Hola <<First Name>>,

Avui és divendres i toca newsletter!

Esperem que hagis passat un bon estiu i que hagis pogut carregar les piles. Ens plau informar-te de les darreres notícies del grup. Recorda que pots trobar notícies de Newsletters antigues aquí.
Graphical abstracts

Journals are increasingly requesting the submission of a “graphical” or “visual abstract” alongside the body of the article. Research has shown that articles which have graphical abstracts are beneficial. The following article gives some advice to make a good graphical abstract.

Nou R package al GRBIO!

Klaus, Mireia i Lupe han creat un nou paquet de R GofCens que ja està disponible a CRAN! Aquest paquet permet fer gràfics i aplicar diferents tests per avaluar la bondat d'ajust de dades censurades per la dreta. Moltes felicitats als tres!

Paquet: aquí

Nova xerrada del Dani!

El passat juliol, durant els cursos d'estiu del CIMAT, en Dani Fernández va impartir la xerrada divulgativa "Hagamos la estadística comprensible". Podeu trobar el vídeo al link de sota.

Vídeo: aquí

Erasmus+ EngiMath

L’objectiu del projecte europeu EngiMath és compartir experiències d’avaluació i tècniques pedagògiques orientades a la docència de les matemàtiques en el context dels estudis d’enginyeria i definir un model d’aprenentatge online. En Carles Serrat lidera el node UPC d'aquest projecte.
 Més info: aquí
Article relacionat: aquí

Flash Reviews

  Recordeu que podeu difondre els vostres nous articles mitjançant els Flash Reviews del GRBIO Divulga omplint aquest formulari.

Si necessiteu ajuda amb el
formulari, podeu contactar amb el David i la Yovi.

Ofertes de feina

BIOINFORMATICClarivate, Barcelona. Topic: Advanced statistical and functional analysis of OMICs data. Contract type: Full time. More infohere.

PROGRAMMERLabcorp Drug Development, España. Topic: Statistical Programmer 2 within our Clinical Pharmacology statistical programming department. Contract type: Online. More infohere.

Pots trobar més ofertes de feina de Newsletters aquí

5 tips to write better papers

Maarten van Smeden is a medical statistician and epidemiologist. He wrote five simple ways to write a better scientific paper. 
1. Carefully formulate a specific research question that you can answer with data.
2. Stick to answering the research question, resist the temptation of finding more interesting stories to tell.
3. Reporting guidelines.
4. Most reporting guidelines come with an Exploration and Elaboration paper. These are gold mines of citations you can check for the best methods guidance there is.
5. Make sure the aims of your paper are clearly formulated on the final paragraph of the introduction.
Twitter thread

Statistical properties of RCT

Stephen Senn has recently written a paper on the bias in RCTs. He abstracts the concept of a RCT as a triple (β,b,s), where β is the primary efficacy parameter, b the estimate, and s the standard error (s>0). If the parameter β is either a difference of means, a logodds ratio or a log hazard ratio, allowing to assume that b is unbiased and Normall. This then allows us to estimate the joint distribution of the z-value z=b/s and the signal-to-noise ratio SNR=β/s based on a sample of 23 551 pairs (b,s) from the Cochrane database. The main finding was that many statistical quantities depend on (β,b,s) only through the pair (z,SNR). 

Causal analyses
of databases

Miguel Hernán has recently published an article about causal inference from observational data. Observational databases are often used to study causal questions. Before being granted access to data or funding, researchers may need to prove that “the statistical power of their analysis will be high”. The goal of a causal analysis is to quantify the effect as unbiasedly and precisely as possible, the solution to observational analyses with imprecise effect estimates is not avoiding observational analyses with imprecise estimates.
Contact with to access to the full text

This email was sent to <<Email Address>>
why did I get this?    unsubscribe from this list    update subscription preferences
Grup de recerca en estadistica i bioinformatica · C/ Jordi Girona 1-3 · Edifici C5 planta 2 · Barcelona, Barcelona 08034 · Spain

Email Marketing Powered by Mailchimp