COVID-19 short-term forecasts Deaths 2020-09-03


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 2020-09-03

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 41527 140437 735 9899 658 274 426 9322 626 29234 336 30559 278 620 1777 35507 6235 2092 1829 3765 5832 264 2013
Last daily increment 13 168 1 1 10 0 1 0 0 40 0 20 5 1 0 10 0 14 2 44 12 0 2
Last week 41 889 2 13 55 0 7 32 2 223 1 99 19 6 0 35 15 74 14 258 11 0 9
Days since peak 146 150 150 141 145 148 141 152 156 135 148 153 137 132 158 152 131 141 144 149 150

Peak increase in estimated trend of Deaths 2020-09-03

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 date --07-2105-0607-1708-2306-16 --07-2706-2407-2307-1205-2907-2204-1504-1307-22 --07-21 --04-2404-2004-2906-23 -- --05-2108-2905-1205-0204-12 --04-1404-2504-2904-1405-2804-3008-0308-0305-2005-2906-2505-13 --05-1808-29 --07-2805-0507-2808-2807-2704-1704-2204-0604-1104-23
Peak daily increment 1065 168 785 591 1662 214 683 2947 92 171 323 125 2226 24 78 72 105 11 46 14 7 112 99 6 64 459 56 137 23 17 30 28 40 25 1566 9 3573 126 5 137 45 26 386 6 104 25 12 16
Days from 100 to peak 115 36 93 133 72 144 79 107 102 48 84 18 28 100 100 21 18 10 60 27 49 41 28 -9 17 23 22 17 41 21 112 112 0 17 85 16 59 147 90 32 103 138 115 -45 7 15 2 -89
Days from peak/2 to peak 106 37 63 115 52 144 72 78 108 49 75 20 19 113 108 27 20 30 74 50 154 44 32 17 21 20 27 18 56 35 125 124 30 31 81 41 49 150 131 33 119 150 111 18 11 30 18 4
Last total 737 124614 9189 11422 20618 68472 7750 21926 66329 29068 3688 17479 14563 6511 186790 2120 861 5129 13493 1955 4468 609 606 11650 5732 1136 372 8115 3110 471 976 4858 9071 3766 6716 1837 1514 2536 2803 403 432 15971 791 1363 32956 4226 835 470 7724 2807 1781 13296 342 2652 1939 1146 240
Last daily increment 59 834 7 78 273 1096 134 129 513 0 65 114 174 49 1070 6 20 65 176 3 1 1 0 149 71 3 0 24 4 10 10 17 17 10 11 7 8 10 24 4 0 7 1 27 8 50 14 2 19 13 20 192 4 11 8 4 7
Last week 137 5110 34 290 1852 5922 581 677 3183 791 363 613 820 266 5034 103 105 152 688 18 3 4 2 693 384 28 19 118 52 26 58 117 53 47 79 27 80 123 151 13 0 41 24 76 87 121 49 23 82 152 112 759 7 102 38 33 39
Days since peak 44 120 48 11 79 38 71 42 53 97 43 141 143 43 44 132 136 127 72 105 5 114 124 144 142 131 127 142 98 126 31 31 106 97 70 113 108 5 37 121 37 6 38 139 134 150 145 133

Deaths count forecast Europe (bold red line in graphs) 2020-09-04 to 2020-09-10

DateUKEUBGDEESFRITPLRO
2020-09-03 41527 140437 658 9322 29234 30559 35507 2092 3765
2020-09-04 41540 140600 668 9325 29250 30570 35510 2099 3807
2020-09-05 41550 140700 679 9332 29260 30580 35520 2113 3848
2020-09-06 41550 140800 690 9333 29280 30600 35520 2115 3889
2020-09-07 41550 141000 701 9335 29290 30610 35530 2120 3929
2020-09-08 41560 141100 713 9339 29300 30620 35530 2137 3970
2020-09-09 41570 141200 725 9349 29320 30640 35540 2156 4011
2020-09-10 41580 141300 736 9352 29330 30650 35540 2169 4052

