There is an interesting discussion over at Environmental Economics discussing the UC student protests against raising student fees. The economic argument they are making is that if university tuition and fees remain the same while at the same time the university is receiving less state subside then the amount (or quality) of instruction occurring will decrease. They then ask the question: is this really what students want?
This title is taken directly from this article which discusses research implies or explicitly says a number of “good” parent tactics are actually bad for your child. The actual list of things that seem good, but aren’t are
The fantastic part of this article is the undertone of sarcasm. Just to be clear, the article states that the above tactics are actually bad for your child according to recent published scientific research. But by saying it in a sarcastic way, the author really says the science is shoddy and these tactics are still good.
From a statistics viewpoint, the research is interesting and following the links provided some of the discussion is right on. For example, following the link under “Giving Your Kids a Creative Name”, the 153rd comment (which happened to be at the top of the list when I looked) hits the nail on the head. The comment points out that the authors didn’t control for minority ethnic groups. So while the authors were trying to say that kids with creative names have a worse time in life, they instead just ended up showing that minority ethnic groups have a worse time.
Synthetic biology holds a lot of promise for developing organisms that perform functions that would otherwise require delicate and expensive devices. Imagine a bacteria designed to eat oil. Put some on an oil spill and they will clean up the area with minimal human intervention. They could even be dropped in from the air.
National Public Radio’s Science Friday had a segment on iGem, International Genetically Engineered Machine competition. This year’s winner was a group of undergraduates from Cambridge who designed a set of bacteria which turn colors in response to stimulus, literally (see image below). Imagine a developing country with possible arsenic in the water. Put some of the questionable water on a petri dish with these bacteria. If they turn green, the water is good and if they turn red you should try another well. This is a great advancement since no specialized equipment, e.g. flow cytometer, is necessary. Hopefully this machine will get incorporated into the BioBrick registry which maintains a list of building blocks for creation of genetically engineered machines.
Originally posted by the blog Calculated Risk and then duplicated on The Big Picture, the figure below shows employment numbers for various recessions in U.S. history. Obviously this data is relevant to many people at the moment. Anybody in my PSTAT 262 care to take a stab at this data as part of their project?
I am curious why the data seem so jumpy in earlier years relative to the smooth curve for the current recession. Bad data gathering techniques? Untrustworthy news sources led to businesses not reacting at the same time?
This story that I picked up on slashdot says that the Centers for Disease Control have partnered with GE Healthcare to receive data on 14 million patients in their network. (Of course, I cannot actually find an announcement from the CDC about this.) The data will be collected on a daily basis and provide information on flu prevalence and spread. To see the current information the CDC uses for flu surveillance go here and for the most recent flu activity go here. Compared to previous CDC surveillance, this method has the advantage of a huge database with timely responses. Of course, samples will still need to be analyzed to classify flu as seasonal or H1N1 (or other variants) which will add some delay in knowing which flu is active and when. My hope is that the CDC allows easier access to the data. I understand we will not receive the medical records for individuals, but some summary statistics on a reasonable spatial/time scale would be helpful.
Today on Andrew Gelman’s blog he discusses whether it is better to use Stata, SAS, or R to run multi-level models on large datasets. Since I am in the process of (possibly) creating a short course on R and since I know very little about Stata and SAS, the topic was definitely of interest. As Gelman often does, there is no distinct correct answer (I like this btw….too many people believe they know the correct answer). Basically he says that if the data in all sub-groups is large, then analysis can be performed separately for all subgroups. In this case, any of the above software packages might work fine. But if an analysis needs to use the entire dataset, then he suggests that Stata > SAS >> R (Stata is better than SAS, but both are much better than R).
The plot below from the National Data Buoy Center is from two different stations (no idea where they are located) measuring air pressure. Although the data shown in this plot isn’t current, data of this sort would be appropriate for my PSTAT 262 project. Apparently the upshot of this particular figure was to decide that the buoy at 42043 has a bias in its reporting of air pressure since it is consistently above the air pressure at station 42035. Any reason to think the air pressure might just be consistently higher there? I have no idea, so I guess I will take the analyst word for it.
Here are a number of datasets that could possibly be used for a project in PSTAT 262. All the time series indicate, in some fashion, our current economic condition.
Previously I have mentioned I’m in the market to get a new phone. The Motorola Droid is a possible alternative to getting an iPhone. This review is pretty enthusiastic and the full specifications can be found here. What is unclear to me at this point is what plan I will need to have to use the functionality of the Droid. I do not want to pay anymore than I currently am, which only gives me voice and free Verizon In calls (I pay per text message). So I understand I will not be able to use phone features that involve sending data over Verizon’s network, but will I be able to take advantage of all the other functionality? I presume yes, but will need to find out before I jump in.
The other day, I criticized a graphic describing swine flu deaths in terms of its relevance to me. The figure below provides the estimates of the marginal probability of dying from different causes including H1N1 (swine flu). Of course, I will still complain and say, I’d prefer to see a figure that is conditional on my being a U.S. resident. Still this figure provides exactly the type of perspective that is needed concerning the impact swine flu is currently having on the world.
With that being said, I believe public health officials are mainly worried about the possibility of H1N1 mutating into something that is much more contagious, or more importantly more deadly. If this happens soon, the world will still not have enough immunity (either through having been infected already or a vaccine) and the deaths could be catastrophic.
[This image is no longer available. That's what I get for linking to the image rather than downloading it and linking to my own version.]