Analysing education data with AI

Over on BlueSky, which suddenly become the main place where education discussion happens, a chance discussion has shown how powerful AI can be in analysing and interpreting data.

Ben Newmark started a discussion about the need to abandon all use of predicted grades.

In all the target grades chat there's a fair few sensible people saying it's wrong to use them before KS4. Respectfully the stage makes no difference. The way they are formed isn't valid so it's really no better to use them when a kid is 15 than it is when they are 11.

— Ben Newmark (@bennewmark.bsky.social) Aug 18, 2024 at 7:52

After much fascinating discussion, Richard Selfridge shared this fascinating but dense set ofdata:

Here's the transition matrix for GCSE Maths in 2022/23. explore-education-statistics.service.gov.uk/data-tables/… Every GCSE grade has at least 1 student who achieved each KS2 Scale score.

[image or embed]

— Richard Selfridge (@richardselfridge.bsky.social) Aug 19, 2024 at 12:22

But it’s not immediately obvious what this means. So I went over to trusty Claude.AI, pasted in the image of the table and asked

Could you analyse this table and tell me the implications for how we try to predict students’ likely GCSE grades from their KS2 SATs?

Here’s what Claude said:

This table provides valuable insights into the relationship between Key Stage 2 (KS2) performance and GCSE outcomes. Let’s analyze the implications for predicting GCSE grades based on KS2 SATs:

  1. Wide range of outcomes:
    The table shows that students with similar KS2 scores (represented by the columns) can achieve a wide range of GCSE grades. This suggests that while KS2 performance is correlated with GCSE outcomes, it’s not a perfect predictor.
  2. Imperfect correlation:
    Even students with high KS2 scores (e.g., 110-113) can achieve lower GCSE grades, and some students with lower KS2 scores can achieve high GCSE grades. This implies that factors beyond KS2 performance significantly influence GCSE outcomes.
  3. General trend:
    There is a general upward trend where higher KS2 scores are associated with higher GCSE grades. However, the relationship is not linear or deterministic.
  4. Overlapping distributions:
    Each KS2 score range shows a distribution of GCSE grades, with significant overlap between adjacent KS2 score ranges. This makes precise predictions challenging.
  5. Ceiling and floor effects:
    At the highest KS2 scores (117-120), there’s a concentration of high GCSE grades, suggesting a ceiling effect. Similarly, at the lowest KS2 scores, there’s a higher proportion of lower GCSE grades, indicating a floor effect.

Implications for predicting GCSE grades:

  1. Use probabilistic approaches:
    Instead of predicting a single grade, consider using probability distributions or ranges of likely outcomes based on KS2 scores.
  2. Consider multiple factors:
    KS2 scores alone are insufficient for accurate predictions. Incorporate other factors such as student engagement, subject-specific aptitude, and ongoing assessments.
  3. Regular reassessment:
    Given the imperfect correlation, regularly reassess predictions throughout the GCSE course as more current data becomes available.
  4. Avoid overly narrow predictions:
    Be cautious about making very specific grade predictions, especially early in the GCSE course.
  5. Differentiated support:
    Use KS2 data to identify students who might need additional support or extension, but remain open to individual variations in performance.
  6. Growth mindset:
    Emphasize to students that their KS2 performance doesn’t determine their GCSE outcomes, encouraging effort and improvement.
  7. Tailored interventions:
    Design interventions that target specific areas of weakness indicated by KS2 performance, but remain flexible based on ongoing GCSE coursework performance.
  8. Data-driven decision making:
    Use this transition matrix data to inform school-wide strategies, resource allocation, and teacher training to support students across the performance spectrum.

In conclusion, while KS2 SATs provide a useful starting point for predicting GCSE performance, they should be used as part of a more comprehensive, dynamic, and individualized approach to student assessment and support throughout the GCSE course.

Not bad, huh?

Funnily enough, one of the first ever blogs I wrote, back in 2011 was about this ‘probabilistic approaches’ idea, when I was a newbie teacher to Twitter and also a school data manager who was coaching/supporting other schools and data managers,

Follow me on BlueSky at https://bsky.app/profile/informededu.bsky.social

5 ways to build rapport and have better conversations

When it comes to conversation, relationships matter. So how can you use conversation to make relationships better, improve trust and really get things done?

Clearly, a good relationship with others makes your life easier. But, as Kim Scott says in her excellent book, Radical Candor, it’s a two way street:

“there’s a chicken-and-egg interaction between your relationships and your responsibilities. You can’t fulfill your responsibilities without good relationships, but the way in which you fulfill your responsibilities is integral to those relationships. They’re built from the outside in and the inside out.”

Great communication both rests on good relationships and builds better relationships. By improving the way you have conversations then you create a virtuous circle for everyone around you.

Good conversations build rapport, but that doesn’t mean you must avoid saying anything challenging. Indeed, uncomfortable conversations can improve relationships, although I’ve previously written about eight ways that we desperately try to avoid them and cause more problems in the long-run.

There’s five simple ideas you can use within conversation to build rapport and get things done.

Just this week, I helped a colleague use these ideas to tackle a tricky issue with their CEO. Their verdict:

“Well that worked. […] I feel like Derren blummin Brown

So here they are:

Pay attention to the whole conversation. Loads of articles tell you ‘don’t sit there thinking of what you’re going to say next, but listen to what they’re saying‘. This is decent advice but it’s not enough. Paying attention means not glancing at your phone, not looking over the person’s shoulder, not thinking about your next meeting and not formulating your next response. And yet, these are all absolutely necessary, but also deeply insufficient. If you’re only listening to the words being said, you’re only listening to a third of the conversation. People communicate in three ways in a conversation.

