How R came to be

Uma entrevista sobre como surgiu o R

Uma entrevista sobre como surgiu o R

How R came to be

Statistician John Chambers, the creator of S and a core member of R, talks about how R came to be in the short video below. Warning: Super nerdy waters ahead.

Tags: , ,

introducing R to a non-programmer in one hour

Uma introdução muito rápida

Uma introdução muito rápida

Biostatistics PhD candidate Alyssa Frazee was tasked with teaching her sister, an undergraduate in sociology, how to use R. She had only one hour.

Once you load in a dataset, things start to get fun. We learned a whole bunch of stuff from this data frame, like how to do basic tabulations and calculate summary statistics, how to figure out if you have missing data, and how to fit a simple linear model. This part was pretty fun because my sister started leading the session: instead of me saying “I’m going to show you how to do this,” it was her asking “Hey, could we make a scatterplot?” or “Do you think we could put the best-fit line on that plot?” I was really glad this happened — I hope it meant she was engaged and enjoying herself!

This is the nice thing about R. There are so many built-in functions and packages that you can get something useful with a few lines of code, and you don’t really even have to know what a function is to get started (although you should eventually). Then you can go as far down the rabbit hole as you want.

Tags: , , , ,

The Age of Data

A era dos dados

A era dos dados

Whiteboards

The Age of Data

Actian Big Data Analytics Platform

Actian DataCloud Platform

Big Data Analytics

Creating Value from Big Data and Hadoop

A New World for Analytics

The Need for an Analytic Platform

Seamless Integration

Analytic Offload

Creating Business Value with Analytics

Tags: , , ,

Um bom texto sobre erros cometidos por profissionais no uso da estatística

Um bom texto sobre erros cometidos por profissionais no uso da estatística

Alex Reinhart, a PhD statistics student at Carnegie Mellon University, covers some of the common analysis mistakes in Statistics Done Wrong.

Statistics Done Wrong is a guide to the most popular statistical errors and slip-ups committed by scientists every day, in the lab and in peer-reviewed journals. Many of the errors are prevalent in vast swathes of the published literature, casting doubt on the findings of thousands of papers. Statistics Done Wrong assumes no prior knowledge of statistics, so you can read it before your first statistics course or after thirty years of scientific practice.

The text is available for free online, and there’s a physical book version on the way.

Tags: , , ,

Probability and Monte Carlo methods

Um bom texto de introdução à probabilidade e simulação de Monte-Carlo

Um bom texto de introdução à probabilidade e simulação de Monte-Carlo

This is a lecture post for my students in the CUNY MS Data Analytics program. In this series of lectures I discuss mathematical concepts from different perspectives. The goal is to ask questions and challenge standard ways of thinking about what are generally considered basic concepts. I also emphasize using programming to help gain insight into mathematics. Consequently these lectures will not always be as rigorous as they could be.

Tags

, , ,

Tags: , ,

Machine Learning MOOC

Um curso muito completo de machine learning

Um curso muito completo de machine learning

About the Course

Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you’ll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Finally, you’ll learn about some of Silicon Valley’s best practices in innovation as it pertains to machine learning and AI.

This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that you’ll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.

FAQ

  • What is the format of the class?The class will consist of lecture videos, which are broken into small chunks, usually between eight and twelve minutes each. Some of these may contain integrated quiz questions. There will also be standalone quizzes that are not part of video lectures, and programming assignments.
  • How much programming background is needed for the course?The course includes programming assignments and some programming background will be helpful.
  • Do I need to buy a textbook for the course?No, it is self-contained.
  • Will I get a statement of accomplishment after completing this class?Yes. Students who successfully complete the class will receive a statement of accomplishment signed by the instructor.

Tags: , , , ,

Why Predictive Modelers Should be Suspicious of Statistical Tests

Um excelente exemplo de correlações espúrias

Um excelente exemplo de correlações espúrias

Well, the danger is really not the statistical test per se, it the interpretation of the statistical test.

Yesterday I tweeted (@deanabb) this fun factoid: “Redskins predict Romney wins POTUS #overfit. if Redskins lose home game before election => challenger wins (17/18) http://www.usatoday.com/story/gameon/2012/11/04/nfl-redskins-rule-romney/1681023/” I frankly had never heard of this “rule” before and found it quite striking. It even has its own Wikipedia page (http://en.wikipedia.org/wiki/Redskins_Rule).

For those of us in the predictive analytics or data mining community, and those of us who use statistical tests to help out interpreting small data, 17/18 we know is a hugely significant finding. This can frequently be good: statistical tests will help us gain intuition about value of relationships in data even when they aren’t obvious.

Tags: , , ,

4 Faces of Big Data

Bom texto sobre os vários aspetos a considerar no Big-Data

Bom texto sobre os vários aspetos a considerar no Big-Data

The 4 Faces of Big Data Challenges You just Can’t Ignore

Date: October 20, 2013 Author: Varoon Rajani
Business Decision makers everywhere yearn for the right information that would help them make informed decisions.

Tags: , ,

Paddy – design a multi-stage survey

Jogo sério para desenho de inquéritos

Jogo sério para desenho de inquéritos

This game is a rice survey based on an actual survey carried out in Sri Lanka. In a small district there are 10 villages with a total of 160 farmers who each have one field in which to grow rice. A census of the area has been undertaken and the acreage cultivated by each farmer is known. There is now to be a crop cuttin survey whose main aim is to estimate the mean yield of rice per acre and hence the total production of rice in the district. The survey will also be used to investigate the use of fertilisers and the different varieties of rice used in the district.

The resources available allow for 30 plots to be sampled. The plots to be harvested are 1/80 acre but the yields are recorded in bushels per acre. Students use a multistage sampling scheme. For example:

  1. Select x villages
  2. From each village choose y fields
  3. Select z plots from each field

The game consists of 10 boxes each containing a number of envelopes, which themselves contain a number of slips of paper. The boxes represent a village so students select the boxes corresponding to their chosen villages. They open the boxes and select the envelopes labelled with their chosen field number. Information on the size of the field, the variety of rice used and the amount of fertiliser applied is also displayed on the envelope label. Finally, they select the slip of paper labelled with their chosen plot number and record the yield.

Tags: , ,

To the Woods – a detailed comparison of Sampling methods

Simulação para aprender amostragem simples e estratificada

Simulação para aprender amostragem simples e estratificada

To the Woods – a detailed comparison of Simple Random Sampling and Stratified Sampling

In this game the aim is to conduct a small survey to estimate the total number of trees in a forest and the proportion of large trees. A tree is considered ‘large’ if its diameter at breast height (DBH) is greater than 30cm. The area of forest from which the sample is to be taken is divided into two regions (‘East’ and ‘West’) by a river. Within each region it is possible to count the number of trees in any 50m x 50m plot. There are 168 plots in total – 96 to the West of the river and 72 to the East.

There are two alternative sampling solutions. Students take a sample of 14 plots and can either use simple random sampling or stratified sampling to choose them. They record the number of small trees, the number of large trees and the total number of trees for each of the 14 observations.

The game consists of 168 small pieces of card, which represent the plots, slipped into slits in a large piece of card representing the forest. A river can be drawn on the large piece of card to divide the forest into two regions. One side is labelled ‘West’ and the other ‘East’. The protruding sections of the plots are labelled with their region side (West or East) and plot number (1 to 96 and 1 to 72, respectively). The student pulls out the chosen plots and records the numbers of large and small trees, which is printed on the lower section of the plot.

Tags: ,