Box and Whisker Charts (Box Plots) are commonly used in the display of statistical analyses. Microsoft Excel does not have a built in Box and Whisker chart type, but you can create your own custom Box and Whisker charts, using stacked bar or column charts and error bars. This tutorial shows how to make box plots, in vertical or horizontal orientations, in all modern versions of Excel.
In its simplest form, the box and whisker diagram has a box showing the range from first to third quartiles, and the median divides this large box, the “interquartile range”, into two boxes, for the second and third quartiles. The whiskers span the first quartile, from the second quartile box down to the minimum, and the fourth quartile, from the third quartile box up to the maximum.
Sample Data and Calculations
To play along at home in Excel 2007 or 2010, download the workbook Excel_2007_Box_Plot_Workbook.xlsx.
Let’s use the following simple data set for our tutorial. The values were taken from a normally distributed population with a mean of 10 and standard deviation of 5. There are four sets of 20 values.
All of these values are positive. If your data set has mixed positive and negative values, this technique requires major modifications.
First, insert a bunch of blank rows, and set up a range for calculations. Only the horizontal version of the box plot uses the last calculated row, “Offset”. It will not hurt to include it in the vertical box plot’s calculations.
First, compute some simple statistics, such as the count, mean, and standard deviation. The formulas used in column B are shown in column G of the screen shot.
Now let’s compute the minimum and maximum, median, and first and third quartiles.
Finally, let’s determine which values we need to plot. Our chart has a box for the second quartile, which shows the difference between median and first quartile calculated above. It has a box for third quartile, which show the difference between the third quartile calculation and the median. The bottom of the lower box rests on the first calculated quartile. The down whisker is as long as the first quartile minus the minimum, and the up whisker is as long as the maximum minus the third quartile.
The offset values are calculated as follows: In my example, I have four categories, Alpha through Delta. I can divide my horizontal chart into four horizontal strips, numbered from 0 to 4, each containing one box-and-whisker unit. I need to position my average points in the middle of each 1-unit horizontal strip. These will ultimately go onto a secondary vertical axis which I will have conveniently scaled from 0 to 4. Hence the Y values I will need are 0.5, 1.5, 2.5, and 3.5.
Chart Construction
Select the header row of the calculated data, then hold Ctrl while selecting the three rows that include Bottom, 2Q Box, and 3Q Box. This multiple-area range is highlighted in orange below.
With this range selected, insert a stacked column chart or a stacked bar chart. Be sure to use the stacked version, and not the 100% stacked version, of the column or bar chart.
The labels in the bar chart go bottom-to-top. To reverse the labels, select the vertical axis, press Ctrl-1 (numeral one) to open the Format Axis dialog, then check the “Categories in Reverse Order” box, then under “Horizontal Axis Crosses”, select “At maximum category”.
To add the down whisker, select the Bottom series, then in the Chart Tools > Layout tab, click Error Bars, and select More Error Bar Options from the bottom of the menu. Choose the Minus direction, select Custom for Error Amount, and click on Specify Value. Leave the contents of the Positive Error Value box alone (“={1}”) in the mini dialog that appears, then clear the Negative Error Value box and select the Whisker- row from the table (B14:E14). Click OK and Close to get back to Excel. These “down” error bars (whiskers) extend from the bottom (left) edge of the 2Q Box downward (leftward) into the Bottom series.
To add the up whisker, select the 3Q Box series,then in the Chart Tools > Layout tab, click Error Bars, and select More Error Bar Options from the bottom of the menu. Choose the Plus direction, select Custom for Error Amount, and click on Specify Value. Leave the contents of the Negative Error Value box alone (“={1}”) in the mini dialog that appears, then clear the Positive Error Value box and select the Whisker+ row from the table (B15:E15). Click OK and Close to get back to Excel.
These “up” error bars (whiskers) extend upward (rightward) from the top (right) of the 3Q Box.
Now we can format the boxes. Select the Bottom series, and apply no fill and no border, so it is hidden. Then select each of the 2Q Box and 3Q Box series, and apply a dark border and a light fill.
– - 
Adding the Mean
To add the mean as a series of markers, select the Mean row in the calculated range (highlighted in blue). If you are making a horizontal box plot, hold Ctrl and also select the Offset row (highlighted in green), so both areas are selected. Copy the selected range.
