A picture is worth a thousand words – actually, the brain processes images 60,000 times faster than it can read, so it’s worth turning your data into pictures. When you’re trying to make a point, impress leadership or win the hearts and minds of process participants, graphs and charts are the way to go. In this 1-hour intermediate webinar we’ll give you some step-by-step training on how to take a column of data and bring it to life on the big screen.
https://goleansixsigma.com/webinar-5-ways-create-charts-graphs-highlight-work/
General Principles of Intellectual Property: Concepts of Intellectual Proper...
WEBINAR: 5 Ways to Create Charts & Graphs to Highlight Your Work (Intermediate)
1. 8/24/2017
Presented by Elisabeth Swan
Managing Partner & Executive Advisor
at GoLeanSixSigma.com
5 Ways to Create Charts and
Graphs to Highlight Your Work
2. Our Expert: Elisabeth
• Managing Partner &
Executive Advisor at
GoLeanSixSigma.com
• Master Black Belt
• Certified Executive Coach
at Burnham Rosen Group
• BA in English Literature
from Columbia University/
Barnard College
• Born in the UK
2
5. Who Is GoLeanSixSigma.com?
5
GoLeanSixSigma.com makes it easy for everyone
everywhere to build their problem-solving muscles.
We provide the most practical, easy to understand and
enjoyable Lean and Six Sigma resources available.
7. 1. How Charts and Data Tell the Story
2. What Does a Histogram Tell You?
3. What Does a Run Chart Tell You?
4. What Does a Box Plot Tell You?
5. What Does a Pareto Chart Tell You?
6. What Does a Scatter Diagram Tell You?
7. How Charting Tricks and Tips Can Help
Today’s Agenda
7
8. • The Bahama Bistro is experiencing excess
breakage which results in replacement costs.
There is no reason why there should be so many
pieces of dishware breaking at the Bistro. No one
has an explanation right now but some
customers have mentioned that we seem to
have a clumsy staff. The company that supplies
the dishware doesn’t always stock the right style
which means the either operating without
enough plates and cups or using non-matching
dishware which is not optimal
Mini-Case Study Problem
8
9. “ABC It for Me”
9
6 pieces of dishware break
per day on average
I’m not
sure why…
11. 5 Ways to Visualize Data
11
Histogram
Run Chart
Pareto Chart
Box Plot
Scatter Plot
12. Poll #1:
12
Which is the bigger pet peeve?
A. When people use (lots of) text to tell a story
B. When people use a “wall of data” instead of
a chart or graph
C. Neither
D.Both
E. Hadn’t really thought about it
14. 14
What’s a Histogram?
# of times at
this level
Scale –
(minutes,
etc.)
Range =
Maximum -
Minimum
Shape –
(bell curve, etc.)
Center (Mean,
Median & Mode)
Time to Seat Customers - June
15. What Does the Histogram Tell Us?
15
What were
the actual
amounts of
broken
dishes each
day in
November?
One day there
were
20 pieces
broken!
16. What Else Can a Histogram Do?
16
Compare process
performance to
customer
requirements
Highlight what is
unacceptable to
customers
26. What Is a Box Plot?
26
Middle 50 % of
the data
Lowest 25% of
the data
Highest 25% of
the data
27. No Really - What Is a Box Plot?
27Bottom 5 Values
Top 5 Values
Time to Make Conch Salad
28. What Does the Box Plot Tell Us?
28
Is there a
shift where
more bowls
break than
others?
Exactly how did they
break 20 in one day?
29. What Else Can a Box Plot Do?
29
It can show a clear
difference in process
capability once
improvements are made
Great to
show
leadership!
30. Mystery of the Broken Bowls
30
Waitstaff are
breaking
bowls, and
breaking them
at lunch.
The soup n’
salad lunch
special is
driving conch
chowder sales.
Customers
want their
chowder hotter
in November…
36. Poll #2:
36
Which chart or graph are you
most comfortable using?
A. Histogram
B. Run Chart (Time Plot)
C. Pareto Chart
D.Box Plot
E. Scatter Diagram
37. How Charting Tricks and Tips Can Help
37
Histogram
Shape, center & spread
Run Chart
Trends over time
Pareto Chart
80/20 rule
Box Plot
Comparison
Scatter Plot
Correlation
38. What Data Goes With Each Chart?
38
Histogram
1 column of data
Scatter Plot
2 columns of paired data
Pareto Chart
Table of categories
and counts
Run Chart
Time ordered data
Box Plot
1 or more columns
of data
39. Poll #3:
39
What is most difficult for you
when creating charts and graphs?
