The Data Analysis Process(2)

After we have defined our business problem and asked appropriate questions that'll help set the pace for our analysis, the next phase of the analysis phase is Prepare.

Prepare: The preparation phase is for the collection of data that would be relevant for our analysis. A lot of work goes into this phase because we have to take into consideration:
Who collected the data, What is included in this data collected, and when was this data collected: is it current, is it relevant, where did the data come from: is it from an external source, or is it the company's internal data and why was this data collected?
If there is no pre-collected data, we have to generate our own data for the purpose of this analysis through surveys or other means.

Process: We have defined the problem, asked for the appropriate data, and also get the data that would be used for this analysis. The next phase is to process the data which involves cleaning, transforming, and getting the data ready for analysis. Real-world data is messy as it is input by humans and prone to error. This is also a very important phase in the data analysis process because if we do not clean the data well, there would also be errors in the analysis. Like they say "Garbage in, garbage out".
Cleaning data involves removing duplicate values, and extra spaces, correcting inaccurate data, dealing with missing data, ensuring there is consistency in the formatting, and also handling outliers(extreme values). Once our data is free of errors, we can advance to the next phase which is the Analysis phase.


To be continued...