Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 0 down vote favorite

I have a household travel survey where information about travel characteristics were obtained from a sample of households. The respondents were given a diary and a GPS device to log their trips for a single day. However, for some respondents additional travel days were collected from the GPS device. Because the additional days of available data are closely correlated with respondents' diary day data, it is not correct to treat these data simply as independent data points. On the other hand, it would be wasteful and unnecessary to completely discard the additional data. So my question is the following:

  1. How do I treat the additional data?

  2. How do I weight this additional data?

Any pointers to the literature is appreciated.

share|improve this question
2  
What kinds of analyses will you be performing with these data? – whuber♦ Sep 4 '12 at 12:29
Will be using the data to estimate, calibrate, and validate travel demand models. So need to understand how to develop weights for the additional data. – krishnan Sep 4 '12 at 14:01
1  
I believe answers will depend on precisely how you will do this estimation and calibration. Providing more specifics therefore could make your question more answerable. – whuber♦ Sep 4 '12 at 14:33
The estimation/calibration is a mix of choice and regression models. Eg., we will estimate the choice of destination available to the household as a choice model. – krishnan Sep 4 '12 at 16:59

Know someone who can answer? Share a link to this question via email, Google+, Twitter, or Facebook.

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.