Distribution of Symptom Counts

Exploratory Data Analysis
The distribution of symptom counts

In the VAERS database, some people report more symptoms than others.

What is the distribution of symptom counts?
How many symptoms are the most common?

—-

Counts:

use VAERS_2019
go

select sum(sym_cnt) Total_symptoms
from dbo.[VAERSDATA]

Total_symptoms:
2,834,970

select count(*) Count
from dbo.[VAERSDATA]

Count:
759,483

Average symptoms per VAERS_ID:
= 2,834,970 / 759,483
= 3.73

—-

Distribution:

SELECT sym_cnt as Symptom_Count
, count(*) Count
from dbo.[VAERSDATA]
group by sym_cnt 
order by 1

—-

—-

Notes:

All data: all VAERS_ID, all years, all symptoms

The most common number of symptoms in VAERS is 2

The average number of symptoms in VAERS is 3.73

99.3% of all VAERS_IDs have 20 symptoms or less