Deaths count forecast (bold red line in graphs) 2020-09-04 to 2020-09-10

DateAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-FLUS-GAUS-IAUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WIUS-WV
2020-09-03 737 124614 9189 11422 20618 68472 7750 21926 66329 29068 3688 17479 14563 6511 186790 2120 861 5129 13493 11650 5732 1136 8115 3110 471 976 4858 9071 3766 6716 1837 1514 2536 2803 15971 791 1363 32956 4226 835 470 7724 2807 1781 13296 2652 1939 1146 240
2020-09-04 759 125800 9196 11490 20930 69430 7924 22040 66880 29220 3747 17570 14700 6555 188000 2134 882 5201 13850 11820 5795 1158 8133 3127 471 980 4919 9085 3773 6725 1851 1524 2576 2825 15980 795 1387 32970 4229 856 477 7749 2860 1827 13620 2666 1947 1152 244
2020-09-05 780 126500 9202 11550 21230 70370 8065 22160 67460 29350 3805 17680 14830 6597 188900 2162 903 5235 14110 11940 5889 1158 8145 3136 473 985 4919 9100 3784 6736 1855 1534 2592 2854 15990 799 1402 32980 4230 871 482 7762 2899 1847 13690 2680 1955 1160 248
2020-09-06 800 126900 9208 11610 21530 71310 8204 22270 67690 29480 3860 17740 14960 6639 189200 2166 924 5246 14280 11950 5916 1164 8155 3139 473 991 4948 9115 3792 6746 1858 1543 2602 2860 16000 803 1402 32990 4235 876 484 7762 2908 1862 13750 2694 1963 1162 252
2020-09-07 821 127500 9214 11660 21830 72230 8339 22380 67960 29600 3916 17810 15090 6680 189700 2180 945 5246 14500 12020 5942 1171 8162 3143 475 997 4964 9130 3794 6756 1859 1553 2627 2863 16010 807 1402 33000 4235 884 485 7762 2918 1871 13810 2708 1971 1162 256
2020-09-08 843 128700 9220 11700 22120 73160 8481 22490 68690 29720 3971 17930 15220 6722 190700 2196 967 5261 14790 12200 6033 1179 8195 3160 480 1010 4996 9146 3799 6767 1865 1562 2655 2904 16020 811 1417 33020 4252 901 491 7782 2952 1901 13970 2722 1979 1169 260
2020-09-09 865 129800 9225 11720 22430 74100 8639 22600 69220 29840 4027 18030 15360 6763 191800 2207 989 5305 15120 12320 6091 1187 8223 3176 486 1024 5013 9161 3806 6777 1875 1571 2688 2943 16040 815 1437 33030 4267 920 496 7809 2984 1917 14150 2735 1987 1180 264
2020-09-10 889 130600 9231 11800 22730 75040 8822 22710 69730 29960 4084 18140 15490 6805 192800 2219 1012 5349 15380 12460 6159 1194 8245 3181 493 1033 5029 9177 3815 6787 1882 1581 2703 2965 16050 818 1464 33050 4298 937 499 7823 3006 1939 14340 2749 1995 1186 268

Deaths count average forecast Europe (bold black line in graphs) 2020-09-04 to 2020-09-10

DateUKEUBGDEESFRITPLRO
2020-09-03 41527 140437 658 9322 29234 30559 35507 2092 3765
2020-09-04 41530 140500 668 9323 29250 30570 35510 2097 3801
2020-09-05 41540 140600 675 9329 29280 30580 35520 2107 3842
2020-09-06 41540 140700 686 9331 29310 30590 35520 2114 3883
2020-09-07 41550 140800 701 9333 29340 30600 35530 2121 3924
2020-09-08 41560 141000 713 9337 29370 30610 35540 2135 3966
2020-09-09 41570 141100 725 9344 29400 30630 35540 2148 4008
2020-09-10 41580 141200 736 9348 29420 30640 35550 2161 4050

