COVID-19 short-term forecasts Deaths 2020-08-29


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 2020-08-29

UKEUATBEBGBSCZDEDKESFIFRGRHUIEITNLPLPTROSENOCH
Peak date04-1004-0604-0604-15 --04-1104-0804-1504-0403-3104-2104-0804-0304-1904-2403-2904-0404-2504-15 --04-1204-0704-06
Peak daily increment 964 3096 20 328 7 10 226 15 946 30 943 5 13 167 781 153 23 31 98 8 60
Days from 100 to peak 23 33 7 22 0 0 22 3 18 1 23 -11 6 21 25 15 19 17 18 -2 14
Days from peak/2 to peak 17 23 16 21 22 13 22 15 14 20 18 18 26 22 20 16 31 23 21 20 19
Last total 41498 139624 733 9891 605 274 421 9299 624 29011 335 30460 260 614 1777 35473 6224 2032 1818 3539 5821 264 2005
Last daily increment 12 76 0 5 2 0 2 9 0 0 0 0 1 0 0 1 4 14 3 32 0 0 1
Last week 69 715 1 -101 60 3 9 24 2 173 1 78 18 1 0 36 24 77 22 267 5 0 4
Days since peak 141 145 145 136 140 143 136 147 151 130 143 148 132 127 153 147 126 136 139 144 145

Peak increase in estimated trend of Deaths 2020-08-29

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-NEUS-NHUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-UTUS-VAUS-WAUS-WIUS-WV
Peak date08-1707-2905-0607-1708-2306-16 --07-2906-2407-23 --05-2907-2204-1504-1407-22 --07-2108-0804-2404-2004-2906-2307-30 --05-21 --05-1205-0204-12 --04-1404-2504-2904-1405-2804-3007-3108-0105-2005-2906-2505-1308-1904-09 -- --07-2805-0507-29 --07-2704-1704-2204-0604-1104-23
Peak daily increment 15 1082 168 785 652 1662 214 683 2947 171 323 125 2230 24 78 136 72 105 11 46 174 14 112 99 6 64 459 56 137 23 17 28 27 40 25 1566 9 18 999 5 137 46 391 6 104 25 12 16
Days from 100 to peak 91 123 36 93 133 72 146 79 107 48 84 18 29 100 100 133 21 18 10 60 119 27 41 28 -9 17 23 22 17 41 21 109 110 0 17 85 16 129 20 89 32 104 115 -45 7 15 2 -89
Days from peak/2 to peak 147 114 37 63 113 52 146 72 78 49 76 20 20 113 108 135 27 20 30 74 119 50 44 32 17 21 20 27 18 56 35 122 122 30 31 81 41 145 15 131 33 119 111 18 11 30 18 4
Last total 611 120262 9161 11181 19063 63498 7261 21359 63819 28471 3419 16977 13981 6284 182761 2059 772 5006 12894 1942 4465 605 604 11105 5447 1100 358 8008 3066 449 921 4741 9030 3734 6637 1814 1459 2427 2683 391 432 15933 769 1302 32938 4252 797 454 7656 2698 1694 12607 335 2568 1901 1119 215
Last daily increment 11 758 6 49 297 948 92 110 673 194 94 111 238 39 961 42 16 29 89 5 0 0 0 148 99 -8 5 11 8 4 3 0 12 15 0 4 25 14 31 1 0 3 2 15 4 147 11 7 14 43 25 70 0 18 0 6 14
Last week 94 5518 42 329 1747 5956 581 716 3339 1018 421 636 922 163 5961 115 85 236 741 24 5 1 4 780 430 63 51 128 63 23 49 136 115 55 53 47 72 187 152 13 3 -13 24 105 55 274 71 37 99 194 153 911 16 101 42 38 36
Days since peak 12 31 115 43 6 74 31 66 37 92 38 136 137 38 39 21 127 131 122 67 30 100 109 119 139 137 126 122 137 93 121 29 28 101 92 65 108 10 142 32 116 31 33 134 129 145 140 128

