COVID-19 short-term forecasts Confirmed 2020-04-24


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 The documentation that is provided is still in progress and not peer reviewed.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.
[2020-04-24] A summary of our work on short-term COVID-19 forecasting appeared as a voxeu.

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.

Confirmed count average forecast Europe (bold black line in graphs) 2020-04-25 to 2020-05-01

DateUKEUATBEBSCZDEDKESFIFRGRHRHUIEITNLPLPTROSENOCH
2020-04-24 143464 941681 15071 44293 6710 7273 154999 8210 219764 4395 158636 2490 2009 2443 18184 192994 36535 10892 22797 10417 17567 7463 28677
2020-04-25 148000 956000 15100 45300 6780 7360 157000 8370 224000 4520 160000 2530 2040 2550 18800 196000 37300 11200 23300 10800 18400 7540 28900
2020-04-26 153000 968000 15200 46400 6850 7460 159000 8530 228000 4650 161000 2560 2060 2650 19300 198000 38100 11600 23800 11100 19400 7610 29100
2020-04-27 158000 979000 15300 47400 6930 7560 161000 8680 232000 4770 163000 2600 2090 2750 19800 201000 38900 11900 24300 11400 20400 7680 29300
2020-04-28 163000 990000 15400 48500 7000 7660 162000 8850 236000 4910 164000 2640 2120 2850 20300 204000 39700 12300 24800 11800 21500 7750 29500
2020-04-29 168000 1001000 15400 49600 7080 7760 164000 9010 240000 5040 165000 2680 2140 2960 20900 207000 40600 12600 25300 12100 22600 7820 29700
2020-04-30 174000 1011000 15500 50800 7160 7870 166000 9180 244000 5180 167000 2720 2170 3080 21400 210000 41400 13000 25900 12500 23800 7900 29900
2020-05-01 180000 1020000 15600 52000 7240 7970 168000 9350 248000 5330 168000 2760 2200 3190 22000 212000 42300 13400 26500 12900 25000 7970 30100

Confirmed count average forecast (bold black line in graphs) 2020-04-25 to 2020-05-01

DateAustraliaBrazilCanadaIndiaIndonesiaIranMalaysiaMexicoPhilippinesSouth AfricaTurkeyUSUS-CAUS-COUS-CTUS-DCUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-24 6677 54043 44054 24530 8211 88194 5691 11633 7192 4220 104912 905358 41368 12255 23921 3528 30525 21575 39658 26140 50969 36627 102196 271621 13120 3850686
2020-04-25 6690 58200 45600 26400 8600 89300 5750 12700 7380 4490 108000 938000 43800 13000 25200 3680 31400 22300 42400 26500 54800 37700 105000 278000 13400 4011000
2020-04-26 6710 62400 47400 28600 9100 90400 5800 13900 7530 4750 112000 970000 46800 13600 26700 3830 32100 23100 45300 26900 58100 38600 109000 282000 13600 4201000
2020-04-27 6720 66900 49400 31000 9600 91600 5860 15300 7690 5030 116000 1004000 49900 14300 28300 4000 32900 23800 48500 27300 61600 39400 112000 287000 13800 4398000
2020-04-28 6740 71800 51400 33600 10100 92700 5900 16800 7850 5320 120000 1040000 53400 15100 30100 4160 33700 24500 52000 27800 65400 40300 116000 292000 14000 4604000
2020-04-29 6750 77000 53600 36400 10700 93900 5950 18500 8010 5630 124000 1077000 57000 15900 31900 4340 34500 25300 55700 28200 69400 41100 119000 297000 14200 4816000
2020-04-30 6770 82600 55900 39600 11200 95100 5990 20400 8180 5960 129000 1117000 60900 16700 33800 4520 35300 26100 59800 28600 73700 42100 123000 302000 14500 5041000
2020-05-01 6780 88600 58400 43000 11900 96300 6030 22500 8350 6310 133000 1157000 65100 17600 35900 4720 36100 27000 64000 29000 78300 43000 127000 307000 14700 5272000

Confirmed count forecast Europe (bold red line in graphs) 2020-04-25 to 2020-05-01

