COVID-19 short-term forecasts Deaths 2020-06-20


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 The documentation that is provided is still in progress and not peer reviewed.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.
[2020-04-27] Our short-term COVID-19 forecasting paper is now available as Nuffield Economics Discussion Paper 2020-W06.
A small adjustment has been made to the scenario forecast methodology, and will be documented shortly.
[2020-04-29] See our blog entry at the International Institute of Forecasters.
US history of death counts revised in Johns Hopkins/CSSE data.
UK death counts have been revised to include the deaths in care homes. In the Johns Hopkins/CSSE data set, which we use, the entire history has been revised. So forecasts made up to 2020-04-29 cannot be compared to later outcomes. In the ECDC data set only the last observation has changed, causing a jump in the series.
[2020-05-06] The New York Times is in the process of redefining its US state data. Unfortunately, at the moment only the last observation has changed (e.g New York deaths jumped from 19645 on 2020-05-05 to 25956 a day later). This means the data is currently useless; however it does bring it close to the Johns Hopkins/CSSE count (25626 on 2020-05-06). The aggregate US count is based on JH/CSSE so unaffected. We now use Johns Hopkins/CSSE US state data, including all states with sufficient counts. So the new forecasts cannot be compared to those previously.
A minor change is that we show the graph without scenario forecast if no peak has been detected yet.
[2020-05-13] We now omit countries with fewer than 200 confirmed cases in the last week (25 for deaths).
The short-term paper has some small updates, including further comparisons with other models.
Data for Ecuador are not reliable enough for forecasting.
Switched to an improved version of scenario forecasting.
[2020-05-18] Minor fixes to the improved version of scenario forecasting, backported to 2020-05-13.
[2020-05-20] Problem with UK confirmed cases: negative daily count. This makes the forecasts temporarily unreliable.
Updated the second paper.
[2020-06-04] Data issues with confirmed cases for France.
Added an appendix to the short term paper with further forecast comparisons for European and Latin American countries.
Both Sweden and Iran have lost their peak in confirmed cases. For Sweden the previous peak was on 24 April (daily peak of 656 cases), for Iran it was on 31 March (peak of 3116). For Iran this looks like a second wave, with increasing daily counts for the last four weeks. For Sweden this is a sudden jump in confirmed cases in the last two days, compared to a fairly steady weekly pattern over the previous six weeks.
[2020-06-06] Removed Brazil from yesterday's forecasts (last observation 2020-06-05).

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.

Deaths count average forecast Europe (bold black line in graphs) 2020-06-21 to 2020-06-27

DateUKEUBEDEESFRITNLPLROSE
2020-06-20 42589 131788 9696 8895 28322 29568 34610 6089 1346 1500 5053
2020-06-21 42700 132000 9700 8910 28400 29600 34700 6090 1360 1510 5070
2020-06-22 42900 132000 9710 8930 28600 29600 34700 6100 1370 1530 5100
2020-06-23 43000 132000 9720 8940 28700 29700 34800 6110 1380 1550 5130
2020-06-24 43200 133000 9730 8960 28800 29700 34800 6110 1400 1560 5160
2020-06-25 43300 133000 9740 8980 29000 29700 34900 6120 1410 1580 5190
2020-06-26 43500 133000 9740 9000 29100 29800 34900 6120 1430 1600 5220
2020-06-27 43600 134000 9750 9020 29300 29800 34900 6130 1440 1620 5250

Deaths count average forecast (bold black line in graphs) 2020-06-21 to 2020-06-27

DateBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-FLUS-GAUS-IAUS-ILUS-INUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NEUS-NJUS-NMUS-NVUS-NYUS-OHUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
2020-06-20 49976 8466 4295 2148 13254 2429 9507 20781 7861 1150 7992 1877 4927 119719 828 224 1345 5494 1647 4251 3144 2601 681 6625 2346 524 2992 7817 3027 6014 1373 935 938 1215 243 12924 466 486 31083 2697 6419 644 516 2183 1607 1265 744
2020-06-21 51400 8490 4360 2190 13600 2490 9600 21500 7980 1150 8120 1930 4940 120000 830 230 1360 5530 1650 4260 3160 2620 680 6670 2350 530 3000 7850 3040 6020 1380 950 940 1220 250 13000 470 490 31100 2700 6450 650 520 2210 1610 1270 750
2020-06-22 53000 8520 4460 2270 14000 2550 9700 22300 8140 1160 8280 1990 4960 121000 840 240 1370 5590 1660 4270 3180 2650 690 6720 2370 530 3010 7880 3060 6030 1390 970 950 1230 250 13000 470 490 31200 2710 6480 650 530 2230 1620 1270 750
2020-06-23 54700 8560 4580 2360 14400 2620 9800 23200 8290 1170 8440 2050 4980 122000 840 240 1400 5640 1670 4280 3210 2680 690 6770 2380 530 3020 7920 3080 6040 1400 990 960 1250 260 13100 480 490 31200 2730 6510 660 530 2260 1630 1280 760
2020-06-24 56500 8600 4730 2450 14900 2680 9900 24000 8450 1170 8600 2120 4990 122000 850 250 1420 5700 1680 4290 3240 2710 700 6820 2400 540 3030 7950 3100 6050 1410 1010 960 1260 260 13200 480 490 31300 2750 6550 660 540 2290 1640 1280 760
2020-06-25 58400 8640 4880 2540 15400 2750 10000 25000 8640 1180 8770 2190 5010 123000 850 260 1440 5760 1680 4300 3270 2730 700 6860 2420 540 3050 7990 3120 6060 1420 1030 970 1270 270 13300 490 500 31300 2770 6580 670 550 2320 1650 1290 770
2020-06-26 60300 8680 5040 2630 15900 2830 10100 25900 8830 1190 8940 2260 5030 123000 860 270 1470 5820 1690 4310 3300 2760 710 6910 2430 550 3060 8030 3140 6070 1430 1050 980 1280 270 13400 490 500 31300 2790 6610 670 550 2350 1660 1300 770
2020-06-27 62200 8720 5210 2730 16400 2900 10200 26900 9020 1200 9120 2340 5050 124000 870 280 1490 5890 1700 4320 3330 2790 710 6960 2450 550 3070 8060 3160 6080 1450 1080 990 1290 280 13400 500 500 31400 2810 6640 680 560 2380 1670 1300 780

Deaths count forecast Europe (bold red line in graphs) 2020-06-21 to 2020-06-27

DateUKEUBEDEESFRITNLPLROSE
2020-06-20 42589 131788 9696 8895 28322 29568 34610 6089 1346 1500 5053
2020-06-21 42700 132000 9710 8910 28300 29600 34700 6100 1360 1510 5080
2020-06-22 42900 132000 9710 8920 28300 29600 34700 6100 1380 1530 5100
2020-06-23 43000 132000 9720 8940 28300 29700 34800 6110 1390 1540 5120
2020-06-24 43200 133000 9730 8950 28300 29700 34800 6110 1410 1560 5140
2020-06-25 43300 133000 9730 8970 28300 29700 34900 6120 1420 1570 5160
2020-06-26 43500 133000 9740 8980 28300 29800 34900 6120 1440 1580 5180
2020-06-27 43600 133000 9750 8990 28300 29800 35000 6130 1450 1600 5200

Deaths count forecast (bold red line in graphs) 2020-06-21 to 2020-06-27

DateBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-FLUS-GAUS-IAUS-ILUS-INUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NEUS-NJUS-NMUS-NVUS-NYUS-OHUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
2020-06-20 49976 8466 4295 2148 13254 2429 9507 20781 7861 1150 7992 1877 4927 119719 828 224 1345 5494 1647 4251 3144 2601 681 6625 2346 524 2992 7817 3027 6014 1373 935 938 1215 243 12924 466 486 31083 2697 6419 644 516 2183 1607 1265 744
2020-06-21 51400 8500 4450 2220 13600 2490 9600 21500 8010 1160 8150 1930 4950 120000 840 230 1370 5550 1650 4260 3170 2620 680 6670 2360 530 3010 7850 3050 6030 1380 960 950 1230 240 13000 470 490 31100 2710 6450 650 520 2210 1620 1270 750
2020-06-22 52900 8550 4600 2300 14000 2560 9700 22200 8220 1170 8310 1990 4970 121000 850 240 1400 5610 1660 4280 3200 2640 690 6720 2380 530 3020 7880 3070 6050 1400 980 950 1240 250 13000 480 490 31200 2730 6480 660 530 2240 1630 1280 760
2020-06-23 54400 8590 4770 2390 14300 2620 9800 23000 8430 1190 8480 2040 4990 122000 850 250 1420 5670 1670 4290 3240 2660 690 6760 2400 530 3030 7910 3080 6060 1410 1010 960 1250 250 13100 480 490 31200 2750 6500 660 540 2270 1630 1290 770
2020-06-24 56000 8630 4930 2480 14700 2690 9900 23800 8640 1200 8640 2100 5000 122000 860 260 1450 5730 1670 4300 3270 2680 690 6810 2410 530 3050 7950 3100 6080 1420 1030 960 1260 250 13100 480 500 31300 2770 6530 670 540 2300 1640 1290 780
2020-06-25 57600 8670 5100 2570 15100 2760 10000 24700 8850 1210 8800 2160 5020 123000 870 270 1470 5790 1680 4310 3300 2700 700 6850 2430 540 3060 7980 3120 6090 1430 1050 970 1270 250 13100 490 500 31300 2790 6560 680 550 2330 1650 1300 780
2020-06-26 59300 8710 5280 2660 15600 2830 10100 25600 9080 1220 8970 2230 5040 123000 880 280 1500 5850 1690 4330 3330 2720 700 6900 2440 540 3070 8010 3140 6110 1440 1080 970 1280 260 13200 490 500 31400 2820 6590 680 560 2360 1660 1310 790
2020-06-27 61100 8750 5460 2760 16000 2900 10200 26500 9300 1230 9150 2290 5060 124000 890 300 1520 5910 1690 4340 3370 2740 700 6940 2460 540 3090 8040 3160 6120 1450 1100 980 1290 260 13200 500 510 31400 2840 6620 690 570 2390 1670 1320 800

