Participant Reactivity Think about how participants might react to environmental cues in an experimental situation and create a hypothetical study on asser

Participant Reactivity Think about how participants might react to environmental cues in an experimental situation and create a hypothetical study on assertiveness. It is important for you to remember that the study should not be designed to test participant reactivity. Summarize the study in a few sentences, and explain how some specific items in the laboratory environment in your made-up study might cause participants to respond in a particular way. What could be done in your study to reduce participant reactivity? Reliability and Validity of Measurement.html

Reliability and Validity of Measurement

The concept of reliability is related to the quality of measurement. If you think about how you use the term “reliable” in everyday language, you might get a hint of how reliability is related to research studies. For example, you often refer to a machine as reliable: “I have a reliable car.”

View the PDF Transcript of Reliable Measure

Concept of Reliability

The table below lists some measurement scales and values that have been created to illustrate the concept of reliability.


Assessment Measures Taken from the Same Person Scores Obtained with each Measurement Reliable or Not

Extrovert scale given to the same person every other day; scale ranges from 0 to 20 with 20 being a high extrovert. 13     19     9 Not Reliable.  The numbers are very different each time the person is given the scale.

Blood pressure taken with wrist cuff every 2 minutes for a healthy person 180/100   130/80   118/100 Not reliable.  The systolic and the diastolic values change each time the pressure is measured.  Unless the person is really ill, this should not happen.

Blood pressure taken with arm cuff every 2 minutes for a healthy person 120/80   121/80   121/79 Reliable. The blood pressure is about the same each time the pressure is measured.

Whenever you use humans as a part of your research study, you should worry about whether the results you get are reliable or consistent. People are notorious for their inconsistency or error; they are easily distractible, they get tired of doing repetitive tasks, they daydream, they misinterpret, and they might have biases.

Next, let’s examine why reliability matters.

An unreliable measure contains a large and varying amount of measurement error, and there is no indication of the true score. Unreliable measures can alter the findings of a study. Because of this, it is important to try and assess the reliability of a measure. If you have a choice between two measurement devices, and one is more reliable than the other, it makes sense to select the more reliable device. Look at the data for the two types of blood pressure machines shown in the table. Perhaps you are conducting a study to examine the relationship between blood pressure and anger. If you want to measure whether blood pressure really does increase or decrease with anger, you need to use a reliable machine.

It is not always possible to calculate reliability exactly; instead, you have to estimate reliability.

Review the linked document for further information on Reliability and Validity

Additional Material

View the PDF transcript for Types of Reliability

View the PDF transcript for Internal Validity


Page 1 of 1
PSY2060 Research Methods

© 2013 South University

Reliable Measure

What does it mean to have a reliable or a dependable measure or observation in
a research context?

In research, the term reliability means “repeatability” or “consistency.”

A measure is considered reliable if it would give you the same result over and
over again—assuming that what you are measuring isn’t changing.

It is believed that every measure is additive of a real score or true value and
measurement error. In other words, most measurements have an error

media/transcripts/SUO_PSY2060 Types of Reliability.pdf

Types of Reliability

PSY2060 Research methods

©2016 South University

Types of Reliability

Reliability and Validity of Measurement

Types of Reliability

There are many types of reliability. However, there are two main types that we will discuss here.

Test-Retest Reliability:

You estimate test-retest reliability when you administer the same test to the same sample on two
different occasions. The blood pressure readings for a sample of healthy students, for example, should be
about the same when taken every two minutes. If you are comparing the blood pressure readings
provided by two different machines for a sample of students, the machine that provides the most
consistent scores when tested and then retested is the most reliable.

Inter-Rater Reliability:

Inter-rater reliability is useful when there is more than one observer measuring the same behavior. This
type of reliability is used to estimate if two observers are being consistent in their observations. For
example—a study that is looking at the tendency to lie when answering personal questions—you will be
sending two of your assistants to a mall to question people. Before you let your assistants go and collect
data, you need to make sure that their inter-rater reliability is high.

