Rothschild Lecture: From Small Data to Big Data and Back: Statistics and Data Science
1 hour 1 min,
884.84 MB,
MPEG-4 Video
640x360,
29.97 fps,
44100 Hz,
1.93 Mbits/sec
Share this media item:
Embed this media item:
Embed this media item:
About this item
Description: |
Bickel, P (University of California, Berkeley)
Wednesday 17th August 2016 - 16:00 to 17:00 |
---|
Created: | 2016-08-23 16:44 |
---|---|
Collection: | Theoretical Foundations for Statistical Network Analysis |
Publisher: | Isaac Newton Institute |
Copyright: | Bickel, P |
Language: | eng (English) |
Abstract: | Modern statistics began with R.A.Fisher’s seminal work in the early twentieth century, with important predecessors such as Karl Pearson, contemporaries such as J.Neyman and successors such as A. Wald. The focus was on small data sets or summaries of larger ones. Analyses were based on simple models and given in terms of estimates, testing and confidence bounds. With the advent of big data, the size of datasets, their complexity and heterogeneity, and the lack of theory to build mechanistic probability models brought new issues to the fore. I will discuss some of these issues: 1. Computation 2. Prediction 3. Sparsity/dimension reduction4. Stability/robustness 5. Reduction to small data |
---|
Available Formats
Format | Quality | Bitrate | Size | |||
---|---|---|---|---|---|---|
MPEG-4 Video * | 640x360 | 1.93 Mbits/sec | 884.84 MB | View | Download | |
WebM | 640x360 | 672.32 kbits/sec | 300.38 MB | View | Download | |
iPod Video | 480x270 | 522.11 kbits/sec | 233.27 MB | View | Download | |
MP3 | 44100 Hz | 250.15 kbits/sec | 111.76 MB | Listen | Download | |
Auto | (Allows browser to choose a format it supports) |