Select the chart, and use Paste Special to add the data as a new series. If you are making a horizontal box and whisker diagram, check the “Category (X Labels) in First Row” box. The “Series Names in First Column” box should already be checked.
The new series is added as another column or bar stacked on top of the existing ones.
– - 
Select this new series, then on the Chart Tools > Design tab, click on Change Chart Type. If you are making a vertical box plot, choose a Line Chart style. If you are making a horizontal box plot, choose an XY Scatter style.
– - 
The points in the horizontal box plot are in reverse order. To change the order of points, select the secondary vertical axis (right edge of the chart), press Ctrl-1 (numeral one) to open the Format Axis dialog, then check the “Values in Reverse Order” box.
If you’re making a horizontal box plot in Excel 2003, this last process is a little more involved. Excel draws both secondary axes, but the vertical one is hidden behind the primary axis with the text labels (below left). Double click on the secondary horizontal axis (top of chart), and on the scale tab of the Format Axis dialog, check “Value (Y) Axis Crosses at Maximum Value” (below right).
– - 
Excel 2003, continued: Double click the secondary vertical axis (right of chart), and on the scale tab, check “Values in Reverse Order” and uncheck “Value (X) Axis Crosses at Maximum Value” (below left). Finally, select the secondary horizontal axis (top) and click Delete; Excel will now plot the XY series on the primary horizontal axis.
– - 
All Versions: Now format the mean series: remove the line, and use an appropriate marker of a contrasting color. If you’ve made a horizontal box plot, hide the secondary Y axis (right edge of the chart) by choosing no tick marks, no tick labels, and no line in the Format Axis dialog.
– - 
That was easy and didn’t take too long.
Peltier Tech Box and Whisker Chart Utility
This tutorial shows how to create Box and Whisker Charts in Excel, including the calculations and specialized data layout needed, and the detailed combination of chart series and chart types required. This manual process takes a little time, can be prone to error, and becomes tedious.
I have created the Peltier Tech Box and Whisker Chart Utility for Excel to create such charts automatically from raw data. This utility, a standard Excel add-in, lays out data in the required layout, then constructs a chart with the right combination of chart types. This is a commercial product, tested on hundreds of machines in a wide variety of configurations, which saves time and aggravation.
The Peltier Tech Box Plot Utility creates charts in either horizontal or vertical orientation. It provides four different methods for calculating quartiles. This add-in also provides three styles for the box plots, including one that shows outliers.
Please visit the Peltier Tech Box and Whisker Chart Utility page or the Peltier Tech Box and Whisker Chart Utility Documentation page for more information.
Hi Jon!!
Thanks for the post. I am a big fan of you.
how we can move secondary Y axis in bottom direction, like for common x-axis, one Y-axis in upward direction and other Y-axis in downward direction.
I’m not sure what you’re doing with the axes. Why do you want two axes, and what are they showing?
I have been enjoying the PTS Box and Whisker in Excel 2003 for the past two years. I now have Excel 2010 … how do I add this in? I have tried to reinstall from the zip file.
Actually, after reinstalling it now shows up under Add-Ins.
Thank you so much for this information. This is VERY helpful.
i want to draw a graph of one dependent variable having two categories and one continuous independent variable, what is the appropriate graph?
David -
Seems to me you want an XY (Scatter) Chart.
Perfect! Exactly what i was looking for! Thanks a lot!
Thanks a million!
I can draw a horizontal boxplot and get the outliers marked as points (using xy scatter plot). However, the outliers are not in line with the actual boxplot (but above the boxplot if I use y>0 and below, if I use y=0). How can I make the outliers “lie on the same axis” as the boxplot.
Thank you so much.
Regards
Franziska
Franziska -
Did you line them up using the same approach I used to align the average markers in this example? The X values need to be the outlier value, and the Y values use the offset values 0.5, 1.5, 2.5, etc. as shown in the last table above.
This is so freaky, suddenly it’s working. Thank you so much – I don’t know how you did it, but it seems you persuaded my Excel to be obedient. Thank you :-)
Franziska -
Ha, I wish I had that kind of control over MY Excel!
Can these box plots identify outliers i.e., the asteris beyound the wiskers?
Brad -
Outliers can be displayed on charts such as these, but you need to add more data series, and adjust the lengths of the whiskers to indicate not min and max data, but data closest to the definition of outlier without being outliers.
