Klang Valley has a disproportionately higher number of Covid 19 cases per mill population. WHY?

There is something about the distribution of Covid 19 cases in the country that I don’t understand. 

If you plot the Covid 19 case rate for each state ie take the number of cases for each state divided by the population of the state, we have the picture as shown in the chart (ie no of cases per million population)

 

You will see that 3 states stand out – KL, Putrajaya and Negri.   OK, we must remember that the number of cases included returnees so the number of cases for some states may be skewed eg

• Selangor has 105 returnees
• Negri has 169 returnees

So I overlaid another plot after excluding the returnees.  Except for Putrajaya, the picture is still the same.

 

I expected the rates to be the same for all the states but the chart shows that for 3 areas it is higher than the national average rate of 241 cases per million

What it means is that if you are in KL, you are about 6 times more likely to find Covid cases c/w the national average.  Indirectly it means a higher risk of infection.   By the same logic, if you are in Negri you are more likely to be infected than if you are in Kedah.

 

So why do KL and Negri stand out?   My first thought was this was the Klang Valley and as Selangor has the next largest rate just before Negri in the chart, the Klang Valley story seems plausible. 

 

To try to figure out the reason, I plotted a scattergram of case rate vs population for all the states and you can see that KL, Selangor, and Negri stand out as outliers.

Can anyone think of an explanation for this pattern? 

At first, I thought that we have a scenario where if you are in a more densely populated area, it meant higher chances of contacts, etc so that you have an extraordinary higher number of cases.

By this logic, it meant that the US with 10 times the population of Malaysia will have significantly more cases than Malaysia ie it will be much higher number of cases than that suggested by the population ratio.   This is actually the situation as the US has 250 times more cases than Malaysia

• USA has 2 million cases
• Malaysia has 8,000 odd cases

Of course, I am just confusing you with statistics. The reason for the higher number of cases in the US is more than just having a bigger population. 

To come back to the chart.  

For the scenario where a higher population leads to a higher infection rate to be proven, the dots in the scattergram should show a trend from the bottom left-hand corner towards the top right-hand corner of the chart.  

But there is no such pattern.  As can be seen from the chart, if you exclude KL and Negri, the case rate is quite independent of the population in each state. 

 

Then I thought that maybe the different land sizes for each state could account for the outliers. So I did a different scattergram as per below that shows the number of cases by the land area of each state. 

 

Again there is no pattern because if the number of cases varies with land size eg more cases if the population is in smaller areas, we would have seen a trend from the top left-hand corner to the bottom right-hand corner of the scattergram. 

If there was this pattern, it would have meant that the rate of infection is related to the population density.  But no such relationship.

Rather, I would say that excluding KL and Selangor, the no of cases does not seem to vary with the land size of each state. 

So it is not land size, it is not a larger population.  What is so special about the Klang Valley that is causing all the extraordinary number of cases?

I know.  It is where most of the politicians are.  

As Sherlock Holmes said when you have eliminated all the impossible, whatever remains, no matter how improbably, must be the truth.

But seriously, can anyone explain this finding? 

- - - - - - - - - - - - - - - - - - - - - - - - - - -

Be fearless to get more to Stay Safe, Share this Blog

PS: This blog is for me to better understand COVID 19 as this will impact my investments. If you are also into equities, follow me at i4value.asia.

Disclaimer:  I am not an epidemiologist, healthcare worker, pharmacist, or staff in the Ministry of Health, but rather is someone with a strong interest in numerical analysis.  The content is an attempt to understand what is happening in the battle against COVID 19 from a data-based perspective. The opinions expressed here are based on information extracted from readily available public sources but I do not warrant its completeness or accuracy and should not be relied on as such.