How can I include year-fixed effects into monthly panel data?

[Stephan Meier]

Hi,

I have monthly panel data on 350 mutual funds over the period January 2007 to December 2015. Here is a small extract of my data:

* Example generated by -dataex-. To install: ssc install dataex
clear
input int FundID str7 Date double(TotalAssets Flows Return Expenses)
1 "oct2012"  75.4    .95325         -8.2476               1.35
1 "nov2012"  76.2   3.49890        -29.2548               1.349
1 "dec2012"  75.7    .46943        -13.5072               1.35
1 "jan2013"    77  -5.46289         86.1624               1.35
1 "feb2013"  98.9  28.90355         -5.544                1.35
1 "mar2013" 107.7   6.25727         31.6872               1.35
end
label var FundID "FundID" 
label var Date "Date" 
label var TotalAssets "FundSize" 
label var Flows "Flow" 
label var Return "SiReturn" 
label var Expenses "Expense"

I am using xtreg and fe to regress Flows on Return and some controls. In the literature, year-fixed effects are used in many of these models. How can I implement year-fixed effects when I have monthly data?

Kind regards,
Stephan

[Carlo Lazzaro]

Stephan:
welcome to this forum.
To create the (numerical) categorical variable -year- you may want to try:

. gen year = substr(Date,4,4)

. destring year,g(num_year)

Then you can include -num_year- in the right-hand side of your panel data regressione equation using -fvvarlist- notation (see related help file):

xtreg <depvar> <otherindepvars> i.year, fe

[Stephan Meier]

Thank you very much for your answer. It works perfectly for my monthly panel data set. I also have the same data set at a quarterly level. What would be the code to generate year-fixed effects for quarterly panel data?

[Carlo Lazzaro]

Stephan:
see -help substr()-.

[Stephan Meier]

Thanks for your help Everything worked perfectly.