The ability to display outliers is built into the Peltier Tech Box and Whisker Chart Utility.
Dear Jon,
Thanks for this post, I was able to build a box and whisker plot from scratch because of you. I need some tweaking however, hope you can still be of help. I need to show the position of outliers (any values outside the USL / LSL) in the graph also. How it can be done?
thanks,
Jhiel
Jhiel -
First, you have to redefine the length of the whiskers. If you are dealing with outliers, the whisker goes as far as the farthest point which is not an outlier. Near outliers are more than 1.5 interquartile ranges (third quartile minus first quartile) outside the first and third quartiles. Far outliers are more than 3 interquartile ranges outside the quartiles.
Then you need to set up your outlier data. Put the category for each outlier in column 1 of a convenient range (the first box is category 1, etc.), and put the value into column 2. Copy this range, select the chart, and use paste special to add this data as a new series. Convert this new series to an XY type, and then assign it to the primary axis (if Excel moved it to the secondary axis).
Very helpful, thanks.
A note: I made a vertical box and whisker chart but Excel kept “forgetting” the plus whisker value. I had to follow the instructions for the horizontal plot to trick Excel into remembering the plus whisker. BTW, how the heck did you ever figure out this workaround!? (and the eternal question: why is MS office so buggy?)
Dear sir,
This is Naidu Ph.D student, before i do not no about Excel Box and Whisker Diagrams (Box Plots) how to draw this diagrams in Excel? why we are using?. But i typed this words in Google then i got your Pelteir tech blog. Then i learned about various charts like Box plot, cluster stock, Dot plot etc.
Thanking you very much giving this opportunity to all
thank you so much, finally I did it!
best wishes
M
huge help. thanks a ton.
I have some borders on the box that are above and below 0. any work around for this? thanks
Want to make the plot horizontal, but Excel 2010 doesn’t have a “Categories in Reverse Order” box in the vertical axis “Format Axis” box, but only “Values in Reverse Order”. Any thoughts would be most appreciated.
The setting is certainly there:
If you already have secondary axes in the chart, you may be trying to format the other vertical axis.
How do you calculate the offset?
Kelly -
In my example, I have four categories, Alpha through Delta. If I scale my secondary vertical axis from 0 to 4, I need points in the middle of each 1-unit division. Hence 0.5, 1.5, 2.5, and 3.5.
can you please help find a solution to box values that are both above and below 0? here’s an example that is causing difficulty.
whisker- 7
1q box -11
mid box 6
3q box 5
whisker+ 9
Thanks a ton!
Hi,
Thanks for the great blog! I was wondering if there is any way of changing the width of the boxes to reflect different sample sizes per cateorgory?
Hi,
Thank you very much for providing those utmost valuable information regarding different charts in Excel. I have drawn a box plot using your instruction. It was fun and interesting. But for my data set, I need to convert the box into standard deviation box. In which the mean value will be middle. And offcourse the whiskers range for upper and lower values would be as it is.
Please help.
Sheikh Ali Ahmed
It is not advisable to use quantities other than quartiles for box plots. You risk distorting the interpretation of those who are familiar with the standard box plot construction, causing them to overestimate the variability in the plotted data (mean ± 1 sd includes 68% of a population, while the interquartile range includes 50% of the population). You also risk distorting the future use of box plots by those who are not yet familiar with them.
Thinks a lot
I have one more question please: It’s about adding the mean in the Blox Plot
I dont know how to do it.
Hello–Thanks so much for this tutorial, ecstatic that I’ve made three box plots from scratch! I was wondering, is there a way to make just two? (i.e. just the ‘alpha’ and ‘beta’ boxes in your example?) The tutorial doesn’t seem to work for this.
Gretchen -
You don’t define what isn’t working, but I suspect it’s something like this.
When you first create a chart, Excel counts rows and columns in the source data range, and tries to minimize series and maximize points per series. You get the following chart, with two series and three categories:
Right click on the chart, select Select Data, and click the Switch Row/Column button, to get the proper starting chart:
From here, follow the steps to get your two-category box plot:
Hi Thanks a lot for posting it. It is a lot helpful. However I am using excel 2007 and when I try to add whisker +, every error bar will have similar length of bar…I couldn’t know what went wrong there
Did you do exactly this, which is the instruction for Excel 2007:
Choose the Plus direction, select Custom for Error Amount, and click on Specify Value. Delete the contents of the Negative Error Value box in the mini dialog that appears, then clear the Positive Error Value box and select the Whisker+ row from the table (B15:E15). Click OK and Close to get back to Excel.
