:/
Thursday, September 30, 2010
Friday, September 24, 2010
biblical nonresponse error
This made me chuckle.
I'm reading parts of Survey Errors and Survey Costs by Groves. At the beginning of the chapter on nonresponse, he quotes Genesis 3:8-10 - where Adam and Eve hear God walking through the garden and hide themselves because they're naked.
The first nonresponders!
I'm reading parts of Survey Errors and Survey Costs by Groves. At the beginning of the chapter on nonresponse, he quotes Genesis 3:8-10 - where Adam and Eve hear God walking through the garden and hide themselves because they're naked.
The first nonresponders!
Thursday, September 23, 2010
SAS fail!
I was just reading this times article on R -- I guess SAS is feeling the pinch from so many people swtiching. In any case, a SAS representative is quoted:
“I think [R] addresses a niche market for high-end data analysts that want free, readily available code," said Anne H. Milley, director of technology product marketing at SAS. She adds, “We have customers who build engines for aircraft. I am happy they are not using freeware when I get on a jet.”
wow!
Happy they're not using freeware when you get on a jet? Because a small corporate staff can make a better product than the whole world working together? I, for one, am happy that I'm not using their product!
Later, one of the co-founders of R (Ross Ihaka) nails it:
“R is a real demonstration of the power of collaboration, and I don’t think you could construct something like this any other way,” Mr. Ihaka said. “We could have chosen to be commercial, and we would have sold five copies of the software.”
The turn to open source here is interesting. But more and more I'm moving to Google's closed-source-but-free model.* I don't think there will be a google R anytime soon, so at least in the stats realm we're fine for a while.
I was surprised to learn yesterday that there are commercial implementations of R. I guess I don't have a problem with people packaging R slightly differently and providing support (and charging a fee). Well, actually I do think it's a little weird to take an open source project and package it such that it becomes (partially) closed.
But what type of support would a commercial operation provide? Surely you couldn't call them and say "We have data on X and we're interesting in some relationships among them - What statistical methods should we use and how do we run them on your product?" Maybe it's just this latter part (how to run them?) that you can ask? But if you've looked up the appropriate methods already, then it's a short jump to figure out how to run it in R.
Maybe this is why I hadn't heard of the commercial implementations before -- they're basically useless in the face of such a strong userbase and narrow scope of the software.
--
*I'm kind of migrating to Chrome and I already use gmail and docs extensively. Oh, and this blog is on blogger.
“I think [R] addresses a niche market for high-end data analysts that want free, readily available code," said Anne H. Milley, director of technology product marketing at SAS. She adds, “We have customers who build engines for aircraft. I am happy they are not using freeware when I get on a jet.”
wow!
Happy they're not using freeware when you get on a jet? Because a small corporate staff can make a better product than the whole world working together? I, for one, am happy that I'm not using their product!
Later, one of the co-founders of R (Ross Ihaka) nails it:
“R is a real demonstration of the power of collaboration, and I don’t think you could construct something like this any other way,” Mr. Ihaka said. “We could have chosen to be commercial, and we would have sold five copies of the software.”
The turn to open source here is interesting. But more and more I'm moving to Google's closed-source-but-free model.* I don't think there will be a google R anytime soon, so at least in the stats realm we're fine for a while.
I was surprised to learn yesterday that there are commercial implementations of R. I guess I don't have a problem with people packaging R slightly differently and providing support (and charging a fee). Well, actually I do think it's a little weird to take an open source project and package it such that it becomes (partially) closed.
But what type of support would a commercial operation provide? Surely you couldn't call them and say "We have data on X and we're interesting in some relationships among them - What statistical methods should we use and how do we run them on your product?" Maybe it's just this latter part (how to run them?) that you can ask? But if you've looked up the appropriate methods already, then it's a short jump to figure out how to run it in R.
Maybe this is why I hadn't heard of the commercial implementations before -- they're basically useless in the face of such a strong userbase and narrow scope of the software.
--
*I'm kind of migrating to Chrome and I already use gmail and docs extensively. Oh, and this blog is on blogger.
Sunday, September 19, 2010
on the relativity of peer-reviews
Got the reviews back on my TRB paper yesterday afternoon. They're uniformly pretty good, but some hilariously contradict each other on the fundamental readability of the paper (see below), and one is a bit over the top. In any case, I'll be heading to DC in January :)
(some gems. paraphrased, of course...):
Reviewer 1: Paper was specific and narrowly focused. This worked well.
Reviewer 2: Well-written, easy to follow, not a single error of syntax detectable.
Reviewer 3: Very clearly organized. Objectives and findings well-stated.
Reviewer 4: Paper is unfocused and leaves the reader confused.
Srsly?! In my response can I just cite Reviewers 1-3 to counteract Reviewer 4?
