Topic 5a - Data and Analysis

Before we can organize data, query it, or mine it for patterns—we have to understand what it is and what we want from it.

Learning Objectives

By the end of this topic, you should be able to:

Learning Activities

To help you meet the learning objectives, we have prepared a combination of readings, activities, and videos.

Course Readings

These reading were designed to introduce the course topics to an audience of educators. They should be considered "required" and read in order.

Supplemental Readings

Some participants find it helpful to read about a topic from a source written for a slightly more technical audience. These supplemental readings cover similar material as the course readings but may not fully align with the course learning objectives. Use them as an optional complement to your study, not a substitute for the course readings.

Lesson Videos

These videos support the readings above and may present the material with some deeper connections and worked examples.

Checking for Understanding, Questions

Review the Learning Objectives at the top of this page. The questions below will help you check your understanding before moving on to Topic 5b.

Data and Information

  1. A school nurse keeps a log of every visit to the nurse's office, recording the student's name, grade, date, and reason for visit. Is this data or information? What would it take to make it information?
  2. Explain in your own words why "data without a question is just storage."

The Data Investigation Cycle

  1. A teacher notices that her students consistently struggle with fraction word problems. She pulls her last three years of quiz scores to see whether the problem is getting worse over time. Which stage of the PPDAC cycle does pulling those scores represent? What stage comes before it?
  2. A principal shares a report at a staff meeting showing that students who participated in the after-school tutoring program scored 12 points higher on the spring math assessment. A teacher responds, "But the kids who sign up for tutoring are probably the ones who care more about their grades to begin with." What concern about data interpretation is the teacher raising?
  3. Describe one data quality problem you might encounter in a real school data set, and explain how you would handle it.

Structured vs. Unstructured Data

  1. A district wants to analyze the following. For each item, identify whether the data is structured, unstructured, or semi-structured, and briefly explain your reasoning.
    • Bus ridership counts by route and date
    • Video recordings of kindergarten students reading aloud for fluency assessment
    • Parent responses to an open-ended survey asking "What is your biggest concern about the upcoming school year?"
    • Cafeteria meal participation records
  2. Why would a relational database be the wrong tool for storing and analyzing the video recordings described in the previous question?

It is completely fine to revisit the readings as you work through these questions.

Checking for Understanding, Answers

You can compare your answers to the following answer key.

Show Answer Key

Data and Information

  1. This is data. The log records raw facts — names, grades, dates, reasons — but those facts do not answer any particular question on their own. To become information, the data would need to be interpreted in relation to a specific question. For example: "Are nurse visits increasing in a particular grade?" or "Are certain reasons for visiting more common on specific days of the week?" The same log could answer many different questions — but until a question is asked and the data is analyzed in relation to it, it remains storage.
  2. Data is a collection of recorded facts — numbers, text, observations. Without a question to answer, there is no way to know which facts matter, how they should be organized, or what any pattern in them would mean. The same dataset can answer completely different questions depending on what you are trying to find out. A question gives the data purpose and direction; without one, even a perfectly collected dataset just sits there. "Storage" captures this precisely: the data is being held, but not used for anything.

The Data Investigation Cycle

  1. Pulling the quiz scores represents the Data stage — the third stage of the PPDAC cycle — in which the investigator gathers the data needed to address the question. The stage that comes before it is Plan: deciding what data to collect, how to collect it, and how it will be analyzed. In this case, the Plan stage would have involved deciding to look at quiz scores specifically (rather than, say, unit test scores or teacher observations), deciding how many years to look back, and thinking about how to measure whether the problem is getting worse over time.
  2. The teacher is raising a concern about confounding variables — specifically, the possibility that the apparent effect of the tutoring program is not caused by the program itself, but by a pre-existing difference between the students who enrolled and those who did not. Students who sign up for tutoring may already be more motivated, have more parental support, or have higher baseline scores. If so, the 12-point difference might reflect that pre-existing difference rather than any benefit from tutoring. This is a concern that arises at the Conclusion stage: being careful about claiming causation when the data only shows correlation.
  3. Many valid answers exist. Examples include: missing values (a student record with no grade entered — handle by deciding whether to exclude the record, impute a value, or flag it separately); inconsistent formatting (dates entered as "9/1/2024" in some records and "September 1, 2024" in others — handle by standardizing the format before analysis); duplicate records (the same student appearing twice with slightly different spellings of their name — handle by deduplicating before analysis); entry errors (a test score recorded as 1100 instead of 110 — handle by setting reasonable bounds and flagging values outside them for human review). The key in all cases is to identify the problem during the Data stage, document how it was handled, and be transparent about it in the Conclusion.

Structured vs. Unstructured Data

    • Bus ridership counts by route and date — Structured. This data fits naturally into rows and columns: each record has a route identifier, a date, and a count. It can be stored directly in a spreadsheet or relational database table with no ambiguity about how to organize it.
    • Video recordings of kindergarten students reading aloud — Unstructured. Video files are binary media — there is no inherent row-and-column organization to the data itself. A database might store metadata about each recording (student ID, date, file name), but the content of the recording is not structured data.
    • Parent responses to an open-ended survey — Unstructured (or semi-structured, depending on how it is collected). Free-text responses do not fit into predefined categories. A system might record the respondent and timestamp (structured), but the response itself is prose that requires human reading or natural language processing to analyze.
    • Cafeteria meal participation records — Structured. Each record has a student, a date, and a participation indicator (or meal type selected). This fits cleanly into tabular form and can be queried directly.
  2. A relational database is designed to store and query structured data — values that fit into typed columns with defined relationships between tables. Video files are binary objects with no inherent relational structure. A relational database cannot store the actual content of a video file in a meaningful way, cannot query what happens inside a video, and is not designed to handle the large file sizes involved. The appropriate tool would be a file storage system (or a media management system) that can hold the video files and link them to a structured record (student ID, date, teacher notes) stored separately. The relational database might store the metadata about each recording, but not the recording itself.

Extend Your Learning

The following resources go a little deeper on topics we touched on but did not fully explore in the readings. These are entirely optional — none of this material appears on the Competency Demo — but each one is a natural "next question" from something covered this week.

  • Unstructured data in K–12 schools
    The readings introduced the structured/unstructured distinction conceptually. This article from PowerSchool grounds it in the specific kinds of data schools actually generate: classroom observations, student writing samples, narrative school improvement plans, and teacher reflections — valuable information that traditional data systems were never designed to handle.
    If It's Not in a Chart, Does It Count? — PowerSchool