Lesson video

Hello, my name is Mrs. Jones, and I'm really pleased you've decided to join this lesson today.

In this lesson, we will look at large data sets and how they can be used to make predictions and evaluate findings.

So let's get started.

Welcome to today's lesson.

Today's lesson is called Global Data from the unit, Data Science, and by the end of this lesson, you will be able to use a data set to investigate predictions and evaluate findings to support a for or against argument.

There are three keywords to today's lesson: Data.

Data is numbers or texts that, on their own, have no meaning.

Prediction: Prediction is a guess on what you think the outcome may be.

Criteria: Criteria is a factor on which you judge or decide something.

There are three sections to today's lesson.

The first is recognise uses of large data sets, the second is use a data set to investigate predictions, and the third is evaluate findings to support an argument.

So let's start with recognised uses of large data sets.

Advances in technology have made it easier to collect, store, and analyse data on a much larger scale.

How do you think a TV streaming service collects data? As soon as you log into a TV streaming service, the company will start to collect data on you.

This will include: what device you are watching on, how you scroll through recommendations, and what you decide to watch, whether you scroll forward, pause, or rewind content.

As you continue to use the service, this information will be updated and refined.

Your data will then be compared to other users' data.

Your data will be grouped with other people's data with similar viewing patterns or preferences.

These groupings are used to make recommendations about what to watch next.

These recommendations are predictions based on what other people in your group have watched or enjoyed.

Streaming services can also use this data to decide which series or content to purchase or fund.

For example, if lots of users watch crime-based series, the streaming service may decide to bid for the rights for a new crime series.

Lots of companies and organisations use large data sets.

Can you think of any other examples? Alex says, "Large data sets from satellites and sensors help predict the weather more accurately." Sam says, "Fitness apps track steps, heart rate, and exercise patterns to give personal health advice." Izzy says, "Cities use traffic data to manage traffic lights, reduce congestion, and improve road safety." Let's have a quick check.

How might a supermarket use large data sets? A: to choose random items to sell? B: to guess what customers like? C: to personalise offers and manage stock? Or D: to decorate the store? Pause the video, consider your answer, and then we'll check it.

Let's check your answer.

The answer was C, to personalise offers and manage stock.

Well done if you've got that correct.

Let's have another check.

How does social media use large data sets? A: to create memes? B: to suggest friends and personalise content? C: to speed up connections? D: to update the app on your phone? Pause the video, consider your answer, and then we'll check it.

Let's check your answer.

The answer was B: to suggest friends and personalise content.

Well done if you got that correct.

Let's do an activity, and you'll need your worksheet.

This map shows a color-coded route.

The amber and red sections illustrate traffic congestion on the route, and there are three sections.

One: What data is needed to create the map? Two: How do you think this data is collected? Three: How does this data help users? Pause the video, use your worksheet, and then we'll go through the answers.

Let's check your answers.

For the first question "What data is needed to create the map?," the mapping service needs to know how many cars are currently in that area and what speed they are travelling at.

We'll also need to know details about the route and the time and date of the journey.

Number two: How do you think this data is collected? The data could be collected from mobile devices or navigation systems in cars.

The service will track the location of the mobile device and how quickly it has moved.

The data may also come from past data the service has on that route at a similar time of day.

And three: How does this data help users? This data helps users because it shows them which routes are busy.

They can use this information to avoid traffic and plan faster or alternative routes.

The service may even suggest alternative routes for the user.

The system will reduce travel time, which will have a number of benefits.

The users will be less stressed about being late or delayed.

The environmental impacts of traffic congestion will be reduced and road safety may be improved.

Well done if you've got those correct.

Let's move to the second part of today's lesson, use a data set to investigate predictions.

We are going to look at a large data set that compares countries across the world to help us answer the following question: Where is the best place in the world to live? Alex says, "I think the best place in the world to live is the UK.

We have free education and good human rights." Sam says, "I think Jamaica would be the best place to live.

The weather is great and the beaches are beautiful." Most of us like the idea of living somewhere like in this picture, but would it really be the best place to spend the rest of your life? Which of the following are most important to you? Life expectancy, average income or wealth, health, CO2 emissions? What are important factors could be used to make a decision about the best place to live in the world? Pause the video and consider your answer, and then we'll check it.