  1. Verbal: the words being said
  2. Paraverbal: the way the words are being spoken
  3. Nonverbal: the body language, movement, facial expression, gestures, blushing, sweating, gaze etc.

When you’re really paying attention, you’re taking careful note of all three, looking out for interesting choices of word or phrase, for pauses, fluidity and intonation as well as the physical clues of what the person feels about what they’re saying or hearing.

You can only build rapport when you are really paying attention. Rapport is built when the other person thinks they’re being listened to, being validated, trusted and made to feel safe. None of that is possible unless your attention is on your partner.

Radiate openness, warmth and engagement. Whether you’re actually speaking or not, you are broadcasting non-verbal signals at all times.

Match your signals to your partner’s mood as much as possible – a warm, relaxed face and body language with regular smiles and nods feels very encouraging. If the other person is expressing anxiety, pain or anger then a gently, warmly compassionate face – gently furrowed eyebrows, slightly tilted head – shows you care. Use neutral words and phrases such as “Mmm”, “I see”, “Ah right”, “Oh wow”, etc. to signal that you’re listening, though use them sparingly and don’t interrupt – silence and open body language and facial expression can be just as good.

Try and avoid crossed arms and do keep your body toward the other person – if you’re taking notes then try to avoid like your body and face’s main focus is the computer or paper – keep your eyes as much as possible on your partner.

Invite more detail. Questions and invitations can encourage your partner to reflect and add detail. “Could you tell me more about…” or “Wow, what’s the story there?” demonstrate interest. Open questions are really helpful – i.e. questions that encourage extended responses not one-word answers. How is always a particularly good way to start a question – ‘how did you come to that conclusion‘ can seem less judgemental than ‘why did you do that?’ Other good questions could include “How had you imagined it” or “How could we make this work?

Avoid judgements wrapped in questions! ‘How did you think that was a good idea?‘ isn’t actually a question, it’s a slap-down wrapped around your opinion…

Demonstrate your listening and understanding. We connect better with people who seem like us, who really get us. There are several little tools here.

One is labelling where you name the emotion your partner is feeling. “It seems like you’re frustrated” or “that’s probably disappointing” or “it sounds like you are really excited” are good examples – they suggest an emotion which lets your partner accept, correct or reject it. Avoid adding in the personal pronoun – “I think you’re happy” makes it about you, not them. Avoid insisting on a label they might reject – “You’re clearly upset” suggests you know them better than they know themselves and is a risky tactic.

Two related tools are paraphrasing and summarising. Paraphrasing is repeating back an idea or phrase in different words – typically using a similar amount of words. Summarising takes a much longer chunk of what’s been said and distils it down to fewer words. It’s always better to offer your paraphrase or summary tentatively or leave room for them to correct you – you can learn a lot by offering your understanding and letting them add detail and correct things.

A final tool is mirroring. The simplest approach is listen to the last few words the person just said and use them in your question or summary. E.g. them: ‘… and after all of that I ended up feeling incredibly frustrated’, you: ‘it’s not surprising that you felt incredibly frustrated, in the circumstances’. It can feel a bit wierd at first but this simple tool works. Some people also suggest mirroring some of your partner’s nonverbal signals – if they smile, you smile, if they lean back in their chair, you do the same briefly after. However, use this sparingly as it can be odd.

Use silence. Susan Scott uses the lovely phrase “let silence do the heavy lifting” in her book Fierce Conversations. Chris Voss, in Never Split the Difference, suggests using silence as a powerful tool after every time you use open questions, mirroring and labelling, leaving the powerful tool to work its magic.

Silence helps the conversation slow down. A pause before you respond gives your partner more time to add more thought. It suggests that you’ve thought carefully about what they’ve said before speaking. You can fill a silence with a slow, relaxed exhale or with a “hmmm” and a nod.

Each time you’re silent, you’re signalling that you’ve chosen not to give your interpretation or opinion. Instead of jumping in, you’re giving thinking time. However, we can also get very uncomfortable with silence, and it makes your partner’s mind start racing to think “what else could or should I say here?” Do use this powerful tool, but do be aware of the impact it can have, especially if the other person is nervous of you and of what you’re really thinking.


All of these five approaches can ensure that each conversation builds more rapport. Not only will you get much more from each conversation as you’re noticing and reflecting on more that’s being said (and not said), but the other person will feel more listened to, more appreciated, more understood, even if the conversation eventually gets to a point of challenge or disagreement.

Of course, there are plenty of other ways to build rapport and trust outside of conversation: doing activities together, sharing personal stories or recounting stories of former experiences together and asking for help and guidance from each other. Trust and rapport are also built through competence, benevolence and integrity. I’ll return to some of these topics in a later blog.

For now, find times to work these ideas into your conversation. I’d recommend a couple of interesting books on the topic for further reading:

  1. Fierce Conversations, by Susan Scott
  2. Never Split the Difference, by Chris Voss

You might also be interested in some other blogs of mine on communication:

Necessary, tough conversations often fail. Here’s 8 reasons why.
7 powerful questions for leaders: creating a culture of ideas
The disagreement dissolver: a check-list for stamping out misunderstanding at work
The art of being level-headed, not emotionally blinded
9 ways for leaders to be better at communication

Necessary, tough conversations often fail. Here’s 8 reasons why.

