COVID-19 short-term forecasts Confirmed 2020-03-28


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 The documentation that is provided is still in progress and not peer reviewed.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

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) 2020-03-29 to 2020-04-04

DateUKEUATBEBGBSCZDEDKESFIFRGRHRHUIEITNLPLPTROSESISKNOCH
2020-03-28 17089 315136 8271 9134 331 2870 2631 57695 2201 73235 1167 37575 1061 657 343 2415 92472 9762 1638 5170 1452 3447 684 292 4015 14076
2020-03-29 19800 354000 9200 10600 360 3170 2950 65000 2370 83000 1270 42500 1150 730 380 2680 99000 11000 1840 6000 1670 3770 740 310 4350 15200
2020-03-30 22500 398000 10200 11700 380 3500 3230 72000 2530 95000 1380 48100 1240 790 420 2930 105000 12200 2040 6700 1880 4090 790 330 4720 16600
2020-03-31 25600 448000 11300 13000 400 3870 3550 80000 2710 108000 1490 54400 1330 860 470 3210 112000 13500 2250 7600 2130 4430 850 350 5110 18100
2020-04-01 29100 504000 12500 14400 420 4270 3900 89000 2900 123000 1620 61600 1440 940 520 3510 119000 14900 2480 8500 2400 4800 910 360 5540 19800
2020-04-02 33100 566000 13900 16000 450 4720 4290 99000 3100 140000 1750 69700 1550 1020 570 3850 127000 16600 2740 9600 2710 5210 970 380 6000 21600
2020-04-03 37800 635000 15400 17900 470 5210 4720 110000 3320 159000 1900 79000 1670 1110 640 4230 135000 18400 3030 10900 3060 5650 1040 400 6500 23600
2020-04-04 43200 712000 17100 19900 500 5760 5200 122000 3550 181000 2060 89400 1800 1220 700 4640 144000 20400 3350 12300 3460 6130 1120 430 7050 25800

Confirmed count average forecast (bold black line in graphs) 2020-03-29 to 2020-04-04

DateAustraliaBrazilCanadaIranMalaysiaPhilippinesSouth AfricaUSUS-CAUS-DCUS-NJUS-NYUS-WA
2020-03-28 3640 3904 5576 35408 2320 1075 1187 121478 5565 342 11124 53363 4311
2020-03-29 4090 4350 6400 38600 2500 1220 1350 143000 6500 380 13400 61000 4850
2020-03-30 4560 4750 7300 41800 2700 1330 1540 165000 7400 420 15400 70000 5320
2020-03-31 5090 5190 8400 45300 2920 1460 1760 191000 8600 470 17700 79000 5850
2020-04-01 5680 5680 9600 49100 3150 1600 2020 222000 9900 520 20500 90000 6440
2020-04-02 6350 6220 10900 53300 3400 1760 2310 258000 11400 580 23800 103000 7090
2020-04-03 7090 6820 12500 57800 3680 1930 2650 302000 13200 640 27700 118000 7830
2020-04-04 7920 7490 14400 62700 3960 2130 3040 352000 15200 720 32300 135000 8640

Confirmed count forecast Europe (bold red line in graphs) 2020-03-29 to 2020-04-04

DateUKEUATBEBGBSCZDEDKESFIFRGRHRHUIEITNLPLPTROSESISKNOCH
2020-03-28 17089 315136 8271 9134 331 2870 2631 57695 2201 73235 1167 37575 1061 657 343 2415 92472 9762 1638 5170 1452 3447 684 292 4015 14076
2020-03-29 19100 354000 9000 10500 340 3090 2850 65000 2360 83000 1280 42300 1140 710 380 2580 98000 10900 1870 5800 1670 3710 740 300 4320 14700
2020-03-30 21700 398000 9800 12100 360 3380 3140 72000 2520 93000 1410 47800 1240 770 410 2820 104000 12200 2130 6700 1890 4050 800 320 4660 15600
2020-03-31 24700 447000 10700 13800 380 3690 3480 81000 2700 105000 1540 53900 1340 830 450 3090 110000 13600 2420 7600 2150 4420 860 340 5030 16600
2020-04-01 28100 503000 11700 15800 410 4030 3840 91000 2890 119000 1690 60800 1450 900 490 3380 116000 15200 2740 8700 2420 4830 930 360 5420 17700
2020-04-02 31900 566000 12800 18000 440 4400 4250 102000 3090 134000 1860 68500 1570 980 540 3700 123000 16900 3110 9800 2730 5270 1000 380 5850 18900
2020-04-03 36300 638000 14000 20500 460 4810 4700 114000 3310 152000 2040 77200 1690 1060 590 4050 130000 18800 3530 11200 3080 5750 1080 400 6320 20100
2020-04-04 41300 719000 15300 23400 500 5250 5190 128000 3550 171000 2240 86900 1830 1150 650 4430 137000 21000 4000 12800 3480 6270 1160 420 6820 21400

Confirmed count forecast (bold red line in graphs) 2020-03-29 to 2020-04-04

DateAustraliaBrazilCanadaIranMalaysiaPhilippinesSouth AfricaUSUS-CAUS-DCUS-NJUS-NYUS-WA
2020-03-28 3640 3904 5576 35408 2320 1075 1187 121478 5565 342 11124 53363 4311
2020-03-29 4070 4290 6200 38500 2480 1180 1260 137000 6400 370 13200 61000 4740
2020-03-30 4570 4750 7000 42000 2660 1350 1330 158000 7200 410 15700 69000 5310
2020-03-31 5120 5240 7800 45700 2870 1540 1400 184000 8200 450 18700 79000 5950
2020-04-01 5730 5780 8800 49800 3090 1750 1480 215000 9400 490 22200 89000 6650
2020-04-02 6410 6380 9900 54300 3330 1990 1560 251000 10700 540 26300 102000 7430
2020-04-03 7170 7050 11200 59200 3580 2260 1640 293000 12100 590 31200 116000 8310
2020-04-04 8020 7780 12600 64500 3860 2570 1730 343000 13800 640 37000 131000 9290

Confirmed count scenario forecast (bold green line in graphs) 2020-03-29 to 2020-04-06

DateESIT
2020-03-28 73235 92472
2020-03-29 83000 97000
2020-03-30 92000 102000
2020-03-31 101000 106000
2020-04-01 110000 110000
2020-04-02 120000 114000
2020-04-03 130000 118000
2020-04-04 139000 122000
2020-04-05 146000 125000
2020-04-06 153000 129000

Initial visual evaluation of forecasts of Confirmed