monfils 418_variable types

monfils 418_variable types - Sta$s$csandresearchdesign...

Info iconThis preview shows pages 1–7. Sign up to view the full content.

View Full Document Right Arrow Icon
Sta$s$cs and research design Lecture 4: Variables, measurement scales, validity Prof. Marie MonFls
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Stats examples?
Background image of page 2
NYT Ar’cle: Beware of too much sleep Jerome Siegel, professor of psychiatry at the University of California, Los Angeles, and the chief of neurobiology research at the V.A. Greater Los Angeles Healthcare System. "People who sleep more than the seven‐ to eight‐ hour average have a signiFcant reduc$on in lifespan, greater than that shown by people who sleep less than average."
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Reader comment, 6. Anon west coast Dr. Siegel clearly implies causa$on here‐‐that more sleep CAUSES shorter life span, and perhaps that's what the studies he's referring to actually show. But all he's told us is that longer sleep is CORRELATED WITH shorter life span, and there are all sorts of reasons why that could be so. There are many illnesses and condi$ons that cause weakness and fa$gue and people suFering from those oXen sleep more than 8 hours a night. So, the "shorter life span" may well be caused by condi$ons that have nothing to do with sleep per se, but that are also causing excessive sleep.This is so basic a point that it's hard to believe any reputable study could ignore it, but based on what Dr. Siegel says in this ar$cle, he seems to assume that if we sleep too much we'll get unhealthy, rather than (much more likely‐seeming) that if we're unhealthy, we'll sleep too much.
Background image of page 4
What is a variable?
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Opera$onal defni$ons • Opera$onal defni$ons – Allow a construct to be studied – IF two or more values are tested, the construct is a variable – IF only a single value is used, it is a constant • e.g., Gender specifc studies • Using constants limits the generality oF fndings • Both variables and constants can be part oF an experimental design.
Background image of page 6
Image of page 7
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 29

monfils 418_variable types - Sta$s$csandresearchdesign...

This preview shows document pages 1 - 7. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online