A. Figuring out what chart to use given the situation
B. Collecting the right data
C. Properly setting up the data in a spreadsheet
D.Using the charting software
E. Some combination of all of these
41. Today We Covered
41
1. How Charts and Data Tell the Story
2. What Does a Histogram Tell You?
3. What Does a Run Chart Tell You?
4. What Does a Box Plot Tell You?
5. What Does a Pareto Chart Tell You?
6. What Does a Scatter Diagram Tell You?
7. How Charting Tricks and Tips Can Help
43. Getting Started
43
Learn more by starting some
more training!
• Yellow Belt Training is FREE at
GoLeanSixSigma.com
• Green Belt Training &
Certification
• Black Belt Training &
Certification
• Lean Training & Certification
44. Upcoming Webinar – 8/21 11am PDT
44
Register today at GoLeanSixSigma.com/webinars
We’ll select upcoming webinars based on your feedback,
so please share your feedback on the survey at the end of close of this webinar.
45. Just-In-Time Podcast
45
Tune in at GoLeanSixSigma.com/cafe for the latest Lean Six Sigma news,
easy ways to apply Lean Six Sigma and interviews with process
improvement leaders like you!
47. Thank you for joining us!
47
More Questions?
Ask us at contact@goleansixsigma.com!
Click here to download
free tools, templates, infographics and more!
Notes de l'éditeur
Moderator (Tracy)
Hello And Welcome to GoLeanSixSigma’s webinar: An Introduction to Lean. I am Tracy O’Rourke from GoLeanSixSigma.com, and I will be your moderator today.
Transition: Our presenter today is...
As you can see,
We have Brick-and-mortar, and online companies.
there are diverse industries such as healthcare, financial services, manufacturing and government
Why? Because Lean Six Sigma is about problem solving, and once you have an organization, you’ve got problems!
Like all of you, these companies want to be the best at problem-solving, so you’re in good company
Transition: More on some of the benefits later...but first let’s review our agenda.
Today we’ll use a mini case study to show how charts and data tell the story of an improvement project
We’ll focus on these 5 basic charts – they are the most commonly seen in improvement projects
And then we’ll give you some tips on how to create these charts and graphs on your own
Okay read this carefully – it’s full of critical information
Okay – now STOP reading! Consider – how many times have you been in this position?
How often are you reading an email or a project charter trying to determine what’s important?
What is this person trying to tell you?
Let’s try a shorter version….
The Short version is, “6 pieces of dishware break per day on average”
I got “ABC It For Me” from a team lead who was quoting his boss – She had no time for long explanations
So this team lead had to get into the habit of editing and tightening his work
My favorite Mark Twain Quote goes like this, “sorry for the long note, if I’d had the time I’d have written a shorter one.”
It’s funny, because it’s true!
Editing your emails, reviewing what you’ve put into a Project Charter, that all takes time!
If you don’t take the time – then you put the burden on the reader
I once had someone describe getting emails back from their boss that said, “TMW”
That’s a 3-Letter acronym for “Too Many Words” – funny – and again, true!
Let’s consider this same issues with numbers…
Okay – read this carefully
Now STOP! – Some of you are already on to me, but, again, I’m making a point
I see this kind of “wall of data” all the time
Everybody has spreadsheets of data – but, like text, they take a while to read and decipher
We’re going to study the “greatest hits” of charts and graphs to see how they can help us get our point across faster
Research shows the human brain processes images 60K times faster than text
Think about that - 60K times is a lot!
When working on a project – your job is to tell the story of improvement
Your data provides you with a great opportunity for telling that story visually
We’re going to use these 5 charting methods to see how they can help
But first, we’d like to hear from you….(Poll)
First up we’re going to cover the Histogram
What’s a Histogram?
Histogram are charts that show the distribution of values produced by a process
They are visual displays of how much variation exists in a process
Let’s look at a basic example
This is an example – It’s unrelated to our broken dish project
- We’ll use this to understand the parts of a Histogram
This is often referred to as a “snapshot” of our data
In this case it’s a snapshot of time to seat customers in the month of June
The X or horizontal axis has the scale – in this case it’s minutes
The Y axis shows frequency at each level
If we take the shortest bar to the left – it shows that one time, it took 14 minutes to seat a customer
So that bar only goes up to 1 on the Y axis
You can calculate the range – the maximum (22.8 minutes) minus the minimum (14 minutes)
Almost a 9 minute range
The other thing we can see is the center of the data – the tallest bar is the “Mode”
The stat software for these charts also calculates the median, the mean and other basic stats
You can also see the shape of the data – is it a normal bell curve or skewed
It’s a great chart since it’s packed with information that can be seen at a glance
Let’s get back to our broken dishware – what can the Histogram tell us about that data?
