you see, in a study whereby one was not able to gather relevant data for ones study and one then decides to use the average of some years in modified Jones model which requires the use of cross sectional research design. Can this approach work?
I am not sure if I understand your question, but I assume you are referring to the use of longitudinal data on the same individuals and then longitudinal data on cross-sectional data. If so, then yes, you can certainly use both approaches in an evaluation. I am attaching a couple of papers I recently wrote which describes the interrupted time series approach (as well as introduces a software program I wrote that conducts these analyses). I suggest you give it a read, since it may provide you with some ideas of how to proceed.
Ariel
Article Conducting Interrupted Time-series Analysis for Single- and ...
Article Applying a propensity-score based weighting model to interru...
Rosemary -
I am not familiar with the "Jones model," but the problem with mixing cross sectional and time series data is that your definitions for estimation, and for estimated variance in particular, are incompatible. They can both be useful, but the assumptions/bases for estimation are different. But, usefulness depends upon your application. Please see the paper at the attached link for more on this.
Cheers - Jim
https://www.researchgate.net/publication/275365705_When_Prediction_is_Not_Time_Series_Forecasting
Research When Prediction is Not Time Series Forecasting
Perhaps you are looking for a "forward looking variable" as noted in this source I just found on the internet:
https://books.google.com/books?id=eOKNtlPHfeUC&pg=PA438&lpg=PA438&dq=Forward-looking+Jones+Model&source=bl&ots=9lzoRRlz5w&sig=TN4QJAVsY2WjPdjiClv8OuWr1k8&hl=en&sa=X&ved=0CBwQ6AEwAGoVChMI7Lv7sPqhxwIVSVg-Ch2h4wag
Sorry though, I cannot personally vouch for it, as I found this just now out of curiosity from seeing your question. If you apply, please apply with caution. There may be substantial information on the internet on the "modified forward looking Jones model."
I am very grateful for all your response. The truth is I am now more knowledgeable. Most importantly, I appreciate the google book site sent to me by James R. Knaub. Thank you!
- Badges
- Science topic
- Similar topics
- Linguistics
- Philology
- Language
- English