Deaths count forecast Europe (bold red line in graphs) 2020-08-30 to 2020-09-05

DateUKEUBGDEESFRITNLPLPTRO
2020-08-29 41498 139624 605 9299 29011 30460 35473 6224 2032 1818 3539
2020-08-30 41500 139800 605 9306 29030 30470 35480 6226 2038 1821 3581
2020-08-31 41510 139900 620 9307 29050 30480 35480 6228 2043 1824 3622
2020-09-01 41520 140000 629 9311 29070 30490 35490 6231 2057 1827 3663
2020-09-02 41540 140100 641 9316 29090 30490 35490 6239 2073 1830 3703
2020-09-03 41550 140200 646 9322 29110 30500 35500 6243 2087 1833 3744
2020-09-04 41560 140400 654 9325 29130 30510 35500 6246 2096 1836 3785
2020-09-05 41570 140500 656 9332 29150 30520 35500 6249 2108 1839 3826

Deaths count forecast (bold red line in graphs) 2020-08-30 to 2020-09-05

DateAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WIUS-WV
2020-08-29 611 120262 9161 11181 19063 63498 7261 21359 63819 28471 3419 16977 13981 6284 182761 2059 772 5006 12894 1942 11105 5447 1100 358 8008 3066 449 921 4741 9030 3734 6637 1814 1459 2427 2683 769 1302 32938 4252 797 454 7656 2698 1694 12607 2568 1901 1119 215
2020-08-30 626 121300 9167 11240 19360 64450 7398 21480 64320 28640 3509 17070 14150 6316 183600 2059 784 5060 13030 1944 11280 5554 1101 358 8016 3078 449 922 4816 9044 3742 6647 1822 1468 2437 2695 773 1314 32950 4363 800 454 7670 2722 1706 12910 2581 1911 1125 215
2020-08-31 640 121800 9173 11310 19640 65380 7522 21590 64600 28800 3600 17120 14310 6346 184000 2069 795 5060 13110 1945 11340 5663 1110 361 8023 3082 452 932 4829 9060 3749 6657 1827 1477 2445 2701 777 1318 32950 4462 805 455 7670 2732 1727 12930 2594 1921 1125 215
2020-09-01 655 123000 9179 11350 19930 66300 7665 21710 65250 28960 3693 17240 14470 6376 185200 2084 807 5072 13250 1952 11530 5771 1123 372 8050 3101 454 943 4854 9075 3757 6666 1834 1486 2499 2736 781 1345 32960 4573 823 464 7693 2760 1765 13120 2607 1931 1134 217
2020-09-02 670 124100 9185 11380 20200 67220 7796 21820 65870 29110 3789 17350 14630 6405 186400 2094 818 5179 13400 1953 11680 5884 1132 380 8079 3117 463 950 4883 9090 3765 6675 1848 1495 2549 2770 785 1366 32970 4707 842 470 7723 2797 1785 13350 2619 1941 1142 221
2020-09-03 685 125100 9191 11480 20480 68140 7952 21940 66400 29270 3887 17460 14790 6434 187400 2116 829 5210 13530 1957 11800 5998 1146 386 8101 3126 466 958 4905 9106 3772 6684 1857 1503 2572 2794 789 1390 32970 4821 857 474 7731 2845 1811 13580 2631 1951 1151 225
2020-09-04 700 125900 9197 11530 20760 69070 8095 22050 66880 29430 3988 17550 14950 6463 188400 2137 840 5242 13660 1964 11890 6115 1160 396 8122 3137 468 966 4939 9122 3780 6692 1862 1512 2587 2817 793 1405 32980 4943 866 481 7752 2876 1841 13770 2643 1960 1154 229
2020-09-05 715 126600 9203 11590 21050 70010 8240 22170 67510 29580 4092 17660 15110 6492 189300 2166 851 5283 13770 1970 12030 6234 1160 400 8131 3144 470 970 4939 9139 3787 6701 1866 1521 2605 2845 797 1422 32990 5057 880 486 7765 2917 1861 13850 2655 1970 1161 238

Deaths count average forecast Europe (bold black line in graphs) 2020-08-30 to 2020-09-05

