I'm about 50 pages into this statistics book. So far I haven't hit anything I haven't seen before. This book does a fairly good job of describing why certain metrics are used, as well as describing ways they can be meaningless. That being said, it's not nearly as mathematically rigorous (so far) as I had expected. It's pages and pages of text with one or two punchline formulas defining the previously described behavior. I'm not going to knock it too hard yet - I guess I expected more math and I'm curious as to why it's not there. I flipped through the later chapters and found mostly the same pattern.
The one statistics course I took in college wasn't a "stats for engineers" course, but it still had a good deal of math involved. For some reason I was really good at it, and I think the reason is kind of silly. A typical formula for basic statistics (like the one for standard deviation) is kind of "pretty". It has a sigma and summation symbol (upper case sigma?) and I would mindlessly doodle it over and over again in various ways, so I wound up memorizing them accidentally. Over time I've forgotten it, naturally. Math retention has never been my strong suit - quite the contrary to the programming retention I seem to have. Maybe it's a function of practice, not innate ability.
I was figuring that statistics would be mathematically rigorous enough that it would prevent me from tackling anything else while researching it. That doesn't seem to be the case so I'm tempted to bring in something else to do. I haven't stopped programming. I've actually done more programming this new year than usual, but it's in Python and it's work related. It scratches the programming itch just as well, so I'm not jumping at tackling the next chapter in the Obj-C book. Hopefully that doesn't hurt me in the long run.
No comments:
Post a Comment