Statistics Week 4

This week's homework lived up to it's description of "really tough".  That said, I had a good time doing it.  I actually got to break out the pen and paper again and do some algebra.  And darn it if algebra isn't just fun.  I'm not completely sure I got the right answers, and I'll be interested to see what my group members came up with, but I had a good time crunching the numbers.  It started to feel like I could really start applying this to some of the numbers we get at school and bring some more meaning to them.

I was also impressed with the Bill Tancer video.  There was one question from the audience that I didn't discuss on the wiki, mostly because I wanted to talk about it here.  A member asked how he determined the background of the participants in his data collection- how did he know which people searching for Stacy Kiebler were male, and which were female.  He answered with a long string of terms that were Greek to me, but it seemed like he gave people the chance to voluntarily submit their information.  The audience member asked, basically, doesn't that skew the data?  Aren't you just analyzing the subset of the population that's actually willing to hand over their information (which he said 90% of the people at Google wouldn't do)?

It made me think of the Nielsen ratings.  A few years ago, I actually filled out the little Nielsen packet, mostly because I collected a teacher's paycheck and $20 sounded awesome.  I caught myself skewing my own data, though (something I alluded to in the wiki).  I caught myself watching stupid shows because I was bored and it was all that was on, but I didn't actually want to encourage the production of those shows, so I claimed that I watched nothing.  Other times, I would see something that was about to come on after my bedtime that looked really interesting, so I claimed that I watched it to encourage more of those shows to be made.  (Yup, I just admitted to liking algebra and having a set bedtime in the same blog post.  Awesome.)  I wondered how many other people did that- gave Nielsen slightly inaccurate data to encourage a particular result in the survey.  I'm sure statisticians have found a way to account for this, but my gut tells me it's probably not quite perfect.  Perhaps these small changes just get accounted for in a large enough sample size?  Either way, it's something that will be in the back of my mind as we go through our own survey data.

Oh, and if anyone from Nielsen is reading and wants their $20 back, I was just kidding.  I totally watched that NatGeo special.

Statistics Week 3

This is one week when I would have had to eat a little crow if I had spoken to anyone about this week's article on preparing a survey.  After reading, it all seemed pretty pointless to me.  I thought it included the kind of unnecessary preparation steps that business-y types sit around in boardrooms and talk about while pretending words like "synergy" mean anything.  If I would have said that out loud, I would have been wrong.

As my group went through the steps, I quickly realized that if we just started randomly writing down questions, it would have been a mess.  As we were creating the questions, our focus slowly and subtly changed, and we went back and tweaked a few of our early additions to our survey.  It was then that Curtis pointed out our goal didn't really match our content anymore.  If we wouldn't have taken the time to formulate and write down a goal, I never would have realized it.  And I probably would have still thought of it as a survey on "tech tools" even though all the questions were now about "tech skills".  If I were to present it, I guarantee I would have coming out looking bad.  It was definitely a good reminder that survey creation has to be very purposeful and centered on a goal, otherwise you won't end up with the results you wanted.

On an unrelated side note that I may have brought up before, but will blather on about anyway, my Language Arts II class recently finished a completely paperless novel unit.  I'm currently working through grading their work, and I couldn't be happier.  Their blog posts were insightful, they worked great as teams, and most made a Prezi for their final project- unreal.  The vast majority of that class has much better Prezi chops than I have.  The only hangup was that I required them to use Today's Meet to meet at least once outside of class, with the stipulation that they had to get some actual work done (not just casually chat).  This was a headache. Maybe if someone else has had students work collaboratively online after school hours, he or she could impart some wisdom on me, because I won't be trying to force another class to go through that portion in the same way I planned it this year.  All things considered, though, the unit is a definite repeat for next year, and I'll probably convert a few other units to the blog/wiki format.

Statistics Week 2

This week was a little bit of fun.  In the past, I've compared looking at student test scores and formative assessments to looking at baseball stats.  This week, in the scenarios in the guided practice, it felt more like I was looking at a player's stat line and evaluating how he would be expected to perform.  I felt like I was guessing a lot of the time, or at least describing a scenario that could be true, as opposed to what necessarily is true.

One stat I'm still hung up on is Standard Deviation.  I understand that it is connected to range, but I'm still a little hazy on exactly what it means for a collection of numbers.  But say there was a set of numbers, most around 100 let's say.  Then there was one at 7.  Would the SD be the same as a series of evenly spaced numbers covering the same range?  If that were the case, I'm not sure how it's necessarily useful given that we already know the range.  If it's not the case, then I need to go back and look into SD a little more.

The survey tools investigation was a bit of an eye-opener.  I didn't realize people were paying so much for survey software.  For an individual teacher, it seemed like the free subscriptions often covered much of what I wanted to do.  One of the tools (I think it might have been Poll Everywhere) offered the ability to identify respondents, and that would definitely be helpful in the classroom were I to use it for a graded assessment.  However, there are plenty of services like Edmodo or Quia for giving quizzes.

540 Week 1- Let the Geeking Out Commence

As I said in my bio page, this was the one class that really caught my eye when I signed up for the Masters program.  I've made a small hobby out of using stats in my classroom, and I really want to learn whether or not I'm using them correctly, and hopefully learn some new techniques.

The terms for the first week seem straightforward enough.  I caught myself applying a few of them to a test I just graded in one of my classes.  I was sort of surprised by the even distribution of grades- B, C, and D were completely even, with a few A's and one F.  This seems like it would be the type of grade distribution which would reflect on honest assessment- median and mean would be similar, and likely multiple modes.  The problem is, this does not reflect the distribution of overall grades the students had going into the test.  So I guess the mystery is what caused some students to get lower than normal grades, in varying degrees, while others were aligned with what they normally have (this class is entirely A and B students).

I just deleted a few paragraphs of boring description of how I would go about doing this, most of which is probably obvious.  (You're welcome.)  Point is, this is the kind of situation I would love to apply statistical analysis to, and figure out what went wrong for some, and fine for others.  The common responses to this problem would probably be either "Well some kids didn't study," or "That teacher isn't doing his job," depending on whom you want to make into a scapegoat.  Hopefully, by the end of this course, I can shed a little more light on a situation like that.