COVID-19 short-term forecasts Deaths 2020-08-26


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 2020-08-26

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 20 328 8 7 10 226 15 946 30 943 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 41465 139270 733 9879 586 273 418 9285 623 28971 335 30412 248 614 1777 35458 6215 1994 1807 3421 5817 264 2003
Last daily increment 16 52 0 -117 14 0 2 4 0 47 0 0 5 0 0 13 8 17 2 54 3 0 1
Last week 62 734 4 -97 54 4 12 22 2 158 1 112 13 5 1 40 24 69 19 267 12 0 5
Days since peak 138 144 142 133 15 137 140 133 144 148 127 140 145 129 124 150 144 123 133 127 141 142

Peak increase in estimated trend of Deaths 2020-08-26

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 --07-2205-0607-17 --06-1607-2007-27 --07-23 --05-2907-2204-1504-1407-24 --07-2508-0804-2404-2004-2906-2307-3008-2205-21 --05-1205-0204-1204-1404-1404-2504-2904-1405-2804-30 --08-0605-2005-2906-2505-1308-2104-0904-29 -- --05-0507-24 --07-2704-1704-2204-0604-11
Peak daily increment 1062 168 785 1662 89 214 2947 171 323 125 2230 24 80 137 72 105 11 46 171 68 14 112 99 6 10 64 459 56 137 23 17 27 40 25 1566 9 19 999 76 137 46 377 6 104 25 12
Days from 100 to peak 116 36 93 72 113 144 107 48 84 18 29 102 104 133 21 18 10 60 119 144 27 41 28 -9 0 17 23 22 17 41 21 115 0 17 85 16 131 20 25 32 99 115 -45 7 15 2
Days from peak/2 to peak 107 37 63 52 119 144 78 49 76 20 20 115 112 135 27 20 30 74 119 147 50 44 32 17 19 21 20 27 18 56 35 127 30 31 81 41 147 15 30 33 114 111 18 11 30 18
Last total 572 117665 9141 10990 18184 60472 6944 21020 62076 28001 3137 16638 13502 6183 179708 1965 732 4895 12532 1927 4463 605 604 10733 5190 1071 337 7954 3041 442 902 4688 8981 3704 6615 1794 1415 2373 2606 384 429 15914 755 1250 32921 4044 763 433 7613 2573 1619 12140 331 2515 1876 1100
Last daily increment 23 1085 5 32 295 1115 86 119 626 188 99 114 194 20 1222 6 21 104 150 1 0 1 1 153 47 12 11 37 18 12 7 32 26 13 6 15 11 58 36 2 0 -39 5 20 3 48 19 5 31 44 19 205 4 21 4 6
Last week 100 5361 44 319 2001 5623 526 756 2970 1167 254 580 884 125 5453 60 91 212 722 24 5 4 9 684 400 55 41 121 62 23 46 192 99 49 55 49 39 183 141 11 1 -18 21 78 60 115 54 21 93 172 155 966 16 88 44 33
Days since peak 35 112 40 71 37 30 34 89 35 133 134 33 32 18 124 128 119 64 27 4 97 106 116 136 134 134 123 119 134 90 118 20 98 89 62 105 5 139 119 113 33 30 131 126 142 137

Deaths count forecast Europe (bold red line in graphs) 2020-08-27 to 2020-09-02

DateUKEUBGDEESFRITNLPLRO
2020-08-26 41465 139270 586 9285 28971 30412 35458 6215 1994 3421
2020-08-27 41480 139400 588 9296 29010 30420 35480 6221 2004 3463
2020-08-28 41480 139600 595 9302 29050 30430 35490 6225 2017 3505
2020-08-29 41490 139700 596 9307 29080 30430 35510 6230 2029 3546
2020-08-30 41500 139800 601 9308 29120 30440 35520 6230 2034 3586
2020-08-31 41500 139900 618 9309 29150 30440 35540 6230 2038 3627
2020-09-01 41520 140100 627 9314 29180 30450 35550 6233 2052 3667
2020-09-02 41530 140100 638 9319 29210 30450 35570 6239 2068 3708

