torsdag 20 juni 2019

Regional Innovation Scoreboard

Regional Innovation Scoreboard | Internal Market, Industry, Entrepreneurship and SMEs

The Regional innovation scoreboard (RIS) is a regional extension of the European innovation scoreboard, assessing the innovation performance of European regions on a limited number of indicators. The RIS 2019 covers 238 regions across 23 EU countries, Norway, Serbia, and Switzerland. In addition, Cyprus, Estonia, Latvia, Luxembourg, and Malta are included at country level.

Read more....
Upplagd av kl.

Västsverige attracts more skilled workers than most regions in Europe

Newsworthy
The battle for talent within the EU is a story about both brain drain and gain. Of the 17 million people aged 15–64 migrating within the EU1, around 4.5 million are highly skilled workers and students. Factors known for attracting these people from their home regions are economic growth, higher wages, robust social security, linguistic and cultural similarity, relatively easier access to the labour market and higher employment rates.2

In contrast, the brain drain phenomenon arises when a region can not compete and suffers a permanent loss of skilled workers or students.

Västsverige is a “receiving” region, with more people moving in than out. In 2017 the net migration rate was 9.5 persons per 1,000 inhabitants.

Upplagd av kl.

Policy-Makers Play Catch-Up in Measuring the Digital Economy

The Canadian Press/Justin Tang
The Epoch Times
Policy-makers are pulling out all the stops to measure and understand the impacts of digitization on the economy. Organizations like Statistics Canada and the Bank of Canada realize that traditional methods can only go so far.

Upplagd av kl.

tisdag 18 juni 2019

Official statistics of Sweden – Annual Report 2018

Statistics Sweden

This report includes Statistics Sweden’s analysis of the quality evaluations that the agencies responsible for statistics (SAM) have conducted for the second consecutive year, in accordance with Section 13a of the Official Statistics Ordinance (2001:100).The analysis comprises all statistical areas and statistical products included in the System for official statistics.

Upplagd av kl.

Challenges and highlights in statistical consulting careers - Part one


https://youtu.be/8AyBK9jZSG4

A Life in Other People’s Data - Dr Shirley Coleman Everyone has interesting data and I find working as a consultant in an academic environment, having to bring in enough money to be self-supporting, to be fun and absorbing. Switching from car parts and shipping sensors in the morning to social housing and gait characteristics of older people in the afternoon keeps me on my toes. All my work revolves around data and the fascination of applying statistical thinking in research, business and industry; and using the findings in teaching and writing. I will give some examples of interactions with small and medium enterprises (SMEs) and some observations on methods of engagement.

Upplagd av kl.

söndag 16 juni 2019

Invandring behövs inte för att försörja en åldrande befolkning

Malte Andersson, ekolog, professor emeritus och Frank Götmark,
professor i ekologi, Göteborgs universitet, The Overpopulation Project.
GP - Debatt
Politiker och media hävdar ofta att landet behöver stor invandring för att möta behov då befolkningen åldras. Påståendet saknar täckning: seriösa demografiska och ekonomiska analyser pekar på att invandringen i stället medför ökad försörjningsbörda och sämre ekonomi för samhället, skriver ekologer Malte Andersson och Frank Götmark.

Upplagd av kl.

fredag 14 juni 2019

Python vs. R — Choosing the Best Programming Language for Data Science

@jonathanrados unsplash.com
Python vs. R 
After a few years of programming in both Python and R, I still struggle with this. Which language is the best language to use for Data Science? I like to think of myself as a technologist with a Statistics degree who is dabbling in Data Science. But, even I can’t shy away from the easy to use aspects of R. The allure of the R programming language stayed with me even as I ventured into Pandas, Numpy and Scipy. Python’s robust packages in machine learning frankly amaze me. It’s literally a one-stop shop. At the same time, it literally takes me less than 30 minutes to run simply statistical analysis in R to explore my dataset. Machine Learning and Deep Learning packages are now becoming the norm in R as well.

Upplagd av kl.

onsdag 12 juni 2019

The Brexit debate and the prosecutor's fallacy

Ny artikel i Qvintensen webbtidskrift



Politics is, by definition, adversarial. Its systems are designed to bring together people with competing views, so that they might argue over and decide on the “affairs of the cities” – which is the literal translation of the Greek word πολιτικά (Politiká). But, in recent times, politics has felt like it has become more adversarial, more polarised.

People on different sides of an argument seem entrenched in their views, and appear not to take the time to listen and carefully consider what their opponents are actually saying, with discussions – in the House of Commons, on TV and radio, and particularly on social media – often descending into mud-slinging.

Read more....
Upplagd av kl.

Vinnare och förlorare i det glesa Sverige – jämför själv

Dagens Samhälle

Sverigedemokraterna växer kraftigt i det glesbefolkade Sverige och Miljöpartiet har tappat sitt grepp om den svenska tätorten. Det är några av resultaten i Dagens Samhälles jämförelse av riksdagspartiernas valresultat i det täta och glesa Sverige. Här kan du själv utforska resultatet av vår unika granskning.

