How to operationalize a project’s objectives with the variables in your dataset
HILO’s help in this guide uses AI: you need an account (the free one includes 100 welcome hilos).
Write the objectives so they can be measured
Write each objective in one sentence, with a verb you can observe (measure, compare, identify) and a single subject. One objective per line.
Take stock of the variables in your dataset
List each column of the dataset with its name, its type (number, category or free text) and the values it takes.
Match each objective with the variables
For each objective, look for the variables that measure it or approximate it.
Define an indicator for each objective
For each objective that can be measured, define an indicator: a name and a formula using the variables, for example “average satisfaction = mean of satisfaction” or “percentage of people with more than an hour of commuting”.
Recognize what is missing and document it
An objective with no variable at all is a finding: it has to be measured with a new question or the objective has to change. Record, for each objective, which variables you used, which ones you approximated and what is missing.
Other ways to do it
You can do it by hand in a spreadsheet (one row per objective and one column per variable) or with an indicator matrix.
HILO is the better fit for a quick first look: it runs in the browser, there’s nothing to install, and the dataset is read on your computer; the objectives and the inventory of variables go to the AI, as explained in step 3. Another tool is the better fit if you need a full indicator framework, with targets and sources, or to work as a team on the same document. Deciding whether a variable measures an objective is always up to you.
Operationalize your own objectives
Load your dataset, paste the objectives and see what you can measure with what you already have.
Updated
More guides
How to measure intercoder reliability
Cohen’s kappa in 5 steps: code separately, build the table, count the agreement, remove chance and report.
How to share a dataset without exposing personal data
Column inventory, what to do with each one, free text, re-identification risk and the code table, in 5 steps.
How to clean a survey dataset before analyzing it
Read the file correctly, find repeats, check columns, spot non-response codes and fix at the source, in 5 steps.
How to merge two survey datasets
Choose between stacking and joining by identifier, check that they measure the same thing, merge and review the result, in 5 steps.
How to code the open-ended responses of a survey
Read a sample, build the categories, assign each response, review and bring them into your dataset, in 5 steps.