Deaths count average forecast (bold black line in graphs) 2020-09-04 to 2020-09-10

DateAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-FLUS-GAUS-IAUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WIUS-WV
2020-09-03 737 124614 9189 11422 20618 68472 7750 21926 66329 29068 3688 17479 14563 6511 186790 2120 861 5129 13493 11650 5732 1136 8115 3110 471 976 4858 9071 3766 6716 1837 1514 2536 2803 15971 791 1363 32956 4226 835 470 7724 2807 1781 13296 2652 1939 1146 240
2020-09-04 740 125300 9195 11470 20860 69210 7881 21980 66620 29200 3742 17550 14640 6531 187500 2135 871 5147 13710 11730 5782 1148 8129 3118 471 979 4880 9078 3771 6723 1840 1521 2549 2821 15970 794 1373 32960 4236 844 475 7737 2833 1805 13420 2661 1946 1149 241
2020-09-05 745 126000 9201 11530 21140 70150 8025 22040 67130 29330 3807 17650 14750 6563 188200 2157 888 5169 13940 11860 5861 1151 8140 3126 472 984 4891 9090 3778 6733 1844 1530 2565 2848 15980 798 1385 32980 4255 857 480 7747 2867 1826 13470 2673 1950 1156 245
2020-09-06 756 126500 9206 11590 21460 71080 8165 22110 67290 29460 3873 17720 14870 6598 188400 2167 906 5182 14080 11880 5902 1158 8151 3130 472 990 4918 9102 3785 6743 1847 1540 2574 2857 15980 802 1390 32990 4255 866 483 7751 2882 1845 13520 2687 1954 1158 248
2020-09-07 768 127200 9212 11650 21750 72030 8290 22170 67550 29600 3932 17800 14990 6633 188700 2182 924 5189 14270 11930 5942 1166 8160 3133 473 997 4937 9114 3792 6754 1848 1550 2597 2865 15990 806 1394 33000 4255 876 486 7754 2898 1862 13580 2701 1958 1158 251
2020-09-08 783 128200 9218 11700 22040 72980 8435 22240 68320 29720 3989 17900 15110 6668 189600 2196 942 5205 14510 12130 6024 1175 8187 3151 477 1008 4966 9127 3799 6764 1855 1560 2629 2902 16000 810 1408 33020 4264 890 491 7770 2927 1889 13720 2716 1968 1165 256
2020-09-09 800 129200 9224 11750 22340 73950 8583 22300 68820 29890 4054 18000 15230 6703 190400 2208 963 5255 14800 12280 6084 1183 8212 3167 482 1017 4993 9140 3806 6775 1869 1570 2671 2935 16000 814 1429 33030 4280 905 496 7792 2958 1912 13880 2731 1972 1175 261
2020-09-10 818 130100 9229 11830 22650 74940 8756 22360 69250 30020 4125 18100 15350 6738 191200 2223 982 5289 15040 12390 6149 1194 8233 3175 486 1026 5018 9152 3813 6785 1879 1580 2694 2959 16010 819 1452 33040 4298 920 500 7803 2995 1938 14050 2746 1978 1183 266

Deaths count scenario forecast (bold purple line in graphs) 2020-09-04 to 2020-09-12

DateUKEUBGDEESFRITPLROAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-FLUS-GAUS-IAUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WIUS-WV
2020-09-03 41527 140437 658 9322 29234 30559 35507 2092 3765 737 124614 9189 11422 20618 68472 7750 21926 66329 29068 3688 17479 14563 6511 186790 2120 861 5129 13493 11650 5732 1136 8115 3110 471 976 4858 9071 3766 6716 1837 1514 2536 2803 15971 791 1363 32956 4226 835 470 7724 2807 1781 13296 2652 1939 1146 240
2020-09-04 41540 140600 664 9327 29230 30590 35510 2099 3801 737 125300 9193 11470 20840 69220 7835 21990 66670 29330 3740 17560 14670 6560 187700 2137 877 5153 13550 11710 5784 1149 8125 3121 471 979 4883 9071 3771 6729 1843 1519 2562 2820 15970 796 1379 32970 4238 843 476 7729 2837 1808 13380 2670 1948 1154 241
2020-09-05 41540 140700 673 9332 29260 30610 35520 2109 3841 744 126000 9198 11500 21080 70180 7933 22080 67030 29450 3792 17660 14780 6618 188500 2152 895 5173 13620 11800 5847 1156 8146 3127 475 988 4897 9077 3775 6745 1847 1526 2583 2838 15970 799 1396 32980 4250 851 479 7738 2858 1832 13460 2689 1954 1163 248
2020-09-06 41550 140800 681 9337 29280 30620 35520 2118 3879 764 126700 9201 11540 21290 71070 8024 22160 67420 29560 3841 17760 14880 6672 189700 2166 913 5188 13690 11900 5903 1161 8159 3131 480 998 4908 9077 3778 6761 1852 1532 2598 2854 15970 803 1403 32990 4250 861 483 7747 2879 1848 13530 2714 1960 1171 255
2020-09-07 41560 140900 690 9344 29300 30650 35520 2129 3914 778 127300 9205 11580 21530 71870 8144 22240 67770 29670 3886 17840 14970 6732 190800 2180 931 5205 13770 11980 5962 1167 8172 3135 486 1008 4917 9077 3782 6778 1856 1538 2615 2869 15970 806 1415 33000 4250 869 487 7754 2895 1866 13620 2745 1967 1182 262
2020-09-08 41570 141000 699 9348 29330 30670 35520 2142 3951 792 127900 9209 11610 21740 72750 8254 22320 68150 29760 3925 17950 15060 6787 191600 2192 950 5220 13830 12060 6029 1172 8188 3138 492 1016 4922 9078 3784 6797 1860 1541 2630 2883 15970 807 1423 33010 4250 879 491 7758 2914 1890 13690 2775 1967 1193 270
2020-09-09 41570 141100 708 9353 29350 30690 35530 2150 3987 805 128400 9212 11640 21930 73580 8370 22390 68400 29840 3966 18020 15140 6846 192500 2202 970 5236 13900 12130 6098 1178 8193 3142 499 1024 4929 9078 3785 6814 1864 1544 2645 2897 15970 809 1428 33020 4250 890 493 7764 2931 1907 13760 2813 1967 1205 277
2020-09-10 41580 141200 715 9358 29370 30710 35530 2167 4022 817 128900 9214 11670 22130 74340 8476 22470 68750 29930 4000 18100 15220 6902 193800 2211 989 5252 13940 12220 6154 1183 8203 3143 506 1033 4944 9078 3786 6832 1867 1547 2660 2905 15970 811 1437 33030 4250 900 497 7768 2950 1920 13820 2847 1967 1219 286
2020-09-11 41580 141200 722 9364 29390 30730 35540 2187 4057 828 129400 9217 11690 22340 75080 8584 22530 69100 30010 4034 18170 15290 6960 194600 2220 1009 5267 14000 12300 6209 1187 8208 3145 512 1040 4944 9078 3787 6849 1870 1549 2672 2919 15970 812 1437 33040 4250 909 499 7770 2967 1932 13890 2888 1967 1233 293
2020-09-12 41580 141300 730 9369 29410 30750 35540 2204 4094 840 129800 9219 11720 22470 75760 8677 22600 69310 30080 4065 18240 15370 7027 196100 2228 1027 5284 14040 12400 6264 1190 8213 3146 519 1047 4946 9078 3787 6866 1873 1549 2684 2928 15970 814 1437 33040 4250 919 502 7772 2982 1944 13940 2934 1967 1249 303

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