In my last post, I looked at factors impacting Michigan primary school test performance. In this post I look at high school performance using the Michigan Merit Examination (MME) 11th grade results to determine what is the role of race, location, poverty, and school type (public, not for profit, and for profit charter). In all of the exam subjects (Math, Reading, Science, Social Studies, and Writing) for profit charters out perform not for profit charters and public schools at a 95%, or higher, confidence level. Not for profit charter schools typically outperform public schools at lower confidence level than their for profit comparisons because their are so few in the data (only 16 as opposed to 79). The higher the ratio of Asian and female students, the better the school performs on the exams.
One of the advantages of a regression analysis is that it can be used to forecast what the result should be based on the factors involved. Some schools will vary more (above and below) the forecast. I hope to illuminate that distinction using an online map in a future post.
The Detroit Free Press recently ran an interesting series of stories about charter schools in Michigan which made me wonder if I could use regression analysis to partition the variation in test results on the basis of race, poverty, location, and type of school. This analysis uses MEAP scores for the 5th grade.
tl;dr — For profit charter schools generally produce worse results than public or not for profit charters while not for profit charters produce better results.
If you’re thinking “eeeeeeeeeehhhhhhhwwwwwwwww math”, I hope to soon incorporate the results into an on line map to make it easy to look at the results for particular schools .
I’ve been working for some time on a Perl module to parse XBRL, a complex XML based format for reporting financial information. The US SEC requires publicly traded firms to provide their financial reports in XBRL. The goal of the Perl module is to provide a clear and easy to use interface to extract data from an XBRL instance and use it for another purpose. In the initial release, the module features a function to render the XBRL instance into a very basic HTML document. Because the XBRL standard is large and complex, support for its features will be added over subsequent releases.
Today’s announcement from HP that WebOS will be set free as an Open Source project opens up room for some interesting changes in the mobile landscape. Both CNET’s Stephen Shankland and The VAR Guy think nothing much will come of this move. As both a long time Open Source zealot and a mobile developer, I think there is more there there than they do.
In a previous post, I showed a pretty simple regression analysis of housing prices and house size for my Zip code. The zip code was used as an easy way to include location in the output. Using PostGIS and geographic data from the City of Sacramento, this post will show a regression analysis ( using the R statistical programming project) using the city’s designated neighborhoods. The raw data real estate data comes from the Sacramento Bee. After describing the model, I’ll apply it the last few months of home sales (not used in developing the model), and see how well it does at predicting results. Read more…
Having worked for many years at HP, the recent announcement cancelling HP’s Webos program is rich with personal irony. Until yesterday’s announcement, I was working on a bar code scanning application for HP’s Pre 3 phone.
Thinking about life as an independent “app” developer, I’m reminded of Canadian Prime Minister Pierre Trudeau’s famous remark about the United States:
Living next to you is in some ways like sleeping with an elephant. No matter how friendly and even-tempered is the beast, if I can call it that, one is affected by every twitch and grunt.
I hope the new PC company gets off to a good start and they get to keep WebOS, but they will have to move forward without my efforts as an “app” developer.