1407
2020-10-09 42570 151100 830 10130 875 860 9580 32740 32290 435 313 879 36070 6492 2766 2047 5206 149200 9641 13210 27500 107000 11650 27750 83080 33060 6004 21810 17290 8715 213100 2598 1518 5769 16470 2084 15070 7136 1422 498 8908 3505 733 1234 5435 9568 7099 2109 2140 3056 3766 302 522 16160 1641 33230 4999 1081 585 8261 3516 258 2623 16760 411 3324 2175 1411
2020-10-10 42600 151400 832 10130 880 882 9586 32840 32330 438 317 891 36070 6492 2796 2059 5243 149700 9662 13260 27620 107600 11730 27910 83490 33120 6045 21860 17340 8759 213800 2600 1531 5785 16530 2086 15150 7160 1428 500 8935 3517 740 1238 5444 9576 7104 2115 2167 3065 3796 309 528 16160 1645 33250 5014 1084 588 8271 3530 261 2642 16830 415 3333 2179 1415
2020-10-11 42610 151700 835 10150 885 904 9592 32940 32370 442 319 903 36080 6498 2822 2068 5250 150200 9679 13300 27730 108400 11800 28030 83670 33190 6080 21940 17390 8808 214600 2606 1544 5802 16590 2088 15200 7180 1434 502 8961 3527 746 1242 5453 9584 7110 2119 2190 3073 3820 315 535 16170 1648 33260 5027 1088 590 8280 3542 264 2660 16900 420 3343 2183 1419
2020-10-12 42640 152100 836 10150 889 927 9597 33030 32410 445 323 912 36090 6504 2840 2075 5271 150800 9696 13340 27840 108800 11870 28150 83850 33250 6119 21970 17430 8847 215100 2609 1556 5821 16630 2091 15250 7196 1440 503 8985 3538 756 1246 5461 9593 7114 2127 2215 3082 3838 320 543 16170 1651 33270 5040 1090 592 8289 3555 267 2676 16970 424 3352 2186 1423
2020-10-13 42650 152400 838 10160 894 950 9601 33110 32430 448 326 921 36090 6510 2860 2081 5296 151200 9705 13390 27960 109300 11930 28280 84140 33300 6150 22000 17470 8887 215900 2612 1566 5838 16680 2092 15300 7208 1445 505 9012 3547 765 1250 5470 9600 7118 2131 2242 3090 3865 326 550 16170 1655 33280 5056 1093 593 8299 3567 270 2692 17030 428 3360 2189 1433
2020-10-14 42650 152600 840 10170 898 970 9604 33190 32450 451 330 934 36090 6515 2879 2086 5308 151600 9705 13430 28030 109900 12000 28320 84400 33350 6186 22010 17520 8926 216600 2615 1575 5854 16730 2093 15340 7220 1450 506 9036 3555 773 1252 5475 9607 7121 2136 2260 3097 3885 331 558 16180 1658 33290 5071 1095 596 8307 3580 272 2708 17090 432 3368 2192 1439
2020-10-15 42650 152900 842 10170 901 995 9609 33260 32460 454 333 942 36090 6523 2897 2092 5341 151900 9705 13470 28120 110600 12060 28490 84660 33400 6215 22020 17550 8955 217100 2618 1585 5867 16770 2093 15370 7232 1452 507 9058 3564 781 1256 5481 9612 7124 2143 2298 3104 3906 337 564 16180 1660 33300 5076 1097 597 8316 3590 275 2723 17150 435 3375 2194 1443

Further information

  • We believe these forecasts fill a useful gap in the short run. They give an indication of what is likely to happen in the next few days, removing some aspect of surprise. Moreover, a noticeable drop in comparison to the extrapolations could be an indication that the implemented policies are having some impact. It is difficult to understand exponential growth. We hope that these forecasts may help to convince viewers to adhere to the policies implemented by their respective governments, and keep all arguments factual and measured.
  • We use the data repository for the 2019 Novel Coronavirus Visual Dashboard operated by the Johns Hopkins University Center for Systems Science and Engineering. This is updated daily, but we tend to update our forecasts only every other day.
    US state data as of 2020-03-28 is courtesy of the New York Times.
  • We can only provide forecasts of what is measured. If confirmed cases are an underestimate of actual cases, then our forecasts will also be underestimates. No other epidemiological data is used. Data definition and collection differs between countries and may change over time.
  • We will update the methodology as we learn what is happening in the next few days or weeks. Once the number of cases levels off, there is no need to provide these forecasts anymore.
  • Countries where the counts are very low or stable have been omitted.
  • The graphs have dates on the horizontal axis (yyyy-mm-dd) and cumulative counts on the vertical axis. They show
    1. bold dark grey line (with circles): observed counts (Johns Hopkins CSSE);
    2. many light grey lines (with open circles): forecasts using different model settings and starting up to four periods back;
    3. red line (with open circles): single forecasts path using default model settings;
    4. black line (with crosses): average of all forecasts, recentered on the last observation;
    5. thin green lines: some indication of uncertainty around the red forecasts, but we do not know how reliable that is.
    Both the red line forecasts and the black lines are also given in the tables above. These forecasts differ, we are currently inclined to use the average forecasts.
  • The forecasts are constructed as follows:
    1. An overall `trend' is extracted by taking a window of the data at a time. In each window we draw `straight lines' which are selected using an automatic econometric procedure (`machine learning'). All straight lines are collected and averaged, giving the trend.
    2. Forecasts are made using the estimated trend, but we note that this must be done carefully, because simply extrapolating the flexible insample trend would lead to wildly fluctuating forecast. We use the `Cardt' method, which has been found to work well in other settings.
    3. Residuals from the trend are also forecast, and combined with trend forecasts into an overall forecast.
  • Scenario forecasts are constructed very differently: smooth versions of the Chinese experience are matched at different lag lengths with the path of each country. This probably works best from the peak, or the slowdown just before (but we include it for the UK nonetheless).
  • The forecast evaluation shows past forecasts, together with the outcomes (in the grey line with circles).
  • EU-BS is Estonia, Latvia, and Lithuania together.
  • This paper describes the methodology and gives further references. Also available as Nuffield Economics Discussion Paper 2020-W06. Still preliminary is the documentation of the medium term forecasts.

