{"id":564,"date":"2020-04-20T16:07:23","date_gmt":"2020-04-20T13:07:23","guid":{"rendered":"https:\/\/grechka.family\/dmitry\/blog\/?p=564"},"modified":"2020-08-17T14:10:41","modified_gmt":"2020-08-17T11:10:41","slug":"covid-19-latent-period-estimation","status":"publish","type":"post","link":"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/","title":{"rendered":"COVID-19 Latent period estimation"},"content":{"rendered":"\n<div class=\"wp-block-jetpack-markdown\"><p>The incubation period for the COVID-19 is reported <a href=\"https:\/\/www.kaggle.com\/covid-19-contributions#Incubation%20period\">many times<\/a>. We can&#8217;t say the same for the latent period (the period since the person is infected but does not spread the infection yet), which is vital characteristic of every infectious disease. Knowing the latent period gives an ability to run simulations which are far more accurate. In this study I try to estimate the latent period for COVID-19 caused by SARS-CoV-2 virus via computational simulations using <a href=\"https:\/\/en.wikipedia.org\/wiki\/Compartmental_models_in_epidemiology\">SEIR model<\/a> with different values controlling the latent period length (e.g. latent period parameter sweep). I try to fit all other parameters to match the observed statistics the best. I do such modelling for 5 different locations worldwide which are currently experiencing different stages of the epidemic.<\/p>\n<p>As a result, Europe locations suggest that latent period is between 2 and 4 days: Austria case suggests the value of 48-96 hours, Italy case suggests the value greater than 48 hours. While China cases suggest shorter latent period.<\/p>\n<\/div>\n\n\n\n<!--more-->\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><h2>Introduction<\/h2>\n<h3>The data<\/h3>\n<p>I use the time series data (infected count, recovered count and deaths count) published by the <a href=\"https:\/\/github.com\/CSSEGISandData\/COVID-19\">John Hopkins University<\/a> as ground truth observations.<\/p>\n<p>I experiment with these 5 locations:<\/p>\n<ul>\n<li>Austria (infection peak has passed)<\/li>\n<li>Beijing, China (there were 2 peaks)<\/li>\n<li>Heilongjiang, China (two more distinct peaks)<\/li>\n<li>Italy (Peak is approaching)<\/li>\n<li>South Korea (single peak passed long ago)<\/li>\n<\/ul>\n<h3>The model<\/h3>\n<p>I use SEIR model where the population is split into 4 groups:<\/p>\n<ul>\n<li>S &#8211; susceptible, subjects who can catch the infection<\/li>\n<li>E &#8211; exposed, subjects who is infected but not yet contagious (e.g. in incubation period)<\/li>\n<li>I &#8211; infected, contagious subjects<\/li>\n<li>R &#8211; removed, subjects either recovered or died due to disease<\/li>\n<\/ul>\n<p>The dynamics of transition between the groups is defined as ODE system.<\/p>\n<p><img decoding=\"async\" src=\"\/dmitry\/blog\/wp-content\/uploads\/2020\/08\/seir.png\" alt=\"SEIR equations\"\/><\/p>\n<p>where <em>\u03b2 (beta)<\/em>, <em>\u03c3 (sigma)<\/em> and <em>\u03b3 (gamma)<\/em> are parameters that control the transition rates.<\/p>\n<h3>Latent period estimation<\/h3>\n<p>Latent period can be estimated as reciprocal to sigma parameter. Thus <code>latent period = 1.0 \/ sigma<\/code><\/p>\n<h3>The parameter fitting procedure<\/h3>\n<p>I let the optimizer to fit the following parameters:<\/p>\n<ul>\n<li>Infection start date<\/li>\n<li>number of the exposed people count on the first day of infection<\/li>\n<li>number of the infected people count on the first day of infection<\/li>\n<li>beta (separate value per week, approximated with spline before passing to ODE) &#8211; infection rate<\/li>\n<li>gamma &#8211; recovery rate<\/li>\n<\/ul>\n<p>The loss function is RMSE.<\/p>\n<p>For every location and every value of sigma (reciprocal of latent period) I use several runs of Nelder-Mead and BFGS optimizers starting at different random initial conditions and take the best fit.<\/p>\n<p>The full computational experiment code is published <a href=\"https:\/\/github.com\/dgrechka\/covid19-global-forecasting\/tree\/master\/sigmaEvaluation\">on the GitHub<\/a>.<\/p>\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\">Italy case<\/h2>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_all-1024x546.png\" alt=\"Achieved model fit loss value for different latent period values for Italy. Lower is better.\" class=\"wp-image-563\" width=\"609\" height=\"324\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_all-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_all-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_all-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_all-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_all-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_all.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>Achieved model fit loss value for different latent period values for Italy. Lower is better.<\/figcaption><\/figure>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>We can see that short latent period values (2 hours &#8211; 48 hours) exhibit higher values of achieved loss value, thus less likely to describe the observations in a valid way.<\/p>\n<p>But we can&#8217;t see any explicit single latent period value longer than 48 hours, that exhibits much lower loss. All of values starting from 72 hours and higher seem to be possible.<\/p>\n<\/div>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_top-1024x546.png\" alt=\"Top SIER fits for Italy\" class=\"wp-image-567\" width=\"768\" height=\"410\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_top-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_top-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_top-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_top-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_top-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Italy_top.