COVID-19 short-term forecasts Deaths 2020-08-15


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 2020-08-15

UKEUATBEBGBSCZDEDKESFIFRGRHUIEITNLPLPTROSENOCH
Peak date04-0904-0404-0604-15 --04-1104-0804-1504-0403-3104-2104-0804-0304-1904-2403-2904-0404-2504-15 --04-2104-0704-06
Peak daily increment 984 3120 20 322 7 10 226 15 945 31 944 5 13 167 781 153 23 31 94 8 60
Days from 100 to peak 22 31 7 22 0 0 22 3 18 1 23 -11 6 21 25 15 19 17 24 -2 14
Days from peak/2 to peak 16 21 16 21 22 13 22 15 14 20 18 18 26 22 20 16 31 23 27 20 19
Last total 46706 137840 728 9935 495 267 395 9235 621 28617 333 30279 226 607 1774 35392 6169 1869 1775 2954 5783 261 1991
Last daily increment 0 253 3 11 3 1 1 5 0 0 0 0 3 0 0 158 2 11 3 50 0 0 0
Last week 132 942 7 63 48 3 5 33 4 114 2 77 14 5 2 187 12 62 19 254 20 5 5
Days since peak 128 133 131 122 126 129 122 133 137 116 129 134 118 113 139 133 112 122 116 130 131

Peak increase in estimated trend of Deaths 2020-08-15

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 --07-1505-0607-17 --06-1607-2007-24 -- -- --05-29 --04-1504-1407-26 --07-18 --04-2404-2004-2906-23 -- --05-2108-0605-1205-0204-1404-1404-1404-2504-2904-1405-2904-30 -- --05-2005-2906-2505-13 --04-0904-29 --08-1105-0507-28 --07-2704-1704-2204-0604-11
Peak daily increment 1071 168 796 1662 87 213 172 120 2230 23 77 71 106 11 47 14 6 112 98 6 10 64 453 56 137 23 17 41 26 1569 9 999 76 5 137 44 404 6 105 25 12
Days from 100 to peak 109 36 92 72 113 141 48 18 29 104 97 21 18 10 60 27 26 41 28 -7 0 17 23 22 17 42 21 0 16 85 16 20 25 104 32 103 115 -45 7 15 2
Days from peak/2 to peak 100 37 62 52 119 141 49 20 20 117 105 27 20 30 73 50 131 44 32 19 19 21 20 27 18 57 35 30 31 81 41 15 30 145 33 119 111 18 10 30 18
Last total 396 107232 9072 10395 14810 49980 6071 19492 56543 25856 2600 15585 11677 5955 169481 1828 600 4491 11218 1896 4453 597 593 9345 4561 975 269 7726 2921 405 810 4307 8744 3624 6510 1699 1313 2080 2343 361 423 15910 711 1069 32833 3824 657 386 7451 2260 1322 10268 301 2381 1762 1038
Last daily increment 17 1742 4 55 318 944 50 161 635 0 158 118 121 21 1029 3 13 69 70 8 0 3 0 204 94 5 4 5 15 2 6 0 0 7 20 6 13 37 30 0 0 7 8 24 6 40 13 1 17 56 19 190 2 11 9 13
Last week 83 6183 44 318 1968 5594 348 1065 4245 4784 330 682 1269 111 6543 121 56 342 841 38 12 6 2 1159 462 44 32 90 86 26 37 162 16 57 67 42 42 184 151 16 4 36 26 112 59 155 54 30 140 229 123 1350 24 55 76 40
Days since peak 31 101 29 60 26 22 78 122 123 20 28 113 117 108 53 86 9 95 105 123 123 123 112 108 123 78 107 87 78 51 94 128 108 4 102 18 19 120 115 131 126