Let's check your answer.

Average temperatures, inequality, unemployment levels, population density, freedom of speech, civil liberties, or crime.

Well done if you've got any of those.

Pick three or four of the following criteria from: life expectancy, average income or wealth, health, CO2 emissions, average temperature, inequality, unemployment levels, population density, freedom of speech, civil liberties, crime, murders per hundred thousand people.

You will use a visualisation tool to help you decide where the best place to live is based on the criteria you have picked.

The link there is a data visualisation tool that shows data on global development: oak.

link/world-data.

Each country is represented by a bubble.

The countries are colour coded by region.

You can click on the bubbles to see specific countries.

Click the play button to see how the data changes over time.

You can focus on specific countries by selecting them in the right-hand menu bar.

You can see that there, as it's selected, all the countries are there and you can select by putting a tick in a specific country.

Let's have a quick check.

What do the individual dots represent on the GapMinder visualisation? Is it A: countries? B: regions? Or C: cities? Pause the video, consider your answer, and then we'll check it.

Let's check your answer.

The answer was A: countries.

Well done if you got that correct.

The graph default compares life expectancy and GDP per capita.

You can change these.

Click the arrow to open the menu to select the Y and X axis.

Let's do an activity.

Make a prediction about where you think the best place to live in the world will be based on your selected criteria.

Remember those four areas that you selected as your criteria.

Go to the link oak.

link/world-data and use the GapMinder visualisation tool to see data for the criteria you have selected.

Pause the video, use that link and complete the activity, and then we'll go through some answers.

Let's have a look at some answers.

I predict that the best place in the world to live will be Australia because they have a good climate, good healthcare and education systems, and have legislation in place to attempt to reduce CO2 emissions.

That's the first bit.

That is the prediction based on the criteria that has been selected for this answer.

Using the GapMinder visualisation tool, we can see the data for the criteria that has been selected.

You can see on the right there where Australia is in 2021.

Well done for completing that activity.

Let's move to the last part of today's lesson.

Evaluate findings to support an argument.

An argument is a statement used to justify a claim or decision based on data analysis.

When presenting findings from data analysis, a data scientist might construct an argument that links evidence, data, to a conclusion.

Large data sets and data visualisations can be used to evaluate findings to support an argument.

Let's do a quick check.

Fill in the blanks to complete the sentence.

Large data sets and data blank can be used to blank findings to support an blank.

And you have three words there to fill in those blanks: evaluate, visualisations and argument.

Pause the video, consider your answer, and then we'll check your answers.

Let's check your answers.

Large data sets and data visualisations can be used to evaluate findings to support an argument.

Well done if you've got that correct.

Sam asks, "Why is data important in an argument? Data makes your point stronger by showing real evidence.

It helps you sound clear, logical, and believable.

It's harder to argue with facts than opinions.

Let's do a quick check.

Why is it useful to include data when making an argument? A: it helps you speak for longer? B: it backs up your point with real evidence? C: it shows that you have a strong personal opinion? Or D: it helps you avoid explaining your point? Pause the video, consider your answer, and then we'll check it.

Let's check your answer.

The answer was B: It backs up your point with real evidence.

Well done if you got that correct.

"I think the best place in the world to live is the UK.

We have free education and good human rights." That's what Alex said as his prediction on the "Where is the best place in the world to live?" What could Alex do to support this argument? Alex could show how the UK compares to other countries in relation to education and human rights.

If the UK scores highly in these areas, then can support his argument.

Let's do an activity.

Use the data visualisations you created for Task B to support your original argument about the best place to live in the world.

Pause the video, complete the activity, and then we'll go through an answer.

Let's check your answer.

My prediction was that the USA was the best country to live in based on life expectancy and GDP.

I compared the data to China, Spain, Sweden, France, Germany, and the UK.

The results show the USA had the highest GDP per capita, but slightly lower life expectancy than some of the other countries.

However, the dot on the visualisation proves my prediction was correct.

Well done for completing that activity and showing your evidence for your argument for your prediction.

In summary, advances in technology have made it easier to collect, store, and analyse data on a much larger scale.

Predictions can be tested and investigated using large sets of data and visualisation tools.

Data and data visualisations can be used to support an argument.

Well done for completing this lesson on Global Data.