This is fantastic right until I get to insertion of means. It works perfect in a vertical box plot. But in the horizontal plot, even when I click on xy scatter style, something is wrong. The line is on the wrong axis, somehow. Anyone else getting this bug (excel 2007)
OH Thank you! It worked! Happy Holidays to you and your family…Gretchen
Hello!
Thanks so much for your tutorial, it really came in handy when constructing my charts! I do have a question though: Are the up and down whiskers equivalent to the min and max for the data sets? Are there box and whisker charts that use the min and max as the up and down whisker? Basically I’m just not sure how to interpret the up and down whiskers based on the quartile calculations you use to get them.
Thanks!
Cassy
Thanks, very helpful
I have used this site several times, so I appreciate you posting it! I now have to do an analysis with positive and negative data, and this says that the method would require major modifications. Is there another page that discusses how to do that? I need to look at chemical sampling data (influent v/s effluent) through a system. Sometimes the system removes the chemical (positive percent removal) and sometimes it loads the chemical (negative percent removal). I need to find out if overall it achieves 85% removal. Any thoughts on that? Thanks!
Kelly -
Scroll down to “Stacked Columns for Positive and Negative Data” in Excel Waterfall Charts (Bridge Charts), or visit the older tutorial at Stacked Column Charts that Cross the X Axis.
Thank you for your easy to follow instructions. I want to put a line across each box and whisker plot for the mean series (instead of a dot). How do I do that? Thanks.
Meena -
The simplest is to use the wide dash marker for the data points. Or if you don’t need the median, use mean for the boundary between the two boxes (but this might confuse people who are familiar with box plots, because box plots were designed to show median, not mean).
Jon,
What is a wide dash marker? My boss wants me to put black dots for all of the data points on the box and whisker plot. He also wants me to put a single red line (in addition to the black median line) for the mean. I followed your instructions and plotted a dot for the mean and then drew a red line using “shapes” in excel before deleting the orginal dot. The problem is that the line drawn keeps moving. How can I make a line that doesn’t move (like the median line)? Thanks. -M
Meena -
The long dash is the 7th marker in the dropdown list, right above the circle. You can enlarge it by changing the size, but it gets thicker as well as wider.
Another way to get a line that doesn’t move around is to draw a line as you’re doing now and format it (size, color, line thickness, etc.), copy the line, select the series, and paste (Ctrl+V). Then you can delete the line you drew. This pastes the line as a new custom marker for the series. This technique works for other shapes as well, but don’t get carried away.
Hi John, thanks so much for your tutorial! I’m creating a horizontal plot and am having trouble adding the mean…I have eight categories (months) on my y axis and the range of my data on the x axis, and each time I try to add my mean series by selecting my months and then my offset data points (0.5 – 4), Excel plots all of my mean values for the month of May only (my first month). Do you happen to know what I might be doing wrong?
Thank you so much,
Megan
How do I make only one axses. The examples show two.
Hi Jon,
Thank for sharing your expertise knowledge with all of us! I learn a lot from your posts.
I need to generate the Box and Whisker Charts for more than one groups with four categories (like alpha, beta, gamma, and delta in the example here )for each. I am wondering if it is possible to differentiate the categories (like green for alpha in all the groups and blue for beta in all the groups, etc.).
Thank you very much for your time and help,
Ping
Hi, Thank you so much for this tutorial. It has really helped a lot. I have one problem though. When I try plot the whisker+ excel just puts the same length error bar for each category. I did exactly what you said in the tutorial. My whisker+ values are 0,0,0,0,0,1 but excel puts each error bar length as 1. I would appreciate any advice on fixing this.
Thanks so much!
Sarah -
Those are funny whisker lengths for a box plot, but that’s not your question.
Adding and setting error bar values is something that many people have a lot of trouble with. While other things can b done “almost exactly” like the instructions, the error bars have to be generated “exactly exactly” as shown.
Remember to use the custom option, and select the entire range containing the error bar values, not just the last cell.
