Your information might be available online but it is definitly NOT the Census Bureau that is sharing the information with the resellers. As one very familiar with the inner workings of the Bureau I can tell you that NO personally identifiable information comes out of the Bureau - ever - even to other government agencies. Your information is protected under title 13 of the United States Code. We even hide data for small area estimates if it is unusual enough that someone might be able to figure what your values are based on their knowledge of that geographic area. We have teams of people that write programs that test this. Anyone who has access to your information is subject to a severe penalty (including jail time) if they distribute outside the Bureau (or even within if those getting it do not have a reason to look at it). The trust that the Bureau would lose if it were ever to go against this policy would cause response to drop and make the estimates extremely poor - it's just not worth it. I can't speak for other government agencies - but the Census Bureau does not and will not ever give personally identifiable data to anyone.
He is not kidding. Excel is a very poor choice for all but the most simple types of data analysis. The biggest probelms IMHO is that it allows the users to just click away at options until something they like appears. Very rarely will users give any thought to all the assumptions that are made when performing a regression anaylsis. But it's there, right...it must be ok to do! So if the linear regression doesn't look ok, they try a squared or cubic regression until the lines match up with their data and they sit back satisfied that they have discovered a fundamental relationship between two or more variables. Just because Excel can draw a pretty line with an equation on a graph doesn't mean that it should. Excel does a disservice to its users by providing a crippled but easy to use set of tools. I want to second the grandparent's support of the excellent open source statistical package R. It is easy to use, has a very large and very active user base, and has a huge number of extensions for all types of techniques. Its graphical capabilities are expecially advanced. I would never publish a graph made from Excel without extensive reformatting, but graphs from R (or Splus) look at home in any journal. (for more on good and bad graph design see Edward Tufte's "The Visual Display of Quantitative Information").
No extra holiday time for Guv'ment workers
on
New Calendar Proposal
·
· Score: 2, Insightful
Under his system, christmas eve, christmas, new years eve, and new years day are all on saturday or sunday. This will happen in 2005 in our current system and us guv'ment types don't get any extra days off. Not that we don't get enough days off anyway (think inauguration day, ex-pres dies, an inch of snow falls, etc) but hey, everyone likes those extra days around christmas.
I had similar experiences in South Africa. I would tell people that I was from Alaska and almost no one knew is was part of the US. Most thought is was part of Canada, some thought it was a country by itself, and a few thought it was an island in the pacific next to Hawaii (cuz that's where it is on all those maps of the US they see).
Dude, you have obviously never met my parents.. Sadly, though, I don't think they are alone in their ignorance. If it isn't on the desktop then for all intents and purposes - it doen't exist.
My bad. I seem to be having trouble finding the article link as well. The closet I found was this but I am not sure if it is the reference the newsies are using or if CERT has changed their site since the first report on Sat, June 26. About 2/3 down the page under the Use a Different Browser heading is this
Use a different web browser
There are a number of significant vulnerabilities in technologies relating to the IE domain/zone security model, the DHTML object model, MIME type determination, and ActiveX. It is possible to reduce exposure to these vulnerabilities by using a different web browser. Such a decision may, however, reduce the functionality of sites that require IE-specific features such as DHTML, VBScript, and ActiveX. Note that using a different web browser will not remove IE from a Windows system, and other programs may invoke IE, the WebBrowser ActiveX control, or the HTML rendering engine (MSHTML). It is possible for a different browser on a Windows system to invoke IE to handle MHTML protocol URLs.
I have had this same problem as well but it hasn't been limited to Firefox. Netscape has shown similar issues. Problems haven't been limiited to my windows box at work either. At home I run Mac OS X and firefox has problems there as well. Safari seems to do fine. At work I have resorted to (ironically) using IE for all my slashdot viewing and Firefox for everything else because of it.
I don't think thats how it works. An entry is a song downloaded or a "tell a friend email sent" but a download is a purchased and downloaded song. From the rules is says
How You Win. Winners will be determined by the order of the Entries received. One 20GB iPod will be awarded for each
Entry sent immediately following the 99,999th song downloaded, until iTunes reaches its 100 millionth Entry. (One 20GB iPod will be given away for the 95,100,000th Entry, 95,200,000th Entry,....99,900,000th Entry).
I read this as saying that tell a friend entries do nothing for the download count. When the download count gets to the point just prior to the win, then and only then is the term "Entry" useful.
Just checked - Apple has posted the official rules now. No mailing necessary actually. It says
How To Enter. You will automatically be entered into the Promotion by: 1) downloading a song from iTunes (any Free Download Single of the Week will be deemed an ineligible entry); or 2) a free alternative means of sending an email to Apple at itunes100@apple.com via the iTunes "Tell a Friend" feature (a song download or Tell a Friend email will be deemed an "Entry(ies"). The "Tell a Friend" feature can be easily accessed at iTunes by selecting a song, and clicking the "Tell a Friend" link that is displayed for that song. One Entry will be automatically submitted for each song downloaded or Tell a Friend email sent. The Promotion begins following the downloading of the 95,000,000th iTunes song, and ends with the downloading of the 100 millionth Entry ("End Date"). Only Entries submitted in this time period will be accepted.