Deaths count forecast (bold red line in graphs) 2020-08-27 to 2020-09-02

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-WI
2020-08-26 572 117665 9141 10990 18184 60472 6944 21020 62076 28001 3137 16638 13502 6183 179708 1965 732 4895 12532 1927 10733 5190 1071 337 7954 3041 442 902 4688 8981 3704 6615 1794 1415 2373 2606 755 1250 32921 4044 763 433 7613 2573 1619 12140 2515 1876 1100
2020-08-27 589 118900 9147 11080 18450 61400 7016 21140 62950 28080 3154 16760 13680 6203 180900 2002 744 4964 12690 1931 10970 5233 1074 344 7966 3054 444 909 4730 8987 3711 6624 1798 1423 2384 2633 759 1285 32930 4066 770 443 7628 2623 1638 12450 2527 1888 1107
2020-08-28 605 119900 9153 11130 18700 62310 7085 21260 63440 28190 3173 16850 13860 6222 182000 2014 757 4981 12840 1934 11100 5314 1085 351 7989 3066 448 916 4772 8991 3718 6633 1806 1430 2409 2659 763 1300 32940 4093 776 448 7648 2662 1682 12700 2538 1899 1110
2020-08-29 622 120700 9158 11190 18960 63210 7155 21370 64020 28310 3196 16950 14030 6241 182900 2024 770 5033 12980 1938 11210 5403 1090 358 8004 3077 448 923 4772 8997 3726 6642 1813 1437 2434 2684 767 1314 32940 4114 785 453 7664 2696 1698 12860 2549 1910 1121
2020-08-30 639 121200 9164 11250 19210 64110 7222 21490 64210 28440 3196 17020 14200 6259 183300 2026 784 5040 13020 1941 11260 5435 1093 365 8012 3080 448 930 4831 9002 3733 6651 1820 1444 2440 2691 771 1315 32950 4114 787 455 7665 2706 1706 12960 2560 1921 1122
2020-08-31 656 121700 9170 11320 19460 65010 7289 21600 64540 28570 3206 17080 14380 6278 183700 2036 798 5040 13100 1945 11340 5458 1102 373 8019 3084 452 936 4848 9007 3740 6659 1824 1451 2447 2697 775 1320 32960 4120 791 459 7665 2719 1725 12980 2571 1932 1122
2020-09-01 673 123000 9176 11350 19710 65910 7357 21720 65170 28700 3206 17190 14560 6297 184800 2048 813 5049 13230 1949 11520 5553 1114 380 8046 3103 454 943 4874 9012 3747 6668 1831 1458 2500 2732 779 1346 32970 4136 805 468 7689 2743 1763 13180 2581 1943 1131
2020-09-02 691 124000 9181 11390 19960 66830 7424 21830 65800 28830 3309 17300 14730 6316 186100 2058 827 5160 13380 1953 11670 5605 1124 387 8074 3119 462 950 4905 9018 3754 6677 1846 1464 2549 2765 782 1366 32970 4178 823 475 7720 2778 1783 13420 2592 1954 1139

Deaths count average forecast Europe (bold black line in graphs) 2020-08-27 to 2020-09-02

DateUKEUBGDEESFRITNLPLRO
2020-08-26 41465 139270 586 9285 28971 30412 35458 6215 1994 3421
2020-08-27 41470 139400 587 9293 28990 30420 35470 6221 2000 3444
2020-08-28 41480 139500 590 9299 29000 30430 35470 6224 2011 3484
2020-08-29 41480 139700 594 9304 29020 30450 35480 6229 2022 3525
2020-08-30 41490 139800 600 9305 29040 30460 35490 6229 2030 3565
2020-08-31 41500 139900 611 9306 29060 30470 35510 6230 2037 3605
2020-09-01 41510 140000 619 9311 29080 30480 35520 6232 2049 3647
2020-09-02 41520 140200 627 9317 29100 30490 35520 6239 2061 3688

