No announcement yet.
  • Filter
  • Time
  • Show
Clear All
new posts

  • Pooled Panel or Cross Sectional Data

    Good Morning I have a query regarding a data set I am handling. I am trying to see the out migration occouring due to climate change. For the out migration module I am using the DHS 2017-2018 survey’s migration module and for the climate variable I have used SPEI. I have imported the SPEI which is available from 1901 to 2015 by matching the year when the migration occoured. I am confused as to what model should I apply now:
    The model I am thinking of currently is logistic regression where the education would be as follows:
    Migrated from (Rural Area=0, Urban area=1)= B0+ B1region+B2place of residence+B3gender+B4 education+B5wealthindex + B6 SPEI for 48 Months+B7 SPIE for 24 Months+ B8SPEI for 12 Months +B9SPEI for 6 months+B10 SPEI for 3 months
    Howver, I am very confused as to what exactly is the nature of my sample now i.e. whether it is cross sectional even after I have matched the SPEI with the year migrated or it is a pooled panel . If it is a pooled panel can I apply fixed effect model to it. What would you suggest the model to be

  • #2
    You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex. Remember, we're mostly not from your area so referring to the DHS survey tells us nothing.

    You haven't really told us the structure of your data. Do you have multiple annual observations on individuals? Observations by region or what? Adding an annual variable to the data set doesn't automatically make it a panel data set or rather make a panel data analysis most appropriate.