DateUKEUATBEBSCZDEDKESFIFRGRHRHUIEITNLPLPTROSENOCH
2020-04-24 143464 941681 15071 44293 6710 7273 154999 8210 219764 4395 158636 2490 2009 2443 18184 192994 36535 10892 22797 10417 17567 7463 28677
2020-04-25 148000 953000 15100 45100 6780 7360 157000 8360 223000 4500 161000 2530 2030 2530 18700 196000 37300 11200 23300 10700 18500 7530 28900
2020-04-26 152000 966000 15200 46100 6840 7450 158000 8510 227000 4620 163000 2570 2060 2640 19200 198000 38000 11500 23800 11100 19400 7600 29000
2020-04-27 157000 979000 15300 47100 6900 7530 160000 8660 232000 4730 165000 2600 2080 2760 19700 201000 38700 11800 24200 11400 20400 7670 29200
2020-04-28 161000 992000 15300 48200 6970 7610 162000 8810 236000 4850 167000 2640 2110 2880 20300 204000 39500 12200 24700 11700 21400 7730 29400
2020-04-29 166000 1004000 15400 49200 7030 7700 164000 8960 240000 4970 169000 2670 2130 3000 20800 206000 40200 12500 25200 12100 22500 7800 29600
2020-04-30 171000 1016000 15500 50300 7090 7780 165000 9120 245000 5090 172000 2710 2160 3130 21400 209000 41000 12800 25700 12400 23700 7870 29700
2020-05-01 176000 1027000 15600 51400 7160 7870 167000 9280 249000 5220 174000 2750 2180 3270 21900 212000 41800 13200 26200 12800 24900 7940 29900

Confirmed count forecast (bold red line in graphs) 2020-04-25 to 2020-05-01

DateAustraliaBrazilCanadaIndiaIndonesiaIranMalaysiaMexicoPhilippinesSouth AfricaTurkeyUSUS-CAUS-COUS-CTUS-DCUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-24 6677 54043 44054 24530 8211 88194 5691 11633 7192 4220 104912 905358 41368 12255 23921 3528 30525 21575 39658 26140 50969 36627 102196 271621 13120 3850686
2020-04-25 6690 57900 45200 26300 8700 89200 5730 12500 7330 4480 108000 935000 43700 12800 25400 3650 31200 22300 42400 26500 55100 37700 105000 277000 13300 4056000
2020-04-26 6700 62100 46400 28300 9200 90300 5790 13300 7490 4770 111000 964000 46300 13600 26900 3800 31900 23000 45500 26900 59500 38600 108000 282000 13500 4265000
2020-04-27 6710 66600 47800 30500 9800 91400 5840 14200 7650 5080 115000 993000 49200 14400 28400 3950 32800 23800 48700 27200 64100 39600 111000 287000 13800 4485000
2020-04-28 6720 71400 49300 33000 10300 92400 5900 15100 7820 5410 118000 1022000 52300 15300 30000 4100 33600 24500 52200 27600 69000 40600 114000 292000 14000 4715000
2020-04-29 6730 76600 50900 35600 11000 93500 5950 16100 7990 5760 122000 1052000 55700 16200 31700 4260 34400 25300 55900 28000 74300 41600 118000 297000 14200 4956000
2020-04-30 6730 82200 52600 38500 11600 94600 6000 17200 8160 6140 125000 1083000 59300 17200 33500 4420 35300 26100 59900 28400 80100 42700 121000 303000 14400 5208000
2020-05-01 6740 88200 54400 41600 12400 95700 6050 18300 8340 6540 129000 1115000 63200 18300 35400 4590 36100 26900 64100 28800 86300 43700 124000 308000 14700 5472000

Confirmed count scenario forecast (bold green line in graphs) 2020-04-25 to 2020-05-03