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>Italy: SEIR model runs with latent period values that fit the observations in the best way.<\/figcaption><\/figure>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>Top fits match the observed infected count almost perfectly for Italy. Wide range of &quot;valid&quot; latent periods are equally possible.<\/p>\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\">South Korea case<\/h2>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_all-1024x546.png\" alt=\"Achieved model fit loss value for different latent period values for South Korea. Lower is better.\" class=\"wp-image-568\" width=\"768\" height=\"410\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_all-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_all-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_all-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_all-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_all-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_all.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>Achieved model fit loss value for different latent period values for South Korea. Lower is better.<\/figcaption><\/figure>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>For South Korea case we can&#8217;t see any ranges of the supposed latent period length that are more likely than others. Even very short latent period of 2 hours still gives a possibility of a good observed values fit.<\/p>\n<\/div>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_top-1024x546.png\" alt=\"\" class=\"wp-image-569\" width=\"768\" height=\"410\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_top-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_top-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_top-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_top-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_top-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Korea_top.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>South Korea: SEIR model runs with latent period values that fit the observations in the best way.<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">Austria case<\/h2>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_all-1024x546.png\" alt=\"Achieved model fit loss value for different latent period values for Austria. Lower is better.\" class=\"wp-image-570\" width=\"768\" height=\"410\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_all-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_all-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_all-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_all-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_all-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_all.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>Achieved model fit loss value for different latent period values for Austria. Lower is better.<\/figcaption><\/figure>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>Austria case suggests that latent period length shorter than 48 hours are unlikely to produce good looking simulations.<\/p>\n<\/div>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_top-1024x546.png\" alt=\"Austria case: SEIR model runs with latent period values that fit the observations in the best way.\" class=\"wp-image-571\" width=\"768\" height=\"410\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_top-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_top-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_top-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_top-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_top-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Austria_top.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>Austria case: SEIR model runs with latent period values that fit the observations in the best way.<\/figcaption><\/figure>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>The distinct group of values equal to 48, 72 and 96 hours produce the simulations that are most close to the observed values<\/p>\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\">Beijing case<\/h2>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_all-1024x546.png\" alt=\"Achieved model fit loss value for different latent period values for Beijing. Lower is better.\" class=\"wp-image-572\" width=\"768\" height=\"410\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_all-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_all-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_all-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_all-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_all-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_all.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>Achieved model fit loss value for different latent period values for Beijing. Lower is better.<\/figcaption><\/figure>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>Short values of 6 and 24 hours are more likely to describe the observed data.<\/p>\n<\/div>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_top-1024x546.png\" alt=\"Beijing case: SEIR model runs with latent period values that fit the observations in the best way.