Läs mer...
Upplagd av kl.

måndag 10 juni 2019

Demoskop och Inizio går samman

Carin Wegenius och Karin Nelsson.
Resumé - Demoskop och Inizio

Analysföretagen Demoskop och Inizio går ihop under namnet Demoskop. Sammangåendet ska öppna upp för utveckling av nya erbjudanden inom både traditionella datainsamlingsmetoder samt inom big data och automatisering.

Läs mer....
Intervju i Dagens Analys
Kommentar från Novus och tweet:
--------------------------------------------
Medievärlden 2019-06-18: "Demoskop lämnar Expressen – blir Aftonbladets nya opinionsinstitut"
Upplagd av kl.
Etiketter:

söndag 9 juni 2019

Med Sabuni får SD dricka champagnen

Foto: Magnus Sandberg, Aftonbladet
Ledare - Aftonbladet
Den 26 april klockan 12:04 lades ett intressant dokument upp på ett slutet Facebookforum befolkat av många liberalpartister. Inlägget introducerades med att ett större opinionsinstitut "har på uppdrag av ett antal Nyamko Sabuni anhängare (Sic!) utfört en opinionsundersökning angående partiledarvalet. Undersökningen är statistiskt säkerställd."

Läser man den bifogade filen, som Aftonbladets ledarsida har fått tillgång till, framgår att nästan alla borgerliga väljare vill ha Nyamko Sabuni som partiledare i Liberalerna. Bland de som skulle rösta på M och KD föredrar hela 56 procent Sabuni medan bara 7 procent vill se Erik Ullenhag.

Dessutom visar mätningen att Sabuni kan dra nya väljare till partiet. Bland Alliansväljare uppger 40 procent att de skulle bli "något mer" eller "mycket mer" benägna att rösta på L med henne som ledare mot bara 13 för Erik Ullenhag och ynka 3 procent för Christer Nylander.

Siffrorna talar sitt tydliga språk, i varje fall om man ställer just dessa frågor. Men min undran är en helt annan, har offensiva opinionsmätningar använts på detta sätt i en intern partistrid förut?

Läs mer.... samt Demoskop-mätning i Expressen
Upplagd av kl.
Etiketter:

Machine learning dates back to at least 300 BC

From Mind Matters
The two main modifications of machine learning compared to typical statistical regression analysis is that (1) the quantities of data are huge, and (2) there is less reliance on the computer operator’s own understanding of statistics. So the “interface” to building and using the model is more straightforward and less reliant on the user understanding advanced statistics.

In summary, machine learning is not a new technique but is simply a modern extension of a tool that we have had in our toolbox since the days of the Babylonians. It continues to serve us well to help us extrapolate our data to estimate the value of unknown results and to help find the signal in noisy data.

Upplagd av kl.

lördag 8 juni 2019

Book review: Superior, by Angela D. Saini

Significance magazine
“The key to understanding the meaning of race is understanding power,” writes Angela D. Saini. Her new book, Superior, explores the roots of “race science” in the modern world. Though it mines human pre-history, it hinges around the major ideological warfare of the 20th century – a time when racial experiments within science were enthusiastically supported in Nazi Germany in its pursuit of policies of “racial hygiene”.

These policies were inspired by the eugenics movement of the 19th and early 20th century, which included statisticians such as Sir Frances Galton, as well as scientists and thinkers from other disciplines, who were convinced that humanity could be improved through selective breeding.

Upplagd av kl.

Inte farligare än så här

Fokus
Rädsla för och övertro på statistik, går hand i hand. Men bra statistik leder till frågor, snarare än svar. Även i frågan om invandring och brottslighet.

Det finns en ursvensk längtan efter definitiv statistik. Siffror och mätresultat som en gång för alla lägger en fråga till handlingarna. Fakta som sätter streck i debatten.

Upplagd av kl.

fredag 7 juni 2019

Beethoven's musical language decoded using data science

Beethoven | Wikimedia Commons
The Week
Researchers have characterised the musical language of German composer and pianist Ludwig van Beethoven for the first time, applying statistical techniques to unlock recurring patterns. Researchers from the Ecole Polytechnique Federale de Lausanne (EPFL) in Switzerland found that very few chords govern most of the music, a phenomenon that is also known in linguistics, where very few words dominate language.

Upplagd av kl.

torsdag 6 juni 2019

Leveraging SMS for Survey Research

Register Now For AAPOR's June Webinar
Text messaging is near ubiquitous in the U.S - most adults now own a cell phone, and a majority report that they check it on a regular basis for messages and other alerts. Research has also shown that text messages are significantly more likely than emails to be opened and to be opened quickly. Internationally, the use of text messaging is rapidly expanding, and Gallup research has found that in over 130 countries, the majorities of households now own a cellphone. With the widespread adoption of text messaging (SMS), how can researchers leverage this technology for reaching respondents and improving survey participation? This webinar will begin by summarizing the existing knowledge on SMS for survey research and discuss the strengths and weakness of SMS for data collection through the lens of total survey error. We will review the challenges and limitations of integrating text messaging into a research design and highlight areas of opportunity. Finally, we will walk through the steps for implementing SMS into communications and data collection.