In great work-places, it’s okay to have tough conversations. In fact, not just okay, it’s an essential habit. Negativity thrives in the spaces that honesty and openness vacate. Bad cultures build where people learn that they can’t speak up, that others won’t speak up, or that under-performance and problems get swept under the rug.

A key starting point for good conversation and culture is to talk about difficult issues and tackle problems early. But it’s hard to confront a problem and improve things.

Improvement requires listening – on both sides. It requires rapport – trust and confidence in each other. If successful, everyone accepts their contribution to the issue and resolves to take responsibility to learn and improve.

But it’s tough to have these conversations and we often avoid the issue, reject any contribution or refuse to take action.

Here’s five signs that your conversation partner is not engaging and owning the issue. (the first three of these come originally from ‘Fierce Conversations‘, I believe.)

  1. Deflect: they raise an issue about someone else (or something else), instead of focusing on this issue and their contribution to it. “But he did something even worse” or “You’re picking on me” or “Why are you talking about this when the real issue is…”
  2. Deny: they flat out refuse to accept that they contributed to the issue. “That’s just not true, I didn’t do that” or “Yes, I did that, but I don’t agree that it’s a sign of poor performance
  3. Defend: they insist that their actions were justified, reasonable or inevitable. “Well, she had it coming.” or “I think anyone would have done the same” or “I have a temper, there’s nothing I can do”
  4. Diminish: they claim that the issue is minor, irrelevant, unremarkable or that their contribution was insignificant. “I think I was barely late, and only a couple of times at that” or “I don’t know why you think this is such a big deal
  5. Disengage: they ‘check out’ of the conversation, refusing to engage. “Fine, have we finished?” or “Okay, I get it, I’m sorry, can we move on?”

All five tactics move us away from the important discussion and prevent ownership and resolution. They’re easy to spot when someone else seems to be evading the issue, but much harder to spot and deal with when we use the same tactics to avoid admitting our own contribution to an issue.

Too many difficult conversations fail to even begin. We use the same five tactics in our own head to justify not having ‘the talk’.

  • “There’s something more important going on right now, best save my energy” or “let’s not rock the boat right now”
  • “Maybe it didn’t really happen”
  • “I mean, they’re only human, I should cut them some slack”
  • “I guess it’s not that bad really”
  • “This procrastination feels really important right now!”

Other times, we do set up the meeting, but then go wrong by:

  • pussyfooting around with small-talk and niceties and never actually have the conversation that’s needed,
  • being so incredibly vague, unspecific and rushed that the other person never really understands what it’s about, or
  • back-peddling: hastily blurting out the issue and then immediately showering the other person with praise and excuses plus diminishing the severity of the issue, all in order to reduce our own feelings of discomfort.

With so many reasons that the discussion can go off track, it’s no surprise that necessary, tough conversations frequently fail to happen.

In a future blog, I’ll discuss some keys to successful tough conversations. In the meantime, I recommend the following books:

  • Radical Candor, by Kim Scott
  • Fierce Conversations, by Susan Scott
  • Discussing the undiscussable by William Noonan

All the above reflections are my attempt to synthesise some of my own learning, reading and experiences in order to help me clarify my own thoughts. I want to publicly express my gratitude to Nicole Fowles (@nfowles5) whose advice, coaching and book recommendations have been transformational! Thank you also to Kathryn Morgan (@KLMorgan_2) for getting me enthusiastic about Fierce Conversations. Please do leave questions, ideas or suggestions for improvement in the comments below!

7 powerful questions for leaders: creating a culture of ideas

Communication is the life-blood of an organisation. Dialogue needs to be honest: seeking objectivity, reducing bias and never covering up truths or views to make things ‘comfortable’. However, a habit of bad conversation stifles problem-solving, dampens enthusiasm and encourages the building of defensive routines.

From my own organisation and having worked with many schools, training providers and charities, it’s clear that the good communication begins with the leaders. As a leader there is always an enormous temptation to jump in and start giving advice without having really listened to the issue, without having sought enough perspectives, and without leaving room for others to grow their own solutions. The trouble is, however good your ideas, they come with a big shiny sign that say ‘the boss likes this, I should prioritise her/his thinking above my own’. What we want is a culture where great ideas and great thinking can take root, driven by everyone.

Here are 7 questions which I think can help.

1. “What’s on your mind?”
This is a great way to open a conversation – it signals that you’re interested in what the other person is thinking, and that you’re open to hearing concerns. It puts the ball in the other person’s court; they get to name the priority and they have control over the agenda.

This question needs to be used together with question 2 which is…

2. “Let me check I’ve understood. Are you saying <re-phrase and summarise>?”
It’s worth doing this check even if you’re reasonably certain you have understood. As you’re listening to what is being said you’re automatically reinterpreting it to your own view of the world. It’s useful to try and re-phrase/summarise and check that a) you’re on the right track and b) you haven’t missed something that’s important to the other person. Sometimes, when I listen to people, some elements of their dialogue spring out at me, but when I summarise the overall meaning I discover that I’ve distorted or obscured some of the key meaning that the other person intended. This technique demonstrates that your first priority is listening and understanding, not to jump in and take over control of the problem or situation.

