Browse: Home / Statistics
By Kamil Bartocha on February 8, 2015

Imagine you are playing the Heads or Tails game and count a successful conversion (win) when the coin lands Heads. A fair coin will land 50% of the time Heads and 50% of the time Tails. If you were playing a game with only a single coin toss in each round, you would have expected […]

Posted in Modeling and forecasting, Statistics | Tagged binomial distribution, confidence intervals, conversion rate |

By Krzysztof Osiewalski on November 29, 2014

In this article we give some hints on how to use your machine in most efficient way while programming in R and when this can be achieved.

Posted in R, Statistics | Tagged parallel, R |

By Krzysztof Zawadzki on November 29, 2014

“I think data-scientist is a sexed up term for a statistician…. Statistics is a branch of science. Data scientist is slightly redundant in some way and people shouldn’t berate the term statistician.” Nate Silver (applied statistician)

Posted in Data, Statistics | Tagged data science, data scientist, modern data scientist |

By Kamil Bartocha on November 23, 2014

Generalized Linear Models (GLMs) extend the ordinary Linear Regression and allow the response variable y to have an error distribution other than the normal distribution. GLMs are great because: They are easy to understand. Most statistical packages contain functions to fit and interpret the resulting model. Linear regression or logistic regression is sufficient for a lot […]

Posted in Modeling and forecasting, Statistics |

By Krzysztof Osiewalski on October 5, 2014

One of the frequently asked questions by marketers is what shall we expect from any market turbulences. This can be an increase in competitors’ spend on advertising, beginning of pricing war or any outlier of current market conditions. Let us address this issue on an example of a competitors high discount price using impulse response […]

Posted in Modeling and forecasting, Statistics |

By Krzysztof Osiewalski on September 26, 2014

When spending significant amount of money on TV (or, more generally, above the line advertisement) the ROI calculation is the fist task that goes to analytics or data science unit within marketing structure. The question to answer is quite hard though: there is no tracking, no digital tools can be applied. Even using things like […]

Posted in General marketing, Modeling and forecasting, Statistics | Tagged Bayesian prediction, casualimpact, impact of TV advertisement, TV ROI |

By Kamil Bartocha on September 6, 2014

Learning statistics is a very important step on the path to becoming a data scientist. It is not an easy subject and many people are often off-put by the complex and convoluted explanations. Luckily, more and more easy to digest tutorials, ebooks and courses become available on the internet. Here is a small selection to […]

Posted in Statistics |

By Krzysztof Osiewalski on August 17, 2014

While positioning the brand in the market, the most important question to ask is who we want to communicate with. With a poor understanding of the customer base this might result in gently saying ‘not so outstanding’ results. If your customers are posh yuppies and you start going for a TV ad with how pricy […]

Posted in Statistics |

By Kamil Bartocha on August 10, 2014

In the last post we looked at the statistics behind simple A/B testing (you can find the whole article here). What if you would like to test more than two alternatives on the website? Working with multiple page layouts requires a statistically sound methodology to confirm results. A/B/n Testing (for lack of a better name) […]

Posted in Statistics | Tagged a/b testing, statistics, testing |

By Kamil Bartocha on August 3, 2014

A/B testing has become the standard and popular way of optimizing website and campaign structure. Tools like Google Analytics Content Experiments and Webtrends Optimize make the test setup effortless. Unfortunately, the common questions remain – Is my sample size big enough? Are my results statistically significant? With a little bit of R we can answer […]

Posted in Statistics | Tagged a/b testing, R, statistics, testing |