
Advanced Statistics Advanced Probability and Statistics Math Forum 
 LinkBack  Thread Tools  Display Modes 
January 29th, 2013, 05:52 AM  #1 
Newbie Joined: Oct 2012 Posts: 17 Thanks: 0  Regression Analysis of Survey Data
Dear Forum users, I want to test for dependence between two data sets: X = data set 1, Y = data set 2 Each data set contains 1000 values with discrete values in the set [1,2,...,10]. The value 1 represents "strongly disagrees" and 10 represents "strongly agrees". When i perform linear regression, the coefficient of the resulting line is 0.8. I interpret this as a dependence between the two sets. Questions: 1. Previously i have only performed regression analysis using continuous data, therefore I am a bit uncertain if what I am doing is OK  basically I am treating the discrete data as if it were continuous data. Is that OK? 2. I also want to use the regression as a predictor. E.g. given a new x value in the set X, I want to predict the associated y variable. However, since i use simple regression analysis the new yvalue can attain a continuous value (e.g. 5.4) which is clearly not a valid value. Should i round this value down to 5? 

Tags 
analysis, data, regression, survey 
Search tags for this page 
Click on a term to search for related topics.

Thread Tools  
Display Modes  

Similar Threads  
Thread  Thread Starter  Forum  Replies  Last Post 
Regression Analysis  Constructing a Model ((Need Help Ple  Olafson  Applied Math  1  April 15th, 2014 06:05 AM 
Question regarding regression analysis of discrete data  sydfremmer  Advanced Statistics  0  December 22nd, 2012 08:26 AM 
Data analysis using Independent Component Analysis (ICA)  ggyyree  Advanced Statistics  1  August 9th, 2012 03:48 AM 
Need help determining if Survey Company is Falsifying Data  SapperLT  Advanced Statistics  0  March 10th, 2012 06:40 AM 
Data analysis using Independent Component Analysis (ICA)  ggyyree  Real Analysis  0  December 31st, 1969 04:00 PM 