【摘 要】
：
Low response rate characterizes nowadays sample surveys. Furthermore, the resulting response set is biased. Special adjustment methods are needed to reduce
【机 构】
：
UniversityofTartu,Estonia
【出 处】
：
The 24th International Workshop on Matrices and Statistics(第
论文部分内容阅读
Low response rate characterizes nowadays sample surveys. Furthermore, the resulting response set is biased. Special adjustment methods are needed to reduce the bias in the estimates. The necessary auxiliary information is not always available, or not powerful enough. In last years, balance of the response set has become a study issue. It is measured by a distance between multivariate means of auxiliary variables in a response set and in a sample. For distance zero or nearly zero, the response is balanced. There are methods to intervene during data collection to get nearly balanced response: The Threshold method, the Equal proportions method (S(a)rndal and Lundquist, 2014). But the effect of this activity for the estimation phase is still unknown. The question is whether estimates from the balanced response set are more accurate than the estimates from the unbalanced one in case the same auxiliary information is used (or variations of auxiliary information). A joint study by S(a)rndal, Lumiste, Traat (2015) gives an indication that balancing the response set is worth the efforts-it protects against highly biased estimates. The results are delivered in the presentation.
其他文献
This paper studies an adaptive lasso-based approach for model selection of a finite order autoregressive [AR(p)] models. We fit an AR($p_{n}$) model to the
Perturbation analysis of Markov chains provides bounds on the e_ect a change in the Markov transition matrix has on the corresponding stationary distributio
Assume that a general linear mixed-effects model y = Xβ + Zγ + ε is given. In this talk, Ill introduce how to derive analytical expressions of the best l
Integer-valued generalized autoregressive conditional heteroscedasticity (GARCH) models have played an important role in time series analysis of count data.
We present a philatelic introduction to magic squares, beginning with the well-known 4×4 Dürer magic square in Melencolia I (1514) depicted in sheetlets f
In this talk we consider the problem of testing (a) sphericity and (b) intraclass covariance structure under a Growth Curve model. The maximum likelihood es
With a history of more than 3000 years, magic squares still are mysterious in various aspects. We in this paper give a comprehensive review and study on cla
Our motivation in this talk is the 13th-century Anxi iron-plate doubly-classic 6x 6 bordered magic square discussed by Kai-Tai Fang at the 22nd International
The R2 statistic in fixed-effects regression settings is routinely interpreted as a measure of proportion of variability explained by the model. Because R2
I will reflect on selected experiences with Simo Puntanen concentrating especially on the scientific adventures we have shared around the globe during the l