COVID-19 short-term forecasts Deaths 2020-09-03 Latin American Countries


General information

  • 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. 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.
  • A list of notes is below. The most recent note:
    [2020-07-01] Modified the short-term model to allow for (slowly changing) seasonality. Many countries show clear seasonality after the initial period, likely caused by institutional factors regarding data collection. This seasonality was also getting in the way of peak detection. As a consequence estimates of the peak date may have changed for countries with strong seasonality.
    Added forecasts of cumulative confirmed cases for lower tier local authorities of England. The data is available from 2020-07-02 including all tests (pillar one and two). Only authorities with more than 5 cases in the previous week are included.

Peak increase in estimated trend of Deaths in Latin America 2020-09-03

ArgentinaBoliviaBrazilChileColombiaCosta RicaDominican RepublicEcuadorEl SalvadorGuatemalaHaitiHondurasMexicoPanamaParaguayPeruVenezuela
Peak date -- --07-2107-1708-2308-07 --05-10 --06-0507-10 --06-2407-23 --07-23 --
Peak daily increment 1065 785 591 10 167 43 6 683 28 2947
Days from 100 to peak 115 93 133 12 39 5 12 79 98 107
Days from peak/2 to peak 106 63 115 108 40 29 83 72 116 78
Last total 9361 5288 124614 11422 20618 460 1801 6648 739 2804 210 1954 66329 2046 373 29068 402
Last daily increment 243 85 834 78 273 7 36 29 8 14 4 30 513 16 15 0 4
Last week 1090 442 5110 290 1852 53 153 144 37 95 9 127 3183 80 93 791 36
Days since peak 44 48 11 27 116 90 55 71 42 42

Deaths count forecast Latin America (bold red line in graphs) 2020-09-04 to 2020-09-10

DateArgentinaBoliviaBrazilChileColombiaCosta RicaDominican RepublicEcuadorEl SalvadorGuatemalaHondurasMexicoPanamaParaguayPeruVenezuela
2020-09-03 9361 5288 124614 11422 20618 460 1801 6648 739 2804 1954 66329 2046 373 29068 402
2020-09-04 9570 5382 125800 11490 20930 469 1841 6679 776 2855 1986 66880 2060 386 29220 415
2020-09-05 9680 5482 126500 11550 21230 477 1885 6709 792 2874 2014 67460 2074 400 29350 428
2020-09-06 9780 5585 126900 11610 21530 486 1919 6740 807 2885 2043 67690 2087 413 29480 441
2020-09-07 10010 5694 127500 11660 21830 494 1962 6770 820 2901 2070 67960 2100 426 29600 455
2020-09-08 10250 5808 128700 11700 22120 503 2003 6801 830 2919 2097 68690 2114 439 29720 469
2020-09-09 10490 5925 129800 11720 22430 512 2050 6832 843 2936 2125 69220 2127 453 29840 483
2020-09-10 10710 6046 130600 11800 22730 520 2083 6863 851 2952 2152 69730 2141 467 29960 498

Deaths count average forecast Latin America (bold black line in graphs) 2020-09-04 to 2020-09-10

DateArgentinaBoliviaBrazilChileColombiaCosta RicaDominican RepublicEcuadorEl SalvadorGuatemalaHondurasMexicoPanamaParaguayPeruVenezuela
2020-09-03 9361 5288 124614 11422 20618 460 1801 6648 739 2804 1954 66329 2046 373 29068 402
2020-09-04 9540 5385 125300 11470 20860 469 1818 6674 752 2823 1969 66620 2056 386 29200 409
2020-09-05 9700 5495 126000 11530 21140 478 1843 6704 764 2845 1987 67130 2069 400 29330 418
2020-09-06 9850 5603 126500 11590 21460 488 1871 6730 777 2862 2009 67290 2082 415 29460 426
2020-09-07 10070 5720 127200 11650 21750 498 1901 6753 789 2882 2032 67550 2095 430 29600 435
2020-09-08 10300 5840 128200 11700 22040 508 1930 6787 801 2904 2055 68320 2108 446 29720 444
2020-09-09 10540 5964 129200 11750 22340 519 1961 6821 815 2932 2078 68820 2121 463 29890 453
2020-09-10 10760 6091 130100 11830 22650 529 1990 6856 827 2958 2102 69250 2134 481 30020 463