A way of making questions 1 and 2 work together even better is to physically sit next to each other during the conversation, perhaps on two adjacent sides of a table, and sketch out ideas as the other person speaks. It could be a flow chart or a napkin sketch. It slows the process down, ensures you can repeatedly check that you’re on the same page, and allows the other person to see a map of what they’re saying and refer back to it later.

An image of a napkin showing a sketch of people sketching on napkins.
Napkin sketching can be a powerful tool for communication. [image source: Fast Company]

I’m grateful to Oliver Caviglioli for introducing me to this whole area of sketching, especially napkin sketching. It certainly takes some practice and it’s not always the right solution, but I have found it useful.

3. “What’s the real challenge here for you?”

Cover of book
The Coaching Habit

This is a lovely question which I recently read in The coaching habit: Say less, Ask more & Change the way you lead forever” (Michael Bungay Stanier). It’s helpful when someone has given you a laundry list of issues or concerns, or where someone has gone round in circles, or is being fuzzy. It forces the other person to search for the nugget that is really important, that matters most. As Stanier says, the word real “implies that there are a number of challenges and to choose from, and you have to find the one that matters most. Phrased like this, the question will always slow people down and make them think more deeply.” The words ‘for you’, are “what pin the question to the person you’re talking to. It keeps the question personal and makes the person you’re talking to wrestle with her struggle and what she needs to figure out”. [quotes from the book, Chapter 3]

4. “It sounds like you’re frustrated/disappointed/angry with X. This suggests that you have a vision in your head of what X should ideally be like, and it’s falling short. Could you describe that vision/ideal?”

This question has led to a few breakthrough moments for me, not only with other people but also even challenging myself to answer it. I was inspired to try this approach after a conversation with Tony Nicholls who inspired me to read about appreciative inquiry, an approach/philosophy of change and improvement that invites people to focus on the positive, not the negative.

This question draws on the ‘dream’ element of appreciative inquiry which is about articulating potential. It allows people to start describing and fleshing out an alternative reality. I have found that people often drift back quickly to describing the deficits – it takes quite a lot of gentle steering to get the other person to stay on ‘positive’ first, while not making them feel you’re ignoring the facts and emotions around the problems – e.g. “I can see that you find that frustrating. I’m keen to understand your ideal so that I can understand why the current situation is falling short.”

It allows them to imagine some light at the end of the tunnel and flip a negative conversation into one with more potential. Once the desired future is clear, it’s much easier to see the path to get there.

5. “Who could you ask to get helpful and different perspectives on this?”

This question serves multiple purposes. Firstly, as a manager, your instinct is to give your perspective and try and solve the problem. This question interrupts that instinct and helps the other person look elsewhere, using their own resourcefulness to do so. Secondly, it ‘zooms out’, reminding both of you that everyone sees the world from their own point of view, that everyone will be missing something, and that multiple perspectives are better than any one.

It’s not necessarily an easy question. If someone is feeling stressed and emotional then it’s hard to ‘zoom out’. An invitation to do so may even sound like a criticism. It may be the right thing to do to simply ‘park the conversation’ and say “it’s good to understand your point of view on this. Can we take a break to allow us both to reflect on this a bit?” You can then come together when the tension is lower, summarise where you were and start the process of ‘zooming out’.

Once you do start thinking of people, it’s worth teasing out “why do you think that person’s perspective might be helpful and different?” as this continues the process of helping the other person imagine themselves in other people’s shoes.

6. “What’s the most helpful thing I can do right now?”

It may be that the other person simply wishes to make you aware of something. It may be they want a specific piece of guidance. Maybe they want some feedback. It puts the ball in the other person’s court to say what you should do. It also stops you from going into ‘telling’ mode by default.

You have probably already helped by simply getting the other person to clearly articulate an issue and what the solution could look like, as well as sources of perspective and expertise. You might have (hopefully) sparked a sense of curiosity and drive to solve the problem.

Even if you’re asked for an opinion you might sometimes say “let’s see what you come up with first as it might be better than any idea I come up with”, or “I could come up with some ideas but I’d rather hear yours first.” Note that it’s worth avoiding signalling that you have ideas that you’re simply hiding or else you could just encourage a game of ‘guess what’s in my boss’s head’.

7. “When will we revisit and review this?”

Toward the end of a conversation you may both feel some relief that some difficult ground has been covered, or excitement that a seed has been sown. However, part of the reason that progress has been made is because you have a) paid attention to it, b) given permission for thinking and honesty and c) made it clear that the other person has ownership. Over time, the other person may see your attention fade, they may start doubting if they are still allowed to be creative and honest, and they may start interpreting things you’re doing and saying (outside of the meeting) as signalling that you’re taking back ownership.

I’ve learned this the hard way, with colleagues feeling I started some creative thinking and then interpreting later actions (sometimes rightly, sometimes wrongly) as implicitly ‘dousing the flames’. It’s important to review and revisit ideas together, if only to continue to show that you’re not just about to jump onto the field of play uninvited – nor end the game early and start a new one – but that you are still very interested and enthusiastic. You may have planted a seed and started an initiative because it’s something you’re excited about. When you come back to it, you may now be excited about something very different. However, by reconnecting, showing interest and attention, and encouraging energy and curiosity, you can stay engaged and seek to maintain growth.