In this analysis he presents the results of an ANOVA (Analysis of Variance). This reminds me of the saying: "If your only tool is a hammer, every problem looks like a nail". The tool the author is using is ANOVA and so he is trying to force the data into that form. Hovever, the assumptions of any ANOVA is that the data is independent, normally distributed, and has constant variance. The response ranges from 1.0 to 5.0. I haven't taken the test myself and do not know if users were allowed to select non-integer values or not but even if they were we can see from the graphs he does present that most of the responses were near the upper bound of 5.0. This type of response is clearly not normally distributed. ANOVA is faily resistant to departures from normality but one would need to fully explore the degree of the departure before placing any weight to the confidence intervals presented. My gut feeling here is that it is highly skewed and will present confidence intervals smaller than what they should be (data is forced to be artifically close due to the upper bound and having so many people report values close to that upper bound). The data can probably be viewed as independent but it must be recognized that this is an assumption. Constant variance departures may be a problem as higher responses are less variable than middle responses (due to the upper bound again). It would probably be much better to use a non-parametric test alternative to ANOVA such as a Kruskal-Wallis.
Scope of inference: This is not a random sample from any population and as such cannot be interpreted to represent anything more than the perceptions of the respondants themselves.
-chris
Slashdot Mirror
They have a USB version that would work with your computer.
Your information might be available online but it is definitly NOT the Census Bureau that is sharing the information with the resellers. As one very familiar with the inner workings of the Bureau I can tell you that NO personally identifiable information comes out of the Bureau - ever - even to other government agencies. Your information is protected under title 13 of the United States Code. We even hide data for small area estimates if it is unusual enough that someone might be able to figure what your values are based on their knowledge of that geographic area. We have teams of people that write programs that test this. Anyone who has access to your information is subject to a severe penalty (including jail time) if they distribute outside the Bureau (or even within if those getting it do not have a reason to look at it). The trust that the Bureau would lose if it were ever to go against this policy would cause response to drop and make the estimates extremely poor - it's just not worth it. I can't speak for other government agencies - but the Census Bureau does not and will not ever give personally identifiable data to anyone.
He is not kidding. Excel is a very poor choice for all but the most simple types of data analysis. The biggest probelms IMHO is that it allows the users to just click away at options until something they like appears. Very rarely will users give any thought to all the assumptions that are made when performing a regression anaylsis. But it's there, right...it must be ok to do! So if the linear regression doesn't look ok, they try a squared or cubic regression until the lines match up with their data and they sit back satisfied that they have discovered a fundamental relationship between two or more variables. Just because Excel can draw a pretty line with an equation on a graph doesn't mean that it should. Excel does a disservice to its users by providing a crippled but easy to use set of tools. I want to second the grandparent's support of the excellent open source statistical package R. It is easy to use, has a very large and very active user base, and has a huge number of extensions for all types of techniques. Its graphical capabilities are expecially advanced. I would never publish a graph made from Excel without extensive reformatting, but graphs from R (or Splus) look at home in any journal. (for more on good and bad graph design see Edward Tufte's "The Visual Display of Quantitative Information").
hmmm. 36-24-26 sounds pretty good to me!
No - just the spelling gene. :)
Under his system, christmas eve, christmas, new years eve, and new years day are all on saturday or sunday. This will happen in 2005 in our current system and us guv'ment types don't get any extra days off. Not that we don't get enough days off anyway (think inauguration day, ex-pres dies, an inch of snow falls, etc) but hey, everyone likes those extra days around christmas.
I had similar experiences in South Africa. I would tell people that I was from Alaska and almost no one knew is was part of the US. Most thought is was part of Canada, some thought it was a country by itself, and a few thought it was an island in the pacific next to Hawaii (cuz that's where it is on all those maps of the US they see).
Dude, you have obviously never met my parents.. Sadly, though, I don't think they are alone in their ignorance. If it isn't on the desktop then for all intents and purposes - it doen't exist.
It was reported on Slashdot the day after it appeared in this June 26 edition of the Washington Post
Try this: Department of Homeland Security and this: US-CERT
I have had this same problem as well but it hasn't been limited to Firefox. Netscape has shown similar issues. Problems haven't been limiited to my windows box at work either. At home I run Mac OS X and firefox has problems there as well. Safari seems to do fine. At work I have resorted to (ironically) using IE for all my slashdot viewing and Firefox for everything else because of it.
In this analysis he presents the results of an ANOVA (Analysis of Variance). This reminds me of the saying: "If your only tool is a hammer, every problem looks like a nail". The tool the author is using is ANOVA and so he is trying to force the data into that form. Hovever, the assumptions of any ANOVA is that the data is independent, normally distributed, and has constant variance. The response ranges from 1.0 to 5.0. I haven't taken the test myself and do not know if users were allowed to select non-integer values or not but even if they were we can see from the graphs he does present that most of the responses were near the upper bound of 5.0. This type of response is clearly not normally distributed. ANOVA is faily resistant to departures from normality but one would need to fully explore the degree of the departure before placing any weight to the confidence intervals presented. My gut feeling here is that it is highly skewed and will present confidence intervals smaller than what they should be (data is forced to be artifically close due to the upper bound and having so many people report values close to that upper bound). The data can probably be viewed as independent but it must be recognized that this is an assumption. Constant variance departures may be a problem as higher responses are less variable than middle responses (due to the upper bound again). It would probably be much better to use a non-parametric test alternative to ANOVA such as a Kruskal-Wallis. Scope of inference: This is not a random sample from any population and as such cannot be interpreted to represent anything more than the perceptions of the respondants themselves. -chris