The original issue was that an average of 6 pieces of dishware break per day
We deal a lot in averages – and they can be helpful
But your process has more going on than the average
Some classic misuses of averages are enlightening
In 1984 – Graduates of University of North Carolina starting salary was over $100,000
That happened to be the year that Michael Jordan graduated from UNC and signed with the Chicago Bulls
Or – another one – the average diaper wearer is 40 years old –
in this case the population is split down the middle – very young and very old – so an average doesn’t work
Let’s take a look at the histogram of broken dishes
The average was 6/day, but the mode (highest bar) is 5 dishes – and that’s because one day there were 20 dishes broken!
Was Michael Jordan using dishes to shoot basketballs?
The data is a bit skewed, they seem to break at least 4 dishes a day and that seems like a lot
But we don’t know when the 20 dishes were broken – early in the month? Later?
Another helpful thing about Histograms is when you add the customer requirements
Back to our example of seating customers.
Everything above 10 minutes is unacceptable to customers
You can even change the color of the bars
In this chase we highlight everything over 10 minutes to show that they’d be “seeing red” or peeved
This is a great way to highlight the beginning of your story – the baseline
You want people to see how bad it is so they’ll support you in fixing it
Now let’s see what else we can learn by showcasing our data with a Run Chart or Time Plot
What’s a Run Chart?
A Run Chart, or Time Series Plot is a graph that shows data in sequence over time
Let’s look at a basic example
The key is that Run Charts shows what’s happening over time
It could be over a day, a month a year or just a shift – the X or Horizontal Axis is always over time
The Y or vertical Axis is whatever is being tracked
things like time to seat a customer, defects per day, it’s a great all purpose chart
The classic center of a Run Chart is the Median
half the data or 10 points are above, in this case
And half the data, the lowest 10 points are below the median
We’re used to seeing Time Plots in the newspapers
And you should always have one of your project data
You want to see the trends and shifts of your data
Is it random fluctuation? Is it going up? Going down?
The Run Chart Tells you what is happening over time
Back to our Broken Dishes project – what can the Run Chart tell us?
What is happening to the dishware breakage over time
A Ha! – It’s getting worse!
The one day that someone broke 20 dishes happened on the last day in November
As soon as you have 7 points in a row above or below the median, the process has shifted
Time to do some more digging since this is costing the company money and probably alarming the customers
Run Charts or Time Plots can also show what happened before and after a problem was addressed
In the case of the time to seat customers, the team would want to highlight the fact that the time decreased once they fixed the issue
There’s a shift here too, but it’s a good one – that’s what you want to showcase at the end of a project
Now lets’ see how the Pareto Chart can highlight our project work
What’s a Pareto Chart?
A Pareto Chart is a Quality Chart that helps identify the most significant sources of defects
Let’s take a a look at an example – this chart shows the different types of food orders
The Pareto Chart is for categorizing data
In this case the team was categorizing what people ordered out of 100 orders
The X Axis shows the categories are Salads, Combinations, Sandwiches and so on
The Y axis shows the frequency or the number of each category
In the case of these orders, 22 out of 100 were for salads
20 out of 100 were Combinations
There is also a second Y axis that shows the percentage
And the orange line in the center shows the cumulative average
If you add the salad orders to the Combination orders, you get 42% of the total
This helps team zero in on the category of highest impact
Let’s see how that might help with the broken dishes project
In the case of the broken dishes, the question is, what are we breaking the most of?
Bowls!
Out of 188 broken dishes in the month of November
150, or 80% were bowls
That’s very helpful since it will help the team narrow the focus of their investigation
This chart caused them to change the project scope to just address broken bowls
Paretos are great ways to highlight data – they help others see – at a glance –the biggest source of problems
They can also be used to dig deeper – lets’ go back to those 100 food orders
In this food order chart – Salads were the most common order
So – it’s even more helpful to the team ordering supplies to know WHICH salads are most popular
Turns out it’s the flying fish Waldorf Salad
That’s a great feature of these charts
One Pareto can lead to anther
These are called nested or “cascading” Paretos
It requires collecting more data
It results in understanding what’s inside the biggest bar
Next up – we’ll consider the misunderstood Box plot
My favorite
What’s a box plot?
