MinP Score Tests with an Inequality Constrained Parameter Space

TL;DR

This paper introduces a new class of one-sided score tests for parameters under inequality constraints, allowing for simultaneous testing of individual elements and improving upon existing joint testing methods.

Contribution

It proposes a novel MinP score test framework based on the minimum of multiple p-values, enabling more detailed inference under inequality constraints.

Findings

Tests outperform existing methods in joint testing scenarios.

The proposed tests effectively identify individual parameter elements.

Simulation results confirm good finite sample performance.

Abstract

Score tests have the advantage of requiring estimation alone of the model restricted by the null hypothesis, which often is much simpler than models defined under the alternative hypothesis. This is typically so when the alternative hypothesis involves inequality constraints. However, existing score tests address only jointly testing all parameters of interest; a leading example is testing all ARCH parameters or variances of random coefficients being zero or not. In such testing problems rejection of the null hypothesis does not provide evidence on rejection of specific elements of parameter of interest. This paper proposes a class of one-sided score tests for testing a model parameter that is subject to inequality constraints. Proposed tests are constructed based on the minimum of a set of $p$-values. The minimand includes the $p$-values for testing individual elements of parameter of interest using individual scores. It may be extended to include a $p$-value of existing score tests. We show that our tests perform better than/or perform as good as existing score tests in terms of joint testing, and has furthermore the added benefit of allowing for simultaneously testing individual elements of parameter of interest. The added benefit is appealing in the sense that it can identify a model without estimating it. We illustrate our tests in linear regression models, ARCH and random coefficient models. A detailed simulation study is provided to examine the finite sample performance of the proposed tests and we find that our tests perform well as expected.