COVID-19 short-term forecasts Deaths 2020-04-18


Disclaimer

  • 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. The documentation that is provided is still in progress and not peer reviewed. 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.

Recent changes

[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.
[2020-03-26] Scenario forecasts that are based on what happened in China earlier this year, only for Italy.
[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).
[2020-04-02] Now including more US States, based on New York Times data. And the world.
[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.
[2020-04-08] Minor correction to peak estimates. Added table with scenario forecasts.
[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.
[2020-04-10] Updated documentation with better description of short-term estimates and peak determination.
[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).
[2020-04-17] Bird and Nielsen look into nowcasting death counts in England.

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.

Deaths count average forecast Europe (bold black line in graphs) 2020-04-19 to 2020-04-25

DateUKEUATBEDEDKESFRIEITNLPLPTROSECH
2020-04-18 15464 81309 443 5453 4459 346 20043 19323 571 23227 3601 347 687 421 1511 1368
2020-04-19 16300 84000 460 5760 4720 360 20400 20100 610 23700 3750 370 720 440 1620 1410
2020-04-20 17000 87000 470 6050 4990 370 20900 21000 660 24300 3890 390 750 450 1730 1460
2020-04-21 17800 90000 480 6350 5280 380 21300 21800 700 24800 4030 410 780 470 1850 1500
2020-04-22 18600 93000 500 6660 5580 390 21800 22700 750 25300 4180 430 820 490 1980 1550
2020-04-23 19500 96000 510 6990 5900 410 22300 23700 800 25900 4340 460 850 510 2120 1600
2020-04-24 20300 99000 520 7340 6250 420 22800 24700 860 26400 4500 480 890 520 2270 1650
2020-04-25 21300 102000 540 7700 6610 440 23300 25800 910 27000 4670 510 930 540 2430 1700

Deaths count average forecast (bold black line in graphs) 2020-04-19 to 2020-04-25

DateBrazilCanadaIndiaIndonesiaIranMexicoPhilippinesTurkeyUSUS-CAUS-COUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-18 2354 1399 521 535 5031 546 397 1890 38664 1146 409 1086 747 670 1272 1267 1560 2307 4070 13362 629 204290
2020-04-19 2570 1540 550 560 5110 610 410 2020 42300 1240 430 1180 800 700 1380 1330 1730 2440 4400 14000 650 219000
2020-04-20 2790 1700 580 590 5200 670 430 2160 46300 1340 440 1310 850 740 1500 1400 1900 2580 4790 14600 660 237000
2020-04-21 3030 1870 610 610 5290 750 450 2310 50700 1440 460 1460 910 770 1620 1470 2090 2730 5210 15200 680 257000
2020-04-22 3290 2050 640 640 5390 830 470 2470 55500 1550 480 1620 970 810 1750 1550 2300 2890 5660 15900 700 279000
2020-04-23 3570 2260 670 670 5480 920 490 2630 60800 1670 500 1810 1030 850 1900 1640 2530 3050 6160 16600 720 302000
2020-04-24 3870 2480 710 710 5580 1030 510 2810 66600 1800 520 2020 1110 890 2050 1730 2800 3230 6700 17300 740 327000
2020-04-25 4210 2720 740 740 5670 1150 530 3000 72900 1940 540 2250 1180 930 2220 1830 3100 3420 7280 18000 760 354000

Deaths count forecast Europe (bold red line in graphs) 2020-04-19 to 2020-04-25

DateUKEUATBEDEDKESFRIEITNLPLPTROSECH
2020-04-18 15464 81309 443 5453 4459 346 20043 19323 571 23227 3601 347 687 421 1511 1368
2020-04-19 16200 84000 460 5710 4730 360 20300 20000 620 23700 3750 370 710 440 1630 1400
2020-04-20 17000 86000 470 5980 4970 370 20600 20800 660 24200 3900 390 740 450 1750 1440
2020-04-21 17800 89000 480 6260 5230 380 20900 21600 710 24700 4050 410 770 460 1870 1490
2020-04-22 18700 92000 500 6540 5510 390 21200 22400 770 25200 4210 430 800 480 2010 1530
2020-04-23 19500 94000 510 6840 5800 400 21500 23200 820 25700 4370 450 830 490 2150 1570
2020-04-24 20400 97000 520 7140 6100 420 21900 24100 880 26200 4540 480 870 510 2310 1620
2020-04-25 21400 100000 540 7460 6420 430 22200 25000 950 26700 4720 510 900 520 2480 1660

