China
Africa
Explore chapters and articles related to this topic
Introduction
Published in Robert M. Bethea, R. Russell Rhinehart, Applied Engineering Statistics, 2019
Robert M. Bethea, R. Russell Rhinehart
In order to guard against the misuse of statistics, it is necessary to realize that while the use of nonrandom samples may give you the same results as a random sample would provide, the chances are that the results would be inconsistent or even biased. A consistent estimator yields values that become progressively closer to the population parameter being estimated as the size of the sample becomes larger. An estimator is unbiased if its expected value is equal to that of the parameter or random variable itself. An efficient estimator is one that not only is unbiased and consistent but also has the smallest possible variance, or spread, about the average or central value. Randomly selected samples offer the best chance of obtaining efficient and effective estimators of population parameters. Only with such estimators can you hope to obtain valid results when you use statistics to help in making decisions.
Disaggregating Regressor Effects
Published in Norman Matloff, Statistical Regression and Classification, 2017
But there is more fundamental unfinished business to address. Does RFA even work in this setting? Is it estimating the right thing? For instance, as the sample size grows, does it produce a statistically consistent estimator of the desired population quantity?
C
Published in Phillip A. Laplante, Dictionary of Computer Science, Engineering, and Technology, 2017
consistent estimator an estimator whose value converges to the true parameter value as the sample size tends to infinity. If the convergence holds with probability 1, then the estimator is called strongly consistent or consistent with probability 1.
Integration of biological and statistical models toward personalized radiation therapy of cancer
Published in IISE Transactions, 2019
Xiaonan Liu, Mirek Fatyga, Teresa Wu, Jing Li
The form of Equation (11) is known as the probit model. The rationale for re-fitting a non-penalized model is that the -penalty is known to have a shrinking effect, which makes an -penalized model a good variable selection model, but not necessarily a good predictive model (Hastie et al., 2015). Next, we discuss two important statistical properties of the estimators , i.e., consistency and bias. In statistics, a consistent estimator is one that converges in probability to the true value of the parameter being estimated as the sample size goes to infinity. The bias of an estimator is the difference between the estimator’s expected value and the true value of the parameter being estimated. If the bias is zero, the corresponding estimator is called an unbiased estimator. A good estimator should be consistent and unbiased.