\" class=\"wp-image-573\" width=\"768\" height=\"410\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_top-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_top-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_top-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_top-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_top-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Beijing_top.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>Beijing case: SEIR model runs with latent period values that fit the observations in the best way.<\/figcaption><\/figure>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>But visual exploration suggests that the value of 6 hours is more likely.<\/p>\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\">Heilongjiang, China case<\/h2>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_all-1024x546.png\" alt=\"Achieved model fit loss value for different latent period values for Heilongjiang,China. Lower is better.\" class=\"wp-image-574\" width=\"768\" height=\"410\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_all-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_all-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_all-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_all-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_all-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_all.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>Achieved model fit loss value for different latent period values for Heilongjiang,China. Lower is better.<\/figcaption><\/figure>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>Observed trend is that for higher latent period values achieved loss is little bit higher.<\/p>\n<p>Again, there is no distinct value for the latent period that gives the outstanding minimum.<\/p>\n<\/div>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_top-1024x546.png\" alt=\"Heilongjiang, China case: SEIR model runs with latent period values that fit the observations in the best way.\" class=\"wp-image-575\" width=\"768\" height=\"410\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_top-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_top-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_top-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_top-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_top-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/Heil_top.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>Heilongjiang, China case: SEIR model runs with latent period values that fit the observations in the best way.<\/figcaption><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\">An attempt to normalize loss values across all locations<\/h3>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/all_normalized-1024x546.png\" alt=\"Normalized achieved loss value for all of the experiment locations\" class=\"wp-image-576\" width=\"768\" height=\"410\" srcset=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/all_normalized-1024x546.png 1024w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/all_normalized-300x160.png 300w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/all_normalized-768x410.png 768w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/all_normalized-1536x819.png 1536w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/all_normalized-1200x640.png 1200w, https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/all_normalized.png 1800w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 984px) 61vw, (max-width: 1362px) 45vw, 600px\" \/><figcaption>Normalized achieved loss value for all of the experiment locations<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">Summary<\/h2>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>Europe locations suggest that latent period is between 2 and 4 days: Austria case suggests the value of 48-96 hours, Italy case suggests the value greater than 48 hours. While China cases suggest shorter latent period.<\/p>\n<\/div>\n\n\n\n<h3 class=\"wp-block-heading\">Need more details?<\/h3>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>I published the data as <a href=\"https:\/\/www.kaggle.com\/dgrechka\/covid19-latent-period-computational-experiment\">Kaggle DataSet<\/a>. The figure producing code is also available as <a href=\"https:\/\/www.kaggle.com\/dgrechka\/covid-19-latent-period-exploration\">Jupyter Notebook on Kaggle<\/a>.<\/p>\n<\/div>\n\n\n\n<h3 class=\"wp-block-heading\">Future work<\/h3>\n\n\n\n<div class=\"wp-block-jetpack-markdown\"><p>I need to carry out statistical hypothesis testing to evaluate the significance of the results.<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":561,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[10,46,5],"tags":[63,64],"class_list":["post-564","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data","category-modelling","category-study-research","tag-model","tag-seir"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.6 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>COVID-19 Latent period estimation - Dmitry A. Grechka<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"COVID-19 Latent period estimation - Dmitry A. Grechka\" \/>\n<meta property=\"og:url\" content=\"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/\" \/>\n<meta property=\"og:site_name\" content=\"Dmitry A. Grechka\" \/>\n<meta property=\"article:published_time\" content=\"2020-04-20T13:07:23+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2020-08-17T11:10:41+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/results___19_0.