DateUKEUBGDEESFRITNLPLPTRO
2020-08-29 41498 139624 605 9299 29011 30460 35473 6224 2032 1818 3539
2020-08-30 41500 139700 608 9300 29020 30470 35480 6224 2039 1820 3578
2020-08-31 41510 139800 619 9301 29050 30480 35490 6226 2047 1822 3618
2020-09-01 41520 140000 627 9305 29070 30480 35500 6228 2059 1825 3659
2020-09-02 41530 140100 637 9310 29090 30490 35500 6235 2073 1828 3699
2020-09-03 41540 140200 644 9316 29120 30500 35510 6240 2085 1831 3740
2020-09-04 41550 140300 651 9321 29140 30510 35520 6242 2096 1834 3781
2020-09-05 41560 140500 656 9328 29160 30530 35530 6246 2108 1837 3823

Deaths count average forecast (bold black line in graphs) 2020-08-30 to 2020-09-05

DateAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WIUS-WV
2020-08-29 611 120262 9161 11181 19063 63498 7261 21359 63819 28471 3419 16977 13981 6284 182761 2059 772 5006 12894 1942 11105 5447 1100 358 8008 3066 449 921 4741 9030 3734 6637 1814 1459 2427 2683 769 1302 32938 4252 797 454 7656 2698 1694 12607 2568 1901 1119 215
2020-08-30 625 120800 9165 11240 19320 64350 7382 21430 63910 28570 3469 17040 14060 6296 183100 2061 779 5020 12910 1943 11140 5518 1104 360 8017 3067 450 926 4783 9040 3736 6645 1820 1462 2432 2690 772 1305 32950 4279 805 454 7663 2710 1712 12680 2574 1905 1119 216
2020-08-31 639 121400 9171 11300 19580 65280 7507 21520 64170 28710 3549 17120 14170 6311 183500 2064 791 5035 12980 1945 11200 5592 1112 364 8028 3071 453 934 4806 9053 3743 6654 1824 1464 2441 2700 775 1311 32950 4307 815 455 7669 2724 1735 12720 2581 1911 1119 216
2020-09-01 654 122400 9177 11350 19830 66220 7650 21600 64800 28850 3630 17230 14310 6331 184400 2068 803 5060 13120 1950 11380 5706 1124 373 8053 3090 456 943 4834 9067 3750 6664 1832 1470 2491 2733 779 1335 32960 4358 831 460 7689 2753 1768 12900 2593 1920 1128 217
2020-09-02 669 123400 9183 11400 20110 67160 7786 21680 65320 28990 3712 17330 14440 6353 185300 2075 815 5133 13280 1952 11520 5796 1134 381 8079 3105 462 951 4864 9080 3757 6673 1846 1478 2538 2765 783 1355 32970 4443 849 465 7714 2786 1792 13110 2604 1926 1137 219
2020-09-03 685 124300 9189 11480 20340 68110 7923 21760 65940 29130 3796 17430 14570 6375 186100 2091 827 5170 13410 1956 11650 5901 1144 386 8100 3116 465 960 4893 9094 3764 6683 1855 1487 2560 2788 788 1380 32980 4514 864 470 7726 2827 1819 13310 2616 1936 1145 222
2020-09-04 701 125200 9195 11540 20670 69080 8060 21840 66460 29310 3882 17530 14710 6398 187000 2106 840 5205 13560 1961 11780 6009 1155 395 8120 3130 468 967 4929 9109 3771 6692 1861 1495 2579 2813 792 1399 32980 4587 875 475 7745 2861 1851 13600 2627 1949 1148 225
2020-09-05 717 126000 9201 11610 21010 70060 8201 21910 67100 29470 3970 17640 14850 6421 187700 2119 853 5252 13710 1966 11920 6128 1161 399 8134 3142 470 975 4946 9123 3778 6702 1868 1503 2604 2840 796 1418 32990 4657 889 479 7762 2897 1875 13770 2639 1957 1158 229

Deaths count scenario forecast (bold purple line in graphs) 2020-08-30 to 2020-09-07

