statistics

A Case Study of Using Bayesian Inference for Decision MakingImage by the author.One question many of us come across while shopping on Amazon is: how do I compare two ratings? Amazon ratings give us two important pieces of information: the distribution of ratings (how many were five stars, four stars, three stars, two stars or one star) and how many reviews each product received. Comparing distributions can be pretty straightforward: we can compare the average ratings between two products and then decide. How do we…

Formula, Definition, Examples, & Python ImplementationPhoto by Pop & Zebra on UnsplashA statistical test called the z-test is run on data that roughly fit the normal distribution, i.e., for data that is not skewed. The z-test can be applied to test differences in proportions between two samples or even one sample for assessing hypotheses. For a population with known variance, it determines whether or not the means of two extensive samples differ. Depending on our choice of hypothesis, a z-test can be categorized…

Learn the math and methods behind the libraries you use daily as a data scientistImage by AuthorTo more formally address the need for a statistics lecture series on Medium, I have started to create a series of statistics boot camps, as seen in the title above. These will build on one another and as such will be numbered accordingly. The motivation for doing so is to democratize the knowledge of statistics in a ground-up fashion to address the need for more formal statistics training in the data science community. These…

Putting a percentage on the likelihood of a nuclear disaster can feel icky—like you’re boiling down the immensity of human suffering into a spreadsheet. “I think what people dislike about this is that people are thinking about the unthinkable,” says Spieghalter. But confronting the unthinkable is unavoidable if we want to reduce the risk of nuclear war now and in the future. “The risk of nuclear war is probably much higher than many of us might want to assume,” says Anders Sandberg, who researches risk at the University…

Statistics at a glance for data science: standard guidelinesImage By AuthorStatistics is a powerful mathematical field. I’m saying “powerful” because it helps us to infer a population outcome from sample data. As it can infer population outcome, it can also be used for the big picture (like overall impact, future forecast, etc.). Statistics is nothing but a combination of some merely isolated topics. Moreover, Statistics discovers new semantics within these topics, which sometimes paves the way for new opportunities.…

Statistics in R Series: Deviance, Log-likelihood Ratio, Pseudo R² and AIC/BICPhoto by Chris Liverani on UnsplashIntroductionIn simple logistic regression, we try to fit the probability of the response variable success against the predator variable. This predictor variable can be either categorical or continuous. We need to quantify how good the model is. There are several goodness-of-fit measurements that indicate the goodness-of-fit.A discrete random variable can often take only two values: one for success and 0 for…

CONSERVATION Once-controversial fish delisted A small fish famous for drawing the first U.S. Supreme Court ruling on the Endangered Species Act was removed last week by the U.S. Fish and Wildlife Service from the list of species under threat of extinction. In 1975, the agency declared the snail darter (Percina tanasi) endangered, concluding that construction of a dam on the Little Tennessee River would doom the 9-centimeter-long animals. Although the court upheld…

We encounter statistics every day, but it is not always easy to interpret them appropriately. During her doctoral thesis work in the abstract field of number theory, Dutch mathematician Ionica Smeets noticed that it was very difficult for laypeople to find understandable scientific explanations of statistics. So she decided to change that. Now Smeets authors books, writes for newspapers and speaks about her field on television. She is widely known in her home country of the Netherlands, where she mediates between science…

Relationship between the degree of preference for painting color compositions and color statistics. Credit: Toyohashi University of Technology A research team led by Professor Shigeki Nakauchi of Toyohashi University of Technology conducted an experimental study of the color composition preferences of 31,353 participants, for a total of 1,200 paintings with artificially manipulated color compositions. The group also…

Learn the math and methods behind the libraries you use daily as a data scientistImage by AuthorTo more formally address the need for a statistics lecture series on Medium, I have started to create a series of statistics boot camps, as seen in the title above. These will build on one another and as such will be numbered accordingly. The motivation for doing so is to democratize the knowledge of statistics in a ground up fashion to address the need for more formal statistics training in the data science community. These…