Marco Francesconi and Cheti Nicoletti, "Intergenerational Mobility and Sample Selection in Short Panels", Journal of Applied Econometrics, Vol. 21, No. 8, 2006, pp. 1265-1293. The data we used are from the first eleven waves of the British Household Panel Survey (BHPS) collected over the period 1991-2001. Our main analysis is restricted to 2691 men (or sons) born between 1966 and 1985, who have at least one valid interview over the panel period under study. This represents our Full Sample which contains information on sons' occupational characteristics and those of fathers. Fathers' variables are collected retrospectively by asking the respondents (the sons) to report their father's occupation when they were 14 years old. All the individuals in the Full Sample who could be successfully matched to their father are part of the subsample, which we refer to as the Restricted Sample. This restricted sample can be selected by choosing individuals for whom the variable match takes the value 1. Finally, to evaluate the potential bias due to measurement error for the fathers' long-run permanent status (occupational prestige), we used a third sample, call Supplemental Sample, which is composed of 1434 men whose sons were born between 1966 and 1985. Both data files, which are ASCII files in DOS format, are zipped in the file mndata.zip. Missing data are indicated by a period (.). Full sample: full.dat (number of observations 2691, number of variables 15) Three lines per observation pid cross wave person identifier birth year son was born agefm father's age for people with match=1 region region 1 inner london 2 outer london 3 r. of south east 4 south west 5 east anglia 6 east midlands 7 west midlands conurbation 8 r. of west midlands 9 greater manchester 10 merseyside 11 r. of north west 12 south yorkshire 13 west yorkshire 14 r. of yorks & humberside 15 tyne & wear 16 r. of north 17 wales 18 scotland lnrph11 house price index race ethnic group membership -9 missing or wild -8 inapplicable -7 proxy respondent -2 refused -1 don't know 1 white 2 black-Caribbean 3 black-African 4 black-other 5 Indian 6 Pakistani 7 Bangladeshi 8 Chinese 9 other ethnic group match dummy indicating individuals who can be matched with their father vcathol dummy indicating people catholic and attendant vprotest dummy indicating people protestant and attendant votherrel dummy indicating people of other religion denomination and attendant HGfather father's Hope-Goldthorpe occupational prestige HGf1 HGfather14 father's Hope-Goldthorpe occupational prestige HGf2 HGfather14me father's Hope-Goldthorpe occupational prestige HGf3 HGsonm son's Hope-Goldthorpe occupational prestige HGs1 HGsonmmin son's Hope-Goldthorpe occupational prestige HGs1 Supplemental sample: supple.dat (number of observations 1434, number of variables 5) pid cross-wave person identifier HGfatherr Hope-Goldthorpe occupational prestige HGfSS agefather current wave father's age HGfm Hope-Goldthorpe occupational prestige average HGfSS agefm average father's age