COVID-19 short-term forecasts Confirmed 2020-04-13


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 The documentation that is provided is still in progress and not peer reviewed.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

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.

Confirmed count average forecast Europe (bold black line in graphs) 2020-04-14 to 2020-04-18

DateUKEUATBEBSCZDEDKESFIFRGRIEITNLPLPTROSENOCH
2020-04-13 88621 750490 14041 30589 5686 6059 130072 6318 170099 3064 136779 2145 10647 159516 26551 6934 16934 6633 10948 6603 25688
2020-04-14 94000 770000 14200 31900 5760 6180 133000 6480 174000 3170 141000 2190 11600 163000 27700 7270 17500 7010 11400 6690 26100
2020-04-15 101000 790000 14400 33400 5870 6340 136000 6680 178000 3290 146000 2240 12600 167000 28900 7660 18300 7400 12000 6790 26600
2020-04-16 108000 810000 14700 35000 5980 6500 140000 6870 182000 3420 151000 2280 13700 171000 30100 8070 19100 7820 12600 6880 27100
2020-04-17 115000 829000 14900 36600 6090 6670 144000 7070 187000 3550 156000 2330 14900 174000 31400 8490 19900 8250 13200 6970 27700
2020-04-18 123000 848000 15100 38300 6200 6830 147000 7270 191000 3680 161000 2390 16200 178000 32800 8940 20800 8720 13900 7070 28200

Confirmed count average forecast (bold black line in graphs) 2020-04-14 to 2020-04-18

DateAustraliaBrazilCanadaIranMalaysiaPhilippinesSouth AfricaUSUS-CAUS-COUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-13 6351 23430 25679 73303 4817 4932 2272 580619 24334 7691 13381 21011 13125 22025 21016 26867 25487 64584 195031 10538 2613902
2020-04-14 6390 24900 27000 74900 4960 5130 2360 612000 25400 8070 14600 22000 13700 23500 21600 29300 26400 67800 203000 10700 2729000
2020-04-15 6450 26800 28500 76500 5090 5290 2430 650000 26500 8420 16000 22900 14500 25100 22300 32000 27400 70900 213000 11000 2861000
2020-04-16 6510 28700 30100 78100 5230 5440 2510 691000 27700 8790 17500 23900 15300 26700 23100 34900 28500 74100 223000 11300 2996000
2020-04-17 6560 30800 31800 79700 5370 5600 2580 734000 29000 9170 19100 24900 16100 28400 23900 38100 29500 77500 234000 11600 3134000
2020-04-18 6620 33100 33600 81400 5510 5770 2660 781000 30300 9570 21000 26000 17100 30300 24700 41700 30600 81000 245000 11800 3277000

Confirmed count forecast Europe (bold red line in graphs) 2020-04-14 to 2020-04-18

DateUKEUATBEBSCZDEDKESFIFRGRIEITNLPLPTROSENOCH
2020-04-13 88621 750490 14041 30589 5686 6059 130072 6318 170099 3064 136779 2145 10647 159516 26551 6934 16934 6633 10948 6603 25688
2020-04-14 94000 768000 14200 31900 5770 6180 133000 6480 174000 3160 140000 2180 11500 163000 27600 7230 17300 6980 11400 6690 26100
2020-04-15 99000 786000 14400 33100 5840 6290 135000 6630 178000 3250 144000 2220 12500 167000 28800 7520 17800 7350 11800 6770 26500
2020-04-16 105000 803000 14600 34500 5910 6390 138000 6780 182000 3340 147000 2260 13600 170000 29900 7820 18200 7730 12300 6850 26900
2020-04-17 111000 820000 14700 35800 5980 6500 141000 6920 186000 3430 150000 2300 14800 174000 31100 8120 18700 8130 12700 6940 27400
2020-04-18 118000 836000 14900 37300 6050 6600 144000 7070 190000 3520 153000 2340 16100 178000 32300 8430 19200 8560 13200 7020 27800