These steps were so easy to follow, so thorough, and the explanations were excellent in describing why values were used where! I am so relieved to find this site to aid in my assignment for school. Thank you so much for posting this!
xx Jenni
Thank you so much, this was an excellent resource and I was able to use it quite quickly to get some great ‘whisker’ plots for a paper. Much appreciated!!!
Hi Jon,
thanks for a post. I did not find if you already find a solution, but it seems your instructions and formulae do not work for number series involving both positive and negative values. I have a data series that range from say -25 to 65. If Q1 is negative, median is positive and Q3 is also positive, than the error line draws from the bottom line of the Bottom rectangle, i.e. say minnus 2, and not from the top line of the Bottom rectangle as is the case of Q1 being a positive value. I have solved the problem with border calculations for 2Qbox, 3Qbox and Whiskers where the calculations must look like this: 2Qbox=Abs(median – abs(Q1)). Similarly for the whiskers. However, still could not find a solution how to adjust for the Bottom calculation correctly. I can send you numbers to check, but do not have your mail. Any suggestion is appreciated.
Marian
Marian -
I haven’t done the write-up for box plots that span positive and negative numbers. For explanations of how to handle stacked column or bar charts that cross the category axis, scroll down to “Stacked Columns for Positive and Negative Data” in Excel Waterfall Charts (Bridge Charts), or visit the older tutorial at Stacked Column Charts that Cross the X Axis.
What modifications you do when you have negative values?
Patricia -
You can see what is needed in Stacked Column Charts that Cross the X Axis, and see it applied to waterfall charts in Excel Waterfall Charts (Bridge Charts).
This is really useful,
I have created 2 diagrams with 5 box and whisker diagrams on each, they have the same x values.
I’ve been trying for ages to superimpose the charts by simply copy and pasting one into the other, but excel won’t let me.
Any advice would be much appreciated.
Superimposing the plots is possible, but is likely to be difficult and problematic to do, and is also likely to result in something difficult to read.
Instead of 5 categories each in two charts, how about treating the data as 10 categories? Related pairs of data will be adjacent, so overlapping will not obscure any data.
I recent purchased you box-and-whisker plot utility. It works great!
One question, however, involved outliers. I believe that outliers are plotted as points that are over 1.5 x the inner-quartile range. That is standard.
Can you give me the criterion for ‘far outliers’? Also, could you provide a reference for this?
Thank you,
Pat Durkin
Patrick -
“Far” outliers exceed 3.0 IQ from the nearest quartiles. I’m sitting in an airport right now, so I can’t look up a reference, but I’ve seen it in multiple places.
Thanks for the useful, easy to follow instructions. I have now created versions of the winning entry for scenario 2 in DM Review’s 2005 data visualization competition (not sure if I can post a link, but Google “Boxes of Insight”, it’s the first 2 links).
The problem with the whisker+ error bars, where the range keeps on defaulting back is solved in Andy’s post on 24th Sept 2011.
Follow the instructions for the horizontal plot for this section, and you will get your error bars – I did this and it worked.
Thanks
Ian
PS – I and my colleagues keep coming back here to find out how to present and chart data more clearly. We really appreciate this excellent resource!
Hi Jon,
Thanks for this great post!
I was trying this on Excel 2010 and I think it is more accurate if instead of selecting the ‘Bottom’ Row, to select the Q1 row instead. Also for the Whisker+ plot, it only works if the Negative Error Value box is left as it is – “={1}”, otherwise for some reason the Positive Error values simply goes back to {1}. Hope that makes sense.
Julian -
I don’t know what you mean by “instead of selecting the ‘Bottom’ Row, to select the Q1 row instead”. The protocol says to select the Bottom Series, then add the negative whiskers.
I hadn’t noticed how flaky the positive error bars were if you didn’t leave ={1} for the negative values. I’ve modified the protocol to suggest not changing the value for the error bar direction which is not shown.
Hi Jon,
Sorry please ignore the first part of my comment. I was referring to the very first part of the chart construction. But I made a mistake in the Bottom row formula and used “= B6″ (which is the Min value) instead of using the Q1 values.
Cheers
I need Help with my maths homework but I’m a idiot and don’t know what the range is in Cumulative Frequency on a box and whisk diagram………I’m stuck, Help is needed
Hi Jon, awesome, detailed work! Thanks for sharing. My attempt to plot two graphs vertically next to one another worked really well until I came to the whiskers part. For some reason I can not choose different values, i.e. when I assign my cell “B17″ as lower value for the data set 1 lower whisker value (through choosing specify error value) it automatically assigns the same value to my second data set (which would be the WRONG lower value/ lower whisker value).
