COVID-19 short-term forecasts Confirmed 2020-04-11


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 The documentation that is provided is still in progress and not peer reviewed.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. 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, but remains preliminary. Also preliminary is the documentation of the medium term forecasts.

Confirmed count average forecast Europe (bold black line in graphs) 2020-04-12 to 2020-04-18

DateUKEUATBEBSCZDEDKESFIFRGRIEITNLPLPTROSENOCH
2020-04-11 78991 712959 13806 28018 5600 5831 124908 5996 163027 2905 129654 2081 8928 152271 24413 6356 15987 5990 10151 6409 25107
2020-04-12 86000 737000 14100 29800 5740 6010 129000 6220 168000 3100 136000 2140 10000 156000 25900 6800 17000 6500 10800 6510 25700
2020-04-13 94000 761000 14300 32000 5870 6230 133000 6510 172000 3330 142000 2190 10900 160000 27600 7200 18200 7000 11600 6620 26400
2020-04-14 103000 785000 14600 34200 6000 6450 137000 6820 177000 3580 149000 2240 11900 164000 29400 7700 19500 7600 12500 6720 27000
2020-04-15 113000 808000 14800 36700 6140 6690 141000 7140 181000 3850 156000 2290 13000 168000 31300 8200 20900 8200 13400 6820 27700
2020-04-16 124000 832000 15100 39300 6270 6930 145000 7470 186000 4130 163000 2350 14200 171000 33400 8800 22400 8900 14400 6930 28400
2020-04-17 136000 856000 15400 42100 6410 7180 150000 7840 191000 4440 170000 2400 15600 175000 35600 9400 24000 9600 15500 7040 29100
2020-04-18 149000 879000 15700 45100 6560 7450 154000 8220 196000 4770 178000 2460 17200 180000 37900 10000 25700 10400 16600 7150 29800

Confirmed count average forecast (bold black line in graphs) 2020-04-12 to 2020-04-18

DateAustraliaBrazilCanadaIranMalaysiaPhilippinesSouth AfricaUSUS-CAUS-COUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-11 6303 20727 23316 70029 4530 4428 2028 526396 22421 6893 11510 18978 12261 19180 20014 22860 23853 58151 180458 10224 2411264
2020-04-12 6390 22500 24800 71800 4670 4580 2080 562000 23600 7240 12700 20000 13100 20900 20900 25100 25100 61600 193000 10600 2539000
2020-04-13 6470 24700 26500 73400 4810 4710 2150 600000 24900 7540 14000 21000 14100 23000 22000 27600 26400 64800 208000 10900 2676000
2020-04-14 6550 27000 28300 75100 4960 4850 2210 642000 26300 7840 15400 22100 15300 25400 23000 30300 27700 68100 224000 11300 2817000
2020-04-15 6630 29600 30200 76800 5110 4990 2280 687000 27800 8160 16900 23200 16500 28000 24000 33300 29100 71500 242000 11700 2962000
2020-04-16 6710 32400 32200 78500 5270 5130 2350 735000 29300 8490 18600 24300 17900 30900 25100 36700 30600 75100 261000 12200 3114000
2020-04-17 6790 35600 34500 80300 5420 5290 2430 789000 31000 8840 20500 25500 19400 34200 26400 40300 32100 79000 282000 12600 3271000
2020-04-18 6870 39200 37000 82100 5570 5440 2510 846000 32700 9200 22600 26800 21000 37700 27600 44300 33800 83000 304000 13000 3434000

Confirmed count forecast Europe (bold red line in graphs) 2020-04-12 to 2020-04-18

DateUKEUATBEBSCZDEDKESFIFRGRIEITNLPLPTROSENOCH
2020-04-11 78991 712959 13806 28018 5600 5831 124908 5996 163027 2905 129654 2081 8928 152271 24413 6356 15987 5990 10151 6409 25107
2020-04-12 84000 733000 14100 29500 5720 6000 128000 6200 168000 3160 135000 2120 10100 156000 25800 6680 16500 6600 10800 6520 25700
2020-04-13 90000 754000 14300 31100 5830 6170 132000 6390 172000 3400 140000 2170 11300 160000 27400 7050 17200 7200 11500 6630 26200
2020-04-14 97000 775000 14600 32800 5950 6340 135000 6570 176000 3650 145000 2220 12700 164000 29000 7440 18000 7900 12200 6730 26800
2020-04-15 104000 796000 14800 34600 6060 6510 139000 6760 181000 3930 150000 2280 14200 167000 30700 7850 18800 8700 13000 6830 27400
2020-04-16 112000 816000 15100 36500 6180 6690 143000 6950 186000 4220 154000 2330 15900 171000 32500 8280 19600 9500 13900 6940 28000
2020-04-17 120000 836000 15300 38500 6290 6870 147000 7140 190000 4540 159000 2390 17800 175000 34500 8740 20500 10400 14800 7040 28600
2020-04-18 129000 856000 15600 40600 6410 7060 151000 7330 195000 4880 164000 2440 20000 179000 36600 9230 21400 11400 15700 7150 29200