Deaths count forecast (bold red line in graphs) 2020-04-19 to 2020-04-25

DateBrazilCanadaIndiaIndonesiaIranMexicoPhilippinesTurkeyUSUS-CAUS-COUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-18 2354 1399 521 535 5031 546 397 1890 38664 1146 409 1086 747 670 1272 1267 1560 2307 4070 13362 629 204290
2020-04-19 2490 1560 540 560 5110 600 410 2010 42300 1220 420 1140 790 690 1450 1310 1730 2430 4340 13900 650 220000
2020-04-20 2650 1690 570 580 5190 660 420 2150 46300 1300 440 1200 840 710 1640 1360 1910 2560 4630 14500 660 237000
2020-04-21 2810 1830 600 600 5270 730 440 2280 50700 1390 450 1270 890 730 1850 1400 2100 2690 4930 15000 680 256000
2020-04-22 2980 1980 630 620 5350 810 450 2430 55500 1490 470 1350 950 760 2070 1460 2310 2820 5250 15600 700 276000
2020-04-23 3170 2140 660 640 5430 890 460 2590 60700 1590 490 1420 1000 780 2320 1510 2550 2970 5590 16100 720 297000
2020-04-24 3360 2310 690 660 5510 980 480 2750 66400 1700 500 1510 1060 800 2610 1570 2810 3120 5950 16700 740 320000
2020-04-25 3570 2500 730 680 5590 1090 490 2930 72600 1820 520 1600 1130 830 2920 1630 3100 3280 6340 17300 760 345000

Deaths count scenario forecast (bold green line in graphs) 2020-04-19 to 2020-04-27

DateUKEUATBEDEDKESFRIEITNLPLPTROSECHBrazilCanadaIranPhilippinesUSUS-CAUS-COUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-18 15464 81309 443 5453 4459 346 20043 19323 571 23227 3601 347 687 421 1511 1368 2354 1399 5031 397 38664 1146 409 1086 747 670 1272 1267 1560 2307 4070 13362 629 204290
2020-04-19 16000 83800 450 5750 4830 360 20600 20000 600 23700 3690 370 710 440 1610 1400 2540 1500 5120 420 42200 1220 430 1170 800 710 1350 1360 1710 2460 4370 14000 640 217000
2020-04-20 16700 85800 460 6050 5090 370 21000 20700 640 24100 3780 380 740 460 1720 1440 2710 1550 5190 430 45400 1300 440 1210 840 740 1420 1430 1840 2580 4640 14600 650 229000
2020-04-21 17400 88000 480 6340 5350 370 21400 21300 670 24500 3870 400 760 470 1820 1470 2880 1550 5270 450 48400 1380 460 1220 890 760 1490 1500 1970 2690 4910 15100 660 241000
2020-04-22 18000 90000 490 6530 5600 380 21700 21900 700 24900 3970 410 790 490 1910 1500 3010 1550 5350 460 50100 1450 470 1230 930 790 1560 1560 2110 2800 5180 15700 680 253000
2020-04-23 18600 91900 500 6790 5840 390 22000 22500 730 25300 4060 430 810 500 2010 1540 3130 1550 5410 480 52600 1530 490 1230 980 810 1630 1630 2240 2910 5440 16200 690 263000
2020-04-24 19100 93800 510 6990 6080 400 22300 23100 760 25700 4160 440 830 520 2100 1570 3250 1550 5460 490 55100 1600 500 1240 1020 820 1700 1690 2370 3010 5690 16700 700 274000
2020-04-25 19700 95800 520 7210 6310 400 22500 23700 780 26100 4230 450 850 530 2190 1590 3370 1560 5510 510 57600 1670 520 1250 1060 840 1760 1750 2500 3110 5960 17200 700 285000
2020-04-26 20200 97600 520 7470 6540 400 22800 24200 810 26300 4280 470 870 540 2280 1620 3520 1570 5550 520 60300 1740 530 1260 1100 850 1820 1810 2620 3210 6200 17600 710 295000
2020-04-27 20700 99000 530 7690 6760 410 23000 24700 840 26600 4350 480 890 550 2370 1650 3700 1590 5600 540 62100 1810 550 1280 1140 870 1880 1870 2750 3300 6430 18100 720 305000

Peak increase in estimated trend of Deaths in Europe 2020-04-18

UKEUATBEDEDKESFRIEITNLPLPTROSECH
Peak date04-1004-0704-0804-10 --04-0404-0204-07 --03-2804-0704-1204-1104-11 --04-04
Peak daily increment 880 3215 23 357 19 902 1021 826 159 21 33 24 61
Days from 100 to peak 22 34 9 17 3 20 23 24 18 6 13 9 12
Days from peak/2 to peak 16 24 17 15 14 16 17 19 18 18 19 17 17
Days since peak 8 11 10 8 14 16 11 21 11 6 7 7 14

Peak increase in estimated trend of Deaths 2020-04-18

BrazilCanadaIndiaIndonesiaIranMexicoPhilippinesTurkeyUSUS-CAUS-COUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
Peak date -- --04-1104-1403-19 --04-13 -- -- --04-11 -- --04-07 --04-14 --04-11 --04-1104-06 --
Peak daily increment 39 40 150 27 24 42 75 141 787 30
Days from 100 to peak 6 16 14 12 8 8 18 14 20 15
Days from peak/2 to peak 15 26 16 26 18 16 21 15 16 30
Days since peak 7 4 30 5 7 11 4 7 7 12

Initial visual evaluation of forecasts of Deaths