Conclusion

I’ve come to learn that I’m often at my happiest when I’m constantly exploring new ideas and sharing things that excited me. However, I’ve also learned the hard way that a tendency to be slow to listen but be quick to share my ideas, suggestions and latest enthusiasm has a toxic effect that encourages others to feel their own ideas aren’t valued and that they are not being heard.

I’m fascinated by the 7 questions above as a way of learning how to keep turning this dangerous habit on its head. I hope they’re of some use to you and I’d warmly invite you to share with me any critique, ideas or questions.

Some further reading

I’ve been enjoying these books recently – they’ve helped to spark some of this thinking.

Cover of book
The Coaching Habit
Image of the book cover
An everyone culture: becoming a deliberately development organisation – Kegan and Laney
Book cover: Multipliers
Multipliers: how the best leaders make everyone smarter – Wiseman and McKeown

Note: thanks to Dame Alison Peacock whose wonderful mantra ‘a culture of ideas’ continues to guide so much of my thinking.

Why I believe in high stakes testing… in the right context

https://commons.wikimedia.org/wiki/File:ATC_Admission_Exam.JPG

Teachers are exceptionally good at creating strong relationships with classes of children and young adults. As knowledgeable, fascinating figures who beam out a sense of ‘I know you can do it’, they are able to use their positive relationships to challenge students to push through difficult and troublesome learning, achieving more than they thought was possible and exploring skills and understanding that they’d have never had access to before.

Learning isn’t always a comfortable process, and wise teachers know that they need to fine-tune the level of difficulty to hover around the edge of students’ comfort zones. Occasionally they need to consolidate and build confidence, sometimes they need to push and take a leap. Sometimes they will pursue a student’s own fascination with a topic and help them achieve amazing things. In other cases they will carefully and lovingly push them in an uncomfortable direction, nurturing a resilience and drive for future life to take on tough challenges with gusto, while enabling students to experience and learn things they’d have never got access to on their own accord.

Learning that isn’t challenging can become dull and uninteresting. As a species, humans love puzzles, challenges and a bit of challenge. We revel in having the hard task of ‘climbing the mountain’ rewarded when we have an opportunity to look at how high we’ve climbed and admire the view. We feel pride and joy as we grow and develop.

There are many ways to create this challenge, of course, so what role do tests play? A solid body research tells us, perhaps surprisingly, that an entirely low-stakes test can be enormously beneficial to the learning process itself. The latest science about how learning occurs in the brain demonstrates that the challenge of remembering and recalling knowledge builds long term memory.

However, not all tests are low stakes. Some test, like public examinations and national assessments may be a little more daunting. Done well, schools can engender a feeling of excitement and challenge in students. Here is a bar for you to leap over, a way to demonstrate how far you’ve climbed, an opportunity to feel proud and gain a recognition of your progress that no-one can ever take away. Done badly, these can make students feel demotivated and scared, leading to a lifetime of bad memories.

Professor Marc Jones studies the different ways that a challenge can affect us physiologically, in different organisations and teams. He notes that stressful situations can be both good for us or bad for us, depending on context.

“The belief in our ability to perform well is clearly a crucial element in being able to perform under pressure. A high level of confidence is important for a challenge state. Second is a feeling of control. Believing you have control over factors that may affect performance and how you perform under pressure is important for a challenge state. Going into pressure situations focusing on factors that cannot be controlled, such as a footballer worrying about match officials, is associated with a threat state. Finally, being focused on what can be achieved – an approach focus is important. Individuals who are challenged are focused on what can be achieved while those that are threatened are focused on what might go wrong.”

So, we can help students associate future challenge with excitement, rather than terror, by carefully building them up for well-calibrated, high-stakes tests such that they feel confident, in-control and focused on the positive. We can support this through a shared ethos of positivity, of belonging and support. It’s the thrill of the high-jump, the heart-pounding excitement of not quite knowing if you’ll make it, followed by the pay-off of practice and dedication – the glow of success.

There is, of course, a constant and very human temptation to avoid challenging students. After all, even if 9 out of 10 students benefit, we may leave 1 out of 10 with a sense of failure. Given how highly attuned we are to their feelings, this can lead to very well-meaning temptation to reduce challenge and ensure that students never feel any stress. The unhappy corollary is that lower challenge can often mean less learning and fewer opportunities for pride and success. hard work with occasional stress followed by success is so much better for young people than a lifetime of well-meaning low bars and low expectations.

The balance to be struck is to keep the challenge high enough that there is some risk, or else the challenge becomes too low. However, we also need to quickly pick students up after a fall, dust them off and engineer another challenge where they can succeed, learn to be resilient, and get their pride back. It’s something that we naturally do with children as they learn to ride their bikes, and teachers are immensely skilled at doing this in the classroom.

Another startling finding is that tests can actually help the most vulnerable students to succeed. Studies have shown that humans are not very good at making objective judgements and will often by fooled by stereotypes. Entirely inadvertently teachers (like all human beings) have often been found to make more negative judgements compared to test scores, for example, with girls in maths, boys in English, and children from disadvantaged backgrounds in all subjects. This is not due to any ill intent, it is merely a limitation of the way our brains work. When we acknowledge and recognise this natural limitation, a well-designed test can help the profession and the school system to overcome these entirely human and inevitable biases and even out entrenched inequality. And that, of course, is what we want for all young people.