Deaths count forecast Europe (bold red line in graphs) 2020-08-16 to 2020-08-22

DateUKEUBEBGDEESFRITPLROSE
2020-08-15 46706 137840 9935 495 9235 28617 30279 35392 1869 2954 5783
2020-08-16 46850 138000 9945 499 9237 28630 30290 35470 1875 3026 5791
2020-08-17 46850 138200 9954 511 9238 28640 30300 35540 1878 3065 5792
2020-08-18 46880 138400 9963 522 9244 28660 30310 35630 1888 3122 5793
2020-08-19 46960 138600 9972 532 9251 28670 30310 35710 1898 3178 5800
2020-08-20 46960 138800 9980 535 9255 28680 30320 35800 1912 3244 5803
2020-08-21 46990 139000 9989 544 9267 28700 30330 35880 1924 3304 5805
2020-08-22 47000 139200 9998 547 9271 28710 30340 35960 1934 3372 5805

Deaths count forecast (bold red line in graphs) 2020-08-16 to 2020-08-22

DateAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-UTUS-VAUS-WAUS-WI
2020-08-15 396 107232 9072 10395 14810 49980 6071 19492 56543 25856 2600 15585 11677 5955 169481 1828 600 4491 11218 1896 9345 4561 975 269 7726 2921 405 810 4307 3624 6510 1699 1313 2080 2343 15910 711 1069 32833 3824 657 386 7451 2260 1322 10268 301 2381 1762 1038
2020-08-16 412 108000 9078 10500 15060 50850 6128 19660 56870 26100 2672 15640 11920 5976 170200 1858 612 4563 11380 1896 9650 4561 979 274 7741 2921 409 811 4371 3634 6519 1703 1321 2129 2363 15920 716 1090 32840 3835 671 389 7451 2297 1347 10330 305 2395 1774 1044
2020-08-17 429 108600 9084 10570 15380 51700 6183 19820 57410 26680 2744 15670 12170 5996 170800 1877 625 4563 11540 1898 9810 4564 984 277 7745 2921 412 814 4392 3643 6527 1706 1328 2157 2384 15940 720 1111 32850 3843 678 391 7451 2334 1373 10450 309 2409 1786 1044
2020-08-18 445 109800 9090 10590 15690 52540 6239 19990 58300 27370 2817 15780 12410 6017 172000 1910 637 4612 11720 1908 10170 4665 993 285 7766 2943 416 822 4415 3652 6535 1712 1335 2206 2415 15960 725 1132 32860 3875 701 400 7471 2371 1399 10680 312 2423 1798 1053
2020-08-19 461 111000 9096 10620 16030 53370 6294 20150 58990 28060 2890 15890 12660 6037 173400 1941 650 4726 12020 1911 10500 4755 1001 288 7783 2957 419 827 4461 3661 6543 1722 1342 2265 2449 15960 729 1154 32870 3901 720 406 7497 2408 1426 10970 316 2437 1810 1059
2020-08-20 478 112200 9102 10730 16340 54210 6349 20310 59620 28770 2963 15980 12900 6056 174400 1952 663 4783 12230 1917 10790 4815 1008 293 7804 2973 422 833 4500 3671 6551 1728 1349 2305 2467 15970 734 1177 32880 3921 739 412 7514 2446 1454 11210 320 2451 1822 1067
2020-08-21 495 112500 9108 10770 16670 55050 6405 20470 60270 29490 3038 16070 13150 6076 175600 1961 676 4822 12560 1923 11150 4871 1016 304 7826 2984 426 840 4531 3680 6559 1734 1356 2356 2493 15980 738 1199 32890 3951 753 415 7543 2483 1482 11510 323 2466 1833 1074
2020-08-22 513 114000 9114 10840 16970 55900 6460 20630 60920 30240 3113 16170 13400 6096 176600 1970 690 4883 12750 1930 11390 4946 1022 309 7831 2997 429 846 4531 3689 6567 1740 1363 2400 2521 16000 742 1223 32890 3980 765 418 7556 2521 1511 11680 327 2480 1845 1085

Deaths count average forecast Europe (bold black line in graphs) 2020-08-16 to 2020-08-22

DateUKEUBEBGDEESFRITPLROSE
2020-08-15 46706 137840 9935 495 9235 28617 30279 35392 1869 2954 5783
2020-08-16 46710 137900 9939 499 9236 28630 30290 35410 1874 3005 5785
2020-08-17 46730 137900 9943 510 9237 28630 30290 35430 1880 3055 5787
2020-08-18 46770 138000 9947 520 9242 28640 30300 35450 1890 3112 5788
2020-08-19 46830 138200 9952 530 9249 28650 30310 35470 1900 3169 5793
2020-08-20 46850 138300 9957 536 9254 28660 30320 35480 1912 3232 5798
2020-08-21 46910 138400 9962 546 9264 28670 30330 35500 1922 3299 5802
2020-08-22 46960 138500 9967 552 9270 28680 30340 35520 1932 3362 5803

