Posts Tagged ‘stats’

Nullius in verba: A crash course in understanding numbers | The Economist

February 18, 2017

Nullius in verba: A crash course in understanding numbers | The Economist


A Field Guide to Lies and Statistics. By Daniel Levitin. Dutton; 292 pages; $28. Viking; £14.99.

Similar to:

How statistics lost their power – and why we should fear what comes next | William Davies | Politics | Th e Guardian

January 30, 2017

How stats lost their power via @alexvespi Death of #DataScience in a “post-truth” world; anecdotes v elitist numbers

for those cold, lonely winter evenings…

July 24, 2016

Guess the correlation Perhaps a useful sanity check for data from published papers. It’s so easy to fool oneself.

How does multiple testing correction work?

June 13, 2016

How does multiple-testing correction work Intuition for teaching: genome-wide error rate on a single gene v family

Spurious Correlations

January 25, 2016

.@fionabrinkman @BioMickWatson @iddux Spurious Correlations
( related to Stat Frankenstein (

At Nearly 90, ‘Super Bowl’ Stock Analyst has a streak going – WSJ

January 18, 2016

SuperBowl Stock Analyst has a streak #Statistical Frankenstein concept from Wall Street perhaps useful for genomics

10 types of regressions. Which one to use?

December 8, 2015

10 types of #regressions. Which one to use? Pitfalls of common approaches, eg linear or logistic via @KirkDBorne

IBM Research: Preserving Validity in Adaptive Data Analysis

September 23, 2015

Preserving Validity in Adaptive Data Analysis Using differential #privacy for correct #stats even w/ test-set reuse

“A common next step would be to use the least-squares linear regression to check whether a simple linear combination of the three strongly correlated foods can predict the grade. It turns out that a little combination goes a long way: we discover that a linear combination of the three selected foods can explain a significant fraction of variance in the grade (plotted below). The regression analysis also reports that the p-value of this result is 0.00009 meaning that the probability of this happening purely by chance is less than 1 in 10,000.

Recall that no relationship exists in the true data distribution, so this discovery is clearly false. This spurious effect is known to experts as Freedman’s paradox. It arises since the variables (foods) used in the regression were chosen using the data itself.

We found that challenges of adaptivity can be addressed using techniques developed for privacy-preserving data analysis. These techniques rely on the notion of differential privacy that guarantees that the data analysis is not too sensitive to the data of any single individual. We rigorously demonstrated that ensuring differential privacy of an analysis also guarantees that the findings will be statistically valid. We then also developed additional approaches to the problem based on a new way to measure how much information an analysis reveals about a dataset.

The Thresholdout Algorithm

Using our new approach we designed an algorithm, called Thresholdout, that allows an analyst to reuse the holdout set of data for validating a large number of results, even when those results are produced by an adaptive analysis.


Science Isn’t Broken | FiveThirtyEight

August 22, 2015

Science Isn’t Broken by @cragcrest Great (but cynical) description of “p-hacking” & “researcher degrees of freedom”

Multiple hypothesis testing in genomics – Goeman – 2014 – Statistics in Medicine – Wiley Online Library

August 17, 2015

Multiple hypothesis testing in genomics Nice overview, comparing familywise error & FDR control + FDP estimation

This paper presents an overview of the current state-of-the-art in multiple testing in genomics data from a user’s perspective. We describe methods for familywise error control, false discovery rate control and false discovery proportion estimation and confidence, both conceptually and practically, and explain when to use which type of error rate. We elaborate the assumptions underlying the methods, and discuss pitfalls in the interpretation of results. In our discussion we take into account the exploratory nature of genomics experiments, looking at selection of genes before or after testing, and at the role of validation experiments.