How can I manually assign different whisker values in the specify error box if I have more than one data set in my graph?
Hope this makes sense. Perhaps you are able to help me? Thanks, Sandra.
Sandra -
Are Data Sets 1 and 2 different chart series, or different points in one chart series? I assume from the question that they are different points in one series.
Put the error values for your data sets (points) into a range of cells, then select this entire range in the custom values dialog.
Amelia -
It’s probably too late to help with your homework, but here goes.
The cumulative frequencies in a box plot by definition are the values at 0% (minimum), 25% (the first quartile), 50% (the median), 75% (the third quartile), and 100% (maximum).
I’m trying to create a box plot with a continuous x variable, but Excel plots it out as if my x variable is categorial (as in your example: alpha, beta, gamma). I want the plots to be placed to scale with the x variable, how can I do this?
Each box/whisker unit shows the distribution of data for one category. These categories are generally not numerical, and in the Excel charts used to make Box Plots, these categories cannot be treated numerically, unless those numbers are uniformly spaced whole numbers (i.e., 1, 2, 3, etc.).
Hi Jon
Thanks for the tutorial. I am really awful at this but my boss has asked me to produce a box and whisker diagram to illustrate the 95 percentile for a number of data sets. I’m guessing that the whiskers will illustrate the 5 and 95 percentiles instead of the max and min values but how do I calculate these percentiles and will the upper and lower quartile values be extracted from these to give the whisker + and – values as in the table above. Any help you could give will be greatly received. Thanks.
I’m currently trying to do the negative one too, so if you have a solution that would be great…
Hi John. I seem to have a repetitive problem in that the first bar will not take the whiskers. They appear on the subsequent bars. Any idea what I’m doing wrong?
Hi Jon, further to this, the whisker ‘caps’ are showing on the first bar, but not the vertical lines, and the caps are in the wrong place (on the edge of the quartile bars). Also, if I hover over where the whiskers should show below the quartile bars, the dialogue box appears telling me what the value at the bottom should be (and says ‘series “bottom” Y Error Bars), but the whiskers remain invisible. Does that help? The whiskers are showing on the subsequent bars which is confusing because the whiskers for all bars should appear at the same time.
Thanks
Fay -
Are the values for the first point’s error bars numerical? It sounds like Excel thinks they are text, and in assigning a numerical value of zero. Make sure the error bar range you specified starts in the cell you think it does, and make sure all values are stored in the cells as values.
Works great on positive data. I’m not sure what the workaround is for mixed positive and negative data but it does not seem to be able to handle both negative data.
Many, many, many, many thanks!!!!
I should have looked at all the comments first. I’m optimistic that your solution for positive and negative data will work. Thanks
Hi Jon
Thank you for your website. I am using your excel box-plot template and it works brilliantly (thank you). But I would like to know if there is a way to over lay data points over the box-plot to show outliers and the overall distribution of the data. There are ways to do this using R or Minitab, but I cannot code, and I really dont want to purchase Minitab right now. Thank you so much.
Respectfully yours,
vijay
Hi Vijay -
It certainly is possible to plot outliers or even all points over the box plots. In fact, I’ve worked out the details for defining and plotting outliers in my commercial box plotter application. For the denser data in the middle of the plot, there are also algorithms needed to jitter the points (shuffle them sideways) so you can tell if multiple points have the same value. I haven’t done this part, though I’m considering an attempt.
When I change the Chart Type for the means to XY Scatter for the horizontal graph, Excel plots the Y value on the X and the X value on the Y. I’m using Excel:mac 2011. I’ve tried having my data in both columns and rows, but it makes no difference.
Andrew -
Are you making a bar chart with horizontal or vertical bars?
Thanks, this has saved me a lot of trouble! Really clear instructions, even for a Excel novice like me!
Hi,
Thank you for your very usful example of box-plot.
But, I have one doubt!
The central box plot represents the 95% CI or range?
The central box represents the span between the 25th percentile of the data and the 75th percentile. In other words, it’s the middle 50% of the data.
