Message:

<p>[QUOTE=&quot;Roerbakmix, post: 4545254, member: 100731&quot;][USER=93416]@EWC3[/USER], <i>probably</i> everybody thinks in probabilities (e.g. what&#039;s the chance of a road traffic accident when I cross this cross section; should I eat this piece of very attractive fruit without knowing whether it&#039;s poisonous or not, etc.). Though I do not know Gorad, I mostly agree with his statement that <i>significance testing</i>, i.e. a formal approach to probabilities should be done with caution (I disagree that formal significance testing should be abandoned, as there is not something as &#039;all formal significance testing&#039;. Should we abandon I2 as a measure of heterogeneity in meta-analysis? Probably, but not always. Should we be cautiousness when interpreting an R2 in linear regression. Definitely. Should we stop reporting a p-value only instead of the standard error or another measure that allows to form conclusions yourself? Absolutely.&nbsp; </p><p><br /></p><p>I regularly teach statistics to medical students as a PhD clinical epidemiology (which is a very sexy job these days, though I have nothing to do with viruses <img src="styles/default/xenforo/clear.png" class="mceSmilieSprite mceSmilie2" alt=";)" unselectable="on" unselectable="on" />) It is pointless to just &quot;bully people with math&quot; without explaining what&#039;s the fuss about (actually, my last paper with a clinical message was very technical, and rejected by all journals until I removed the formulae and put them in the supplement ...<img src="styles/default/xenforo/clear.png" class="mceSmilieSprite mceSmilie65" alt=":meh:" unselectable="on" unselectable="on" />). However, as a medical doctor, I have to be able to read, interpret and distill information from clinical papers, which usually present data in such a way that fits the data (or not). Most students really don&#039;t really bother, and skip the methods section of the article (with all the hocus pocus statistics) but clinical papers can be extremely dangerous when conclusions are incorrectly derived from wrong interpretation of data (either intentionally or not). Thus, in my opinion, teaching students &quot;tough math/stats&quot; in general is important, but teaching students to <i>read critically</i> is way more important.[/QUOTE]</p><p><br /></p>

Your name or email address:

Do you already have an account?

• No, create an account now.
• Yes, my password is:
• Forgot your password?

Stay logged in