Recent changes and notes

[2020-07-01] Modified the short-term model to allow for (slowly changing) seasonality. Many countries show clear seasonality after the initial period, likely caused by institutional factors regarding data collection. This seasonality was also getting in the way of peak detection. As a consequence estimates of the peak date may have changed for countries with strong seasonality.
Added forecasts of cumulative confirmed cases for lower tier local authorities of England. The data is available from 2020-07-02 including all tests (pillar one and two). Only authorities with more than 5 cases in the previous week are included.
[2020-06-29] Tables in April included the world, but not the world as we know it (double counting China and the US). So removed the world from those old tables.
Why short-term forecasts can be better than models for predicting how pandemics evolve just appeared at The Conversation.
Thursday 2 July webinar at the FGV EESP - São Paolo School of Economics. This starts at 16:00 UK time (UTC+01:00) and streamed here.
[2020-06-24] Research presentation on short-term COVID-19 forecasting on 26 June (14:00 UK time) at the Quarterly Forecasting Forum of the IIF UK Chapter.
[2020-06-06] Removed Brazil from yesterday's forecasts (only; last observation 2020-06-05).
[2020-06-04] Data issues with confirmed cases for France.
Added an appendix to the short term paper with further forecast comparisons for European and Latin American countries.
Both Sweden and Iran have lost their peak in confirmed cases. For Sweden the previous peak was on 24 April (daily peak of 656 cases), for Iran it was on 31 March (peak of 3116). For Iran this looks like a second wave, with increasing daily counts for the last four weeks. For Sweden this is a sudden jump in confirmed cases in the last two days, compared to a fairly steady weekly pattern over the previous six weeks.
[2020-05-20] Problem with UK confirmed cases: negative daily count. This makes the forecasts temporarily unreliable.
Updated the second paper.
[2020-05-18] Minor fixes to the improved version of scenario forecasting, backported to 2020-05-13.
[2020-05-13] We now omit countries with fewer than 200 confirmed cases in the last week (25 for deaths).
The short-term paper has some small updates, including further comparisons with other models.
Data for Ecuador are not reliable enough for forecasting.
Switched to an improved version of scenario forecasting.
[2020-05-06] The New York Times is in the process of redefining its US state data. Unfortunately, at the moment only the last observation has changed (e.g New York deaths jumped from 19645 on 2020-05-05 to 25956 a day later). This means the data is currently useless; however it does bring it close to the Johns Hopkins/CSSE count (25626 on 2020-05-06). The aggregate US count is based on JH/CSSE so unaffected. We now use Johns Hopkins/CSSE US state data, including all states with sufficient counts. So the new forecasts cannot be compared to those previously.
A minor change is that we show the graph without scenario forecast if no peak has been detected yet.
[2020-04-29] See our blog entry at the International Institute of Forecasters.
US history of death counts revised in Johns Hopkins/CSSE data.
UK death counts have been revised to include the deaths in care homes. In the Johns Hopkins/CSSE data set, which we use, the entire history has been revised. So forecasts made up to 2020-04-29 cannot be compared to later outcomes. In the ECDC data set only the last observation has changed, causing a jump in the series.
[2020-04-27] Our short-term COVID-19 forecasting paper is now available as Nuffield Economics Discussion Paper 2020-W06.
A small adjustment has been made to the scenario forecast methodology, and will be documented shortly.
[2020-04-24] A summary of our work on short-term COVID-19 forecasting appeared as a voxeu.
[2020-04-17] Bird and Nielsen look into nowcasting death counts in England.
[2020-04-16] Added scenario forecasts to all graphs now. This would now be the preferred forecast for most.
This is the first time with a peak in confirmed UK cases (also for deaths, but this is uncertain because it is at the same date).
[2020-04-10] Updated documentation with better description of short-term estimates and peak determination.
[2020-04-09] Added table with estimated peak dates (if happened) and dates to and since the peak. Note that this can be a local peak, and subsequent re-acceleration (or data revisions) can result in a new peak later.
[2020-04-08] Minor correction to peak estimates. Added table with scenario forecasts.
[2020-04-06] Added a post hoc estimate of the peak number of cases. This needs at least three confirmed observations (four for deaths) after the event. It is based on the averaged smooth trend, and can change later or be a local peak. It is marked with a vertical line with the date label, or a date with left arrow in the bottom left corner of the graph. This is backported to 2020-04-04.
[2020-04-02] Now including more US States, based on New York Times data.
[2020-03-31] Scenario forecasts, based on what happened in China earlier this year, are presented for several countries (line marked with x). Created more plausible 90% confidence bands (dotted line in same colour).
[2020-03-26] Scenario forecasts that are based on what happened in China earlier this year, only for Italy.
[2020-03-24] Our forecasts are starting to overestimate in some cases. This was always expected to happen when the increase starts to slow down. Scenario forecasts that are based on what happened in China earlier this year, but only for Italy and Spain sofar.

Initial visual evaluation of forecasts of Deaths