Great tests can also be part of the suite of powerful tools to help teachers to learn more about students’ needs. Where teachers use formative assessment in their own professional development, we know that it helps them grow and improve more effectively and ensure they can help future generations achieve even more. A mix of professional judgement and skilfully designed tests helps us grow and become ever better at supporting young people’s learning. Not only that, both low, medium and high-stakes assessments can give us rich and powerful insights into our learners thinking, with pointers to how we can plan future lessons and tasks to help them most effectively and personally.

In so many classrooms, students will do so much for the teachers they respect – they want to please them, feel proud, and do well. However, we live in in a world of high-stakes inspections, performance related pay, performance management and league tables. If teachers are made to feel not only stressed and anxious about students achieving, but if they also lack confidence and support, then this will inevitably be picked up by the students as well. This could, of course, negate many positives from high challenge tests. Not only that , badly designed tests in a low-trust culture leads to a toxic environment, gaming and teacher burn-out. It leads to superficial teaching to try and desperately ‘drill’ the learning into students heads, no matter how short term, out of survival desperation. This is the very antithesis of what we aspire for our students - I do understand why there is so much anger around and why it’s so tempting to aim this fury at tests themselves.

For high stake assessment to work, therefore, we not only need to focus on the conditions for students but also to focus on the conditions for the teachers.

We need every teacher to feel confident, in control, well supported and focused on the positive. This requires accountability systems that are paired with support and warmth, where success is shared and the right level challenge remains positive and keeps us excitingly hovering around the edge of our own comfort zones. It requires school leaders who have positive, trusted relationships with teachers and, by extension, who have similar relationships with those who hold them to account as well. It requires a faith that, if a high bar is not jumped, there will be support and encouragement from peers and leaders to pick schools and teachers back up and help them try again. Everyone deserves more than one shot, especially when an increasing number of teachers and heads are considering whether they even want to stay in this great profession.

Testing is no panacea, and tests are too often accompanied by crude carrots and painful sticks in a low trust, punitive approach that tries to get performance through fear. It is right to reject such a system that causes bad stress and propagates too much fear and provides too little support. However, let’s not throw the baby out with the bathwater. Great testing is one of the most powerful implements in a teacher’s toolbox. Let’s fix the system, provide the right support, and use this tool to provide powerful learning, memorable success and a deep well of pride for every student that provides a solid foundation for a happy, fulfilled and successful life.

Article image from Wikimedia Commons: https://commons.wikimedia.org/wiki/File:ATC_Admission_Exam.JPG

How learning science might inform dance: A cognitive psychologist responds

https://commons.wikimedia.org/wiki/File%3AJive_Langella_Moshenska_1107.JPG

Dr Yana Weinstein (@DoctorWhy) responds to my speculative post about cognitive science and ballroom/latin dance.

I’ve been a professional cognitive psychologist for 10 years and an amateur Latin dancer for 2, so I couldn’t not get over-excited when I saw this post. Unfortunately, none of the cognitive psychology research has been carried out with dancers (at least, to our knowledge), and I’m currently suppressing a very impractical urge to go in this direction! (I’ve already gotten myself in trouble with a project on music memorization – you have no idea how hard it is to branch out beyond generic cognitive tasks to this kind of applied work).

So all we have are the rather well-informed speculations discussed here. Let me speculate further.

1. Chunking – I wonder if it’s not an accident that my teacher always breaks up new choreography into 15-30 second chunks for us. I’m sure she’s not aware that this is the duration of working memory, but maybe she naturally defaulted to this duration.

For this part of the suggestion – “dancing with a partner or being aware of others watching you may be factors that overwhelm or impede learning” – there is also some relevant research. For example, it has been suggested that certain types of test anxiety may lead to off-task thoughts that take up part of working memory resources.

2. Interleaved vs. Massed practice – so much to say here. First of all, don’t confuse spacing with interleaving (it is extremely easy to confuse the two, and honestly, I still do myself sometimes even though I co-wrote a chapter with a large section on each one ). For example, in the main point, “you’ll end up with stronger memory of routines if you interleave dances” is about interleaving, but in the suggestion, “it has been shown that by giving ourselves a bit of time to forget an idea then […] the long-term strengthening of memory of this approach is much greater” is about spacing.

Spacing is more about how you would distribute practice over a period of time. If your performance is in a week, should you practice for an hour every day, or 7 hours the day before? I think we all know the answer.

Interleaving has been most commonly studied with math problems: should you do 10 of the same type of problem, or mix it up? What’s tricky and confusing about the two is that interleaving naturally adds in spacing, so it is hard to have a pure measure of the effectiveness of interleaving without also implicating spacing. However, this paper  attempts to hold spacing constant and still finds a long-term benefit of interleaving.

I don’t know if this has been explicitly specified, but my strong suspicion is that the reason interleaving is helpful is that it enables you to practice doing a problem “cold” (i.e., without the carry-over effect of having just done a similar problem). It’s important, though, to consider what your goal is. If you tend to go to dances where you’re expected to dance salsa and then bachata, interleaved (as I do), then yes – practice them interleaved. But if the two dances tend to be danced in separate parties (e.g., salsa and tango), then I’m not sure interleaving is going to be as necessary, because you will always get to warm up and then after that you’re in a massed testing situation. The grain size of what you are interleaving also matters. You could take this to the absurd: do you need to interleave practicing one rumba dance with doing one yoga pose? Probably not.

