I am a newbie in statistics, however my job requires me to do a Multivariate time series analysis.

I have 32 observations. Main independent variable, dependent variable and 4 other variable which I will control. This is basically to understand how GDP (i.v) effects the main D.V.

Now i am confused, what to do? which model to use? log? and lag values? checking data whether it is stationary, how should i do that?

Can Please someone tell me step by step direction, how should I go ahead with this?

please help.

  • $\begingroup$ There are too many questions here for a Q&A website. I think it would be better if you provide more information about your variables/data, and especially what you have tried so far. If you have no/very limited knowledge about time series analysis, reading some introductory texts and checking tutorials might be more helpful. $\endgroup$ – T.E.G. Nov 7 '16 at 4:36
  • $\begingroup$ Thank you for your reply. I have number of crimes as the D.V and GDP per capita as I.V, from a single country for last 40 years. Trying to find if increase in GDP effects the crimes. I have 5 other control variables from world bank, like education, health, social welfare, development, etc. I do not know what to do now, data is time series. What should be my first step? checking stationary or non-stationary? then which model should I use? should I take log values? and which model should I apply like vector auto regression? and how to check for robustness? please help. $\endgroup$ – MIS87 Nov 7 '16 at 15:47

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.