Analysis of the data presented by the Ministry of Health on the spread of COVID-19 by a local data scientist revealed discrepancies between what was recorded and what was presented.
In one instance, some 1,200 cases were left out of a graph presented to the public.
On the company’s website ubylitics.com, Ubilytics co-founder and data scientist for almost 15 years Derick Cornwall posted his analysis which came to the following conclusion:
“Our analysis has revealed that all of the epidemiological updates presented by the Ministry of Health in the month of September did not accurately reflect the progression of COVID-19 in Trinidad and Tobago. There was a growing number of previously reported positive cases that were missing from these updates.”
Even after the epidemiological presentations were adjusted as the ministry cleared its backlog of tests, the discrepancies remained. The largest discrepancy was in the graph presented to the public on September 25, days after the backlog was deemed to have been cleared. It showed that some 1,216 cases were not reflected in the graph.
In an interview with Guardian Media yesterday, Cornwall said: “There are 1,200 cases that are missing from this particular epi-curve (in) this particular graphical update from…what was reported in the daily updates.”
This kind of “faulty data”, he said, can lead to erroneous and biased conclusions “because you’re seeing things in the data that isn’t actually there.”
The extent to which the ministry knew about this particular problem – we don’t know. The extent to which decision-makers like…the Minister of Health, the Prime Minister when they were making their deliberations of what to do next in terms of the implementation or relaxation of measures- how much did they know about the state of these particular graphs?” With this in mind, he said, “the issue needs to be resolved.”
In Cornwall’s article, he pointed out other logical errors which could have been made due to these missing figures such as the branding of the “last lap” for the September 2 spike in cases.
“The peak itself was not, in fact, significant; instead, it only appeared so because data was missing from the entire right-hand side of the epidemiological update. There was, in effect, some sort of systematic under-reporting of cases in the epidemiological data which resulted in the apparent anomalous nature of the September 2nd peak,” he said in the article.
“We waited to see if this missing data would have been added to the following epidemiological update. It wasn’t.”
Guardian Media attempted to reach health officials for a comment on the matter such as Chief Medical Officer Dr Roshan Parasram and Technical Director of the Ministry’s Epidemiology Unit Dr Avery Hinds but calls and messages went unanswered. Minister of Health Terrence Deyalsingh, however, told Guardian Media that Dr Hinds would clarify the matter at today’s news conference.