Also, I suspect that level of familiarity with the material is also a factor, and some massing is necessary before interleaving can be useful. Have you noticed how a teacher will always introduce a small chunk (cf., chunking), and then you will mass-practice it until it feels comfortable, and only then practice it with whatever comes before and after? It seems obvious now that I think about it, but clearly what this is doing is getting the information from working memory into long-term memory! Think about how the first few times you run through a new chunk, you’re really just copying the teacher in the moment, so you’re not really using your long-term memory. So maybe the ideal practice protocol includes some massing to transfer information to LTM, and then lots of interleaving. But does this mean you should scramble the order of chunks within a choreography and practice them in different orders? This is the same as the rumba vs. yoga pose question, and I’m honestly not sure.

3. Transfer – the suggestions are great, but the main point is more about context than transfer. When we talk about transfer, we usually mean to a new problem (rather than the same problem in a different environment). For example, if you know salsa, how well will you dance bachata? Probably pretty badly until you get taught at least the basic step and some basic moves – and then you’ll probably pick it up faster than a novice dancer, showing some transfer. A more subtle example of transfer might be: say you were taught musicality with a particular song (e.g., here’s a good part of the song to do a dip). An example of transfer would be noticing those moments in a different song.

4. Still images and attentional focus – the point about learning from still images better surprises me, but I must not know the research on moving vs. still images. I just can’t imagine that any better way of demonstrating a dance move could involve still images, but I’m willing to consider the possibility. I suspect, though, that some research (that I either do not know, or cannot recognize from the description) is being misapplied because the learning outcome (what we call “criterion test”) of the study was not mimicry of a physical movement. The idea of attentional focus during learning is also fairly unfamiliar to me, although it definitely makes sense, and perhaps could be addressed by having the dancer wear bright red shoes or bright red gloves depending on whether they were demonstrating feet or arms??

5. Self-explanation – this seems reasonable, and on a totally personal level, I have to say my instructor doesn’t really let us ask questions. I mean, of course she clarifies specific points, but I tend to ask a lot of questions, and she has more or less shut me down on some occasions because it was slowing down the class. Now, as a teacher I completely appreciate the frustration of tangential, time-consuming questions, but I like to think (probably erroneously!) that my questions are relevant. It just feels as though she has a certain amount of material to get through each class, and any elaborative interrogation (and it’s really not that elaborative – I’m usually just trying to figure out exactly how something fits together) cuts into that time. Perhaps a discussion session after class would be valuable.

6. I don’t know the research on putting two concrete examples side-by-side, but I feel that this point also addresses the value of feedback. To which point, maybe it’s useful to mention that the jury is still out on whether immediate or delayed feedback is best for learning.

Overall, though, here’s my take on learning dance: I feel like we are generally pretty well aligned with the cognitive principles. Most importantly, I think – and David didn’t mention this in his post, possibly because it’s too obvious – we make constant use of the testing effect. We learn by doing the dance, over and over, from memory. We don’t sit for an hour listening to our dance teacher describe the moves and taking notes; we don’t practice by watching the teacher’s performance video over and over again (though we do consult it in between attempts to get it right); and the teacher doesn’t just call on one student at a time to do one small part of the routine while others watch passively. Why, then, is the same not true in a typical school classroom? Why aren’t our kids repeatedly practicing retrieval of the information the teacher is trying to teach?

And here is a dress rehearsal of my latest routine with Leah’s Chicas! 🙂

6 ways learning science might improve Ballroom & Latin practice & lessons

https://commons.wikimedia.org/wiki/File%3AJive_Langella_Moshenska_1107.JPG

Today I found a great way to bring my not-so-secret past as a competitive latin dancer* together with my enthusiasm for research into teaching and learning. As those who know me through the mainstream education world will know, I’m fascinated by how students learn and how we help teachers learn how to teacher better.

I met up with teacher-to-the-champions Mr Graham Oswick, who along with some wonderful other teachers** did his best, many years ago, to inject some form of technique and style into my remarkably resistant body.

We had a chat about what teachers, students and competitors might learn from the most up to date research about how the brain learns***. Stemming from that discussion, here are 6 ideas from my reading of some cognitive science literature*** that I think might plausibly transfer into more effective teaching and learning in ballroom and latin.

I should note – I’ve not tested these and I’d love to hear if anyone has conducted some high quality research. Also, if any cognitive scientists would like to correct any mistake from my inevitably non-expert interpretation then I’d really welcome your input!

