Searcharxiv⌕ Search

arXiv subjects

Paul Kabaila

Publications and source records attributed to Paul Kabaila.

42 records · Page 3Linked to original sources
arXiv2009

Computation of confidence intervals in regression utilizing uncertain prior information

We consider a linear regression model with regression parameter beta =(beta_1, ..., beta_p) and independent and identically N(0, sigma^2)distributed errors. Suppose that the parameter of interest is theta = a^T beta where a is a specified vector. Define the parameter tau = c^T beta - t where the vector c and the number t are specified and a and c are linearly independent. Also suppose that we have uncertain prior information that tau = 0. Kabaila and Giri (2009c) present a new frequentist 1-alpha confidence interval for theta that utilizes this prior information. This interval has expected length that (a) is relatively small when the prior information about tau is correct and (b) has a maximum value that is not too large. It coincides with the standard 1-alpha confidence interval (obtained by fitting the full model to the data) when the data strongly contradicts the prior information. At first sight, the computation of this new confidence interval seems to be infeasible. However, by the use of the various computational devices that are presented in detail in the present paper, this computation becomes feasible and practicable.

stat.CO↗
arXiv2009

Confidence intervals in regression utilizing prior information

We consider a linear regression model with regression parameter beta=(beta_1,...,beta_p) and independent and identically N(0,sigma^2) distributed errors. Suppose that the parameter of interest is theta = a^T beta where a is a specified vector. Define the parameter tau=c^T beta-t where the vector c and the number t are specified and a and c are linearly independent. Also suppose that we have uncertain prior information that tau = 0. We present a new frequentist 1-alpha confidence interval for theta that utilizes this prior information. We require this confidence interval to (a) have endpoints that are continuous functions of the data and (b) coincide with the standard 1-alpha confidence interval when the data strongly contradicts this prior information. This interval is optimal in the sense that it has minimum weighted average expected length where the largest weight is given to this expected length when tau=0. This minimization leads to an interval that has the following desirable properties. This interval has expected length that (a) is relatively small when the prior information about tau is correct and (b) has a maximum value that is not too large. The following problem will be used to illustrate the application of this new confidence interval. Consider a 2-by 2 factorial experiment with 20 replicates. Suppose that the parameter of interest theta is a specified simple effect and that we have uncertain prior information that the two-factor interaction is zero. Our aim is to find a frequentist 0.95 confidence interval for theta that utilizes this prior information.

stat.ME↗
arXiv2009

The Asymptotic Efficiency of Improved Prediction Intervals

Barndorff-Nielsen and Cox (1994, p.319) modify an estimative prediction limit to obtain an improved prediction limit with better coverage properties. Kabaila and Syuhada (2008) present a simulation-based approximation to this improved prediction limit, which avoids the extensive algebraic manipulations required for this modification. We present a modification of an estimative prediction interval, analogous to the Barndorff-Nielsen and Cox modification, to obtain an improved prediction interval with better coverage properties. We also present an analogue, for the prediction interval context, of this simulation-based approximation. The parameter estimator on which the estimative and improved prediction limits and intervals are based is assumed to have the same asymptotic distribution as the (conditional) maximum likelihood estimator. The improved prediction limit and interval depend on the asymptotic conditional bias of this estimator. This bias can be very sensitive to very small changes in the estimator. It may require considerable effort to find this bias. We show, however, that the improved prediction limit and interval have asymptotic efficiencies that are functionally independent of this bias. Thus, improved prediction limits and intervals obtained using the Barndorff-Nielsen and Cox type of methodology can conveniently be based on the (conditional) maximum likelihood estimator, whose asymptotic conditional bias is given by the formula of Vidoni (2004, p.144). Also, improved prediction limits and intervals obtained using Kabaila and Syuhada type approximations have asymptotic efficiencies that are independent of the estimator on which these intervals are based.

math.ST↗
arXiv2007

Confidence intervals for the normal mean utilizing prior information

Consider X_1,X_2,...,X_n that are independent and identically N(mu,sigma^2) distributed. Suppose that we have uncertain prior information that mu = 0. We answer the question: to what extent can a frequentist 1-alpha confidence interval for mu utilize this prior information?

math.ST↗
arXiv2007

Upper bounds on the minimum coverage probability of confidence intervals in regression after variable selection

We consider a linear regression model, with the parameter of interest a specified linear combination of the regression parameter vector. We suppose that, as a first step, a data-based model selection (e.g. by preliminary hypothesis tests or minimizing AIC) is used to select a model. It is common statistical practice to then construct a confidence interval for the parameter of interest based on the assumption that the selected model had been given to us a priori. This assumption is false and it can lead to a confidence interval with poor coverage properties. We provide an easily-computed finite sample upper bound (calculated by repeated numerical evaluation of a double integral) to the minimum coverage probability of this confidence interval. This bound applies for model selection by any of the following methods: minimum AIC, minimum BIC, maximum adjusted R-squared, minimum Mallows' Cp and t-tests. The importance of this upper bound is that it delineates general categories of design matrices and model selection procedures for which this confidence interval has poor coverage properties. This upper bound is shown to be a finite sample analogue of an earlier large sample upper bound due to Kabaila and Leeb.

math.ST↗