Getting Started: Data Confidence & Good Habits
Before diving into specific datasets or tools, it’s helpful to review principles of good research habits for data confidence. The following sections introduce key concepts that will help you work with data more effectively and confidently!
Strong research starts with understanding what data actually represent. Data may show counts, rates, trends, or comparisons, each tells a different part of the story. This section introduces the fundamentals of data literacy, including how data are generated through the research process and the differences between qualitative and quantitative data.
Recommended Resource:
Ohio University Libraries – Research Data Literacy 101 This resource from the Ohio University Libraries provides an introductory overview of data and data literacy as part of a larger three-part series. It defines what data are (including qualitative vs. quantitative), explains core terms like data vs. statistics, introduces why and how data are used in research, and links to resources for finding, interpreting, and working with data effectively.
Strong research begins with clarity of purpose. Before collecting or analyzing any data, ask: What do you want to know? Who is your audience? And what kind of data will best illustrate your message? Being intentional about your question, your stakeholders, and your evidence ensures that your work is focused, meaningful, and actionable from the start.
Recommended Resource:
Creating a Data Plan – 12 Months to Better Data from RIPL
The Research Institute for Public Libraries (RIPL) website outlines a year-long, free monthly webinar series offered in 2024. It shares an overview of the program—based on key steps in research and evaluation like identifying purpose, planning, collecting, analyzing, and using data—and links to recordings of each session, which cover topics such as data planning, survey design, visualization, culturally relevant data, meaningful metrics, and using data for decision-making and advocacy.
| Tip: Planning Pays Off Before collecting data, decide: – What do you want to learn more about, or what questions are you trying to answer? – What do you want to gain from researching this question, or what problem are you hoping to solve? – How will you use the results? For example, are you hoping to identify a trend or make a decision? Clear goals make it much easier to collect the right data. |
Public libraries have a strong tradition of protecting patron privacy. When collecting or using data, it’s important to balance the benefits of research and analysis with ethical responsibilities around confidentiality and data protection.
Recommended Resource:
The Research Institute for Public Libraries (RIPL) webinar on library patron privacy and data use explores how public libraries can balance protecting patron privacy with using customer behavior data to personalize and improve services, discussing theory and practical approaches to find a middle ground along the privacy–personalization continuum.
| Tip: Protect Patron Privacy When working with library data: – Avoid sharing personally identifiable information – Use aggregated data whenever possible – Be transparent about how data are collected and used Even well-intentioned analysis should respect library privacy principles. |
Confusing correlation and causation
Just because two things happen together does not mean one caused the other.
Often when looking at data, novice researchers make the mistake of assuming that just because two things are linked, one must be causing the other. This can lead to false conclusions — for example, thinking eating ice cream causes sunburns, when really it’s sunny weather influencing both. Always ask: Could there be another factor at play?
Using data outside its intended scope or assuming there isn’t data to answer a question
Data collected for one purpose (ie: the Annual Library Report) may not answer every question or be applicable in all circumstances. Sometimes you may need to explore collecting additional data on your own.
Comparing Unlike Groups
Be careful when comparing libraries, populations, or time periods that are not truly comparable. A great example of this is the “Covid Era.” We all know that comparing what happened in our libraries in 2020-2021 with other typical years will not yield the best outcome!
Unclear Research Questions
Without a clear question, it’s easy to collect too much data without learning anything meaningful.
Know Your Data
Every dataset has limitations. Understanding how data were collected helps you interpret them correctly. This is especially important when analyzing trends over time. Make sure you know how the data were collected in prior years and confirm that the same methodology is being used today.
Always Remember your Audience
Keeping your intended audience in mind is helpful throughout the data collection, analysis and reporting process. It can be helpful to periodically ask yourself: Who cares about this data, and why?
Sample Size Matters
When a dataset is too small, it becomes difficult to draw reliable conclusions. Small datasets can produce misleading results because a few data points can strongly influence the outcome, making patterns appear that may not exist in the broader population.
Avoid Confirmation Bias
Confirmation bias can lead you to overlook important information. Be careful not to dismiss data that challenges your understanding or expectations.
Mistakes
Even the most careful data collectors make mistakes, and understanding where errors arise is the first step toward preventing them. The most common culprits include human error (transposed numbers, duplicate entries), inconsistent definitions across staff, and ambiguous survey questions that lead people to interpret prompts differently. Recognizing these pitfalls doesn’t mean distrusting data — it means building habits of documentation, cross-checking, and communication that make your data more trustworthy over time.
Libraries collect data from many sources: circulation systems, program tracking, surveys, and community datasets. Establishing a clear internal process helps ensure that information is consistent and useful.
Key steps include:
- Assign responsibility – Everyone should have a basic understanding of the data that is collected, as it is important to the success of libraries. However, it’s important to have a point person for data collection and analysis. Identify a staff member or small team responsible for managing and analyzing data. This improves efficiency when responding to requests, compiling reports, and maintaining consistent data collection.
- Collect data regularly – Data collection should occur in specifically defined increments (daily, weekly, monthly, quarterly, etc.) and it should happen regularly. With libraries, there are a variety of streams of data, which can complicate things.
- Document procedures – Record how data is being collected (automated, manual) and stored so the process is consistent over time.
- Define Key Performance Indicators (KPIs) – Decide which metrics best measure success for your library.
| Tip: Find Your Data Friends Don’t go it alone! Pair up with data-confident peers for guidance and troubleshooting, and check your ideas with people who aren’t as familiar with the data. If they get it, you know you’re on the right track! |
Excel and Google Sheets are powerful tools for managing, analyzing, and visualizing your library data, and you don’t need to be an expert to get started. Here are the key basics you’ll want to know:
Getting Started with Data in Spreadsheets
Start simple. Focus on one dataset at a time and practice organizing it clearly.
- Sorting and Filtering – Quickly organize your data to see trends, focus on specific dates, or narrow down by categories. Use filters and sorting before jumping into calculations or charts – it makes analysis much easier.
- Formatting Numbers and Dates – Make your data readable by using consistent formats for currency, percentages, dates, and decimals.
- Simple Formulas – Learn basic functions like SUM, AVERAGE, and COUNT to summarize your data.
- Conditional Formatting – Highlight important values, trends, or outliers to make patterns stand out.
- Intro to Pivot Tables – Pivot tables let you summarize and explore your data in flexible ways, e.g., total checkouts by month or program attendance by age group.
- Basic Charts – Visualizing your data with bar charts, line graphs, or pie charts makes it easier to communicate your findings. Think about your audience – use visuals and labels that anyone can understand.
| Tip: Protect Your Raw Data Always keep a copy of your original data set (raw data) unchanged. Use a separate tab or workbook apart from any calculations or charts to avoid accidental changes. This prevents accidental errors and makes troubleshooting easier. |
Where to Learn More – If you want step-by-step guidance or interactive training, here are some great beginner-friendly resources.
Recommended Resources:
- Depict Data Studio – Practical tips for making attractive, easy-to-read visualizations in Excel (depictdatastudio.com)
- Excel or Google Sheets Tutorials on LinkedIn Learning, Udemy, Niche Academy, or Gale Courses (check with your library system)
- Excel Tutorials on Badgerlink / EBSCO All Resources Database