  1. When learning something new we have a limited working memory that can reliable hold about 3 to 5 ‘chunks’ of information at any one time before we feel overwhelmed and overloaded. For novice dancers each ‘chunk’ may be small movements, single steps, movement of one muscle. However, expert dancers have learned to combine multiple ideas into more complex mental schema which can be accessed as a single chunk, allowing experts to build up more complex ideas that would overwhelm beginners.
    • Suggestion: limit the amount of new steps and ideas you focus on at any one time when learning something new to avoid being overwhelmed by an impossible learning task. For new ideas, steps or technique, playing music, dancing with a partner or being aware of others watching you may be factors that overwhelm or impede learning as they all take part of your attention and therefore working memory.
  2. It’s tempting to try and learn and practice dances in chunks. This is known as massed practice. e.g. where you focus on all of the Samba for 20 minutes before moving to Rumba for another 20 minutes. However, cognitive science shows us that long-term memory of dances is stronger if we interleave practice. Oddly, it has been shown that by giving ourselves a bit of time to forget an idea then, even though the next time we try to remember it will be harder, the long-term strengthening of memory of this approach is much greater than repeating the same ideas back-to-back.
    • Suggestion: even though it feels harder, you’ll end up with stronger memory of routines is you interleave dances rather than doing massed practice of repeating one dance several times before moving to the next.
  3. One of the most frustrating problems in dancing is where you remember a routine and technique in the studio but where it goes out of your head in an exam or on the competition floor. One element of the problem is clearly related to stress but another issue could be related to the idea of transfer. This is where the learning of an idea is strongly associated in your memory with a particular location, environment, music, and so on. Learning science suggests that we can help overcome this by mixing up our practice and learning in all sorts of different ways, to ensure that the only common factor is the actual core idea that we’re focused on, rather than letting it get bound up with other factors.
    • Suggestion: mix up practice in as many ways as possible to strengthen your learning and adaptability. Try different music, different tempos, different locations facing different directions. Start at different points of the routine. Wear a variety of practice wear – heavier and lighter.
  4. A common way to teach ideas in dancing is for the instructor or teacher to demonstrate an idea by dancing it themselves while the student watches. However, learning science shows that novices are very likely to have attention focused on some of the wrong aspects of the demonstration. Another issue is that the act of processing the moving image also takes up valuable working memory which takes attention away from the key aspects being demonstrated. Research has shown that students often learn new ideas better from a series of still images where the key aspects are simply and clearly highlighted and where details that are not important to the key idea are de-emphasised.
    • Suggestion: work hard to focus attention on the key aspects being communicated. During teaching demonstrations you could perhaps attach something brightly coloured to the area of focus. Another idea is to use a series of still images (or, even better, simple line drawings) and talk through them using a highlighter to show the key areas of focus.
  5. Research suggests that the most successful students are constantly engaged in self-talk – internally re-explaining what they are seeing and experiencing to make sense of it. Less successful students do less of this. This mental process helps to create the links between practice and theory – i.e. between the what and the how and why. In more successful practice and teaching, students are encouraged and helped to engage in self-explanation, e.g. by pausing frequently in demonstrations or by being given worked examples with gaps to fill in.
    • Suggestion: during lessons and practice, make time to verbalise both the sequence of steps and the logic of why actions are taking place. Repeated demonstrations are less effective than switching back and forwards between instructor-narrated demonstrations and student-narrated practice, or even student-narrated demonstrations.
  6. One of the more effective ways of learning is to see two concrete examples of an idea or practice side by side and then work with a teacher to identify key differences. It is significantly more effective to be able to see ideas side-by-side than it is to watch one example and then another, especially when key aspects can be put right next to each other and highlighted.
    • Suggestion: use video to capture the teacher and the students dancing the same moves to the same music, then play back side-by-side, pausing and slowing to emphasise key aspects of difference. Stills from both might be used on-screen with a digital highlighter to emphasise key differences in shaping, or slow-motion used to show differences in rhythm or size/volume of movement.

To re-iterate, these ideas are taken from general literature on cognitive science, not from any specific literature on learning or practising dance. However, they do seem to be generally applicable in a wide variety of settings and learning so I hope they might start a useful discussion among ballroom and latin dance teachers, students and competitors about improving the way that steps, techniques and routines are taught and learned.

Anyone fancy exploring this further?


 

*In case of scepticism, here’s a video of me dancing with the lovely Leah Rolfe back in 2007 – should be noted Leah has gone on to much greater things since finding a significantly better partner in the amazing Adelmo. I also danced with other amazing partners such as Sharon Withers, Sarah Farrell, Laura John, Georgina Weeds , to name just a few.

**Other amazing teachers included Bruce Richardson, Vicky Cunniffe, Lorraine Kuznik, Neil Dewar, Ian Waite, Karen Hardy, Luca Sartori and Goran Nordin, Margaret Redmond and several others. I’m ridiculously grateful to them all, even if I’m no longer dancing.

colvin clark ev based training*** These ideas are all taken from Ruth Colvin Clark – Evidence-based training methods where you can also see references for all of the research quoted.

Note: the image used as a header for this blog is cropped from an original by Ailura (Own work) [CC BY-SA 3.0 (http://creativecommons.org
/licenses/by-sa/3.0
) or CC BY-SA 3.0 (http://creativecommons.org/
licenses/by-sa/3.0
)], via Wikimedia Commons – from https://commons.wikimedia.org/ wiki/File AJive_Langella_Moshenska_1107.JPG

The science of learning (part 2)

Following on from “Learning that works (part 1)” which was about what happens in our brains regarding paying attention, this post looks at how we assimilate and associate ideas and form memories. It’s a bit oversimplified, but gives a sense of what’s going on, I hope.

Slide1 Slide2 Slide3 Slide4 Slide5 Slide6 Slide7 Slide8 Slide9

PS As the lovely @Nick_J_Rose has pointed out, I’ve simplified things and somewhat conflated the ideas of ‘chunking’ and ‘schema’ – the former being about working memory and the latter being about long term memory. I’m grateful as ever for his feedback and I’ll try and unpick this in the next blog. You can read more about chunking, schemas and prototypes here.

DISCLAIMER: I’m neither a qualified psychologist nor neuroscientist so please let me know if I’ve made any errors here. I’d be really interested in any feedback that you have – please comment below!