Chapter 4, Problem 1Q-P99

Summary Introduction

Concept introduction

Reliability and validity are important concepts in scientific research. “Reliability” refers to how consistent a test's result is, while “validity” refers to the extent to which the test measures what it is supposed to. These concepts determine the usefulness of a test and allow us to infer whether it is a good tool to assess the given construct.

Explanation of Solution

Answer and explanation

Recently, there has been an increase in the use of standardized tests in schools. While they do usually happen to be valid and reliable, most of the tests that a student takes in school are not tested for these properties. Class tests have face validity, implying that it looks from the question that the test is measuring what it is supposed to, but that does not correspond to content or construct validity. Since most of the tests are based on the information given in textbooks, they have some content validity.

When it comes to reliability, class tests that are objective or are based on facts tend to have high inter-rater reliability, while those that measure a subjective quality, such as creative writing and art, tend to have low inter-rater reliability. In general, the reliability and validity of these tests depends on the test maker. Without any formal analysis, one cannot ascertain how useful a test it is.

Tests that are published in magazines and are available online rarely have any validity or reliability. Since they often do not operationalize the variable that they claim to measure, these tests do not have high validity or reliability. The aim of these tests is to have high face validity, to make the test taker feel that the test is useful. Hence, they lack any real validity. Also, since many of these tests measure variables that are influenced by extraneous factors, such as mood, they tend to have low test-retest reliability.