Data Analysis in Practice: statistics and visualisation on real data

01

Start with real data and check it first

In simple words

Before you cook with food from a market, you look at it and smell it. Data is the same. Before you calculate anything, you look at the data and ask: what is this, who made it, and does it look right?

Before this course: Data Analytics Basics (course 7.3). You should already know the four types of analytics, how to write a clear question, how to clean a CSV with a log, and mean, median and mode. If not, do that course first. Here we go one step deeper: real datasets, distributions, uncertainty, relationships and honest charts.

Key facts

A real public dataset is better practice than made-up numbers because it has gaps, odd values and notes you must read.
Your country's statistics agency publishes data tables you can download (see In your country below). This lesson uses Canada as the example: Statistics Canada publishes tables you can download as CSV. Example: table 18-10-0004-01, Consumer Price Index, monthly, not seasonally adjusted. Its page offers several CSV download options, including the entire table as a CSV zip file.
In Canada, the Open Government Portal (open.canada.ca) lists many more open datasets.
Before analysing, do a first look check:

Check	Question to ask
Source	Who published it, and when was it last updated?
Rows and columns	What does one row mean (a person, a month, a city)?
Units	Dollars, thousands of dollars, percent, index points?
Missing values	Are blanks, "..", "x" or "F" symbols used? What do they mean?
Time span	Which dates are covered? Any gaps?
Definitions	Read the table footnotes and metadata.

Know the unit of analysis. If one row is one month, you cannot say anything about individual people.
Index numbers (like the CPI) show change relative to a base period, not a price in dollars.

In your country

Statistics Canada is Canada's central statistical agency, under the Statistics Act. It runs the Census every five years.
Source: Statistics Canada, about us: www.statcan.gc.ca/en/about/about

Two main statistics agencies: the Census Bureau (people, housing and the economy, census.gov) and the Bureau of Labor Statistics (jobs, unemployment, prices and wages, bls.gov).
Source: Census Bureau, What we do: www.census.gov/about/what.html ; BLS, About us: www.bls.gov/about-bls/home.htm

The national statistics office is the Philippine Statistics Authority (PSA), created by RA 10625 (2013).
Source: RA 10625 text: lawphil.net/statutes/repacts/ra2013/ra_10625_2013.html

The national statistics office is the National Bureau of Statistics (NBS, stats.gov.cn). Its data query portal is data.stats.gov.cn.
Source: National Bureau of Statistics: www.stats.gov.cn/

The statistics office is the Statistics Bureau (Ministry of Internal Affairs and Communications), at stat.go.jp. Its portal for government statistics is e-Stat.
Source: Statistics Bureau of Japan: www.stat.go.jp/english/index.html ; e-Stat: www.e-stat.go.jp/en/

The national statistics office is the Ministry of Data and Statistics (formerly Statistics Korea), at mods.go.kr. Its site points to the KOSIS statistical portal in English.
Source: Ministry of Data and Statistics: mods.go.kr/anse/

Step by step

Open the Statistics Canada table page for 18-10-0004-01 (or a table on a topic you like from your own country's statistics agency).
Read the title, the frequency and the footnotes before downloading.
Use the download options to get a CSV, and save a copy of the original file untouched.
Open the copy in Excel or Google Sheets.
Fill in the first look check table above, in a note: source, what one row is, units, missing symbols, time span.
Count rows and look at the smallest and largest value in each column (=MIN(), =MAX(), =COUNT()).
Write down one question this data could answer, using the rules from course 7.3.
Check: a friend could read your note and know what the data is without opening the file.

Watch on YouTube

Accessing Canadian datasets from the Statistics Canada websiteUTMLibrary · YouTube · youtube.com

Videos by other creators on YouTube, for reference. They are not made by or affiliated with The Future Market.

LESSON 01Start with real data and check it first

LESSON 01 / ANIMATED LESSON / AI VOICE00:00 / 01:00

Voice

Read the video script

[Host] "Before you calculate anything, look at your data like a detective."
[Screen: Statistics Canada table page with Download options] "Real data comes with notes. Read the title, the units and the footnotes first."
[Text on screen: Source, Row meaning, Units, Missing, Time span] "Five checks: source, what a row means, units, missing values, time span."
[Host] "Five minutes of checking saves hours of wrong answers."

Try it now

Download one table from Statistics Canada or your own country's statistics agency. Write the first look check (six lines) and one question the table can answer. Keep the raw file untouched.

ClaudeStuck? Copy a ready-made prompt for Claude

Copy this, open Claude, paste it, and Claude will walk you through the lesson step by step.

For a grown-up: Claude is for adults (18+). Copy this, paste it into Claude, and use the answer to explain the lesson to your child.

I'm learning "Data Analysis in Practice: statistics and visualisation on real data" on The Future Market. Lesson 1: "Start with real data and check it first".

What the lesson teaches:
- A real public dataset is better practice than made-up numbers because it has gaps, odd values and notes you must read.
- Your country's statistics agency publishes data tables you can download (see In your country below). This lesson uses Canada as the example: Statistics Canada publishes tables you can download as CSV. Example: table 18-10-0004-01, Consumer Price Index, monthly, not seasonally adjusted. Its page offers several CSV download options, including the entire table as a CSV zip file.
- In Canada, the Open Government Portal (open.canada.ca) lists many more open datasets.
- Before analysing, do a first look check:
- Check - Question to ask
- Source - Who published it, and when was it last updated?
- Rows and columns - What does one row mean (a person, a month, a city)?

The exercise I'm working on:
Download one table from Statistics Canada or your own country's statistics agency. Write the first look check (six lines) and one question the table can answer. Keep the raw file untouched.

I'm stuck. Please:
1. Explain the main idea in plain, simple words with one everyday example.
2. Walk me through the exercise one small step at a time. Ask me what I've done so far before giving the next step.
3. Don't just give me the final answer. Help me do it myself, and check my work when I share it.

I'm a parent helping my child (about 8 years old) with a lesson called "Start with real data and check it first" from the course "Data Analysis in Practice: statistics and visualisation on real data".

Here's what the lesson says:
Before you cook with food from a market, you look at it and smell it. Data is the same. Before you calculate anything, you look at the data and ask: what is this, who made it, and does it look right?

The activity:
Download one table from Statistics Canada or your own country's statistics agency. Write the first look check (six lines) and one question the table can answer. Keep the raw file untouched.

Please explain this so an 8-year-old understands: short sentences, a fun everyday example, and no hard words.
Then give me 3 simple questions I can ask my child to check they understood, and a way to do the activity together, one tiny step at a time.

Open Claude

Sources

Statistics Canada, Consumer Price Index, monthly, not seasonally adjusted (table 18-10-0004-01): www150.statcan.gc.ca/t1/tbl1/en/tv.action?pid=1810000401
Government of Canada, Open Government: open.canada.ca/en/open-data

My notes

I learned this

02