0
$\begingroup$

I am doing a project on R commander and the project says, "The set of exoplanets discovered to this day is a sample of all exoplanets that exist in the universe. Discuss whether you think this sample is random (i.e., representative of the population)." How do I calculate this on R commander?

$\endgroup$
  • 3
    $\begingroup$ I believe you're being asked to think rather than calculate. $\endgroup$ – Scortchi - Reinstate Monica May 13 '15 at 13:36
  • $\begingroup$ ok but how can I prove it? That's what I'm not sure of.. $\endgroup$ – alexander sarandiev May 13 '15 at 13:58
  • 1
    $\begingroup$ Asking if the sample's random is short for "was it obtained by (simple) random sampling?". Unless you have either data on undiscovered exoplanets or theoretical predictions to compare to your sample, you need to think about the methods used to detect exoplanets. $\endgroup$ – Scortchi - Reinstate Monica May 13 '15 at 15:10
  • $\begingroup$ I only have data on exoplanets discovered. So that means I draw a conclusion based on the quantity of exoplanets discovered? $\endgroup$ – alexander sarandiev May 13 '15 at 16:05
  • 1
    $\begingroup$ I think you can assume it's a small proportion of the number of exoplanets out there. But can you assume "each individual has the same probability of being chosen at any stage during the sampling process"? (Did you look at the Wikipedia articles I gave links to?) $\endgroup$ – Scortchi - Reinstate Monica May 13 '15 at 16:12
2
$\begingroup$

OK, so you have a big bias on your sample which is the way they are discovered, their ellipse size (distance), size, speed (frequency), reflectiveness, etc. The trick is accounting for this. Most of the big, close, reflective, or frequent exoplanets must be found already, not the same for the small slow, or dark. Simply because we can't see them. So, your sample is NOT a random sample of the exoplanet population, this means you can't infer from the discovered ones the characteristics of the entire population. You can infer for that subset of the exoplanet population with this characteristics. If you had the chances of discovery for small versus big/ dark and reflective/... you could tell the characteristics of the entire population... but you don't have that no do you!

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.