Data Analysis (EDA) and Data Visualization with Python

Vigneshwer Dhinakaran

Ny artikel i Qvintensen webbtidskrift

There is so much data in today’s world. Modern businesses and academics alike collect vast amounts of data on myriad processes and phenomena. While much of the world’s data is processed using Excel or (manually!), new data analysis and visualization programs allow for reaching even deeper understanding. The programming language Python, with its English commands and easy-to-follow syntax, offers an amazingly powerful (and free!) open-source alternative to traditional techniques and applications.

Read more....

Statistical reform: Improving data analysis skills in research

StatsLife
Addressing the deficits in statistical thinking and data analysis skills across academia should be a priority, says RSS fellow Darren Dahly, principal statistician and senior lecturer in research methods at HRB Ireland Clinical Research Facility Cork. Here he explains why.

Read more....

10 Powerful Python Tricks for Data Science you Need to Try Today

Analytics Vidhya

10: rpy2: R and Python in the Same Jupyter Notebook!

R and Python are two of the best and most popular open-source programming languages in the data science world. R is mainly used for statistical analysis while Python provides an easy interface to translate mathematical solutions into code.

Here’s the good news – we can use both of them in a single Jupyter Notebook! We can make use of both ecosystems and for that, we just need to install rpy2.

Read more...

Facts for Future - Nordic Statistical Meeting 2019

Nordic Statistical Meeting 2019



Statistics Finland has the pleasure of inviting you to the 28th Nordic Statistical Meeting. The conference takes place in Helsinki on 26 to 28 August 2019 under the theme Facts for Future.

Register here...

Papers, Presenters and Speakers

Top 10 Big Data Analytics LinkedIn Groups

Analytics Insight
LinkedIn is the chief place for enterprise innovation experts to accumulate, connect with each other, share thoughts, and network with other people. If you are a specialist who works in the data science or predictive analytics space, or you’re simply searching for extra insights into what the smartest in the business are discussing, LinkedIn professional groups are an extraordinary place to begin

Read more....

The registered reports revolution Lessons in cultural reform

Ny artikel i Qvintensen webbtidskrift av Chris Chambers

The rise of the “registered report” – a type of research article that is reviewed and accepted before results are known – offers lessons for the current debate surrounding p‐values and significance.

On 12 November 2012, as my train sped towards London, I received one of the most important emails of my life. The message cordially informed me that the publisher of Cortex, a scientific journal that I had recently joined as an editor, had approved our request to launch a new type of article called a registered report.

Läs mer....

Artificial intelligence is no silver bullet for governance

Artificial intelligence is no silver bullet for governance https://t.co/Sq4leKi4cz via @financialtimes

— lars lyberg (@LybergL) August 16, 2019

RSS & PSI's joined webinar: Survival Analysis

https://youtu.be/nafus8nqwIs

Presenters: 

Peter Thall (MD Anderson) 

Bayesian non-paramedic statistics: A new toolkit for discovery in cancer research 

Kyu Ha Lee (Harvard) 

Bayesian semi-paramedic analysis of semi-competing risks data: investigating hospital readmission after a pancreatic cancer diagnosis

Is Python Strangling R to Death?

Datanami
As programming languages go, there’s no denying that Python is hot. Originally created as a general-purpose scripting language, Python somehow became the most popular language for data science. But is Python’s fame coming at the expense of R? Yes, according to some folks in the IT industry, who say R is a dying language.

Read more...

‘Abandon statistical significance’

Nature
In March, three statisticians and more than 800 signatories argued for scientists to abandon the entire concept of statistical significance. “We are not calling for a ban on P values,” wrote the researchers. It’s just time to stop bucketing results into ‘statistically significant’ and ‘statistically non-significant’ because of the powerful sway such dichotomies hold on the human mind. “We must learn to embrace uncertainty,” they argue.

Nature | 11 min read (from March)
Statistician Blake McShane tells the Nature Podcast why he co-authored a call to abandon statistical significance.

Sommarhetta och torka i Europa under tolv århundraden

Stockholms universitet

Genom historien har södra Europa tenderat att bli torrare och norra Europa fuktigare under varmare klimatperioder. Samtidigt faller de nutida trenderna i sommartorka hittills inte utanför ramen för de senaste tolv århundradenas naturliga variationer. Det visar en ny artikel publicerad av en internationell forskargrupp som studerat sambandet mellan sommartemperatur och torka runt om i Europa.

