Overview
Teaching: 15 min
Exercises: 0 minQuestions
Introduction to spreadsheets for good data organization
Objectives
Understand how to organize data so computers can make the best use of the data
Authors:Christie Bahlai, Aleksandra Pawlik
Contributors: Jennifer Bryan, Alexander Duryee, Jeffrey Hollister, Daisie Huang, Owen Jones, Clare Sloggett, Harriet Dashnow and
Ben Marwick
Good data organization is the foundation of your research project. Most researchers have data or do data entry in spreadsheets. Spreadsheet programs are very useful graphical interfaces for designing data tables and handling very basic data quality control functions.
In this lesson, we’re going to talk about:
Overall good data practices
Spreadsheets are good for data entry. Therefore we have a lot of data in spreadsheets. Much of your time as a researcher will be spent in this ‘data wrangling’ stage. It’s not the most fun, but it’s necessary. We’ll teach you how to think about data organization and some practices for more effective data wrangling.
If you’re looking to do this, a good reference is Head First Excel by O’Reilly
Data analysis in spreadsheets usually requires a lot of manual work. If you want to change a parameter or run an analysis with a new dataset, you usually have to redo everything by hand. (We do know that you can create macros, but see the next point.)
It is also difficult to track or reproduce statistical or plotting analyses done in spreadsheet programs when you want to go back to your work or someone asks for details of your analysis.
Commands may differ a bit between programs, but the general idea is the same.
Questions:
- How many people have used spreadsheets in their research?
- How many people have accidentally done something that made them frustrated or sad?
Spreadsheets encompass a lot of the things we need to be able to do as researchers. We can use them for:
We do a lot of different operations in spreadsheets. What kind of operations do you do in spreadsheets? Which ones do you think spreadsheets are good for?
Spreadsheets are good for data entry, but in reality we tend to use spreadsheet programs for much more than data entry. We use them to create data tables for publications, to generate summary statistics, and make figures.
Generating tables for publications in a spreadsheet is not optimal - often, when formatting a data table for publication, we’re reporting key summary statistics in a way that is not really meant to be read as data, and often involves special formatting (merging cells, creating borders, making it pretty). We advise you to do this sort of operation within your document editing software.
The latter two applications, generating statistics and figures, should be used with caution: because of the graphical, drag and drop nature of spreadsheet programs, it can be very difficult, if not impossible, to replicate your steps (much less retrace anyone else’s), particularly if your stats or figures require you to do more complex calculations. Furthermore, in doing calculations in a spreadsheet, it’s easy to accidentally apply a slightly different formula to multiple adjacent cells. When using a command-line based statistics program like R or SAS, it’s practically impossible to accidentally apply a calculation to one observation in your dataset but not another unless you’re doing it on purpose.
However, there are circumstances where you might want to use a spreadsheet program to produce “quick and dirty” calculations or figures, and some of these features can be used in data cleaning, prior to importation into a statistical analysis program. We will show you how to use some features of spreadsheet programs to check your data quality along the way and produce preliminary summary statistics.
In this lesson, we will assume that you are most likely using Excel as your primary spreadsheet program - there are others (gnumeric, Calc from OpenOffice), and their functionality is similar, but Excel seems to be the program most used by biologists and ecologists.
In this lesson we’re going to talk about:
Key Points
Good data organization is the foundation of any research project.