article thumbnail

Excellent Analytics Tips #20: Measuring Digital "Brand Strength"

Occam's Razor

When their competitors are ramping down (perhaps due to their inflexibility), Amazon can read the market much better (notice Christmas 2010 as well) and are well placed (thanks to Paid and Organic Search strategies) to grab all these new people who are coming into the market to shop. You have to hand it to the Marketing folks at Amazon.

article thumbnail

Estimating the prevalence of rare events — theory and practice

The Unofficial Google Data Science Blog

This problem can be phrased as an optimization problem — given some fixed review capacity how should we sample videos? But importance sampling in statistics is a variance reduction technique to improve the inference of the rate of rare events, and it seems natural to apply it to our prevalence estimation problem.

Metrics 98
Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Fitting Bayesian structural time series with the bsts R package

The Unofficial Google Data Science Blog

SCOTT Time series data are everywhere, but time series modeling is a fairly specialized area within statistics and data science. They may contain parameters in the statistical sense, but often they simply contain strategically placed 0's and 1's indicating which bits of $alpha_t$ are relevant for a particular computation. by STEVEN L.

article thumbnail

Changing assignment weights with time-based confounders

The Unofficial Google Data Science Blog

For example, imagine a fantasy football site is considering displaying advanced player statistics. A ramp-up strategy may mitigate the risk of upsetting the site’s loyal users who perhaps have strong preferences for the current statistics that are shown. One reason to do ramp-up is to mitigate the risk of never before seen arms.

article thumbnail

Using random effects models in prediction problems

The Unofficial Google Data Science Blog

We often use statistical models to summarize the variation in our data, and random effects models are well suited for this — they are a form of ANOVA after all. Journal of the American Statistical Association 68.341 (1973): 117-130. [5] Journal of the American Statistical Association, Vol. bandit problems). 7] Nicholas A.

article thumbnail

The Definitive Guide To (8) Competitive Intelligence Data Sources!

Occam's Razor

In May 2010 (!). The secret to making optimal use of CI data lies in one single realization: You must ensure you understand how the data you are analyzing is collected. It will probably be the category that will grow the most because frankly in context others look rather sub optimal. The Optimal Competitive Analysis Process.

Metrics 123
article thumbnail

10 Fundamental Web Analytics Truths: Embrace 'Em & Win Big

Occam's Razor

Part of it is fueled by a vocal minority genuinely upset that 10 years on we are still not a statistically powered bunch doing complicated analysis that is shifting paradigms. As of 2010 I still have a lot more years that I spend in the traditional data warehousing / business intelligence world than in web analytics. This is sad.

Analytics 118