Deaths count scenario forecast (bold purple line in graphs) 2020-06-21 to 2020-06-29

DateUKEUBEDEESFRITNLPLROSEBrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-FLUS-GAUS-IAUS-ILUS-INUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NEUS-NJUS-NMUS-NVUS-NYUS-OHUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
2020-06-20 42589 131788 9696 8895 28322 29568 34610 6089 1346 1500 5053 49976 8466 4295 2148 13254 2429 9507 20781 7861 1150 7992 1877 4927 119719 828 224 1345 5494 1647 4251 3144 2601 681 6625 2346 524 2992 7817 3027 6014 1373 935 938 1215 243 12924 466 486 31083 2697 6419 644 516 2183 1607 1265 744
2020-06-21 42700 132000 9710 8910 28400 29600 34600 6090 1360 1510 5090 51400 8490 4350 2200 13800 2470 9600 21700 7910 1160 8150 1920 4950 120000 830 230 1350 5530 1650 4260 3160 2630 690 6660 2360 530 3000 7850 3040 6030 1380 960 950 1220 250 13000 470 490 31100 2710 6460 650 520 2220 1620 1270 750
2020-06-22 42800 132000 9710 8930 28500 29600 34700 6100 1370 1520 5110 52600 8530 4450 2270 14300 2520 9700 22600 8020 1160 8320 1980 4960 121000 830 240 1370 5580 1660 4260 3190 2640 690 6690 2370 530 3010 7880 3060 6040 1390 990 950 1230 250 13000 470 490 31100 2720 6480 650 530 2250 1620 1280 760
2020-06-23 42900 133000 9720 8940 28600 29700 34700 6100 1380 1540 5130 54000 8570 4560 2340 14900 2570 9800 23300 8160 1170 8510 2030 4980 121000 830 250 1390 5630 1670 4270 3210 2660 690 6720 2390 530 3020 7910 3080 6050 1400 1030 950 1240 260 13000 470 490 31200 2740 6510 660 530 2280 1630 1280 780
2020-06-24 43100 133000 9730 8950 28700 29700 34800 6110 1400 1550 5150 55500 8610 4670 2420 15400 2620 9900 24100 8340 1180 8700 2080 4990 122000 840 260 1400 5670 1670 4270 3230 2680 700 6750 2400 530 3040 7930 3090 6060 1410 1060 960 1250 260 13100 470 490 31200 2750 6540 660 540 2310 1640 1290 790
2020-06-25 43200 133000 9730 8960 28700 29700 34800 6110 1410 1560 5170 57000 8640 4750 2520 15900 2660 10000 24900 8490 1180 8890 2130 4990 122000 840 280 1420 5710 1680 4280 3250 2690 700 6780 2410 540 3050 7950 3110 6070 1420 1100 960 1260 260 13100 480 490 31300 2770 6560 670 550 2350 1640 1290 800
2020-06-26 43300 133000 9740 8970 28700 29700 34800 6110 1410 1570 5180 58400 8680 4820 2610 16300 2710 10000 25700 8640 1180 9060 2170 5000 122000 850 290 1430 5740 1680 4280 3270 2710 710 6800 2430 540 3060 7970 3120 6080 1430 1150 960 1270 260 13100 480 490 31300 2780 6590 670 550 2380 1650 1290 810
2020-06-27 43400 133000 9750 8980 28700 29700 34900 6120 1420 1580 5200 59900 8720 4910 2700 16800 2760 10100 26600 8790 1190 9240 2210 5010 123000 850 300 1440 5760 1690 4290 3280 2730 710 6830 2440 540 3070 7990 3140 6090 1440 1190 970 1270 260 13100 480 500 31300 2790 6610 670 550 2420 1650 1300 830
2020-06-28 43500 133000 9750 8990 28700 29800 34900 6120 1430 1590 5210 61300 8740 4990 2780 17200 2800 10200 27500 8880 1190 9450 2250 5020 123000 860 310 1450 5780 1690 4290 3290 2750 710 6850 2440 540 3070 8010 3150 6090 1450 1230 970 1280 270 13200 480 500 31400 2800 6630 680 560 2470 1660 1300 850
2020-06-29 43600 133000 9760 9000 28700 29800 34900 6120 1430 1600 5220 62700 8770 5060 2860 17600 2840 10200 28400 8970 1200 9660 2280 5030 123000 860 330 1460 5800 1700 4300 3300 2760 720 6880 2450 540 3080 8020 3160 6100 1450 1270 970 1290 270 13200 480 500 31400 2810 6650 680 560 2510 1660 1300 860

