COVID-19 short-term forecasts Deaths 2020-10-26


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:
    [2020-10-11]Short-term forecasting of the coronavirus pandemic (with Jennie Castle and David Hendry) is now in press at the International Journal of Forecasting.

Peak increase in estimated trend of Deaths in Europe 2020-10-26

UKEUATBEBGBSCZDEDKESFIFRGRHRHUIEITNLPLPTROSESINOCH
Peak date (mm-dd)04-1006-1909-0708-15 --10-06 --09-2508-1006-1904-2109-1810-22 -- --07-2308-1509-26 -- -- --09-01 --08-1406-16
Peak daily increment 964 805 5 9 2 11 1 914 30 61 10 4 127 19 4 3 7
Days since peak 199 129 49 72 20 31 77 129 188 38 4 95 72 30 55 73 132
Last total 44998 165313 992 10810 1136 356 2365 10091 708 35031 354 34746 581 452 1472 1885 37479 7072 4483 2343 6470 5933 251 279 2111
Last daily increment 102 1465 13 0 42 8 164 29 6 279 1 510 7 15 47 3 141 26 45 27 79 0 11 0 28
Last week 1031 6415 78 321 117 31 746 209 20 821 3 1110 53 70 261 20 774 258 762 130 474 11 59 1 -34
Previous peak date --04-0604-0604-15 --04-11 --04-1504-0403-31 --04-08 -- --04-2304-2403-2904-0404-2604-0305-0204-12 --04-0704-06
Previous peak daily increment 3095 20 328 7 226 15 946 943 14 167 781 153 23 30 25 98 8 60
Low between peaks -892 0 2 -2 3 0 -1351 7 0 6 -6 -5 0 1

Peak increase in estimated trend of Deaths 2020-10-26

AustraliaBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-DCUS-DEUS-FLUS-GAUS-HIUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-MTUS-NCUS-NDUS-NEUS-NHUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-SDUS-TNUS-TXUS-UTUS-VAUS-WAUS-WIUS-WV
Peak date (mm-dd)09-0307-2110-0207-1708-2309-1209-23 --10-0507-2309-14 --07-2209-2408-0409-1609-1507-2108-0610-1307-1309-0906-2308-0708-2209-18 --09-0905-1208-15 -- --08-0908-2004-2909-0905-28 --08-2610-21 -- --05-2005-2906-2505-1308-1308-3108-29 --07-2805-0507-28 -- --07-2710-0209-1508-06 --09-16
Peak daily increment 35 1065 79 785 318 1159 121 1716 2947 159 323 69 1078 99 124 78 138 28 9 1 46 175 66 5 19 112 12 36 106 56 38 23 31 14 40 25 1566 9 18 26 92 5 137 45 386 5 68 13 5
Days since peak 53 97 24 101 64 44 33 21 95 42 96 32 83 40 41 97 81 13 105 47 125 80 65 38 47 167 72 78 67 180 47 151 61 5 159 150 123 166 74 56 58 90 174 90 91 24 41 81 40
Last total 905 157397 10026 14003 30348 119502 13411 32953 89171 34149 7039 26092 19008 9874 225706 2866 1833 5874 17386 2226 4588 642 685 16449 7639 211 1657 580 9522 3907 969 1410 5648 9874 4089 7469 2353 2621 3263 303 4170 461 601 475 16292 976 1745 33405 5217 1251 655 8659 3823 375 3122 17978 459 3577 2318 1788 426
Last daily increment 0 263 31 59 348 488 112 337 247 0 62 217 40 75 477 0 21 1 28 3 11 0 4 20 18 0 22 7 17 13 13 3 17 17 3 30 4 5 8 6 13 5 5 2 7 9 1 4 11 2 2 12 21 0 29 23 0 2 25 10 1
Last week 0 2560 177 301 1076 3588 677 1919 2278 329 349 1619 352 429 4654 61 105 38 331 44 29 0 17 344 151 23 81 45 245 132 74 68 76 123 51 168 107 168 61 51 178 49 38 7 65 34 18 59 134 60 22 143 127 45 209 420 12 95 39 155 15
Previous peak date -- --05-06 -- --06-16 --03-20 -- --07-12 -- --04-1504-13 -- -- -- --04-2404-2004-29 -- --04-07 --05-22 -- --05-02 --04-1404-1404-25 --04-14 --04-30 -- -- -- -- -- --04-22 --04-1205-1804-2904-16 -- --04-29 -- -- --04-1704-2204-0604-1004-23
Previous peak daily increment 168 1662 150 92 125 2223 72 105 11 44 14 99 10 64 459 137 17 317 10 3573 76 7 24 6 104 25 12 16
Low between peaks 4 388 20 16 532 2 3 1 12 5 12 -1 6 52 3 7 15 6 1 9 -17 0

