Pearson Correlation in Sleep Studies

Click For Summary
The discussion centers on the use of Pearson correlation in sleep studies to compare device measurements based on acceleration values. Concerns are raised regarding the appropriateness of Pearson correlation for potentially non-linear data, as the values obtained from devices may not exhibit a linear relationship. The inquiry highlights a lack of clarity around the specific metrics being compared and the overall goals of the investigations. Additionally, there is an emphasis on the need for more accessible explanations of technical terms and methodologies in sleep research. Understanding the nature of the data and the objectives of the studies is crucial for accurate analysis and interpretation.
trustnoone
Messages
17
Reaction score
0
Hi guys, so I've been researching sleep studies and I've been looking at comparison on devices used, and most of them seem to obtain a magnitude value based on the acceleration seen on the device by the user.

What I'm wondering about though is that the comparison between devices seem to be using the Pearson Correlation.
Example:
http://www.journalsleep.org/Articles/290214.pdf

http://www.sciencedirect.com/science/article/pii/S0165027000003642

http://www.itc-ltd.co.jp/pdf/Kushida_et_al.pdf

But from what I read, the Pearson correlation only works with linear correlations, while I would assume the values based here would be quite random values, and while I would imagine there is a correlation say between the devices, I wouldn't imagine it to be linear which I thought was what the Pearson correlation needed?

Am I wrong? I will admit, I don't understand the correlation when I tried to read up on it.
 
People aren't likely to read specialist papers in order to find out what "a magnitude value based on the acceleration seen on the device" means. Magnitude of what? What is the goal of the investigation? What aspect of devices is being compared?
 

Thread 'Area of Overlapping Squares'

Here is a little puzzle from the book 100 Geometric Games by Pierre Berloquin. The side of a small square is one meter long and the side of a larger square one and a half meters long. One vertex of the large square is at the center of the small square. The side of the large square cuts two sides of the small square into one- third parts and two-thirds parts. What is the area where the squares overlap?
View full post »

Similar threads

MHB Visual illustration of Pearson correlation coefficient r
  • · Replies 1 ·
Replies
1
Views
2K
Graduate I need a Straight Compact Linear data model
  • · Replies 2 ·
Replies
2
Views
2K
Kalman Filtering with missing observations
  • · Replies 6 ·
Replies
6
Views
4K
Graduate Correlation between parameters in a likelihood fit
  • · Replies 3 ·
Replies
3
Views
2K
Atomic displacements, replacements, and radiation damage of structural materials
  • · Replies 1 ·
Replies
1
Views
1K
Undergrad Two-body correlation function computation
  • · Replies 1 ·
Replies
1
Views
3K
Two-Phase Pressure Drop (I need an expert)
  • · Replies 0 ·
Replies
0
Views
1K
Using correlation coefficients as x in a regression?
  • · Replies 2 ·
Replies
2
Views
2K
Graduate Project Progress Report and possible Radio Astronomy Technique?
  • · Replies 8 ·
Replies
8
Views
928
Do MRI machines cause heart attacks and seizures?
  • · Replies 13 ·
Replies
13
Views
3K