Peak increase in estimated trend of Deaths in Europe 2020-06-20

UKEUATBEBSCZDEDKESFIFRHUIEITNLPLPTROSENOCH
Peak date04-0904-0704-0704-1004-1104-0904-1504-0403-3004-2104-0704-1904-2403-2804-0704-2404-1105-0104-2204-0804-04
Peak daily increment 1019 3232 22 349 8 11 269 18 896 17 1028 14 101 839 159 29 33 25 120 9 61
Days from 100 to peak 22 34 8 17 1 0 23 3 17 1 23 6 22 24 18 18 13 29 25 -1 12
Days from peak/2 to peak 16 24 16 15 22 14 22 14 13 24 16 26 25 19 18 28 19 37 27 21 17
Last total 42589 131788 688 9696 255 336 8895 600 28322 326 29568 570 1715 34610 6089 1346 1528 1500 5053 244 1956
Last daily increment 128 127 0 1 0 1 8 0 7 0 14 2 1 49 8 12 1 16 0 0 0
Last week 891 2291 11 41 1 7 94 3 1186 0 222 8 9 265 30 99 11 90 179 2 18
Days since peak 72 74 74 71 70 72 66 77 82 60 74 62 57 84 74 57 70 50 59 73 77

Peak increase in estimated trend of Deaths 2020-06-20

BrazilCanadaChileColombiaIndiaIndonesiaIranMexicoPeruPhilippinesRussiaSouth AfricaTurkeyUSUS-ALUS-ARUS-AZUS-CAUS-COUS-CTUS-DCUS-DEUS-FLUS-GAUS-IAUS-ILUS-INUS-KSUS-KYUS-LAUS-MAUS-MDUS-MIUS-MNUS-MOUS-MSUS-NCUS-NEUS-NHUS-NJUS-NMUS-NVUS-NYUS-OHUS-OKUS-PAUS-SCUS-TNUS-TXUS-VAUS-WAUS-WI
Peak date --05-0406-08 --06-16 --03-19 -- --04-1205-2906-1504-2004-1505-06 --05-0804-2304-2404-2004-2505-1605-0604-2005-2005-1304-2904-1404-1604-1404-2704-2904-2205-28 --05-0605-2905-2005-2904-2905-1204-1204-0704-2904-2105-0504-2904-0605-1504-2204-0605-29
Peak daily increment 179 294 1225 147 27 184 70 125 2272 17 37 87 51 115 12 11 54 46 16 127 50 7 11 75 221 63 151 27 22 27 23 15 300 10 10 1068 54 9 170 18 10 39 47 31 14
Days from 100 to peak 33 53 72 14 11 48 47 23 30 23 26 26 21 18 5 22 35 20 26 43 25 -6 1 18 26 22 25 41 23 46 0 16 29 15 0 18 25 8 32 14 -5 41 7 14 51
Days from peak/2 to peak 34 48 56 16 25 48 61 25 21 37 37 30 28 20 26 47 41 25 48 44 32 18 21 21 26 26 26 55 38 58 41 31 28 40 18 13 31 27 33 34 8 50 14 30 65
Last total 49976 8466 4295 2148 13254 2429 9507 20781 7861 1150 7992 1877 4927 119719 828 224 1345 5494 1647 4251 531 434 3144 2601 681 6625 2346 256 524 2992 7817 3027 6014 1373 935 938 1215 243 339 12924 466 486 31083 2697 368 6419 644 516 2183 1607 1265 744
Last daily increment 1022 58 202 102 306 56 115 387 400 20 161 46 22 595 16 10 25 68 4 13 1 1 40 7 0 45 19 3 2 20 28 22 20 11 7 0 13 0 2 22 2 7 68 30 1 20 5 9 25 5 10 14
Last week 6644 248 972 478 3734 295 670 3640 1173 62 1054 397 120 3987 60 45 156 395 49 50 16 12 213 188 29 318 106 11 25 91 204 120 71 75 79 47 83 29 19 265 31 23 258 138 9 204 44 49 199 61 48 52
Days since peak 47 12 4 93 69 22 5 61 66 45 43 58 57 61 56 35 45 61 31 38 52 67 65 67 54 52 59 23 45 22 31 22 52 39 69 74 52 60 46 52 75 36 59 75 22

Initial visual evaluation of forecasts of Deaths