We examine the empirical role of difierent explanations for the lack of ∞ows of capital from rich to poor countries|the \Lucas Paradox." The theoretical explanations include difierences in fundamentals across countries and capital market imperfections. We show that during 1970i2000 low institutional quality is the leading explanation. For example, improving Peru’s institutional quality to Australia’s level, implies a quadrupling of foreign investment. Recent studies emphasize the role of institutions for achieving higher levels of income, but remain silent on the speciflc mechanisms. Our results indicate that foreign investment might be a channel through which institutions afiect long-run development.

/pdf/why-doesn-t-capital-flow-from-rich-to-poor-countries-an-3i855ji9t9.pdf

Why Doesn't Capital Flow from Rich to Poor Countries? An Empirical Investigation

Problems with the use of "moderator" variables.

In this paper we introduce certain numbers, called collinearity indices, which are useful in detecting near collinearities in regression problems. The coefficients enter adversely into formulas concerning signif- icance testing and the effects of errors in the regression variables. Thus they provide simple regression diagnostics, suitable for incorporation in regression packages.

/pdf/collinearity-and-least-squares-regression-40zprrrygs.pdf

Collinearity and Least Squares Regression

This book explains how computer software is designed to perform the tasks required for sophisticated statistical analysis. For statisticians, it examines the nitty-gritty computational problems behind statistical methods. For mathematicians and computer scientists, it looks at the application of mathematical tools to statistical problems. The first half of the book offers a basic background in numerical analysis that emphasizes issues important to statisticians. The next several chapters cover a broad array of statistical tools, such as maximum likelihood and nonlinear regression. The author also treats the application of numerical tools; numerical integration and random number generation are explained in a unified manner reflecting complementary views of Monte Carlo methods. Each chapter contains exercises that range from simple questions to research problems. Most of the examples are accompanied by demonstration and source code available in from the author's Web site. New in this second edition are demonstrations coded in R, as well as new sections on linear programming and the Nelder-Mead search algorithm.

Numerical Methods Of Statistics

A Survey of Ridge Regression and Related Techniques for Improvements over Ordinary Least Squares

Longley [10] proposed a set of data for use in testing regression programs. This paper shows that the numerically accurate solution in this example was probably an unreasonable estimate of the regression coefficients. This is true because the accuracy of the data and appropriateness of the model may affect the solution more than the computational method. An easily computed index is derived that can be used to indicate such computational instability. The basic conclusion is that a concern about highly accurate computational methods must be tempered with a concern for whether the data are accurate enough to make the results meaningful.

/pdf/the-acceptability-of-regression-solutions-another-look-at-5f16mwa65s.pdf

The Acceptability of Regression Solutions: Another Look at Computational Accuracy

Longley proposed a set of data for use in testing regression programs. This paper shows that the numerically accurate solution is likely to be an unreasonable estimate of the regression coefficients for this problem. This is true because the accuracy of the data and appropriateness of the model may affect the solution more than the computational method. An easily computed index is derived that can be used to indicate such computational instability. The basic conclusion is that a concern about highly accurate computational methods must be tempered with a concern for whether the data are accurate enough to make the results of such computation meaningful.

The acceptability of regression solutions: another look at computational accuracy

A Fortran Computer Program for a Moderated Stepwise Prediction System

Large-scale group-score assessments are widely used to inform educational policymakers about the needs and accomplishments of various populations and subpopulations. The purpose of this chapter is to chronicle ETS’s technical contributions in this area. The focus is on a subset of important educational achievement testing programs, ones that assess large populations (e.g., the United States as a whole, an individual state), use population-defining variables (e.g., racial/ethnic, gender), and include consideration of other policy-relevant factors (e.g., the number of hours watching TV, number of mathematics courses taken).

/pdf/large-scale-group-score-assessment-eg9atjexcz.pdf

Large-Scale Group-Score Assessment

In many selection situations, some predictor of success, such as a test, is used to discriminate between the applicants to be accepted and those to be rejected. Using an interpretation of Brogden [1946], this paper shows the effect of using a correlated variable on the mean criterion score of the selected group. The distribution of the means of all possible selections is discussed and a simple formula is provided for calculating the probability of achieving as high or higher mean using random selection as opposed to using a correlated variable. It is shown that even fairly small correlations result in selection decisions that are not often exceeded by chance. The Brogden interpretation and significance test is shown to extend simply to the case of several predictors.

https://www.onlinelibrary.wiley.com/doi/pdf/10.1002/j.2333-8504.1981.tb01247.x

John L. Barone

Papers

The Acceptability of Regression Solutions: Another Look at Computational Accuracy

The acceptability of regression solutions: another look at computational accuracy

A Fortran Computer Program for a Moderated Stepwise Prediction System

Large-Scale Group-Score Assessment

The usefulness of selection tests in college admissions