This week’s post is from Pauline Ndirangu, an Open Data Fellow 2016 who is part of our Data Science Team where she surfaces stories from different data sets. “I find purpose by extracting tales from data. My main tools for this are R and Python with progressive experience in building dashboards. Find me on Medium @paulinenimo to come along with me on this journey. My areas of interest are finance, education and health. ”


Public Safety is a pressing concern in Kenya, specifically, road safety. We hear of fatal road accidents on the news daily. The campaigns about road safety have been on for a while. There have been over fifty fatalities caused by road accidents in the last three weeks alone. From the Kisii accident involving University students to the more recent Salgaa accident claiming the lives of seven family members, road carnage is robbing Kenya of its most valuable resource: its people.
In 2015, there were over 3000 fatalities on our roads, that is, approximately seven out of 100,000 people lost their lives. The figures paint a gruesome picture on road carnage in the country.


I sought to investigate this further. First ,who is most likely to be involved in a fatal accident?
Data from show that in 2014, private means got involved in more fatal accidents than any other means. Commercial vehicles came second while PSVs came in third. Motorcycle accidents were fourth. These four are also quite evident to be the most common causes of road accidents in 2015 as well. However, PSVs became the most common cause of fatalities with motorcycles coming in at second, commercial vehicles in third and private means in fourth. There has been a lot of focus on the road safety especially in private means and may have led to the decrease in accidents. The motorcycle accident raw numbers have been relatively unchanged and thus more attention needs to be focused on remedying the trend.

Next, when are the accident most likely to occur?. Considering dats of the week as points of reference, fatal accidents occur relatively lower on Monday through Thursday than they do on Friday through Sunday. The highest number of fatal accidents occur on Saturday followed by Sunday for both years. There may be reasons behind this. Saturday and Sunday are considered by some to be days of worship. Is it that maybe Saturdays are usually non-working and non-school days so most people travel and perform other leisure activities then? Does the same apply for Sunday? Is the number higher on Friday because people tend to go out and have a drink or two?

Finally, when (time of day) are accidents likely to occur. The figures for 2015 show that accidents that occur in the morning hours appear to have a low number of fatalities then they have a spike at 5am. The numbers decrease as the morning goes by and spike at around mid day. The numbers increase and stay high until 10pm. Could this be proportional to the volume of road users at different times of the day? Possibly.

Fatal accidents seem to occur mostly in the evening, specifically around 6pm. This can be argued to be caused by the volume of traffic and passengers created by the end of working hours. It can also be argued that a number of road users are on a rush to complete tasks such as pick children from school or that users are too tired to pay much attention to the road. More data is required to be in order to show validity of above arguments.

Road Accidents Claim 10 Kenyan Lives Everyday

Prestone Adie

I drive Data Analytics where I surface stories from data that might not be immediately obvious. With a background in Actuarial Science I'm proficient in R and Python for data analysis and takes avid interest in anything data. Find me on twitter Follow @AdiePrestone where we can talk data, street food, cars and books.

Post navigation