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1800\" \/>\n\t<meta property=\"og:image:height\" content=\"960\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"dmitry\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"dmitry\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/\",\"url\":\"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/\",\"name\":\"COVID-19 Latent period estimation - Dmitry A. Grechka\",\"isPartOf\":{\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/results___19_0.png\",\"datePublished\":\"2020-04-20T13:07:23+00:00\",\"dateModified\":\"2020-08-17T11:10:41+00:00\",\"author\":{\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/#\/schema\/person\/63485104fdec6dbe258ea67c2e053a6f\"},\"breadcrumb\":{\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/#primaryimage\",\"url\":\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/results___19_0.png\",\"contentUrl\":\"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/results___19_0.png\",\"width\":1800,\"height\":960,\"caption\":\"Latent period estimation for Austria\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/grechka.family\/dmitry\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"COVID-19 Latent period estimation\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/#website\",\"url\":\"https:\/\/grechka.family\/dmitry\/blog\/\",\"name\":\"Dmitry A. Grechka\",\"description\":\"Personal blog\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/grechka.family\/dmitry\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/#\/schema\/person\/63485104fdec6dbe258ea67c2e053a6f\",\"name\":\"dmitry\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/grechka.family\/dmitry\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/ce55dc1fed08e9a15667f56e3285826aa634c717d9c0e34809d717f699bb7b0b?s=96&d=identicon&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/ce55dc1fed08e9a15667f56e3285826aa634c717d9c0e34809d717f699bb7b0b?s=96&d=identicon&r=g\",\"caption\":\"dmitry\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"COVID-19 Latent period estimation - Dmitry A. Grechka","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/","og_locale":"en_GB","og_type":"article","og_title":"COVID-19 Latent period estimation - Dmitry A. Grechka","og_url":"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/","og_site_name":"Dmitry A. Grechka","article_published_time":"2020-04-20T13:07:23+00:00","article_modified_time":"2020-08-17T11:10:41+00:00","og_image":[{"width":1800,"height":960,"url":"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/results___19_0.png","type":"image\/png"}],"author":"dmitry","twitter_misc":{"Written by":"dmitry","Estimated reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/","url":"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/","name":"COVID-19 Latent period estimation - Dmitry A. Grechka","isPartOf":{"@id":"https:\/\/grechka.family\/dmitry\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/#primaryimage"},"image":{"@id":"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/#primaryimage"},"thumbnailUrl":"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/results___19_0.png","datePublished":"2020-04-20T13:07:23+00:00","dateModified":"2020-08-17T11:10:41+00:00","author":{"@id":"https:\/\/grechka.family\/dmitry\/blog\/#\/schema\/person\/63485104fdec6dbe258ea67c2e053a6f"},"breadcrumb":{"@id":"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/"]}]},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/#primaryimage","url":"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/results___19_0.png","contentUrl":"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/results___19_0.png","width":1800,"height":960,"caption":"Latent period estimation for Austria"},{"@type":"BreadcrumbList","@id":"https:\/\/grechka.family\/dmitry\/blog\/2020\/04\/covid-19-latent-period-estimation\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/grechka.family\/dmitry\/blog\/"},{"@type":"ListItem","position":2,"name":"COVID-19 Latent period estimation"}]},{"@type":"WebSite","@id":"https:\/\/grechka.family\/dmitry\/blog\/#website","url":"https:\/\/grechka.family\/dmitry\/blog\/","name":"Dmitry A. Grechka","description":"Personal blog","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/grechka.family\/dmitry\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":"Person","@id":"https:\/\/grechka.family\/dmitry\/blog\/#\/schema\/person\/63485104fdec6dbe258ea67c2e053a6f","name":"dmitry","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/grechka.family\/dmitry\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/ce55dc1fed08e9a15667f56e3285826aa634c717d9c0e34809d717f699bb7b0b?s=96&d=identicon&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/ce55dc1fed08e9a15667f56e3285826aa634c717d9c0e34809d717f699bb7b0b?s=96&d=identicon&r=g","caption":"dmitry"}}]}},"jetpack_featured_media_url":"https:\/\/grechka.family\/dmitry\/blog\/wp-content\/uploads\/2020\/04\/results___19_0.png","jetpack_sharing_enabled":true,"jetpack_likes_enabled":true,"_links":{"self":[{"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/posts\/564","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/comments?post=564"}],"version-history":[{"count":10,"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/posts\/564\/revisions"}],"predecessor-version":[{"id":589,"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/posts\/564\/revisions\/589"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/media\/561"}],"wp:attachment":[{"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/media?parent=564"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/categories?post=564"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/grechka.family\/dmitry\/blog\/wp-json\/wp\/v2\/tags?post=564"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}