A Box Plot, also known as a Box and Whiskers Plot, is a graph dividing a data set into quartiles and with a center box containing 50% of the data and two whiskers that each represent 25% of the data
That sounds like some kind of cartoon cat, so let’s get a closer look
This chart involves New terms and not intuitive
Deals in quartiles – but that just means fourths – you divide the data by 4
Shows the distribution sort of like a Histogram (see if it’s skewed)
This still doesn’t quite make the box plot clear
Let’s compare it to the run chart
Now you can see how the box plot divides the data set into 4
Since there are 20 data points, each quartile contains 5 data points
The bottom quartile is the lowest five values
The top quartile represents the highest 5 values
Generally takes a bit of experimentation to get a feel for it
This just shows the 2 methods of displaying data and how they’re related
We’ve been showing you a single box but this chart is best for comparisons
Let’s get back to the broken dishes…
Back to the case of the broken bowls
We can use the box plot to stratify the data by shift
Breakfast and lunch experience some broken bowls, but the median breakage and variation is much greater at lunch
This begs the question, what’s different about lunch?
The box plots are also helpful at showing the outliers – there are those 20 bowls again!
With this software it’s a dot
In other software packages it’s an asterisk – or multiple asterisks
It’s just letting you know that this data point was different from the rest of the data set
One common method of comparison is to reflect on the process after it’s been improved
Box plots are great for showing “before and “after”
It’s much easier to compare box plots than histograms since you can get them closer together
You can see if the variation was reduced, along with whether or not the median moved in the right direction
Again – a great visual to share with leadership that tells your story quickly
So far – the charts are telling us a story
Breakage is increasing over time
80% of the breakage is bowls
Most of the breakage is happening at lunch time
When asked about this - The staff said the soup and salad special was driving the sales of conch chowder –
Hence the use of bowls…
And they say the customers keep asking for the chowder to be hotter
They suspect the staff is dropping the bowls because they’re too hot to handle
Hmm – if we only had a chart that could tell whether or not the heat of the chowder affected the breaking of the bowls
This last chart helps us to understand if there’s correlation between to variables
it’s a great chart to use when trying to prove or disprove hypotheses
What’s a Scatter Plot?
- The Scatter Plot is a chart that shows if whether there is a relationship between 2 variables
Here’s an example that is comparing outside daily temperature and Daily Sales
Let’s review the part of the graph
Scatter Plots require “paired variables”
That means there are two columns of data
They Y or dependent variable is on the vertical axis
The X or independent variable is on the horizontal access
We’re trying to see if changes in X, result in changes in Y
This graph shows that as the daily temperature increases…
The daily sales also increase – seems to be a correlation…
Now let’s get back to that hot chowder
Does the breakage goes up as the temperature of the chowder goes up?
YES!
We can go watch the waiters and waitresses to confirm, but the data shows a correlation
Of course – there may be no correlation at all
I worked with a team in hotel and they were trying to understand why their staffing model wasn’t working
They had always based the staffing in their onsite restaurant on the number of guest reservations for that day
But when they compared the reservations to the number of orders, they found nothing
It’s only when they removed lunch and dinner orders that they found correlation
The number of reservations DID correlate to the number of breakfast orders
That Scatter Plot helped them change their staffing model for the better
It’s official – Conch Chowder is the biggest selling lunch items – along with the sandwich
It was so popular they didn’t have enough trays to go around
And since they were making it hotter to respond to customers,
- Without enough trays, the bowls were too hot to handle
Since the Soup n’ Salad Special is not going away, the bistro is investing in more trays
Problem solved
Let’s review:
Histogram: - Shows the Center, The Spread and the shape of the data
– great to show how the process performs against customer expectations
Run Chart/Time Plot: - Shows data over time
Great to see if there are trends or shifts in the data
Pareto Chart: Shows categories of the sources of defects
- Great to focus on the biggest contributor to the problem
Box Plot: Shows data divided into quartiles
- Great to compare the center and distributions of different strata of data
Also great to show before and after improvements
Scatter Plot: Chart they shows whether or not two variables are correlated
Great to help prove or disprove hypotheses
This a behind the scenes look
You cannot create these charts unless you have the data properly set up
The histogram is one column
The Run Chart is time based so you can add a date or time column
Pareto is just a table with a the category names and their totals
The Box Plot could be one column or as many columns as you want to compare
The Scatter Plot requires paired data – always in two columns
T
These links take you to both instructions for each chart and data sets so you can try them out yourself
There are instructions for both Minitab and SigmaXL
If you don’t have either, you can get a 30 – day free trial of SigmaXL and see if you like it
There are lots of other software packages as well as Excel add-ons
They all function pretty much the same way
Scatter Plots and Line Charts are easy to make in Excel without additional software
Good Luck!
I hope our visit to the Bahama Bistro helped you see how Charts and Data can tell the story
These 5 Charts are basic but have great versatility in what visuals they provide
Please visit our website and try these out for yourself –
Just adding one chart in place of text or data will make a huge difference in how others view your work
Remember: People process images 60K times faster than text – That’s a big difference!