Testing for inter-rater reliability requires having the research assistants measure the same person being
questioned. To make sure that the assistants have an opportunity to measure the same behavior, a
recording of the person, who is answering the questions, should be used. Let’s say you have 100
questions, with three categories each that are being asked. Individually, for each question, each assistant
could check one of the three categories. Imagine that on 86 of the 100 observations, the assistants
checked the same category. Hence, the lying score by different observers for the same behavior in the
same person is significantly close.

© 2016 South University

media/transcripts/SUO_PSY2060 Internal Validity.pdf

Internal Validity

PSY2060 Research methods

©2016 South University

Internal Validity

Reliability and Validity of Measurement

Reliability is just one concept to consider when conducting studies. Another
important consideration is validity. Two of the several types of validity that you will cover
in this course are internal and external validity.

Internal Validity

Internal validity refers to how a study is conducted and whether the results are due
to the variables that are measured or manipulated. This type of validity is easiest to
understand when analyzed in an experimental situation.

Perhaps you were hired as a consultant by the Army to determine if soldiers can
assemble a new rifle under adverse weather conditions. The Army is concerned that cold
temperatures will make it difficult for the men to assemble the rifles. You Hypothesize that
if the temperature makes it difficult to assemble the rifles, there will be an increase in
assembly time as compared to the assembly time in a room with a normal temperature.
To test the hypothesis that cold temperature leads to an increase in assembly time, you
will measure the time it takes for a group of soldiers to assemble rifles in a room with 70°
Fahrenheit temperature. You will then compare the time it takes for a different group to
assemble rifles at 0° Fahrenheit temperature. Both groups must assemble the rifles
without gloves after they have been in the respective temperature conditions for 45
minutes. The following table contains fictitious assembly times for the groups in the two
different temperatures:

Measurement Time for Rifle Assembly in Seconds:


78.00 53.00

92.30 49.50

104.80 55.20

109.20 49.50

75.90 55.20

87.00 49.00

114.20 58.20

57.50 64.50

The following table shows the difference score between assembly times:

PSY2060 Research methods

©2016 South University

Internal Validity

Reliability and Validity of Measurement

Difference in Measurement Time for Rifle Assembly in









One of the keys to understanding internal validity is the recognition that when it is
associated with experimental research it refers both to how well the study was run and
how confidently one can conclude that the change in the dependent variable was
produced solely by the independent variable and not extraneous ones.

What if you discovered that two soldiers’ in one of the groups were exhausted from
a previous exercise or that in the cold room there were some exhaust fumes. Do you
think that the fumes could have altered their performance? Do you think the two tired
soldiers underperformed? If all these factors come into play, then you would have to
question the internal validity of the research.

Let’s consider that the internal validity of your experiment research was
compromised by the existence of fumes in one of the rooms. In such a case, you cannot
be sure if the difference in performance was caused by the fumes or the temperature
manipulation. In this situation, the internal validity problem affects one group and not the
other. Such a situation is called a confound. Unless you suspect that there is a
confound, you would come to the wrong conclusions at the end of your research.

A confound occurs when an extraneous variable impacts one group more than
another. Confounds are a major threat to internal validity. When a confound occurs, you
cannot claim that it was only the variable you manipulated that affected the research
results. Thus, your study will not have internal validity.

Another threat to internal validity is error variance; however, error variance does
not impact one group more than another. Let’s say that you are using an automated blood
pressure machine to take blood pressure measurements for a study and there is an
electrical short in the machine. The machine measures correct pressure most of the time;

PSY2060 Research methods

©2016 South University

Internal Validity

Reliability and Validity of Measurement

however, sometimes it records lower than the normal pressure. This is a problem but if
the error is spread between the two groups, since you are using the same machine, the
erratic measurements are random. Each group will have some readings of lower than
normal blood pressure measurements.

© 2016 South University

Looking for this or a Similar Assignment? Click below to Place your Order