DateUKEUATBEBSCZDEDKESFIFRGRHRHUIEITNLPLPTROSENOCHAustraliaBrazilCanadaIndiaIndonesiaIranMalaysiaMexicoPhilippinesSouth AfricaTurkeyUSUS-CAUS-COUS-CTUS-DCUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-24 143464 941681 15071 44293 6710 7273 154999 8210 219764 4395 158636 2490 2009 2443 18184 192994 36535 10892 22797 10417 17567 7463 28677 6677 54043 44054 24530 8211 88194 5691 11633 7192 4220 104912 905358 41368 12255 23921 3528 30525 21575 39658 26140 50969 36627 102196 271621 13120 3850686
2020-04-25 147000 943000 15100 44800 6790 7390 156000 8370 220000 4500 159000 2540 2020 2480 18400 195000 37000 11100 23100 10600 18000 7530 28800 6710 55700 45600 25800 8340 89200 5690 12700 7250 4350 108000 922000 43200 12500 25100 3650 30900 22100 41000 26400 51800 36900 105000 272000 13300 3911000
2020-04-26 150000 951000 15200 45300 6860 7480 158000 8530 222000 4590 159000 2600 2030 2540 18600 196000 37600 11300 23300 10900 18500 7590 29000 6730 58200 47000 27100 8510 90100 5720 13800 7360 4550 110000 944000 45100 12800 26200 3780 31400 22600 42700 26700 53400 37600 108000 276000 13500 3981000
2020-04-27 153000 957000 15200 45900 6930 7570 159000 8660 225000 4680 159000 2650 2050 2620 18800 198000 38000 11500 23500 11100 19000 7650 29100 6750 59500 48100 28300 8710 90900 5750 14600 7430 4710 112000 961000 46700 13100 27200 3910 31800 23100 44100 27000 54700 38200 111000 279000 13600 4041000
2020-04-28 156000 964000 15300 46500 6990 7660 160000 8800 227000 4790 159000 2710 2060 2670 18900 199000 38400 11600 23700 11300 19500 7700 29300 6760 61700 49200 29400 8890 91600 5790 15300 7520 4870 114000 977000 48300 13300 28200 4030 32300 23500 45500 27200 55600 38700 112000 282000 13700 4101000
2020-04-29 159000 970000 15300 46900 7050 7730 161000 8900 228000 4860 159000 2740 2070 2710 19100 200000 38800 11700 23900 11400 19900 7740 29400 6780 62900 49900 30300 9050 92300 5820 16000 7590 5030 116000 991000 49900 13500 29100 4150 32600 23800 46800 27300 56400 39200 114000 283000 13900 4152000
2020-04-30 161000 975000 15400 47400 7090 7800 162000 9010 229000 4910 159000 2780 2090 2740 19300 201000 39000 11900 24000 11600 20100 7780 29400 6790 63900 50500 30900 9170 92900 5850 16400 7660 5100 117000 1003000 51100 13700 29600 4190 33000 24100 47700 27500 57400 39600 116000 285000 14000 4191000
2020-05-01 163000 979000 15400 47700 7140 7850 163000 9100 231000 4950 160000 2820 2100 2770 19500 202000 39300 12000 24200 11700 20600 7820 29600 6790 64600 51200 31400 9280 93400 5880 16900 7730 5200 119000 1013000 52400 13800 30300 4270 33300 24400 48700 27700 58100 40000 117000 287000 14100 4232000
2020-05-02 164000 985000 15500 47900 7190 7900 164000 9190 232000 4990 162000 2820 2110 2800 19700 203000 39500 12000 24300 11800 20900 7850 29700 6800 65200 52100 31800 9380 93800 5900 17300 7780 5310 120000 1022000 53500 14000 30900 4350 33500 24600 49500 27800 59500 40300 119000 289000 14200 4266000
2020-05-03 166000 991000 15500 48200 7220 7940 165000 9260 233000 5020 163000 2840 2120 2820 19900 204000 39800 12100 24400 11900 21300 7870 29700 6810 66400 52700 32200 9470 94200 5930 17800 7840 5420 122000 1031000 54600 14200 31500 4430 33900 24800 50200 27900 60000 40600 120000 291000 14300 4297000

Peak increase in estimated trend of Confirmed in Europe 2020-04-24

UKEUATBEBSCZDEDKESFIFRGRHRHUIEITNLPLPTROSENOCH
Peak date04-1003-2803-2604-1003-2503-2803-2804-0403-2704-0604-1204-2103-3004-1004-1303-2104-1004-1704-1004-11 --03-2703-23
Peak daily increment 5997 29741 875 1461 287 284 6005 333 8155 181 12992 102 76 130 971 5701 1179 403 916 377 298 1205
Days from 100 to peak 36 34 18 34 11 15 27 25 25 24 42 41 11 20 30 27 35 33 28 28 21 18
Days from peak/2 to peak 22 18 13 26 11 14 15 25 14 24 26 44 15 22 24 17 29 31 23 25 19 12
Days since peak 14 27 29 14 30 27 27 20 28 18 12 3 25 14 11 34 14 7 14 13 28 32

Peak increase in estimated trend of Confirmed 2020-04-24

AustraliaBrazilCanadaIndiaIndonesiaIranMalaysiaMexicoPhilippinesSouth AfricaTurkeyUSUS-CAUS-COUS-CTUS-DCUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
Peak date03-28 --04-17 -- --03-3104-02 --03-31 --04-1104-10 -- -- -- --04-0304-07 --04-04 --04-0404-0404-0404-02 --
Peak daily increment 411 1788 3106 180 361 4790 31658 1194 986 1782 1658 3845 9744 528
Days from 100 to peak 18 37 35 24 17 23 38 19 22 19 17 20 27 26
Days from peak/2 to peak 14 28 28 25 13 17 21 13 17 13 13 13 15 22
Days since peak 27 7 24 22 24 13 14 21 17 20 20 20 20 22

Initial visual evaluation of forecasts of Confirmed