Deaths count scenario forecast (bold purple line in graphs) 2020-09-04 to 2020-09-12

DateArgentinaBoliviaBrazilChileColombiaCosta RicaDominican RepublicEcuadorEl SalvadorGuatemalaHondurasMexicoPanamaParaguayPeruVenezuela
2020-09-03 9361 5288 124614 11422 20618 460 1801 6648 739 2804 1954 66329 2046 373 29068 402
2020-09-04 9530 5340 125300 11470 20840 467 1810 6676 750 2827 1973 66670 2058 384 29330 410
2020-09-05 9730 5411 126000 11500 21080 475 1833 6700 758 2846 1995 67030 2070 392 29450 416
2020-09-06 9920 5482 126700 11540 21290 484 1855 6721 762 2860 2014 67420 2081 414 29560 422
2020-09-07 10090 5547 127300 11580 21530 490 1877 6744 768 2874 2038 67770 2091 428 29670 428
2020-09-08 10310 5618 127900 11610 21740 496 1896 6763 777 2893 2054 68150 2100 442 29760 436
2020-09-09 10510 5695 128400 11640 21930 501 1921 6781 784 2906 2079 68400 2110 457 29840 445
2020-09-10 10710 5759 128900 11670 22130 507 1939 6798 792 2925 2097 68750 2117 474 29930 451
2020-09-11 10910 5823 129400 11690 22340 512 1960 6814 799 2935 2114 69100 2126 486 30010 459
2020-09-12 11100 5883 129800 11720 22470 516 1978 6828 806 2943 2129 69310 2134 501 30080 466

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.

Recent changes and notes

[2020-07-01] Modified the short-term model to allow for (slowly changing) seasonality. Many countries show clear seasonality after the initial period, likely caused by institutional factors regarding data collection. This seasonality was also getting in the way of peak detection. As a consequence estimates of the peak date may have changed for countries with strong seasonality.
Added forecasts of cumulative confirmed cases for lower tier local authorities of England. The data is available from 2020-07-02 including all tests (pillar one and two). Only authorities with more than 5 cases in the previous week are included.
[2020-06-29] Tables in April included the world, but not the world as we know it (double counting China and the US). So removed the world from those old tables.
Why short-term forecasts can be better than models for predicting how pandemics evolve just appeared at The Conversation.
Thursday 2 July webinar at the FGV EESP - São Paolo School of Economics. This starts at 16:00 UK time (UTC+01:00) and streamed here.
[2020-06-24] Research presentation on short-term COVID-19 forecasting on 26 June (14:00 UK time) at the Quarterly Forecasting Forum of the IIF UK Chapter.
[2020-06-06] Removed Brazil from yesterday's forecasts (only; last observation 2020-06-05).
[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.
[2020-05-20] Problem with UK confirmed cases: negative daily count. This makes the forecasts temporarily unreliable.
Updated the second paper.
[2020-05-18] Minor fixes to the improved version of scenario forecasting, backported to 2020-05-13.
[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.
[2020-05-06] 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.
[2020-04-29] 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.
[2020-04-27] 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.
[2020-04-24] A summary of our work on short-term COVID-19 forecasting appeared as a voxeu.
[2020-04-17] Bird and Nielsen look into nowcasting death counts in England.
[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).
[2020-04-10] Updated documentation with better description of short-term estimates and peak determination.
[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.
[2020-04-08] Minor correction to peak estimates. Added table with scenario forecasts.
[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.
[2020-04-02] Now including more US States, based on New York Times data.
[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).
[2020-03-26] Scenario forecasts that are based on what happened in China earlier this year, only for Italy.
[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.

Initial visual evaluation of forecasts of Deaths