Deaths count average forecast (bold black line in graphs) 2020-08-27 to 2020-09-02

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-WI
2020-08-26 572 117665 9141 10990 18184 60472 6944 21020 62076 28001 3137 16638 13502 6183 179708 1965 732 4895 12532 1927 10733 5190 1071 337 7954 3041 442 902 4688 8981 3704 6615 1794 1415 2373 2606 755 1250 32921 4044 763 433 7613 2573 1619 12140 2515 1876 1100
2020-08-27 581 118600 9145 11060 18380 61240 6975 21090 62650 28230 3171 16720 13620 6201 180500 1977 737 4918 12650 1929 10820 5237 1073 340 7960 3053 442 906 4715 8986 3707 6622 1799 1420 2377 2624 758 1278 32920 4061 769 438 7624 2602 1641 12330 2518 1884 1105
2020-08-28 592 119600 9151 11120 18710 62150 7047 21180 63160 28530 3225 16810 13780 6220 181300 1989 751 4937 12800 1934 10960 5310 1082 345 7978 3065 444 912 4751 8994 3713 6631 1806 1425 2389 2647 762 1294 32930 4088 774 444 7640 2637 1676 12560 2524 1895 1109
2020-08-29 607 120400 9157 11190 18990 63070 7122 21260 63780 28830 3279 16910 13930 6240 182000 2000 765 4980 12950 1939 11080 5389 1088 350 7992 3075 444 919 4766 9002 3720 6641 1814 1432 2408 2672 766 1309 32930 4110 783 448 7656 2669 1697 12720 2532 1903 1120
2020-08-30 624 121000 9162 11250 19320 64000 7195 21350 63950 29130 3330 16980 14090 6259 182300 2007 779 5000 12970 1941 11120 5433 1093 355 8002 3078 446 923 4809 9011 3727 6650 1820 1439 2415 2681 770 1314 32940 4110 786 452 7663 2686 1716 12820 2540 1909 1120
2020-08-31 639 121700 9168 11320 19650 64930 7257 21450 64350 29430 3384 17060 14240 6278 182600 2020 792 5021 13030 1944 11220 5471 1102 361 8011 3081 448 930 4832 9020 3733 6659 1824 1446 2426 2690 774 1321 32940 4114 791 455 7669 2704 1737 12880 2549 1915 1120
2020-09-01 658 122800 9174 11380 19940 65890 7328 21540 65200 29750 3440 17170 14400 6298 183500 2035 807 5050 13180 1948 11440 5550 1112 368 8034 3104 451 936 4861 9030 3740 6668 1831 1453 2467 2723 778 1345 32950 4138 804 463 7689 2743 1768 13110 2559 1928 1126
2020-09-02 675 123900 9180 11430 20300 66850 7397 21630 65860 30070 3524 17270 14560 6318 184500 2050 822 5122 13360 1951 11630 5613 1120 375 8054 3118 456 943 4894 9041 3747 6678 1846 1461 2503 2752 782 1369 32960 4176 819 473 7714 2774 1794 13390 2568 1939 1137

Deaths count scenario forecast (bold purple line in graphs) 2020-08-27 to 2020-09-04

DateUKEUBGDEESFRITNLPLROAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth 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-WI
2020-08-26 41465 139270 586 9285 28971 30412 35458 6215 1994 3421 572 117665 9141 10990 18184 60472 6944 21020 62076 28001 3137 16638 13502 6183 179708 1965 732 4895 12532 1927 10733 5190 1071 337 7954 3041 442 902 4688 8981 3704 6615 1794 1415 2373 2606 755 1250 32921 4044 763 433 7613 2573 1619 12140 2515 1876 1100
2020-08-27 41470 139600 586 9291 29000 30460 35460 6220 1999 3453 591 118500 9147 11050 18570 61080 6973 21120 62780 28310 3196 16720 13640 6204 180300 1981 737 4922 12650 1930 10840 5264 1075 341 7954 3049 442 906 4710 8981 3710 6624 1798 1417 2375 2624 758 1266 32930 4058 763 439 7623 2596 1646 12300 2515 1890 1105
2020-08-28 41480 139700 592 9297 29030 30490 35460 6225 2006 3488 617 119200 9152 11100 18900 61800 7048 21220 63340 28600 3243 16800 13750 6229 180800 1991 749 4951 12760 1931 10960 5328 1083 350 7975 3057 442 912 4731 8981 3714 6636 1806 1422 2402 2643 762 1280 32940 4072 772 444 7637 2618 1674 12440 2515 1903 1112
2020-08-29 41490 139800 598 9301 29060 30500 35460 6230 2012 3523 634 119800 9158 11150 19220 62520 7100 21320 63830 28850 3324 16870 13870 6256 181200 1999 759 4977 12840 1932 11080 5391 1091 359 7991 3063 444 922 4747 8981 3719 6647 1815 1425 2425 2662 765 1297 32950 4085 781 448 7647 2636 1704 12580 2521 1911 1119
2020-08-30 41510 140000 605 9307 29090 30530 35460 6236 2017 3561 656 120500 9163 11200 19570 63160 7153 21410 64450 29130 3392 16930 13980 6287 181300 2011 771 4998 12960 1933 11170 5456 1098 369 8006 3068 444 934 4756 8981 3722 6657 1823 1430 2446 2687 767 1314 32960 4096 789 452 7659 2656 1733 12710 2527 1922 1127
2020-08-31 41520 140100 612 9315 29120 30560 35460 6242 2025 3595 673 120900 9168 11230 19930 63780 7187 21490 65060 29360 3449 17010 14080 6322 181500 2019 784 5019 13080 1933 11260 5523 1106 379 8016 3073 446 947 4773 8981 3726 6670 1831 1434 2469 2710 769 1333 32970 4107 798 457 7668 2674 1766 12810 2532 1934 1136
2020-09-01 41530 140300 619 9323 29150 30580 35460 6248 2030 3638 688 121500 9171 11280 20330 64430 7237 21570 65510 29570 3514 17070 14180 6356 181700 2028 797 5038 13210 1933 11340 5586 1113 390 8026 3076 447 962 4785 8981 3727 6683 1839 1437 2492 2730 771 1348 32990 4117 806 462 7676 2690 1797 12940 2536 1940 1145
2020-09-02 41540 140500 624 9330 29180 30620 35460 6254 2033 3680 703 122000 9175 11310 20690 65000 7265 21640 66010 29720 3597 17140 14270 6393 181900 2036 810 5060 13320 1933 11430 5641 1120 401 8036 3079 447 978 4799 8981 3730 6699 1847 1440 2519 2751 774 1367 32990 4124 816 468 7683 2705 1829 13050 2537 1948 1155
2020-09-03 41550 140700 630 9341 29200 30650 35460 6258 2036 3721 718 122500 9178 11340 21050 65490 7298 21720 66400 29880 3676 17210 14360 6435 182000 2043 824 5082 13420 1933 11500 5693 1126 412 8044 3084 447 995 4811 8981 3731 6715 1855 1442 2549 2768 776 1383 33010 4128 825 473 7688 2720 1859 13150 2538 1955 1165
2020-09-04 41560 140800 637 9350 29220 30660 35460 6262 2039 3758 732 122900 9182 11380 21400 66000 7332 21790 66690 30080 3755 17280 14440 6479 182000 2047 838 5106 13440 1933 11580 5754 1133 421 8052 3088 447 1012 4824 8981 3731 6735 1863 1445 2576 2786 777 1400 33020 4128 833 478 7696 2733 1887 13260 2538 1961 1175

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