COVID-19 short-term forecasts Deaths 2020-08-20


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 2020-08-20

UKEUATBEBGBSCZDEDKESFIFRGRHUIEITNLPLPTROSENOCH
Peak date04-1004-0404-0604-1508-1104-1104-0804-1504-0403-3104-2104-0804-0304-1904-2403-2904-0404-2504-15 --04-2104-0704-06
Peak daily increment 964 3120 20 322 8 7 10 226 15 945 31 944 5 13 167 781 153 23 31 94 8 60
Days from 100 to peak 23 31 7 22 89 0 0 22 3 18 1 23 -11 6 21 25 15 19 17 24 -2 14
Days from peak/2 to peak 17 21 16 21 138 22 13 22 15 14 20 18 18 26 22 20 16 31 23 27 20 19
Last total 41403 138536 729 9976 532 269 406 9263 621 28813 334 30300 235 609 1776 35418 6191 1925 1788 3154 5805 264 1998
Last daily increment 6 127 0 7 5 1 2 14 0 16 0 0 0 0 1 6 10 12 2 48 3 2 2
Last week 45 949 4 52 40 3 12 33 0 196 1 21 12 2 2 184 24 67 16 250 22 3 7
Days since peak 132 138 136 127 9 131 134 127 138 142 121 134 139 123 118 144 138 117 127 121 135 136

Peak increase in estimated trend of Deaths 2020-08-20

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-WI
Peak date --07-2105-0607-1708-0506-1607-2307-2406-2407-23 --05-2907-2204-1504-1407-2208-0807-2108-0804-2404-2004-2906-2308-1408-1505-21 --05-1205-0204-1404-1404-1404-2504-2904-1405-29 --08-1508-0605-2005-2906-2505-13 --04-0904-29 -- --05-0507-23 --07-2704-1704-2204-0604-11
Peak daily increment 1082 168 789 314 1661 91 214 683 2725 172 334 120 2230 24 10 81 137 71 106 11 47 179 67 14 112 98 6 10 64 453 56 137 23 29 27 41 26 1569 9 999 76 137 44 374 6 105 25 12
Days from 100 to peak 115 36 92 115 72 116 141 79 107 48 84 18 29 100 84 100 133 21 18 10 60 134 137 27 41 28 -7 0 17 23 22 17 42 124 115 0 16 85 16 20 25 32 98 115 -45 7 15 2
Days from peak/2 to peak 106 37 62 109 52 122 141 72 79 49 75 20 20 113 128 108 135 27 20 30 73 134 140 50 44 32 19 19 21 20 27 18 57 137 127 30 31 81 41 15 30 33 114 111 18 10 30 18
Last total 472 112304 9097 10671 16183 54849 6418 20264 59106 26834 2883 16058 12618 6058 174255 1905 641 4683 11810 1903 4458 601 595 10049 4790 1016 296 7833 2979 419 856 4496 8882 3655 6560 1745 1376 2190 2465 373 428 15932 734 1172 32861 3929 709 412 7520 2401 1464 11174 315 2427 1832 1067
Last daily increment 9 1204 2 93 204 983 72 139 625 176 88 107 195 19 1078 29 10 50 120 3 1 1 0 117 54 6 7 27 11 4 14 28 138 7 17 6 8 27 34 2 1 6 5 38 -4 22 10 4 12 41 36 240 4 17 13 7
Last week 93 5781 29 331 1691 5813 397 933 3198 978 441 591 1062 124 5803 80 54 261 662 15 5 7 2 908 323 46 31 112 73 16 52 189 138 38 70 52 76 147 152 12 5 29 31 127 34 145 65 27 86 197 161 1096 16 57 79 42
Days since peak 30 106 34 15 65 28 27 57 28 83 29 127 128 29 12 30 12 118 122 113 58 6 5 91 100 110 128 128 128 117 113 128 83 5 14 92 83 56 99 133 113 107 28 24 125 120 136 131

