1,869 subjects churned during the analysis time.7,043 subjects originally but only 7,032 subjects were used in the analysis.Stata command: stset tenure, failure(churner) We now present the key survival data analysis results below. The filename is a bit longer: WA_Fn-UseC_-Telco-Customer-Churn.csv. In Watson Analytics, tap Add and upload Telco Customer Churn.Download the Telco Customer Churn sample data file.To source the original customer dataset follow these instructions:
Stata label define tv#
Services that each customer has signed up for – phone, multiple lines, internet, online security, online backup, device protection, tech support, and streaming TV and moviesĬustomer account information – how long they’ve been a customer, contract, payment method, paperless billing, monthly charges, and total chargesĭemographic info about customers – gender, age range, and if they have partners and dependents The Stata do file at the end of this blog is about the csv data importation, data cleansing, data exploration and survival data analysis.Ĭustomers who left within the last month – the column is called Churn In our case, we exported the resulting dataset as a csv file for use in Stata.
Stata label define code#
We are sincerely grateful to WatsonAnalytics team and Dr Lauren Oldja for her Python source code which we ran (see ).
When the customer service churns is the event of interest in survival data analysis.Customer churning is when the customer service ceases.
How is this related to customer churning? This, among other things, precludes the use of OLS from survival data analysis.