Deaths count average forecast (bold black line in graphs) 2020-08-16 to 2020-08-22

DateAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-UTUS-VAUS-WAUS-WI
2020-08-15 396 107232 9072 10395 14810 49980 6071 19492 56543 25856 2600 15585 11677 5955 169481 1828 600 4491 11218 1896 9345 4561 975 269 7726 2921 405 810 4307 3624 6510 1699 1313 2080 2343 15910 711 1069 32833 3824 657 386 7451 2260 1322 10268 301 2381 1762 1038
2020-08-16 409 107700 9076 10440 15090 50730 6112 19590 56810 26330 2627 15650 11870 5964 170000 1839 610 4498 11330 1897 9500 4579 980 270 7733 2921 408 811 4348 3633 6513 1704 1315 2106 2350 15920 712 1080 32840 3825 663 388 7455 2273 1341 10360 303 2392 1768 1039
2020-08-17 421 108300 9082 10510 15400 51620 6161 19720 57350 26980 2670 15730 12110 5979 170500 1859 624 4519 11500 1899 9660 4605 985 273 7740 2921 411 814 4376 3642 6517 1707 1320 2127 2370 15920 716 1096 32840 3830 669 390 7460 2293 1365 10510 306 2406 1777 1040
2020-08-18 435 109400 9088 10560 15730 52510 6218 19850 58270 27680 2724 15840 12370 5995 171500 1886 637 4567 11680 1902 9950 4680 994 280 7758 2940 415 820 4406 3652 6522 1712 1325 2177 2401 15940 719 1119 32850 3860 680 398 7470 2336 1392 10750 310 2419 1791 1049
2020-08-19 447 110600 9095 10610 16070 53410 6283 19980 58970 28340 2783 15950 12630 6011 172600 1912 650 4646 11990 1905 10210 4763 1002 284 7775 2953 418 825 4448 3661 6527 1723 1331 2233 2435 15940 723 1143 32850 3886 691 404 7487 2376 1418 11040 313 2433 1799 1054
2020-08-20 460 111700 9101 10710 16410 54320 6338 20120 59610 29090 2848 16060 12900 6027 173600 1928 664 4700 12240 1909 10480 4820 1010 290 7795 2967 421 830 4485 3670 6534 1728 1337 2278 2455 15950 727 1170 32860 3909 702 408 7503 2416 1445 11240 317 2446 1811 1063
2020-08-21 472 112400 9106 10780 16760 55250 6393 20240 60300 30270 2913 16170 13180 6043 174600 1946 679 4756 12540 1914 10780 4877 1017 300 7813 2976 425 835 4521 3680 6542 1734 1342 2328 2487 15960 731 1196 32870 3944 714 413 7519 2448 1473 11550 321 2460 1824 1074
2020-08-22 489 113600 9112 10850 17090 56190 6443 20350 61040 30940 2980 16280 13460 6060 175500 1966 693 4817 12790 1917 11030 4945 1025 306 7826 2986 428 841 4541 3689 6549 1740 1348 2378 2520 15970 735 1223 32870 3964 723 418 7531 2494 1499 11770 324 2474 1836 1085

Deaths count scenario forecast (bold purple line in graphs) 2020-08-16 to 2020-08-24

