06.06.2013 Views

Theory of Statistics - George Mason University

Theory of Statistics - George Mason University

Theory of Statistics - George Mason University

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

x =<br />

⎛<br />

⎜<br />

⎝<br />

x1<br />

.<br />

xd<br />

⎞<br />

⎟<br />

⎠,<br />

and there is certainly no need to use the silly notation<br />

x = (x1, . . ., xd) T .<br />

Preface ix<br />

A vector is not a matrix.<br />

There are times, however, when a vector may be treated like a matrix in<br />

certain operations. In such cases, the vector is treated as a matrix with one<br />

column.<br />

Appendix C provides a list <strong>of</strong> the common notation that I use. The reader<br />

is encouraged to look over that list both to see the notation itself and to get<br />

some idea <strong>of</strong> the objects that I discuss.<br />

Solving Problems<br />

The main ingredient for success in a course in mathematical statistics is the<br />

ability to work problems. The only way to enhance one’s ability to work<br />

problems is to work problems. It is not sufficient to read, to watch, or to<br />

hear solutions to problems. One <strong>of</strong> the most serious mistakes students make in<br />

courses in mathematical statistics is to work through a solution that somebody<br />

else has done and to think they have worked the problem.<br />

While sometimes it may not be possible to solve a given problem, rather<br />

than looking for a solution that someone else has come up with, it is much<br />

better to stop with a partial solution or a hint and then sometime later return<br />

to the effort <strong>of</strong> completing the solution. Studying a problem without its solution<br />

is much more worthwhile than studying the solution to the problem.<br />

Do you need to see a solution to a problem that you have solved? Except<br />

in rare cases, if you have solved a problem, you know whether or not your<br />

purported solution is correct. It is like a Sudoku puzzle; although solutions<br />

to these are always published in the back <strong>of</strong> the puzzle book or in a later<br />

edition <strong>of</strong> the medium, I don’t know what these are for. If you have solved<br />

the puzzle you know that your solution is correct. If you cannot solve it, I<br />

don’t see any value in looking at the solution. It’s not going to make you a<br />

better Sudoku solver. (Sudoku is different from crossword puzzles, another<br />

<strong>of</strong> my pastimes. Seeing the solution or partial solution to a crossword puzzle<br />

can make you a better crossword solver.) There is an important difference in<br />

Sudoku puzzles and mathematical problems. In Sudoku puzzles, there is only<br />

one correct solution. In mathematical problems, there may be more than one<br />

way to solve a problem, so occasionally it is worthwhile to see someone else’s<br />

solution.<br />

The common wisdom (or cliché, depending on your viewpoint) that it takes<br />

10000 hours to master a field or a skill is probably applicable to statistics.<br />

<strong>Theory</strong> <strong>of</strong> <strong>Statistics</strong> c○2000–2013 James E. Gentle

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!