COVID-19 short-term forecasts Deaths 2020-04-08


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 The documentation that is provided is still in progress and not peer reviewed.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.
[2020-04-08] 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.

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.
  • 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, but remains preliminary. Also preliminary is the documentation of the medium term forecasts.

Deaths count average forecast Europe (bold black line in graphs) 2020-04-09 to 2020-04-13

DateUKEUATBEDEDKESFRIEITNLPTROSECH
2020-04-08 7097 52801 273 2240 2349 218 14792 10869 235 17669 2248 380 220 687 895
2020-04-09 8000 56800 300 2510 2620 230 15500 12000 260 18200 2430 410 240 790 950
2020-04-10 8900 61600 310 2760 2860 260 16100 13500 280 18700 2620 440 260 870 1010
2020-04-11 9900 66800 330 3040 3130 280 16800 15100 310 19300 2830 470 280 970 1080
2020-04-12 11100 72500 360 3350 3430 300 17500 17000 330 19800 3060 500 290 1080 1140
2020-04-13 12400 78700 380 3700 3760 330 18300 19000 360 20400 3300 530 320 1210 1210

Deaths count average forecast (bold black line in graphs) 2020-04-09 to 2020-04-13

DateBrazilCanadaIranUSUS-CAUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-08 819 407 3993 14695 506 335 322 370 464 652 433 959 1504 6268 454 106840
2020-04-09 930 470 4120 16700 560 390 360 410 530 720 500 1080 1730 7000 490 117000
2020-04-10 1030 540 4260 18700 610 440 400 450 580 790 550 1190 1960 7800 520 129000
2020-04-11 1140 610 4400 20900 670 500 450 500 640 870 610 1310 2210 8700 560 142000
2020-04-12 1260 700 4550 23400 730 560 500 550 710 950 680 1440 2490 9600 600 156000
2020-04-13 1400 790 4700 26200 790 630 550 600 780 1030 760 1600 2820 10700 640 172000

Deaths count forecast Europe (bold red line in graphs) 2020-04-09 to 2020-04-13

DateUKEUATBEDEDKESFRIEITNLPTROSECH
2020-04-08 7097 52801 273 2240 2349 218 14792 10869 235 17669 2248 380 220 687 895
2020-04-09 8000 56500 280 2460 2670 230 15300 11500 240 18100 2390 410 230 820 940
2020-04-10 9100 60600 300 2720 3030 240 15900 12300 260 18600 2550 430 250 970 990
2020-04-11 10200 64900 310 3000 3440 260 16500 13100 270 19100 2730 460 270 1140 1050
2020-04-12 11500 69600 330 3300 3880 270 17100 14000 290 19600 2910 500 290 1330 1110
2020-04-13 13000 74700 350 3640 4390 280 17700 14900 310 20100 3120 530 310 1550 1170

Deaths count forecast (bold red line in graphs) 2020-04-09 to 2020-04-13

DateBrazilCanadaIranUSUS-CAUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-08 819 407 3993 14695 506 335 322 370 464 652 433 959 1504 6268 454 106840
2020-04-09 890 470 4120 16500 560 380 370 410 500 740 490 1050 1720 6730 480 117000
2020-04-10 980 530 4250 18600 610 420 410 440 550 820 560 1150 1970 7330 510 128000
2020-04-11 1070 590 4370 20900 670 470 460 480 600 910 640 1260 2250 7980 540 140000
2020-04-12 1170 660 4510 23500 740 530 510 520 660 1000 730 1380 2550 8670 580 153000
2020-04-13 1280 730 4640 26400 810 590 570 560 730 1110 840 1510 2910 9430 610 167000

Deaths count scenario forecast (bold green line in graphs) 2020-04-09 to 2020-04-17

DateEUATDKESITNLPTCH
2020-04-08 52801 273 218 14792 17669 2248 380 895
2020-04-09 55400 290 230 15500 18200 2380 400 940
2020-04-10 57900 310 250 16300 18700 2510 430 1000
2020-04-11 60600 320 260 17000 19100 2640 460 1050
2020-04-12 62900 330 270 17700 19600 2760 490 1090
2020-04-13 65200 330 290 18300 20000 2890 520 1150
2020-04-14 67500 340 300 18700 20300 3010 540 1180
2020-04-15 69600 340 310 19100 20600 3120 570 1220
2020-04-16 71600 340 320 19400 20800 3210 570 1240
2020-04-17 73700 350 330 19800 21000 3230 570 1280

Peak increase in estimated trend of Deaths in Europe 2020-04-08

UKEUATBEDEDKESFRIEITNLPTROSECH
Peak date -- -- -- -- --04-0404-02 -- --03-28 -- --04-03 --04-03
Peak daily increment 18 897 824 18 61
Days from 100 to peak 3 20 24 1 11
Days from peak/2 to peak 14 16 19 10 16
Days since peak 4 6 11 5 5

Peak increase in estimated trend of Deaths 2020-04-08

BrazilCanadaIranUSUS-CAUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
Peak date -- --03-19 -- -- -- -- -- -- -- -- -- -- -- -- --
Peak daily increment 150
Days from 100 to peak 14
Days from peak/2 to peak 16
Days since peak 20

Initial visual evaluation of forecasts of Deaths