DateUKEUBEBGDEESFRITPLROSEAustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-FLUS-GAUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-TNUS-TXUS-UTUS-VAUS-WAUS-WI
2020-08-15 46706 137840 9935 495 9235 28617 30279 35392 1869 2954 5783 396 107232 9072 10395 14810 49980 6071 19492 56543 25856 2600 15585 11677 5955 169481 1828 600 4491 11218 1896 9345 4561 975 269 7726 2921 405 810 4307 3624 6510 1699 1313 2080 2343 15910 711 1069 32833 3824 657 386 7451 2260 1322 10268 301 2381 1762 1038
2020-08-16 46760 138000 9942 506 9239 28630 30310 35390 1874 2996 5787 411 107900 9079 10440 15100 50440 6121 19610 56980 26230 2600 15660 12010 5966 170400 1864 612 4529 11350 1896 9530 4570 982 273 7743 2929 408 812 4354 3635 6510 1704 1315 2112 2363 15910 714 1084 32840 3832 662 391 7466 2289 1340 10510 304 2393 1773 1043
2020-08-17 46790 138100 9951 513 9243 28640 30330 35400 1884 3030 5789 426 108600 9086 10490 15390 51050 6169 19740 57500 26470 2625 15750 12300 5976 171100 1881 623 4569 11470 1899 9710 4642 988 278 7760 2939 411 817 4374 3644 6516 1710 1321 2136 2381 15920 718 1099 32840 3851 667 396 7482 2318 1357 10720 307 2404 1781 1049
2020-08-18 46800 138300 9960 520 9247 28640 30340 35410 1894 3075 5792 441 109200 9093 10530 15670 51440 6214 19840 58090 26840 2666 15840 12550 5989 171800 1896 634 4608 11600 1902 9840 4696 994 281 7777 2949 413 820 4392 3652 6526 1718 1324 2164 2401 15920 722 1118 32850 3870 674 400 7497 2344 1374 10930 309 2413 1790 1053
2020-08-19 46810 138500 9966 528 9251 28650 30370 35410 1903 3123 5794 455 109900 9100 10570 15940 51790 6257 19970 58660 27370 2705 15930 12890 5995 172400 1911 645 4646 11720 1904 10030 4759 1000 289 7794 2958 415 823 4412 3660 6533 1725 1329 2191 2422 15920 725 1138 32850 3891 680 404 7513 2371 1392 11140 311 2421 1797 1056
2020-08-20 46820 138700 9972 535 9254 28660 30380 35410 1912 3173 5795 467 110500 9106 10610 16200 52190 6297 20080 59270 27690 2743 16010 13160 5997 172900 1925 656 4680 11850 1906 10170 4810 1006 294 7807 2969 416 826 4426 3668 6537 1731 1333 2217 2443 15930 729 1155 32860 3906 685 408 7530 2400 1407 11350 313 2428 1803 1060
2020-08-21 46840 138800 9975 541 9256 28660 30400 35410 1918 3218 5796 476 111100 9112 10630 16450 52420 6335 20170 59810 28190 2780 16090 13470 5998 173300 1934 667 4712 11980 1909 10310 4860 1010 299 7818 2980 418 828 4439 3674 6540 1738 1336 2244 2461 15930 733 1172 32860 3920 690 412 7547 2425 1423 11550 314 2435 1808 1064
2020-08-22 46850 139100 9976 549 9259 28660 30410 35420 1924 3265 5798 482 111800 9118 10670 16690 52700 6370 20280 60400 28850 2817 16170 13810 6003 173600 1948 680 4747 12100 1911 10460 4918 1014 306 7828 2987 419 830 4449 3680 6548 1744 1339 2296 2482 15930 737 1193 32860 3933 695 415 7563 2452 1440 11740 315 2442 1812 1066
2020-08-23 46850 139300 9979 555 9261 28660 30440 35420 1930 3312 5800 496 112300 9123 10700 16970 53030 6404 20380 60940 29630 2850 16240 14170 6007 173900 1961 690 4776 12210 1912 10610 4969 1019 313 7838 2996 420 831 4453 3686 6549 1750 1342 2326 2500 15930 741 1211 32860 3946 699 419 7579 2479 1455 11940 316 2448 1818 1069
2020-08-24 46860 139500 9979 561 9262 28660 30460 35420 1936 3353 5801 502 112900 9128 10730 17260 53260 6435 20470 61490 29800 2885 16310 14380 6008 174000 1974 700 4806 12330 1912 10740 5025 1023 317 7848 3001 420 832 4456 3691 6553 1756 1344 2352 2517 15930 745 1226 32860 3958 704 422 7593 2504 1468 12120 317 2452 1826 1071

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