Deaths count forecast Europe (bold red line in graphs) 2020-10-27 to 2020-11-02

DateUKEUATBEBGBSCZDEDKESFRGRHRHUIEITNLPLPTROSI
2020-10-26 44998 165313 992 10810 1136 356 2365 10091 708 35031 34746 581 452 1472 1885 37479 7072 4483 2343 6470 251
2020-10-27 45220 166400 1004 10820 1164 362 2542 10140 710 35110 34840 590 465 1532 1889 37610 7132 4641 2371 6527 260
2020-10-28 45390 167500 1015 10840 1190 367 2725 10180 713 35230 34950 599 481 1591 1892 37730 7186 4794 2397 6582 268
2020-10-29 45550 168600 1027 10860 1215 373 2897 10220 715 35350 35070 608 498 1653 1895 37850 7225 4968 2423 6639 277
2020-10-30 45740 169600 1039 10880 1239 378 3079 10270 717 35460 35180 616 510 1715 1898 37960 7262 5123 2449 6694 285
2020-10-31 45920 170700 1051 10900 1263 384 3268 10300 719 35570 35290 625 528 1780 1901 38080 7312 5301 2474 6749 294
2020-11-01 46050 171800 1062 10920 1287 389 3456 10330 721 35680 35410 633 541 1847 1904 38200 7340 5408 2499 6805 303
2020-11-02 46160 172800 1074 10930 1312 395 3685 10360 724 35790 35520 642 554 1916 1907 38310 7368 5469 2525 6861 312

Deaths count forecast (bold red line in graphs) 2020-10-27 to 2020-11-02

DateBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-FLUS-GAUS-HIUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-MTUS-NCUS-NDUS-NEUS-NJUS-NMUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-SDUS-TNUS-TXUS-VAUS-WAUS-WI
2020-10-26 157397 10026 14003 30348 119502 13411 32953 89171 34149 7039 26092 19008 9874 225706 2866 1833 5874 17386 2226 4588 16449 7639 211 1657 580 9522 3907 969 1410 5648 9874 4089 7469 2353 2621 3263 303 4170 461 601 16292 976 33405 5217 1251 655 8659 3823 375 3122 17978 3577 2318 1788
2020-10-27 158100 10050 14040 30440 120100 13510 33280 90080 34230 7092 26360 19230 9940 226300 2891 1850 5885 17450 2227 4591 16620 7679 212 1666 580 9535 3930 983 1416 5657 9891 4096 7488 2353 2639 3278 309 4197 470 605 16290 980 33410 5217 1260 660 8675 3829 382 3156 18060 3590 2329 1791
2020-10-28 158700 10070 14050 30600 120600 13610 33540 90720 34310 7143 26630 19310 10010 227300 2916 1868 5898 17540 2236 4594 16700 7700 223 1682 590 9595 3947 1002 1432 5667 9908 4102 7507 2384 2679 3298 314 4225 481 610 16300 984 33410 5261 1277 662 8705 3845 388 3187 18150 3604 2335 1831
2020-10-29 159200 10090 14120 30750 121100 13710 33760 91020 34380 7194 26890 19420 10080 228100 2940 1885 5903 17620 2240 4597 16760 7722 225 1691 595 9637 3979 1024 1448 5674 9924 4108 7525 2401 2679 3307 320 4252 489 614 16310 988 33420 5266 1287 664 8729 3879 394 3218 18170 3617 2340 1851
2020-10-30 159700 10110 14180 30910 121700 13800 33960 91760 34460 7245 27140 19470 10150 228900 2959 1901 5909 17670 2250 4599 16830 7763 227 1712 602 9667 4001 1041 1458 5695 9941 4114 7543 2415 2711 3313 325 4280 499 618 16320 991 33420 5292 1297 674 8756 3895 400 3248 18270 3631 2347 1880
2020-10-31 160100 10130 14230 31060 122200 13890 34170 92220 34530 7296 27390 19520 10210 229700 2964 1918 5915 17700 2256 4602 16890 7803 229 1715 609 9711 4021 1045 1466 5695 9957 4120 7561 2424 2791 3327 331 4308 508 622 16320 995 33420 5313 1304 677 8777 3911 406 3277 18370 3645 2347 1896
2020-11-01 160200 10160 14280 31210 122800 13990 34350 92520 34600 7347 27640 19540 10280 230000 2964 1935 5919 17710 2260 4605 16920 7808 229 1717 610 9732 4034 1045 1470 5713 9973 4125 7579 2442 2796 3327 336 4336 514 627 16330 999 33430 5314 1309 677 8789 3921 413 3307 18400 3659 2347 1904
2020-11-02 160500 10180 14340 31370 123300 14090 34520 92710 34670 7399 27890 19580 10350 230400 2964 1952 5922 17730 2263 4608 16950 7825 230 1737 615 9745 4045 1054 1473 5728 9990 4131 7597 2445 2800 3329 342 4364 519 631 16340 1002 33430 5322 1312 679 8799 3935 419 3337 18430 3673 2368 1916

Deaths count average forecast Europe (bold black line in graphs) 2020-10-27 to 2020-11-02