Confirmed count forecast (bold red line in graphs) 2020-04-12 to 2020-04-18

DateAustraliaBrazilCanadaIranMalaysiaPhilippinesSouth AfricaUSUS-CAUS-COUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
2020-04-11 6303 20727 23316 70029 4530 4428 2028 526396 22421 6893 11510 18978 12261 19180 20014 22860 23853 58151 180458 10224 2411264
2020-04-12 6390 22400 24400 71700 4630 4520 2060 561000 23600 7200 12900 19800 12900 20400 20800 25000 25000 61100 193000 10500 2534000
2020-04-13 6480 24200 25700 73300 4770 4660 2100 598000 24800 7510 14200 20700 13500 21900 21600 27300 26000 63800 207000 10800 2655000
2020-04-14 6560 26100 26900 74900 4900 4790 2140 640000 26100 7840 15600 21600 14200 23500 22400 29900 27100 66600 222000 11100 2778000
2020-04-15 6650 28100 28200 76600 5040 4930 2180 685000 27400 8170 17200 22600 14900 25200 23200 32600 28100 69400 239000 11300 2902000
2020-04-16 6730 30400 29600 78200 5180 5070 2220 735000 28900 8530 19000 23600 15700 27000 23900 35700 29200 72200 257000 11600 3028000
2020-04-17 6810 32800 31000 79900 5320 5210 2260 790000 30400 8900 21000 24600 16400 28900 24800 39000 30300 75100 276000 11900 3157000
2020-04-18 6900 35500 32400 81700 5460 5350 2300 849000 32100 9280 23100 25600 17300 30900 25600 42600 31500 78100 297000 12200 3288000

Confirmed count scenario forecast (bold green line in graphs) 2020-04-12 to 2020-04-20

DateUKEUATBEDEDKESFRITNLPLPTNOCHUS-WAAustraliaIranMalaysia
2020-04-11 78991 712959 13806 28018 124908 5996 163027 129654 152271 24413 6356 15987 6409 25107 10224 6303 70029 4530
2020-04-12 84000 734000 14100 29300 129000 6230 168000 133000 155000 25300 6630 16800 6480 25700 10500 6420 71800 4610
2020-04-13 89000 754000 14300 30600 132000 6430 173000 136000 159000 26300 6940 17600 6530 26300 10900 6530 73500 4700
2020-04-14 94000 774000 14700 31900 136000 6610 177000 141000 162000 27200 7220 18500 6590 26800 11200 6650 75300 4810
2020-04-15 100000 792000 15000 33100 139000 6760 182000 143000 165000 28100 7450 19200 6640 27400 11400 6810 77000 4900
2020-04-16 103000 811000 15200 34300 142000 6930 186000 149000 168000 28900 7660 19800 6690 27900 11700 6980 78900 5000
2020-04-17 108000 828000 15400 35400 145000 7090 190000 151000 171000 29600 7910 20500 6740 28400 12000 7110 80500 5100
2020-04-18 113000 847000 15700 36400 148000 7270 194000 156000 173000 30200 8090 20900 6790 28900 12300 7220 82400 5200
2020-04-19 116000 864000 16000 37400 151000 7430 198000 158000 175000 30600 8290 21100 6840 29400 12500 7350 84200 5310
2020-04-20 118000 882000 16300 37900 154000 7620 202000 163000 178000 31100 8510 21700 6890 29900 12800 7490 85400 5400

Peak increase in estimated trend of Confirmed in Europe 2020-04-11

UKEUATBEBSCZDEDKESFIFRGRIEITNLPLPTROSENOCH
Peak date --04-0403-26 --03-2503-2703-2804-0703-27 --04-0404-01 --03-21 --04-07 -- -- --03-2703-23
Peak daily increment 32734 874 287 285 6014 344 8182 9937 95 5704 407 300 1205
Days from 100 to peak 41 18 11 14 27 28 25 34 21 27 23 21 18
Days from peak/2 to peak 25 13 11 13 15 28 14 20 24 17 21 19 12
Days since peak 7 16 17 15 14 4 15 7 10 21 4 15 19

Peak increase in estimated trend of Confirmed 2020-04-11

AustraliaBrazilCanadaIranMalaysiaPhilippinesSouth AfricaUSUS-CAUS-COUS-CTUS-FLUS-GAUS-ILUS-LAUS-MAUS-MIUS-NJUS-NYUS-WAWorld
Peak date03-28 --04-0503-2904-0203-3103-2604-0604-0404-03 --04-03 -- --04-04 --04-0404-03 --04-02 --
Peak daily increment 411 1498 3101 180 351 190 31456 1345 391 1187 1777 1665 3828 519
Days from 100 to peak 18 25 33 24 17 8 34 27 19 19 19 17 19 26
Days from peak/2 to peak 14 17 26 25 13 8 17 18 16 13 13 13 12 22
Days since peak 14 6 13 9 11 16 5 7 8 8 7 7 8 9

Initial visual evaluation of forecasts of Confirmed