Improving Efficiency of Model Based Estimation in Longitudinal Surveys Through the Use of Historical Data


  • Roberto Gismondi ISTAT, Istituto Nazionale di Statistica



In this context, supposing a sampling survey framework and a model-based approach, the attention has been focused on the main features of the optimal prediction strategy for a population mean, which implies knowledge of some model parameters and functions, normally unknown. In particular, a wrong specification of the model individual variances may lead to a serious loss of efficiency of estimates. For this reason, we have proposed some techniques for the estimation of model variances, which instead of being put equal to given a priori functions, can be estimated through historical data concerning past survey occasions. A time series of past observations is almost always available, especially in a longitudinal survey context. Usefulness of the technique proposed has been tested through an empirical attempt, concerning the quarterly wholesale trade survey carried out by ISTAT (Italian National Statistical Institute) in the period 2005-2010. In this framework, the problem consists in minimising magnitude of revisions, given by the differences between preliminary estimates (based on the sub-sample of quick respondents) and final estimates (which take into account late respondents as well). Main results show that model

variances estimation through historical data lead to efficiency gains which cannot be neglected. This outcome was confirmed by a further exercise, based on 1000 random replications of late responses.


D. A. BLOCK, M. R. SEGAL (1989). Empirical Comparison of Approaches to Forming Strata Using Classification Trees to Adjust for Covariates, Journal of the American Statistical Association, Vol.84, 408, pp.897-905.

G. CICCHITELLI, A. HERZEL, G. E. MONTANARI (1992). Il campionamento statistico, Il Mulino, Bologna.

K. R. COPELAND, R. VALLIANT (2007). Imputing for Late Reporting in the U.S. Current Employment Statistics Survey, Journal of Official Statistics, Vol.23, 1, pp.69-90.

T. DALENIUS, J. L. HODGES (1959). Minimum Variance Stratification, Journal of the American Statistical Association, 54, pp.88-101.

K. DJERF (1997). Effects of Post-stratification on the Estimates of the Finnish Labour Force Survey, Journal of Official Statistics, 13, pp.29-39.

A. H. DORFMAN, R. VALLIANT (2000). Stratification by Size Revised, Journal of Official Statistics, Vol.16, 2, pp.139-154.

R. GISMONDI (2008). Reducing Revisions in Short-term Business Surveys, Statistica, LXVIII, 1, 85-115.

D. HEDLIN, H. FALVEY, R. CHAMBERS, P. KOCIC (2001). Does the Model Matter for GREG Estimation? A Business Survey Example, Journal of Official Statistics, 17, 4, pp.527-544.

J. G. IBRAHIM, H. ZHU, N. TANG (2008). Model Selection Criteria for Missing-Data Problems Using the EM Algorith, Journal of the American Statistical Association, Vol.103, 484, pp.1648-1658.

G. KALTON (2002). Models in the Practice of Survey Sampling (Revisited). Journal of Official Statistics, 18, pp.129-154.

J. R. KNAUB JR. (2004). Modeling Superpopulation Variance: Its Relationship to Total Survey Error, InterStat,

N. M. LAIRD, J H. WARE (1982). Random-Effects Models for Longitudinal Data, Biometrics, 38, pp.963-974.

R. LEHTONEN, C. E. SÄRNDAL, A. VEIJANEN (2003). The Effect of Model Choice in Estimation for Domains, Including Small Domains, Survey Methodology, 29, 1, pp.33-44.

R. J. A. LITTLE (1995). Modelling the Drop Out Mechanism in Repeated-Measures Studies, Journal of the American Statistical Association, 90, pp.1112-1121.

S. LUNDSTRÖM, C.E. SÄRNDAL (1999). Calibration as a Standard Method for Treatment of Nonresponse, Journal of Official Statistics, Vol.15, 2, pp.305-327.

M. PARK, W. FULLER (2008). The Mixed Model for Survey Regression Estimation, Journal of Statistical Planning and Inference.

C. E. SÄRNDAL, S. LUNDSTROM (2005). Estimation in Surveys with Non Response, J. Wiley & Sons, New York.

C. E. SÄRNDAL, B. SWENSSON, J. WRETMAN (1999). Model Assisted Survey Sampling, Springer.

E. V. SLUD, L. BAILEY (2010). Evaluation and Selection of Models for Attrition Nonresponse Adjustment, Journal of Official Statistics, Vol.26, 1, pp.127-143.




How to Cite

Gismondi, R. (2013). Improving Efficiency of Model Based Estimation in Longitudinal Surveys Through the Use of Historical Data. Statistica, 73(2), 177–199.