Deaths count forecast Europe (bold red line in graphs) 2020-08-21 to 2020-08-27

DateUKEUBEBGDEESFRITNLPLROSE
2020-08-20 41403 138536 9976 532 9263 28813 30300 35418 6191 1925 3154 5805
2020-08-21 41430 138600 9976 544 9271 28810 30310 35430 6191 1932 3231 5807
2020-08-22 41430 138800 9976 547 9276 28810 30320 35430 6191 1943 3293 5807
2020-08-23 41430 138800 9976 549 9276 28810 30330 35440 6191 1952 3354 5807
2020-08-24 41440 139000 9976 562 9276 28810 30330 35440 6191 1957 3410 5808
2020-08-25 41450 139100 9976 570 9281 28810 30340 35450 6191 1967 3468 5811
2020-08-26 41460 139300 9976 579 9290 28810 30350 35450 6195 1982 3520 5822
2020-08-27 41470 139400 9976 583 9299 28810 30360 35460 6201 1995 3580 5824

Deaths count forecast (bold red line in graphs) 2020-08-21 to 2020-08-27

DateAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
2020-08-20 472 112304 9097 10671 16183 54849 6418 20264 59106 26834 2883 16058 12618 6058 174255 1905 641 4683 11810 10049 4790 1016 296 7833 2979 856 4496 8882 3655 6560 1745 1376 2190 2465 15932 734 1172 32861 3929 709 412 7520 2401 1464 11174 2427 1832 1067
2020-08-21 486 113400 9103 10750 16490 55780 6481 20420 59990 27170 2957 16220 13040 6077 175600 1936 651 4773 12040 10290 4854 1023 304 7844 2985 856 4543 8958 3663 6569 1745 1392 2229 2492 15930 738 1187 32870 3954 709 420 7540 2439 1492 11460 2439 1843 1075
2020-08-22 499 114200 9108 10800 16790 56700 6542 20580 60620 27440 3024 16340 13190 6096 176600 1942 662 4824 12140 10480 4938 1029 312 7852 2999 859 4543 9020 3671 6577 1747 1407 2260 2520 15950 743 1215 32880 3981 720 428 7556 2486 1520 11650 2451 1855 1085
2020-08-23 513 114700 9114 10860 17080 57610 6603 20730 60800 27700 3092 16410 13320 6115 177100 1946 664 4831 12170 10570 4960 1030 320 7865 3003 860 4608 9076 3679 6586 1752 1422 2266 2523 15950 747 1225 32890 3981 723 437 7558 2494 1549 11750 2463 1867 1086
2020-08-24 526 115400 9120 10930 17380 58510 6663 20880 61140 27950 3156 16470 13480 6133 177500 1967 670 4831 12220 10640 4980 1039 329 7874 3006 866 4625 9130 3687 6594 1754 1436 2275 2534 15960 751 1239 32890 3986 726 445 7559 2510 1579 11830 2474 1880 1087
2020-08-25 540 116600 9125 10960 17680 59420 6724 21040 61910 28190 3220 16610 13720 6152 178800 1987 685 4863 12400 10870 5053 1051 337 7897 3030 876 4649 9182 3695 6603 1758 1450 2309 2574 15970 755 1266 32900 4019 739 453 7580 2562 1610 12060 2486 1892 1091
2020-08-26 554 117800 9131 10990 17980 60330 6784 21190 62580 28440 3284 16730 13920 6170 180100 2001 696 4960 12590 11070 5121 1059 346 7919 3045 886 4688 9234 3703 6611 1768 1465 2347 2606 15970 759 1303 32910 4054 757 461 7611 2583 1641 12310 2497 1904 1105
2020-08-27 568 118900 9136 11090 18280 61250 6845 21350 63190 28680 3349 16830 14140 6189 181200 2022 705 5008 12720 11190 5173 1066 354 7943 3057 896 4722 9286 3711 6620 1774 1479 2373 2634 15980 764 1343 32920 4077 766 469 7625 2623 1673 12540 2509 1916 1111

Deaths count average forecast Europe (bold black line in graphs) 2020-08-21 to 2020-08-27