DateUKEUATBEBGBSCZDEDKESFRGRHRHUIEITNLPLPTROSI
2020-10-26 44998 165313 992 10810 1136 356 2365 10091 708 35031 34746 581 452 1472 1885 37479 7072 4483 2343 6470 251
2020-10-27 45160 166300 1003 10850 1156 363 2520 10130 711 35160 34940 589 463 1520 1888 37600 7121 4594 2364 6545 260
2020-10-28 45330 167300 1015 10880 1176 368 2676 10160 714 35290 35070 597 475 1569 1892 37710 7173 4723 2382 6613 267
2020-10-29 45490 168300 1026 10920 1191 373 2831 10200 716 35410 35210 607 488 1618 1896 37810 7212 4865 2400 6687 273
2020-10-30 45660 169300 1037 10960 1206 377 2997 10240 718 35540 35340 617 497 1667 1899 37910 7246 5000 2418 6753 280
2020-10-31 45830 170200 1048 11000 1218 380 3173 10260 720 35640 35480 626 509 1711 1903 38010 7292 5147 2436 6816 289
2020-11-01 45990 171000 1059 11040 1231 384 3343 10290 722 35750 35610 636 517 1759 1907 38110 7317 5277 2454 6879 294
2020-11-02 46140 172000 1070 11070 1253 387 3542 10320 725 35870 35750 647 527 1807 1910 38200 7341 5394 2472 6941 300

Deaths count average forecast (bold black line in graphs) 2020-10-27 to 2020-11-02

DateBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-FLUS-GAUS-HIUS-IAUS-IDUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-MTUS-NCUS-NDUS-NEUS-NJUS-NMUS-NYUS-OHUS-OKUS-ORUS-PAUS-SCUS-SDUS-TNUS-TXUS-VAUS-WAUS-WI
2020-10-26 157397 10026 14003 30348 119502 13411 32953 89171 34149 7039 26092 19008 9874 225706 2866 1833 5874 17386 2226 4588 16449 7639 211 1657 580 9522 3907 969 1410 5648 9874 4089 7469 2353 2621 3263 303 4170 461 601 16292 976 33405 5217 1251 655 8659 3823 375 3122 17978 3577 2318 1788
2020-10-27 157900 10050 14040 30510 120000 13520 33230 89660 34200 7082 26350 19080 9940 226500 2876 1850 5879 17450 2231 4593 16520 7655 213 1676 584 9560 3944 985 1420 5658 9892 4096 7494 2361 2644 3285 310 4201 468 608 16300 981 33410 5227 1265 660 8686 3846 381 3152 18050 3588 2340 1819
2020-10-28 158400 10070 14070 30670 120600 13630 33440 90050 34260 7129 26620 19160 10010 227200 2894 1867 5889 17550 2239 4596 16610 7679 220 1690 592 9614 3958 1001 1434 5668 9909 4103 7515 2390 2678 3304 319 4229 478 613 16300 985 33420 5264 1280 663 8712 3862 387 3177 18140 3602 2344 1859
2020-10-29 158900 10090 14120 30810 121100 13730 33620 90230 34330 7174 26880 19240 10080 227800 2913 1885 5895 17640 2244 4599 16690 7703 223 1700 597 9654 3988 1020 1448 5678 9926 4109 7540 2407 2692 3314 325 4258 487 619 16310 989 33430 5270 1290 666 8736 3890 396 3201 18170 3616 2347 1879
2020-10-30 159300 10110 14180 30970 121700 13830 33800 91000 34390 7226 27140 19320 10150 228400 2929 1902 5902 17690 2253 4602 16760 7739 226 1718 603 9687 4011 1035 1459 5694 9943 4115 7559 2421 2721 3321 331 4285 497 624 16310 993 33440 5286 1301 673 8762 3907 403 3228 18260 3631 2352 1909
2020-10-31 159800 10130 14220 31150 122300 13930 33970 91300 34450 7276 27410 19400 10220 228800 2939 1920 5910 17730 2259 4605 16840 7774 228 1725 608 9724 4027 1042 1469 5700 9960 4121 7577 2431 2775 3334 339 4310 507 628 16320 997 33440 5299 1308 676 8782 3922 411 3252 18360 3645 2352 1922
2020-11-01 160000 10150 14270 31290 122800 14010 34100 91450 34520 7323 27660 19470 10290 229000 2948 1937 5916 17740 2264 4608 16900 7797 230 1731 610 9746 4037 1048 1476 5715 9977 4128 7593 2442 2792 3336 344 4329 516 631 16320 1001 33450 5303 1313 678 8797 3933 417 3273 18390 3660 2352 1925
2020-11-02 160400 10170 14320 31450 123400 14110 34280 91590 34580 7366 27910 19550 10360 229200 2956 1955 5921 17750 2270 4612 16960 7819 232 1743 615 9765 4051 1059 1483 5729 9994 4134 7610 2447 2810 3339 349 4349 524 635 16330 1005 33460 5307 1317 681 8811 3946 423 3297 18410 3674 2360 1934

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

[2020-10-11]Short-term forecasting of the coronavirus pandemic (with Jennie Castle and David Hendry) is now in press at the International Journal of Forecasting.
[2020-10-10]Temporarily removed forecasts from the Chinese scenarios, while investigating possibility to use own history from the first wave.
Added information on the previous peak (if present) to the peak tables.
Local forecasts for England: now dropping last four observations.
[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