Review of Technical Principles (5 min)
- Know your variables and what are the most useful calculations you can do with them
- Know your units of measurement to make sure you are writing about them in an understandable way
- Look at your distribution to get a sense of how to communicate a “typical” value through a measure of central tendency (i.e., mean, median, mode)
- When talking about typical values, it might be helpful to describe how varied your data are (e.g., lots of similar values, a bunch of different values, values clustered at the low and high end with few in the middle). Other than looking at the distribution in a histogram or box plot, you can do this numerically through standard deviation or through interquartile range. This can help contextualize a given value for how close it is to a “typical” value in the distribution. Quartiles can also help you calculate outliers if you want a way to communicate if a given value might be an outlier or not.
- You may not need to communicate anything about your distribution, but this can be helpful for your own understanding of the data even if you do not find it helpful to communicate it.
- Use standards or cutoffs to help make your values meaningful.
- Be mindful of how you communicate digits and what decimal places you use.
Making Comparisons (30 min)
Comparison is really the bread and butter of communicating something about data. It is hard to know if something is meaningful unless you have something to compare it against:
- How large or small is the value?
- How fast or slow was the pace of change over time?
- Is it below or above an important standard or cutoff (e.g., poverty line)?
Miller outlines several calculations we can make that can help us communicate about comparisons:
- Rank: A comparison relative to other values, to include percentile when there are a lot of values (e.g., “the least expensive car,” “weight was in the 67th percentile”). See pp. 101-105.
- Difference: Subtracting a reference value from number of interest (e.g., “so far, MLB teams hit 797 more home runs this year compared to 2018”). See pp. 105-106.
- Ratio: Dividing the number of interest by the reference value (e.g., “I doubled my take-home pay per week with my new job, making $600 per week instead of $300 [Number of interest = $600, reference value = $300]”; “I now make 80% of what I did a year ago at this new job because my industry sucks and has the power to do this…I now make $40,000 instead of $50,000 per year [number of interest = $40k, reference value = $50k]. See pp. 106-108.
- Percentage difference: Divide difference of number of interest and reference value by reference value and multiply by 100 (e.g., “so far, MLB teams hit 797 more home runs this year compared to 2018, a 14% increase [number of interest = 6,382, reference value = 5,585″). See pp. 109-111. See also 112-113 on common errors when reporting percentage points, percentile, and percentage change.
- z-score: Subtract the mean from the number of interest and divide by the standard deviation. A positive score is above the mean, a negative score is below the mean. Only use when distribution is approximately normal (i.e., “bell shaped”). Helps when comparing two values that come from very different distributions. For instance, if you are comparing a 6-month-old baby that was 2.5cm shorter than the average to a 6-year-old 2.5cm shorter than the average, because variation within distributions are way different for these age-ranges, a z-score can be useful. Kevin is looking at different groupings of hockey players based on their contract value to think about contract value compared to production as a hockey player. If the distributions for each grouping are very different, it might be useful for him to use a z-score to compare across those groupings. See pp. 114-115.
- Attributable risk: see pp. 115-118. Really only useful for experimental data. Can be tricky with observational data that most of you all are using because it too easily gets caught up in questions of causality that are probably not that useful for what you will be doing. It is handy, though, when thinking about trying to do something different compared to a standard.
Everything but z-score involves some basic arithmetic, but even z-score is pretty simple if you know what a standard deviation is (which you do! and if you don’t, you will just need a few moments to remember after glancing at an example or definition or last class’s lesson).
There are some minor mathematical issues to keep in mind before choosing (see pp. 118-120). For instance: If a variable has a possible value that is lower than zero, you cannot use a ratio to compare.
Generally, though, from a rhetorical perspective, once you have a valid way to compare mathematically, it doesn’t really matter how you choose to compare values. What matters is what your goal is as a writer and what sorts of interests your audience has.
Some tips:
- Always report value to set context and provide data for other calculations, then present one or two types of comparisons to give a more complete sense of the relationship
- To help readers interpret both value and difference, mention the highest and lowest possible values and observed range in the data
- Value is also important for putting a ratio in context…always give values for percentage change and difference as well.
- Specify type of measure: Honda Civics most frequently stolen but Corvette stolen at highest rate.
Activity
On page 113, there is a great paragraph that gives an example of some of the quantitative comparisons used in the chapter. I want you to write a similar paragraph where you also choose a specific perspective or story that you want to tell about Rafael Devers, a baseball player for the Red Sox that dramatically improved this year.
Look at Devers’ statistics to find a number under “Career Stats” (e.g., HR for home runs, RBI for runs batted in, AVG for batting average, OBP for on-base percentage) and tell a story about Devers overall and his change from last year to this year. The variable “AB” will be useful–this is “at bat,” meaning the total amount of times he went to try to hit a baseball (this will be helpful for constructing ratios with AB as a reference value.).
Incorporate rank, difference, ratio, and percentage difference into your paragraph. To find where he ranks or ranked go here and change between 2018 and 2019 as needed.
Paste your paragraph to this google doc when done
Peer Response (20-30 min)
Use the following to inform a reading of your partner’s work:
- Miller’s 7 principles
- the technical principles from last class
- what we covered about public writing (e.g., general structure of: informing about research question/importance, the analysis, the application/action)
- the reading about the importance of context for datasets to inform your reading of your partner’s work
Check out the “review,” too, from 9/12 to think more broadly about rhetoric and data overall.
Take a moment to think about what you want to look for when reading.
PROCESS:
- First person reads there paper aloud.
- While reading aloud, listener silently takes notes on elements that are really effective and elements they think could use more work. The listener also has specific reasons why they feel that way.
- Also, while reading aloud, the author is encouraged to pause to take notes about things they noticed.
- After author is done reading aloud, the listener repeats back to the author what they think the general story or argument of the piece is (i.e., the “big picture”).
- The author and listener discuss how much or little this impression aligns with the author’s view of the “big picture” of the piece.
- Then, the listener discusses the “effective” things and the “work on in revision things” they noticed. The author responds and takes notes.
- They check in for next steps the author will take based on discussion.
- Switch roles and repeat #1-7.
NOTE: Don’t be a jerk! Consider how you would like to hear feedback. That being said, don’t be too general and non-confrontational either…constructive criticism!
Next Time
-do reading
-do journal along with reading
-I will share some of your good work!