To my wonderful students: These paragraphs are a revision of advice recently given to a student writer. 

Writing is a craft we all must master. And we all will. You are young: enthusiasm and energy come through in your writing: keep that and add to it. Become a better writer by growing as a writer and as a person. It took me time to become a decent writer. I hope you become better than me, and in less time. Every paper, report, memo, email, text is opportunity: take it and become a better writer.

The best writing instruction ever: Good writing is bad writing rewritten. I got it from Stephen King. Where Stephen King got it, I don't know. I'm giving it to you. You tell your students.

Write your first draft. Now go back, edit and revise. Rinse and repeat. 

Academics must write with accuracy. Compulsively read and re-read each sentence you write and game the sentence: Pretend to be an intelligent reader, but ignorant of the background. Search for multiple interpretations. Many first drafts have multiple meanings. Then put your re-write hat on and fix the sentence. One sentence at a time. Ditto: Does this sentence say what you want it to say? Ditto: Does this sentence belong here? Or elsewhere in this paper? Or in a different paper altogether? 

Density. Good writing has high information content per word. Find the words that don't convey meaning and delete them. You can eliminate 10% of the words from a first draft. Now go back and eliminate another 10%. Have you said something before? Delete it.

Writing is work. Successful writing: a pleasure. 

For those of you lucky enough to be at UCLA Tuesday and Thursday mornings for 10 weeks, 8:30 to 10:00, I'm teaching my course on longitudinal data and heirarchical models.  The text is my book, Modeling Longitudinal Data, Springer, 2005.  

Redundancy, duplication and reiteration are not desirable in technical writing. Assume your reader remembers everything previously written! 

1. You write "As mentioned before", "As previously stated", "From section X.X we know that" in a biostat paper or thesis proposal. 
   1. Continue writing. 
      1. It is okay to continue writing, because it is okay for you to write incorrectly or sub-optimally. 
      2. We all write sub-optimally.
      3. Get the words out, finish the draft. 
   2. It is permitted that your draft may be flawed. 
      1. The words on the page are just a draft and are not important. 
      2. The words on the page are not final yet. 
      3. Therefore it is okay to change the words. 
   3. It is not okay that the final version has major flaws.
      1. Bad writing will irritate your reader.
      2. Bad writing slows the reader. 
      3. Bad writing wastes the time of everyone who has to read your paper. 
      4. Fewer people will read your paper. You will have less impact. 
      5. If you are submitting a research paper to a journal, there will be serious consequences.
         1. At best, the referees will be irritated by the poor writing and make you revise it extensively. They may suggest rejecting the paper merely because of the writing. 
         2. At worst, the editor will reject the paper without even allowing referees to put their two cents in.
      6. Bad writing will be taken as a sign that
         1. You don't care about what you are writing;
         2. That you think the topic isn't important; or
         3. That you are a poor thinker.
      7. None of the previous item is true:
         1. You wouldn't be writing this if you didn't care,
         2. You wouldn't work on this topic if you didn't think it was important.
         3. You can't be that poor of a thinker, you got into graduate school for goodness sakes!
   4. Back to the business at hand. The current text is flawed. Make it better. 
   5. ​The text says the same thing in at least two places.
      1. The text is allowed to make a statement one time. The text is allowed to make a statement one time.
      2. If a statement occurs twice, there's a good chance it occurs three times. Or more. Check. 
      3. Which copy to keep? First (contact)? Second (base)? Last (supper)?​
         1. Is the statement needed at the first occurrence, or can it wait until the second? The best place to make a statement is the place where its consequences are utilized immediately which will leave hooks in the reader's memory to make recall easier. 
         2. If you leave the statement in place at the first occurrence, state it in a way the reader will recall at each spot without a restatement.
      4. ​Remove all but one copy of the statement. 
      5. Now your task is to make sure the reader will understand the text with the removal. 
         1. Repair the text in each place where you have removed duplicate text.
         2. Smooth and shorten. 
         3. Likely you will need to rearrange text, lots of text.
         4. Can the two or three locations be combined?
2. Often there are additional duplicates: text, phrases, definitions, statements.
   1. Scan through quickly for duplicates. 
   2. Identify an important phrase that you use several times. Use global search to identify every usage. At each use, does the text say the same (or similar) thing about or with it? 
   3. Go fix. 
   4. Reduce. Do not re-use. Do not re-cycle! 
3. A related writing problem is identified by the phrase "in other words". In other words signifies what we intended to write is important, but we're pretty sure the reader won't get it from the current set of words.
   1. There is fault here; the fault is in the initial phrasing.
   2. Thus we restate the point in other words, usually immediately in the next sentence.
   3. Solution: Typically the restatement is easier to follow so keep it and delete the first flawed version.
   4. Smooth your text.
   5. Have you omitted important information from the first statement? Is it really important? If yes, add it back. Tersely. But not the whole thing. 
4. Taking a break from writing if needed. 
   1. It's hard to edit immediately after writing until you've garnered some experience switching modes. 
   2. After 10 minutes of break, go back and edit to remove duplicates. 
      1. Until you are an experienced editor, going back and editing can be painful. But editing is as important as the initial writing. Even if you're not ready, go back and edit. 
      2. Get to it. 

Enjoy!

Statistics, Statistical Analysis, Quantitative Thinking, Statistical Humor, Biostatistics, Teaching, Writing, Publishing, Statistical Analysis, Jokes, Numbers, Numeracy, Whatever I'm Interested In (WIII), Science, Public Health, Medicine, Research, Business of Science, Advice to Students, How to do all of that, How not to do all of that.  

Am applying to a stat blog aggregation site. One of the questions there is a blog description, and another is 'additional information'. As my blog is single, perhaps I could give them my blog's phone number? Looking for other blogs to hang out with.  

2013 and 2014 as integers to factor are fairly interesting. Each has three prime factors with no repeats. Each has one one digit prime factor, one 2 digit prime factor under 20 and one 2 digit prime factor over 30. It's a miracle!

2013 = 2 * 19 * 53

2014 = 3 * 11 * 61

and no factors in common. No repeated factors. 2015 follows completely in the footsteps of 2013 and 2014

2015 = 5 * 13 * 31

No repeated factors and no prime factors in common with 2013 or 2014!

It's not until we get to 2016 that the pattern is not just broken, but completely destroyed: 2 repeated factors and no factor over 7.

2016 = 2^⁵ * 3^² * 7

At least the powers 5 and 2 are also prime. And there are exactly 3 distinct prime factors, and 3 is prime.  

Today's quiz.

• What was the last prime year?
• What was the most recent year before 2013 that had the same properties of factorization as 2013, 2014 and 2015?  As this is ambiguous, try these versions of this question
  • Three prime factors, one under 10, one between 10 and 20, one over 30.
  • That, plus no prime factors in common with 2013, 2014 or 2015?
  • What is the next year that satisfies both these properties?
• What was the last year with exactly two factors?  (Note: three distinct correct answers, give both. )

Remember: there are 3 kinds of statisticians, those who can count, and those who can't.  

Todays relatively hard bonus quiz.  All questions refer to years AD prior to 2014.

• How many years with a prime number of prime factors where each prime factor's multiplicity is prime?
• How many with one prime factor?
  • Two distinct prime factors?
  • ​Three distinct prime factors?
• ​Repeat that last question, where each factor has multiplicity one.  

Meta bonus quiz question: What assumptions am I making that distinguishes the quiz from the relatively hard bonus quiz?

Happy new year!