DateUKEUBEBGDEESFRITNLPLROSE
2020-08-20 41403 138536 9976 532 9263 28813 30300 35418 6191 1925 3154 5805
2020-08-21 41410 138600 9980 539 9266 28820 30300 35420 6191 1932 3205 5805
2020-08-22 41420 138700 9990 544 9270 28840 30310 35430 6191 1942 3262 5805
2020-08-23 41420 138800 9990 549 9271 28850 30320 35430 6192 1952 3317 5805
2020-08-24 41430 138900 9990 559 9272 28860 30330 35440 6193 1960 3375 5806
2020-08-25 41440 139000 10000 567 9277 28880 30340 35440 6193 1970 3432 5808
2020-08-26 41450 139200 10010 575 9284 28890 30350 35450 6195 1981 3488 5815
2020-08-27 41470 139300 10010 581 9290 28910 30360 35450 6197 1993 3551 5815

Deaths count average forecast (bold black line in graphs) 2020-08-21 to 2020-08-27

DateAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
2020-08-20 472 112304 9097 10671 16183 54849 6418 20264 59106 26834 2883 16058 12618 6058 174255 1905 641 4683 11810 10049 4790 1016 296 7833 2979 856 4496 8882 3655 6560 1745 1376 2190 2465 15932 734 1172 32861 3929 709 412 7520 2401 1464 11174 2427 1832 1067
2020-08-21 485 113100 9100 10700 16470 55700 6465 20360 59720 27770 2916 16150 12810 6074 175100 1914 646 4707 12010 10240 4841 1022 300 7838 2984 857 4527 8891 3662 6563 1748 1383 2216 2476 15940 736 1182 32870 3948 711 415 7537 2417 1481 11360 2432 1839 1069
2020-08-22 501 113900 9105 10760 16770 56660 6519 20480 60340 27990 2953 16250 12980 6092 175900 1925 656 4748 12100 10420 4915 1028 305 7846 2997 859 4544 8899 3669 6569 1753 1392 2244 2501 15950 740 1203 32870 3977 718 419 7553 2461 1505 11500 2439 1849 1077
2020-08-23 518 114500 9110 10820 17060 57620 6582 20600 60530 28320 2993 16320 13150 6110 176300 1935 662 4771 12130 10510 4952 1032 311 7859 3000 861 4593 8907 3677 6576 1761 1401 2253 2506 15950 744 1216 32880 3978 722 424 7561 2478 1532 11600 2446 1858 1078
2020-08-24 535 115200 9114 10890 17370 58590 6636 20720 60850 28600 3035 16390 13320 6129 176700 1953 669 4791 12180 10590 4989 1041 317 7869 3003 865 4617 8916 3683 6585 1765 1410 2263 2516 15960 748 1231 32890 3983 726 428 7567 2499 1560 11690 2454 1867 1078
2020-08-25 552 116300 9121 10950 17660 59570 6695 20840 61710 28850 3082 16510 13550 6147 177600 1973 682 4831 12350 10820 5058 1051 323 7890 3025 871 4645 8925 3691 6593 1772 1420 2298 2554 15970 752 1254 32900 4014 739 436 7586 2545 1592 11860 2463 1881 1082
2020-08-26 570 117500 9126 11000 18000 60570 6760 20950 62450 29080 3135 16620 13770 6166 178600 1995 692 4907 12530 11030 5134 1058 330 7905 3037 877 4683 8934 3700 6602 1783 1429 2337 2587 15970 756 1282 32900 4048 752 443 7608 2578 1622 12110 2472 1890 1092
2020-08-27 588 118600 9132 11090 18320 61580 6826 21070 63140 29320 3189 16720 14010 6184 179400 2013 702 4958 12660 11180 5200 1066 336 7925 3050 883 4720 8943 3708 6611 1790 1439 2363 2606 15970 760 1316 32910 4064 761 449 7624 2617 1653 12290 2481 1901 1097

Deaths count scenario forecast (bold purple line in graphs) 2020-08-21 to 2020-08-29