Confirmed count forecast (bold red line in graphs) 2020-04-14 to 2020-04-18

DateAustraliaBrazilCanadaIranMalaysiaPhilippinesSouth AfricaUSUS-CAUS-COUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-13 6351 23430 25679 73303 4817 4932 2272 580619 24334 7691 13381 21011 13125 22025 21016 26867 25487 64584 195031 10538 2613902
2020-04-14 6400 24700 26800 74800 4940 5050 2340 612000 25300 8060 14800 21800 13600 23300 21500 29500 26400 67600 203000 10700 2739000
2020-04-15 6440 25900 28000 76300 5060 5240 2430 646000 26300 8430 16200 22800 14200 24700 22100 32100 27300 70700 211000 10900 2857000
2020-04-16 6480 27200 29300 77900 5200 5430 2520 684000 27400 8830 17800 23800 14700 26100 22600 35000 28200 73800 220000 11100 2975000
2020-04-17 6510 28500 30600 79400 5330 5630 2610 725000 28600 9230 19500 24800 15200 27600 23100 38100 29100 77100 228000 11300 3093000
2020-04-18 6540 29900 32000 80900 5470 5840 2700 770000 29800 9650 21400 25900 15800 29100 23600 41400 30000 80500 237000 11500 3212000

Confirmed count scenario forecast (bold green line in graphs) 2020-04-14 to 2020-04-22

DateUKEUATBEDEDKESFRITNLPLPTNOCHUSUS-NJUS-NYUS-WAAustraliaIranMalaysia
2020-04-13 88621 750490 14041 30589 130072 6318 170099 136779 159516 26551 6934 16934 6603 25688 580619 64584 195031 10538 6351 73303 4817
2020-04-14 94000 770000 14400 32000 133000 6470 175000 139000 164000 27800 7240 17800 6650 26200 611000 67800 204000 11000 6460 75000 4930
2020-04-15 99000 789000 14600 33300 136000 6590 180000 141000 167000 28900 7480 18500 6700 26800 637000 70800 212000 11300 6550 76700 5030
2020-04-16 103000 807000 14800 34500 139000 6710 184000 144000 171000 29900 7700 19200 6750 27300 664000 73800 221000 11600 6650 78300 5140
2020-04-17 107000 825000 15000 35600 141000 6840 188000 146000 174000 30900 7900 19800 6800 27800 688000 76700 228000 11800 6720 79900 5240
2020-04-18 109000 844000 15100 36800 144000 6990 192000 148000 177000 31800 8110 20500 6840 28300 713000 79300 236000 12100 6830 81600 5340
2020-04-19 112000 862000 15100 37600 147000 7150 197000 150000 180000 32300 8260 21100 6890 28800 734000 82100 243000 12400 6910 83100 5440
2020-04-20 115000 879000 15200 38100 148000 7300 200000 151000 183000 32600 8400 21500 6940 29300 757000 84900 250000 12600 6970 84700 5540
2020-04-21 118000 896000 15300 38600 150000 7440 204000 153000 185000 33200 8530 21800 6990 29700 776000 87600 256000 12900 7010 86100 5630
2020-04-22 122000 913000 15300 38700 152000 7590 208000 154000 187000 33700 8630 22100 7040 30200 789000 90200 262000 13100 7050 87500 5720

Peak increase in estimated trend of Confirmed in Europe 2020-04-13

UKEUATBEBSCZDEDKESFIFRGRIEITNLPLPTROSENOCH
Peak date --04-0403-2603-2903-2503-2803-2804-0603-2704-0604-0404-02 --03-21 --04-0704-0104-0804-0803-2703-23
Peak daily increment 32723 875 1476 287 284 6007 333 8157 175 10193 96 5704 407 830 349 557 297 1205
Days from 100 to peak 41 18 22 11 15 27 27 25 24 34 22 27 23 19 25 32 21 18
Days from peak/2 to peak 25 13 14 11 14 15 27 14 24 19 25 17 21 15 22 30 19 12
Days since peak 9 18 15 19 16 16 7 17 7 9 11 23 6 12 5 5 17 21

Peak increase in estimated trend of Confirmed 2020-04-13

AustraliaBrazilCanadaIranMalaysiaPhilippinesSouth AfricaUSUS-CAUS-COUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
Peak date03-2804-0804-0503-3104-0203-3103-2604-0604-0504-03 --04-0304-07 --04-04 --04-0404-0304-0504-0204-10
Peak daily increment 411 1660 1498 3109 180 361 190 31670 1335 389 1180 942 1771 1657 3807 9695 524 126784
Days from 100 to peak 18 25 25 35 24 17 8 34 28 19 19 22 19 17 19 28 26 79
Days from peak/2 to peak 14 18 17 28 25 13 8 17 19 16 13 17 13 13 12 16 22 63
Days since peak 16 5 8 13 11 13 18 7 8 10 10 6 9 9 10 8 11 3

Initial visual evaluation of forecasts of Confirmed