Thursday, September 16, 2010
defining content analysis
Introduction
I was initially confused because I assumed that Krippendorff would take issue with Neuendorf's definition of content analysis but I wasn't sure why I thought that. Now I'm pretty sure that he's only criticizing far earlier definitions, although a little disingenuously. Check it out:
Definitions
Neuendorf (2002): Content analysis is a summarizing, quantitative analysis of messages that relies on the scientific method … and is not limited as to the types of variables that may be measured or the context in which the messages are created or presented.
Krippendorff (2004): Content analysis is a research technique for making replicable and valid inferences from texts (or other meaningful matter) to the contexts of their use.
Exemplary older one:
Berelson (1952): Content analysis is a research technique for the objective, systematic, and quantitative description of the manifest content of communication.
Discussion
Krippendorff takes big time issue with the idea that CA has to describe the "manifest content of communication." He claims that this definition of CA arises from the Shannon-Weaver model of communication which leads to the idea that one message has one and only one meaning. If we accept this model, then content is inherent in a text rather than acknowledging that multiple readings of a text are possible (i.e. there is a multiplicity of "content" and thus meanings associated with a message/text, depending on context - K's favored view, which is just constructivist?). If we take Berleson's definition (according to Krippendorff) then we have to accept the idea that the only thing we can content analyze is that which is the same for the sender, receiver, and content analyst (which would obviously be extremely limiting and boring).
Now, I think this is a bit of a straw man, since the early content analysts probably wouldn't agree with Krippendorff's description of what they were doing. If K is right, though, then he would have a point. I'm just not sure I can justify the expense of intellectual energy right now to dig deeper.
In any case, it seems that Neuendorf's definition is consistent with Krippendorff's since she has the idea of context, and says that any variables are possible (i.e. from extremely manifest to extremely latent). The idea of inference is also interesting -- apparently early content analysts (Olsti) wanted to be able to make inferences from the CA results to characteristics of the source or effects on the receiver. Krippendorff and Neuendorf are both fine with this in principle, but they want us to have more information about the source/audience for corroboration (which I'm in total agreement with).
Conclusion
At root it seems like K is just trying to inject some constructivism into this positivist model of CA from the 50's (this is a pretty tired debate by now, I'm sure...?). Neuendorf seems to acknowledge this also, but her exposition is a lot clearer than K's (in my opinion).
I was initially confused because I assumed that Krippendorff would take issue with Neuendorf's definition of content analysis but I wasn't sure why I thought that. Now I'm pretty sure that he's only criticizing far earlier definitions, although a little disingenuously. Check it out:
Definitions
Neuendorf (2002): Content analysis is a summarizing, quantitative analysis of messages that relies on the scientific method … and is not limited as to the types of variables that may be measured or the context in which the messages are created or presented.
Krippendorff (2004): Content analysis is a research technique for making replicable and valid inferences from texts (or other meaningful matter) to the contexts of their use.
Exemplary older one:
Berelson (1952): Content analysis is a research technique for the objective, systematic, and quantitative description of the manifest content of communication.
Discussion
Krippendorff takes big time issue with the idea that CA has to describe the "manifest content of communication." He claims that this definition of CA arises from the Shannon-Weaver model of communication which leads to the idea that one message has one and only one meaning. If we accept this model, then content is inherent in a text rather than acknowledging that multiple readings of a text are possible (i.e. there is a multiplicity of "content" and thus meanings associated with a message/text, depending on context - K's favored view, which is just constructivist?). If we take Berleson's definition (according to Krippendorff) then we have to accept the idea that the only thing we can content analyze is that which is the same for the sender, receiver, and content analyst (which would obviously be extremely limiting and boring).
Now, I think this is a bit of a straw man, since the early content analysts probably wouldn't agree with Krippendorff's description of what they were doing. If K is right, though, then he would have a point. I'm just not sure I can justify the expense of intellectual energy right now to dig deeper.
In any case, it seems that Neuendorf's definition is consistent with Krippendorff's since she has the idea of context, and says that any variables are possible (i.e. from extremely manifest to extremely latent). The idea of inference is also interesting -- apparently early content analysts (Olsti) wanted to be able to make inferences from the CA results to characteristics of the source or effects on the receiver. Krippendorff and Neuendorf are both fine with this in principle, but they want us to have more information about the source/audience for corroboration (which I'm in total agreement with).
Conclusion
At root it seems like K is just trying to inject some constructivism into this positivist model of CA from the 50's (this is a pretty tired debate by now, I'm sure...?). Neuendorf seems to acknowledge this also, but her exposition is a lot clearer than K's (in my opinion).
Friday, September 10, 2010
Subscribe to:
Posts (Atom)