Läs mer....

When interviewers select HHs and respondents ....

When interviewers select HHs and respondents, *high* response rate can mean *low* data quality. POQ article using @ESS_Survey, w A Koch @gesis_org

Instead of a graphic, here's a video demonstrating the idea behind the paper.#openaccess @AAPOR @srmsasahttps://t.co/2xPRY3ARP7 pic.twitter.com/U0hDCX2dru

— Stephanie Eckman (@stephnie) August 12, 2019

Statistics: Online Courses

Training and Tutorials on LinkedIn Learning

Keep learning in moments that matter.
Courses for every step of your career. Instructors with real-world experience.
Start my free monthNeed to train your team? Learn More.

Get the training you need to stay ahead with expert-led courses on Statistics.

Read more....

RSS Prize Winners Best presentations of RSC 2018

https://youtu.be/bSoaIGAMAMI

Using Health Economics in the Design, Monitoring and Analysis of Adaptive Clinical Trials 

Laura Flight - University of Sheffield 

Bayesian Nonparametric Methods for Stochastic Epidemic Models 

Rowland Seymour - University of Nottingham 

Parallelisation of a Common Changepoint Detection Method 

Samuel Tickle - Lancaster University

Busting the Single Biggest Myth About Machine Learning

MarTech Advisor

Machine learning only lives up to its hype and is truly helpful when working in conjunction with the added statistical tools found in most regular models and human data experts, who can identify whether the models produced reliable results and alter them accordingly. It’s only through this continuous fine-tuning process that you’re truly able to unlock its power.

Read more....

Getting things into perspective: The BIG picture

From climate4you

Fig.2. Reconstructed global temperature over the past 420,000 years based on the Vostok 

ice core from the Antarctica (Petit et al. 2001). The record spans over four glacial 

periods and five interglacials, including the present. The horizontal line indicates 

the modern temperature. The red square to the right indicates 

the time interval shown in greater detail in the following figure.

The diagram (Fig.2) shows a reconstruction of global temperature based on ice core analysis from the Antarctica. The present interglacial period (the Holocene) is seen to the right (red square). The preceding four interglacials are seen at about 125,000, 280,000, 325,000 and 415,000 years before now, with much longer glacial periods in between. All four previous interglacials are seen to be warmer (1-3oC) than the present. The typical length of a glacial period is about 100,000 years, while an interglacial period typical lasts for about 10-15,000 years. The present interglacial period has now lasted about 11,600 years.

Read more....

The Demand for Right-Wing Extremism

The Demand for Right-Wing Extremism (DEREX) Index was designed by @Pol_Cap 🇭🇺 using responses collected from 29 of our #survey questions.

It includes country scores for welfare chauvinism, anti-establishment #attitudes, right-wing values and fear.https://t.co/4lVcyeyW9K pic.twitter.com/q1I7JFwoL3

— European Social Survey (@ESS_Survey) August 1, 2019

How to Make Baseline Charts in R

FlowingData

By shifting the baseline to a reference point, you can focus a line chart on relative change, which can improve the visibility of smaller categories.

Read more....

Anna Rosling Rönnlund - Medgrundare Stiftelsen Gapminder

Foto: Mattias Ahlm/Sveriges Radio

Sommar & Vinter i P1 | Sveriges Radio

Creativ chef för Stiftelsen Gapminder som jobbar med att skapa en lättförståelig faktabaserad världsbild. Startades med hennes man Ola Rosling och svärfar Hans Rosling.

Medförfattare till den internationella bästsäljaren Factfulness: tio knep som hjälper dig att förstå världen. I fjol skänkte Bill Gates boken till alla studenter som tog examen i USA och i Sverige kan alla gymnasietreor ladda ner den gratis.

Var med och utvecklade verktyget Trendalyzer som med rörlig ”bubbelgrafik” visar globala statistiska förhållanden.

"Jag kommer att prata om varför jag, som aldrig tänkt på mig själv som en siffermänniska, har ägnat hela mitt yrkesliv åt just siffror och statistik om människors liv och levnadsstandard. Och varför jag, som aldrig skulle gifta mig, blev pangkär och började jobba ihop med min man – och min svärfar, för att göra världen mer begriplig."

