researchers to discuss recent advances and Our last invited session deals with the
applications of FDA. Topics addressed will ever-growing phenomenon of online
range from theoretic properties and infer- advertising and its implications for the
ence in functional linear regression to new statistician. Online advertising is a multi-
regularization techniques and the applica- billion-dollar industry—as evident from
tion of functional models to the analysis of the phenomenal success of companies such
complex data structures. as Google, Yahoo, and Microsoft—and
Three of our invited sessions address it continues to grow at a rapid rate. With
computations challenges driven by large- broadband access becoming ever-present,
scale and complex real-world applications. internet traffic continues to grow in vol-
These applications include online adver- ume and diversity, providing a rich supply
tising, social networks, and Wikipedia of inventory to be monetized. Fortunately,
data. Wikipedia is an important unin- the surge in supply also has been accom-
tended consequence of the internet. It panied by increase in demand, with more
demonstrates how valuable content can dollars being diverted to internet advertis-
be created by distributed volunteer effort ing relative to traditional advertising media, dimensional data, experimental designs to
and provides statisticians with a rich such as television, radio, or newspaper. learn emerging trends, protecting advertis-
data source on the connectivity between Marketplace designs that maximize rev- ers by constantly monitoring traffic quality,
knowledge domains, the investment/ enue by exploiting billions of advertising ranking search engine results, and modeling
growth trade-offs needed to bootstrap opportunities through efficient allocation extremely large and sparse social network
a distributed business, and the difficult of available inventory are key to success. behavior. The session about statistical chal-
problem of quality assurance in a climate Due to the massive scale of the problem, the lenges in online advertising and search will
of complex error sources. Also, from the only feasible way to accomplish this is by discuss many of these challenges.
standpoint of our professional society, learning the statistical behavior of the envi- It is not too late for section members
Wikipedia offers a new model for ser- ronment through massive amounts of data to contribute, as there are still open slots
vice the ASA can provide its members by constantly flowing through the system. This for topic-contributed sessions. For more
integrating a range of user-created code, gives rise to a series of challenging statisti- information about participating, contact
data, discussion, and articles. The session cal problems that include prediction of rare Wolfgang Jank, program chair, at wjank@
on analysis of Wikipedia data includes events from extremely massive and high-
rhsmith.umd.edu. n
analyses of key Wikipedia data sets and a
discussion of a possible Wikipedian future
for ASA publications.
Another internet phenomenon that
poses new and exciting challenges for the
statistician is the online social network.
Online social networks have become
ubiquitous. Sites such as MySpace and
Facebook create online communities
where users define their own social net-
works; other sites, such as blogs and
online forums, create de facto networks as
users link to each other’s opinions. There
has been a flurry of research on these net-
works on topics such as dynamic network
evolution, community detection, discov-
ering influential actors, etc. However,
most of this work has been done outside
of statistics—in the fields of machine
learning, artificial intelligence, and com-
puter science—and published at data
mining conferences. In the session about
analysis of massive online social networks,
we will discuss a variety of topics about
online social networks, blogs, and product
review networks. We also will discuss why
statisticians have been absent from this
field to date and what contributions our
community can make.
JANUARY 2008 AMSTAT NEWS 39
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84