{preheader}
  ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌   ‌
 
View this email in your browser
 
 
 

          Data cleaning can be an essential step of the research process that identifies potential inaccuracies and addresses them for a more uniform dataset. Data cleaning can be done in Excel, using scripts, or with specialized data cleaning tools. Before you begin cleaning, create a copy of your raw data file and work from there. There are many different approaches to cleaning. Here are a few questions that you can ask of your data to see if they would benefit from cleaning!

➀ Column names
Do they make sense? Do they avoid spaces and special characters?
Are units of measure specified? 

➁ Data types
Do the data correspond to expected type based on the column name?
Does every value in a column consistently follow the same data type and format?

➂ Ranges
Do the minimum and maximum values fit expected ranges?

➃ Extra spaces
Are there white spaces that might inhibit matching and splitting column values?

➄ Non-standardized casing
Do the values share a uniform case, such as lowercase or sentense case?

➅ Irregular spelling
Are values spelled according to established conventions?

➆ Blank cells 
Are there missing values or blank cells in your dataset?

➇ Duplicates
Is there potential duplication of values that should be unique?

* Here is a printable version of the guide.

Have additional questions about preparing your dataset for analysis? Schedule a consultation with CITL to receive custom data cleaning support.

 
 
 

☆☆☆ Browse Past Nudges ☆☆☆

 
 
 

Have you been nudged into action by the Data Nudge?
Tell us about it using this feedback form and we'll send you a
Research Data Service gift bag!