Upplagd av kl.
Etiketter:

Observational Studies Explained

Statistics By Jim

Observational studies use samples to draw conclusions about a population when the researchers do not control the treatment, or independent variable, that relates to the primary research question.

Upplagd av kl.

fredag 31 maj 2019

Summer school in survey methodology (1-12 July 2019)

Upplagd av kl.

Measures to prevent data falsification

European Social Survey (ESS)
A working paper that assesses ways to address possible data falsification in the European Social Survey (ESS) has been published on our website.

Several measures initiated by the Core Scientific Team (CST) are already in place to ensure the best possible interviewing is undertaken in all participating countries.

Read more...
Upplagd av kl.

Survey methods seminar on response rates

Upplagd av kl.
Etiketter:

torsdag 30 maj 2019

Det finns nu valresultat att analysera

Upplagd av kl.

Vet valmyndigheten att underlaget för kampanjuppföljningen saknar felmarginaler och känd säkerhet?

Upplagd av kl.

LGBT+ resources for statisticians and data scientists

Significance magazine

In professional and classroom settings, we strive to communicate the intention of a respectful and productive interaction. In order to accomplish this, we all need to be mindful of our implicit biases, especially when beginning new professional relationships and establishing learning environments. The resources provided in this article are presented with this very intention.

Upplagd av kl.

onsdag 29 maj 2019

Brå: Ökningen av sexualbrott 2015–2017 beror inte på flyktingar

Brå tror att Metoo-upproret gjort att fler kvinnor
anmält sexualbrott. Foto: Janerik Henriksson/TT
SvD
Asylmottagandet 2015 förklarar inte den kraftiga ökningen av anmälda och rapporterade sexualbrott de senaste åren. Snarare är orsaken en ökad anmälningsbenägenhet och internet, skriver Brå i en ny studie.

Upplagd av kl.

5th International Conference on Big Data for Official Statistics kicks off with focus on SDGs

5th International Conference on Big Data for Official Statistics

The UN Global Working Group’s 5thInternational Conference on Big Data for Official Statistics took place from April 29th to May 3rd in the Land of a Thousand Hills — Kigali, Rwanda. This global event attracted representatives from NSO’s, the private sector, and government officials. A comprehensive agenda of three days of workshops and two days of conference provided the participants with information on tools, technologies, and resources, as well as several presentations around Sustainable Development Goals (SDGs), national statistics, and integration.

Upplagd av kl.

onsdag 22 maj 2019

New podcast explores why 'statistically significant' is so misunderstood

IMAGE: PHOTO WITH GRAPHIC OVERLAY AND QUOTE 'A SMALL 
P-VALUE IS LIKE A RIGHT SWIPE IN TINDER. IT MEANS YOU HAVE 
AN INTEREST. IT DOESN'T MEAN YOU'RE READY 
TO BOOK THE...view more 
CREDIT: MONCHU
EurekAlert! Science News: Featuring researcher and Executive Director of the American Statistical Association, Ron Wasserstein

'Statistical significance' is one of the most widely misunderstood phrases in science, according to a 2013 Scientific American article.

It's a controversial topic. Probability values (p-values) have been used as a way to measure the significance of research studies since the 1920s, with thousands of researchers relying on them since. With this reliance, though, comes misunderstanding and, therefore, misuse.

Upplagd av kl.

söndag 19 maj 2019

Karaoke in the Classroom Helps Students Master Statistics

From NBC
https://www.nbcdfw.com/news/local/Karaoke-in-the-Classroom-Helps-Students-Master-Statistics_Dallas-Fort-Worth-509926412.html
Upplagd av kl.

lördag 18 maj 2019

Nationella Trygghetsundersökningen 2018 från Brå riskerar att vilseleda, skriver flera debattörer

Foto: Hanna Franzén/TT
SvD

En granskning av Nationella Trygghetsundersökningen 2018 från Brå visar på uppseendeväckande brister, så stora att det kan befaras att NTU i praktiken vilseleder allmänhet, medier och politiker. Det skriver flera debattörer.

Läs mer...
Upplagd av kl.
Etiketter:

onsdag 15 maj 2019

Visual insights

Blog about Stats

In large amounts of data, information is hidden that can hardly be recognized with simple means. Special methods for data analysis are in demand and visualization techniques in particular help to overview the information gained and to pass it on in an understandable way.

Media have recognised the potential of statistical and other data years ago; this has led to what has been practised as data journalism in various large newspapers and also in newspaper co-operations.

Upplagd av kl.

måndag 13 maj 2019

Om åldersbedömningar och att lära sig av misstagen

Magnetröntgen av knä har använts på över 10000
ungdomar för åldersbedömningt
Ny artikel i Qvintensen webbtidskrift

Vi vill dela med oss av våra gemensamma erfarenheter och funderingar under det senaste året, då vi har jobbat med granskning av myndigheters missbruk av statistik. Vår förhoppning är att vi därmed kan ge goda råd för hur myndigheter ska undvika liknande misstag, hur vi som forskare bör agera och hur vi bör utveckla utbildningen för studenter som läser statistik.

Upplagd av kl.
Prenumerera på: Inlägg (Atom)