Is it possible for a test to be reliable and yet not valid illustrate give a situation that may support your answer?

Reliability and validity are two important characteristics of any measurement procedure.

Reliability has been defined as ‘the extent to which results are consistent over time… and if the results of a study can be reproduced under a similar methodology, then the research instrument is considered to be reliable.’ (Joppe 2000). This means a test is considered reliable if the same results are produced repeatedly, if it were to be carried out again. The more consistent the results produced, the higher the reliability of the measurement procedure.

Reliability is addressed in a variety of ways. These include:  

1. Inter-Rater Reliability – is the variation in measurements taken by different people using same methods. In order to ensure reliability, the degree of variation must be small.
2. Test-Retest Reliability – is established by comparing scores of the same individual, to calculate a correlation. There must be a strong correlation to ensure reliability.
3. Split-Half Reliability – is obtained by dividing up the test into two comparable halves, in order to calculate consistency between the two scores. Consistency must be present in order for the test to be considered reliable.

Despite having methods to ensure reliability, there are issues which arise which can affect the reliability of the test and results. The researchers are human, and that means the experiment is open to human judgement and error. However, this can be solved by carefully reporting methodology in the study and, if using qualitative methods, double coding.

These solutions make reliability much easier to assess.

Validity, on the other hand, determines whether the research truly measures what it intended to measure, (Joppe, 2000).  This means it looks at the extent to which a test measures what it claims to measure, and therefore, answers the research question or hypothesis. How valid a test is, depends on the purpose of the research.

Validity is addressed in a variety of ways, and include:

1. Content (face) Validity – is the degree to which a test measures an intended content area. It must measure what it claims to measure, in order to be considered valid.
2. Concurrent Validity- measures the extent to which a correlation exists between a new measure and a standard measurement procedure.  The scores should be directly related in order to obtain validity.
3. Convergent Validity – is the degree to which scores obtained from two different methods of measures. There must be a strong relationship, for validity to be demonstrated.

Despite having methods in place to ensure validity, there are threats. There are two main threats: experimenter bias and demand characteristics. Again, the researcher is human and this means the study will always be open to human error. The experimenter may influence the outcome of the research because of his/hers expectations regarding the results. This however, can be solved through the use of single blind or double blind studies, in which the researcher has no idea what the predicted outcome is. Again, the participants are human, and this can lead to the problem of demand characteristics, in which participants behave in a different way. Participants normally modify their behaviour in response to the fact they are participating in a study and are aware they are being measured. They strive to be a good participant. Although it is essentially impossible to prevent participants from modifying their behaviour, there are methods in place which can reduce this effect. Solutions include: using observations or concealing the measurement procedure.

Despite being very different, both reliability and validity are important in research.  As the saying goes ‘a valid test is always reliable but a reliable test is not necessarily valid’, but it is important to ensure that both reliability and validity are demonstrated.

This entry was posted in Uncategorized. Bookmark the permalink.

Statistics Definitions > Reliability and Validity

Contents:

• Overview
• What is Reliability?
• The Reliability Coefficient
• What is Validity?

Overview of Reliability and Validity

Outside of statistical research, reliability and validity are used interchangeably. For research and testing, there are subtle differences. Reliability implies consistency: if you take the ACT five times, you should get roughly the same results every time. A test is valid if it measures what it’s supposed to.

Tests that are valid are also reliable. The ACT is valid (and reliable) because it measures what a student learned in high school. However, tests that are reliable aren’t always valid. For example, let’s say your thermometer was a degree off. It would be reliable (giving you the same results each time) but not valid (because the thermometer wasn’t recording the correct temperature).

What is Reliability?

Reliability is a measure of the stability or consistency of test scores. You can also think of it as the ability for a test or research findings to be repeatable. For example, a medical thermometer is a reliable tool that would measure the correct temperature each time it is used. In the same way, a reliable math test will accurately measure mathematical knowledge for every student who takes it and reliable research findings can be replicated over and over.

Of course, it’s not quite as simple as saying you think a test is reliable. There are many statistical tools you can use to measure reliability. For example:

• Kuder-Richardson 20: a measure of internal reliability for a binary test (i.e. one with right or wrong answers).
• Cronbach’s alpha: measures internal reliability for tests with multiple possible answers.

Internal vs. External Reliability

Internal reliability, or internal consistency, is a measure of how well your test is actually measuring what you want it to measure. External reliability means that your test or measure can be generalized beyond what you’re using it for. For example, a claim that individual tutoring improves test scores should apply to more than one subject (e.g. to English as well as math). A test for depression should be able to detect depression in different age groups, for people in different socio-economic statuses, or introverts.

One specific type is parallel forms reliability, where two equivalent tests are given to students a short time apart. If the forms are parallel, then the tests produce the same observed results.

The Reliability Coefficient

A reliability coefficient is a measure of how well a test measures achievement. It is the proportion of variance in observed scores (i.e. scores on the test) attributable to true scores (the theoretical “real” score that a person would get if a perfect test existed).

The term “reliability coefficient” actually refers to several different coefficients: Several methods exist for calculating the coefficient include test-retest, parallel forms and alternate-form:

• Cronbach’s alpha — the most widely used internal-consistency coefficient.
• A simple correlation between two scores from the same person is one of the simplest ways to estimate a reliability coefficient. If the scores are taken at different times, then this is one way to estimate test-retest reliability; Different forms of the test given on the same day can estimate parallel forms reliability.
• Pearson’s correlationcan be used to estimate the theoretical reliability coefficient between parallel tests.
• The Spearman Brown formula is a measure of reliability for split-half tests.
• Cohen’s Kappa measures interrater reliability.

The range of the reliability coefficient is from 0 to 1. Rule of thumb for preferred levels of the coefficient:

• For high stakes tests (e.g. college admissions), > 0.85. Some authors suggest this figure should be above .90.
• For low stakes tests (e.g. classroom assessment), > 0.70. Some authors suggest this figure should be above 0.80

What is Validity?

Validity simply means that a test or instrument is accurately measuring what it’s supposed to.

Click on the link to visit the individual pages with examples for each type:

• Composite Reliability
• Concurrent Validity.
• Content Validity.
• Convergent Validity.
• Consequential Validity.
• Criterion Validity.
• Curricular Validity and Instructional Validity.
• Ecological Validity.
• External Validity.
• Face Validity.
• Formative validity & Summative Validity.
• Incremental Validity
• Internal Validity.
• Predictive Validity.
• Sampling Validity.
• Statistical Conclusion Validity.

References

Everitt, B. S.; Skrondal, A. (2010), The Cambridge Dictionary of Statistics, Cambridge University Press.
Gonick, L. (1993). The Cartoon Guide to Statistics. HarperPerennial.

---------------------------------------------------------------------------

Need help with a homework or test question? With Chegg Study, you can get step-by-step solutions to your questions from an expert in the field. Your first 30 minutes with a Chegg tutor is free!

Comments? Need to post a correction? Please Contact Us.