Hi Jon;
Thank you so much for your tutorial on Box plot, however, i dont seem to get how you inserted mean values as series. If i try it, the mean values are stacked on the first series. If i try to paste special mean values i get a pop up menu then for values in (Y) i checked column, then checked categories (X Labels in First row) then OK. Can you please advise
The added series is in fact stacked on the existing series. You then have to change the chart type to a line or XY type.
Hi!
This site is absolutely fantastic – it has been proved itself handy time and time again and is always my 1st port of call!
I was wondering, howver, if you could provide guidance on how you would design a clustered boxplot chart in Excel? I have tried to use both the BoxPlot guidance and Cluster-Stack guidance in parallel for this particular chart design but I just keep getting a bit tripped up along the way.
It would be very useful to have this summarised in some way (or to be provided with a link to somewhere where I could find this) – perhaps an example would be to provide “male” & “female” results clustered on the “alpha”, “beta”, “gamma” and “delta” used in the example above?
Thanks for your time and I hope to hear from you soon.
P
Very good presentation
When I clear the negative values i cant seem to get to whisker row. i have no idea how to find it
Anye – I don’t know what your negative numbers refer to.
What is the best way to handle the box plot when the whisker value is >> than the box values. If you go full scale you squeeze the box. I have read your opinions on broken axis, and even tried a panel chart with the box plots. Just wanted to get your opinion on the best way to display data like that.
What is it important to show? Are you comparing this with other boxes in the same chart? If this is the only one that has such a high value, maybe you can truncate the chart without showing the entire whisker. A panel is going to be difficult to construct, but you could show two charts side by side.
Unfortunately the majority of my data has the same issues. I was trying to show 5 or 6 box plots side by side. The max point is important to show but I wanted the audience to also get a feel for the distribution of the data points. That is why I was drawn to the broken axis for the whisker
THank you so much for this, it is so simple to do and it saved me a lot of time!
Jon,
This post has been so helpful, but I’ve fallen over at the final hurdle. I’m using Excel 2010 and have a horizontal box showing the 5th – 25th %ile, the middle 50%, and the 75th-95th ile%. There are 44 categories and the outliers sit on 0% & 100%
I now want to plot the relative position for a single data point in each category (bar). However, no matter how I do this (X-Y scatter or Line) Exel plots these points across the x axis rather than along the y axis, so that point 1 is on the extreme left rather than the top of the chart and point 44 is on the extreme right rather than the bottom.
If I add the series to the stacked boxes it does this correctly. If I try and swap rows and columns it does this for the other series as well.
Don’t think it is significant but my data is laid out with categories in rows and series in Columns
I have tried eveyrhting I can around your instructions above but can’t make any headway
Any ideas?
Colin -
Sounds like your definitions of the boxes and positions of the outliers are different from standard practice, so you run the risk of confusing your audience, unless they really know know what you’re doing.
Anyway, to plot data points on the chart, you have to remember that X is vertical and Y horizontal for a horizontal bar chart, but X is horizontal and Y is vertical for points plotted using scatter or line charts (and for this you want to use a scatter chart series). You have to edit the data for just the one series in the select data dialog or by editing the series formula.
Thank you so much for this! I’d been tearing my hair out for weeks and continually have to use workarounds to present statistical data. Am so happy I could dance!
Hi, thanks so much for this walkthrough. Very easy to follow and much simpler than what I was trying to come up with!
Naomi
Hi there, I am wondering if you can help me. I need to make a box and whisker plot in Excel but I am comparing combinations of drugs. There are two drugs A and B. Drug A has doses 0, 110, 210, 330 and drug B has one dose 200. There are 8 groups:
Drug A (0) + Drug B;
Drug A(0);
Drug A (110) + Drug B;
Drug A (110);
Drug A (210) + Drug B;
Drug A (210);
Drug A (330) + Drug B;
Drug A (330).
I need to group these 8 groups into 4 groups comparing
Drug A (0) with or without Drug B;
Drug A (110) with or without Drug B;
Drug A (210) with or without Drug B;
Drug A (330) with or without drug B.
I need to make a box and whisker plot but with 8 box and whiskers but they need to be different colours/shades within their drug group. I.e there will be a legend saying black box and whisker is with Drug B and grey box and whisker is without Drug B. Then on x axis will be Drug A doses. Each Drug A dose on Y axis will have two box and whisker plots, one black and one grey.
If this has made any sense at all please could you let me know how i would go about making a box and whisker plot like this.
Kind regards,
Sarah.