Global Innovation Index 2019 - Sweden #2

Global Innovation Index 2019 – 12th Edition

Switzerland is the world’s most innovative country followed by Sweden, the United States of America (U.S.), the Netherlands and the United Kingdom (U.K.), according to the GII 2019.

Read more...

Hands-on statistics – How random are you? (low tech)

https://youtu.be/isUX6hbWgb4

Hands-on statistics activities have been developed for our members to use in careers fairs, at festivals and in schools. This video demonstrates one of the activities in use. Written instructions for this hands-on activity are available at www.rss.org.uk/hands-on

Hands-on statistics – How random are you? (high tech)

https://youtu.be/y3QoEycT6d4

Hands-on statistics activities have been developed for our members to use in careers fairs, at festivals and in schools. This video demonstrates one of the activities in use. Written instructions for this hands-on activity are available at www.rss.org.uk/hands-on

Julian Wheatland: I want there to be a more balanced view of Cambridge Analytica

Salon.com
In an interview, Wheatland explains why he agreed to be part of the Netflix documentary “The Great Hack”

"The Great Hack," a new Netflix documentary, painfully relives the 2016 presidential election by following the personal journeys of key players in the Cambridge Analytica/Facebook data scandal. David Carroll, a media professor who spends the film doggedly trying to retrieve his personal data from Cambridge Analytica. British journalist, Carole Cadwalladr, who exposes how Cambridge Analytica harvested data from more than 50 million Facebook users to create targeted ads for the Trump 2016 campaign. And Brittany Kaiser, the former director of business development at Cambridge Analytica, turned whistleblower. While Kaiser and former Cambridge Analytica employee Chris Wylie, surfaced as whistleblowers when the events unfolded in real time after the election, “The Great Hack” introduces us to a new character: Julian Wheatland, Cambridge Analytica’s acting CEO. Unlike the other former Cambridge Analytica employees we know, Wheatland has a different perspective on the demise of the company. If you still have questions after watching “The Great Hack,” you might find answers here. Salon interviewed Wheatland at the San Francisco screening of the “The Great Hack” on July 22.

Read more...

Till minne: Bengt Swensson

DN.SE

Bengt Swensson, Örebro, har avlidit i en ålder av 82 år. Han efterlämnar hustru och barn med familjer.

Bengt var professor emeritus i statistik vid Örebro universitet. Hans specialområde var matematisk och statistisk metodik för urvalsundersökningar (sample surveys), speciellt så som denna används i framställning av officiell statistik.

Läs mer....

Applications of Statistics: Statistics and Genetics: A fruitful relationship

https://youtu.be/5lFHlPWcGMg

Presentation of contents:

RSS Statistical Excellence Awards ceremony 2019

https://youtu.be/cwx_s_D9nAk

Our annual Awards ceremony is the ideal time to celebrate all the fantastic work that has been done with statistics and data over the past year.

Regional Statistics - European Forum for Geography and Statistics

European Forum for Geography and Statistics

We are happy to say that the new issue of Regional Statistics has been published!


METHODOLOGICAL ISSUES

Marie Haldorson: High demand for local area level statistics – How do National Statistical Institutes respond?
http://www.ksh.hu/docs/hun/xftp/terstat/2019/rs090106.pdf

STUDIES

Fernando Delbianco – Andrés Fioriti– Fernando Tohmé : Quantifying worldwide economic distress http://www.ksh.hu/docs/hun/xftp/terstat/2019/rs090108.pdf

Bacsosz Sztavrosz: Analysis of the geographical diversification of financial instruments http://www.ksh.hu/docs/hun/xftp/terstat/2019/rs090110.pdf

UseR! 2019 Spatial workshop part I

UseR! 2019 Spatial workshop part I

Since data collections can only be done somewhere, and at some time, all data is, in principle spatial and temporal. In many cases location are implicit, and for instance encoded as ID of an object. In other cases, locations are encoded with coordinates.

Read more...

What's happening with statistics education?

Tes News
Statistics experts Will Hornby and Darren Macey tell Lucy Rycroft-Smith how the subject is being transformed by technology – and how teachers can embrace the change.

It’s been said that there needs to be change in statistics education in schools. Do you agree?

Darren Macey: It has been suggested by many that the growth of computer science in industry and the growing role of data science in the commercial world is not currently well served by education, at least until you get to university level.

Read more....

Visualisering med öppna data och öppen källkod