DateUKEUBGDEESFRITNLPLPTROAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WIUS-WV
2020-08-29 41498 139624 605 9299 29011 30460 35473 6224 2032 1818 3539 611 120262 9161 11181 19063 63498 7261 21359 63819 28471 3419 16977 13981 6284 182761 2059 772 5006 12894 1942 11105 5447 1100 358 8008 3066 449 921 4741 9030 3734 6637 1814 1459 2427 2683 769 1302 32938 4252 797 454 7656 2698 1694 12607 2568 1901 1119 215
2020-08-30 41510 139800 613 9303 29030 30480 35490 6227 2037 1821 3571 625 121100 9167 11230 19410 64250 7324 21460 64160 28640 3478 17070 14090 6312 183900 2059 776 5040 13010 1943 11210 5489 1112 365 8026 3075 452 938 4802 9030 3736 6657 1824 1459 2449 2697 775 1318 32950 4252 806 454 7673 2709 1716 12840 2569 1919 1126 215
2020-08-31 41520 140000 621 9308 29050 30490 35490 6231 2046 1824 3604 640 121800 9171 11280 19790 65090 7396 21560 64390 28850 3533 17170 14200 6354 185100 2059 787 5070 13120 1946 11310 5543 1123 371 8043 3083 456 952 4850 9030 3743 6667 1833 1466 2471 2715 779 1334 32960 4264 812 457 7686 2733 1737 12970 2581 1920 1134 215
2020-09-01 41530 140000 627 9313 29050 30500 35500 6236 2053 1828 3640 655 122500 9176 11330 20180 65960 7491 21640 64630 28940 3603 17260 14290 6394 186400 2063 797 5093 13180 1947 11410 5592 1138 378 8061 3089 460 967 4891 9030 3749 6676 1840 1473 2487 2737 783 1348 32970 4276 822 461 7697 2756 1761 13070 2590 1928 1141 215
2020-09-02 41530 140200 632 9319 29050 30510 35510 6241 2058 1831 3683 670 123200 9181 11380 20540 66730 7577 21720 64910 28940 3675 17360 14380 6441 187900 2074 809 5121 13280 1950 11490 5651 1147 385 8075 3096 464 984 4956 9030 3754 6690 1848 1477 2511 2758 786 1363 32980 4288 831 465 7708 2777 1785 13180 2596 1939 1149 216
2020-09-03 41540 140300 639 9324 29050 30510 35510 6246 2063 1835 3725 684 123800 9184 11420 20860 67560 7653 21810 65110 28950 3730 17450 14460 6494 189400 2083 821 5155 13390 1950 11580 5719 1160 392 8090 3103 468 1003 5013 9030 3759 6703 1856 1480 2529 2776 789 1377 32990 4289 847 468 7719 2794 1807 13290 2604 1945 1156 218
2020-09-04 41550 140500 644 9331 29050 30520 35510 6250 2066 1838 3763 699 124300 9188 11470 21140 68300 7737 21880 65270 28950 3798 17550 14540 6548 190500 2092 833 5181 13430 1950 11660 5791 1169 399 8104 3108 471 1023 5068 9030 3762 6714 1865 1483 2551 2796 793 1391 33000 4294 858 471 7729 2813 1829 13370 2612 1955 1164 218
2020-09-05 41560 140500 650 9337 29050 30520 35510 6258 2069 1841 3801 715 124800 9192 11510 21380 69030 7838 21940 65510 28950 3879 17650 14620 6603 191800 2099 847 5212 13520 1951 11730 5874 1175 405 8116 3110 475 1042 5129 9030 3762 6730 1874 1486 2573 2816 796 1405 33010 4300 869 475 7739 2834 1850 13460 2614 1959 1172 218
2020-09-06 41570 140600 655 9344 29050 30520 35510 6265 2072 1844 3838 729 125400 9195 11560 21660 69810 7934 22010 65780 28950 3941 17760 14700 6661 193300 2103 859 5240 13590 1952 11800 5943 1181 412 8126 3111 480 1062 5190 9030 3762 6745 1882 1489 2591 2836 798 1417 33020 4321 879 477 7748 2854 1871 13550 2618 1967 1177 218
2020-09-07 41580 140700 660 9352 29050 30520 35510 6276 2073 1848 3873 743 125900 9198 11600 22010 70480 8018 22070 66000 28950 4003 17860 14770 6715 194500 2107 871 5266 13650 1952 11870 6006 1187 418 8137 3113 484 1083 5264 9030 3763 6758 1890 1491 2610 2856 801 1430 33030 4345 889 479 7756 2869 1890 13620 2619 1971 1185 218

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