Mario Fiorini, "Fostering Educational Enrolment Through Subsidies: The Issue of Timing", Journal of Applied Econometrics, Vol. 27, No. 5, 2012, pp. 741-772. This paper uses data from the National Child Development Study (NCDS). Data from the initial survey in 1958 and from the following 6 sweeps (1965, 1969, 1974, 1981, 1991 and 1999-2000) are used to construct information about parental background, cognitive abilities, educational choices and labor market outcomes. The NCDS data are confidential. Access is granted by the Economic and Social Data Service (ESDS): http://www.esds.ac.uk/longitudinal/access/ncds/l33004.asp Once the data are available, there are 3 steps to follow. Step 1 Given the initial data set, I first pull together the files and then derive the variables of interest. This is done running the file NCDS.do (Stata) in the attached zip file mf-stata.zip. The DO file calls other files that are included in the zip file. The final outcome is a Stata file called NCDS.dta which is used at the following step. [please note that directories within the DO files have to be adjusted according to where the data files and the do files have been placed] Step2 I then convert the data to panel form and prepare them for use within Matlab. This is done in the file versionXV.do (which calls historyXV.do). These files are in mf-stata2matlab.zip The final outcome is a Stata file called versionXV.dta which can be converted to Matlab format using programs such as StatTransfer Step3 To estimate the model, run the JMP.m file in Matlab. The estimation is done using a combination of two minimization routines e04ucf from the NAG library and fminsearch from the Matlab statistics toolbox, so users must have access to these routines. The policiy counterfactuals and the welfare analysis are done using the file Policy.m. All the relevant files are included in the zip file mf-matlab.zip. All .do and .m files are ASCII files in DOS format. Unix/Linux users should use "unzip -a". For any problem or query please contact me at: mario.fiorini [AT] uts.edu.au