ARTICLE
ABSTRACT
The Colombian Observatory of Science and Technology -OCyT- developed, in 2009, a survey about understanding of Science and Technology in students of high school in Bogotá, Colombia. The sampling design was stratified according to the nature of school (public or private). Two sources of unit nonresponse were detected. The first one corresponds to schools that did not allowed to collect information. The second source corresponds to students who did not assist during the days when survey was applied. Estimates were obtained through two different approaches. Results obtained in both cases do not show visible differences when estimating ratios; even though, some great differences were observed when estimating totals. Results obtained using the second approach are believed to be more reliable because of the methodology used to handle item nonresponse.
KEYWORDS
Sampling design; nonresponse bias; calibration.
REFERENCES
DAZA, S. ED, (2011). Entre datos y relatos: percepciones de jóvenes escolarizados sobre la Ciencia y la Tecnología. Observatorio Colombiano de Ciencia y Tecnología, Bogotá.
HANSEN, M.H., and HURWITZ W.N. (1943). On the theory of sampling from finite populations. Annals of Mathematical Statistics 41, 517-529.
HORVITZ, D.G., and THOMPSON, D.J. (1952). A generalization of sampling without replacement from a finite universe. Journal of the American Statistical Association 47, 663-685.
R Development Core Team, (2011). A Language and environment for Statistical Computing, http_//www.r-project.org.
SÄRNDAL, C.E. and SWENSSON, B. and WRETMAN, J., (1992). Model Assisted Survey Sampling. Springer.
SÄRNDAL, C.E. and LUNDSTRÖM, S., (2005). Estimation in Surveys with Nonresponse. Wiley