DateUKEUBEBGDEESFRITNLPLROSEAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
2020-08-20 41403 138536 9976 532 9263 28813 30300 35418 6191 1925 3154 5805 472 112304 9097 10671 16183 54849 6418 20264 59106 26834 2883 16058 12618 6058 174255 1905 641 4683 11810 10049 4790 1016 296 7833 2979 856 4496 8882 3655 6560 1745 1376 2190 2465 15932 734 1172 32861 3929 709 412 7520 2401 1464 11174 2427 1832 1067
2020-08-21 41410 138700 9978 539 9263 28820 30310 35470 6191 1931 3201 5805 491 112900 9105 10720 16530 55490 6470 20400 59630 27210 2940 16140 12800 6075 175000 1919 650 4718 11920 10230 4868 1023 305 7839 2989 856 4525 8882 3662 6560 1752 1383 2214 2477 15940 738 1177 32880 3948 714 414 7537 2419 1475 11240 2434 1847 1067
2020-08-22 41420 138900 9982 545 9266 28820 30320 35520 6191 1940 3248 5805 507 113800 9110 10760 16780 56120 6523 20540 60140 27440 3019 16230 12970 6089 175700 1935 659 4753 12040 10390 4931 1031 313 7857 2999 859 4548 8885 3668 6568 1758 1391 2236 2497 15940 742 1202 32880 3966 723 417 7551 2440 1499 11390 2440 1865 1070
2020-08-23 41420 139200 9984 550 9269 28850 30330 35570 6196 1948 3289 5806 524 114500 9115 10790 17040 56540 6574 20670 60640 27730 3091 16310 13140 6102 176300 1949 668 4784 12150 10550 4998 1040 319 7874 3008 866 4578 8887 3673 6573 1765 1401 2257 2518 15940 746 1227 32890 3983 730 421 7566 2462 1526 11520 2443 1883 1073
2020-08-24 41430 139400 9984 555 9270 28870 30330 35640 6201 1956 3337 5807 540 115400 9120 10820 17280 56870 6623 20790 61160 27970 3171 16390 13300 6112 176900 1964 678 4815 12280 10710 5072 1047 325 7893 3017 873 4595 8887 3678 6577 1772 1409 2279 2540 15950 750 1246 32890 3999 738 426 7582 2481 1554 11650 2447 1905 1075
2020-08-25 41430 139700 9986 560 9271 28900 30330 35700 6206 1962 3388 5808 556 116000 9124 10860 17520 57250 6667 20910 61610 28230 3245 16470 13450 6123 177400 1976 688 4842 12410 10870 5143 1054 334 7908 3023 876 4610 8887 3683 6582 1778 1416 2298 2562 15950 754 1264 32890 4013 747 430 7595 2501 1579 11770 2450 1925 1077
2020-08-26 41440 139900 9986 564 9271 28920 30330 35770 6216 1968 3444 5810 571 116600 9129 10880 17760 57500 6714 21010 61900 28470 3321 16540 13600 6132 177800 1989 697 4869 12530 11030 5216 1061 345 7924 3030 881 4622 8887 3688 6585 1784 1421 2317 2584 15950 758 1282 32900 4026 756 434 7608 2518 1604 11880 2451 1948 1078
2020-08-27 41440 140300 9986 568 9271 28930 30330 35860 6220 1971 3495 5810 587 117200 9133 10910 17960 57650 6753 21110 62250 28750 3383 16620 13740 6139 178000 2005 707 4894 12660 11180 5288 1068 361 7940 3037 885 4631 8888 3693 6587 1791 1426 2336 2605 15950 762 1305 32900 4034 767 438 7619 2535 1631 11980 2455 1970 1079
2020-08-28 41440 140600 9986 572 9278 28950 30330 35920 6225 1974 3550 5810 603 117700 9136 10930 18160 57920 6787 21180 62530 28910 3451 16680 13870 6144 178100 2023 718 4917 12810 11320 5357 1074 368 7957 3044 888 4637 8889 3695 6587 1798 1430 2353 2633 15960 766 1326 32910 4045 776 443 7628 2554 1660 12080 2456 1992 1079
2020-08-29 41440 140900 9986 576 9279 28970 30330 36040 6230 1976 3604 5810 617 118200 9139 10950 18320 58290 6825 21260 62850 29260 3517 16760 13990 6149 178200 2044 727 4939 12950 11460 5428 1081 376 7970 3050 895 4642 8895 3699 6587 1804 1440 2370 2660 15960 770 1346 32910 4054 786 447 7638 2569 1687 12170 2458 2015 1079

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