Scribd
Upload
41 views3 pages

A1 233 Sarah Eddy

The document discusses a self-esteem assessment and questions related to variables used, face validity, construct validity, and internal consistency. Continuous variables and self-reporting are used to measure trait self-esteem. Face validity assesses how well a test measures its intended construct, while construct validity measures agreement between variables. Split-half reliability shows the self-esteem assessment lacks internal consistency based on differing even and odd item scores.

Uploaded by

eddys4
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
41 views3 pages

A1 233 Sarah Eddy

The document discusses a self-esteem assessment and questions related to variables used, face validity, construct validity, and internal consistency. Continuous variables and self-reporting are used to measure trait self-esteem. Face validity assesses how well a test measures its intended construct, while construct validity measures agreement between variables. Split-half reliability shows the self-esteem assessment lacks internal consistency based on differing even and odd item scores.

Uploaded by

eddys4
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Assignment 1

1. What kind of variables are being used here to measure trait self-esteem, and what kind of
assessment? How do you know? (4 points).
Rubric: 0 – 2 points: Student properly identifies the kind of variables and measure of
assessment.
0 – 2 points: Student gives a proper and cogent explanation, adequately defending
their answer.

In measuring self-esteem, we are using a continuous variable to complete our


measurement. Continuous variables have open-ended values, such as numerical values,
which show differences in magnitude. These variables are measured on a continuum
rather than a set group of criteria, allowing for specificity in assessment. In contrast,
nominal or categorical variables would be concrete values without any natural order to
them. These variables are non-numerical and contain categorical data.

Because this measure of assessment is completed by the patients themselves, this would
be defined as self-reporting. Had a professional completed the assessment for the client, it
would be defined as an observer rating. Additionally, should we try to classify this as an
inventory, we would need to be measuring multiple aspects of the client’s personality on
multiple subscales.

2. What is face validity? Try to provide an example for an item assessing happiness. Do you
believe the items on this self-esteem measure are high or low in face validity? Why or
why not? What are the pros and cons associated with face validity? (4 points).
Rubric: 0 – 1 point: Student gives a proper definition of face validity and provides an apt
example for happiness.
0 – 3 points: Student gives a proper answer as to whether the items are high or low in
face validity, and defends their response cogently while citing benefits and drawbacks to this
form of validity.

The concept of face validity measures the extent to which a test measures the quality it
intends to measure. A valid assessment of happiness would be a survey consisting of
questions such as “I feel happiness the majority of the time” or “I generally feel happy or
content,” as it is directly related to happiness. I believe that the Rosenberg Self-Esteem
Scale demonstrated high face validity, as the questions are highly related to elements of
self-esteem, such as self-worth, self-respect, and self-confidence. The benefit of using
face-valid testing is the ease of interpretation of results. Because the questions are so
readily related to what it is trying to measure, the interpretation is facilitated. The
downfall of this method of testing however, is that participants may withhold information
regarding their feelings.

3. What is construct validity? (Try to provide your own example, not one used during class).
Do you believe these items on the self-esteem scale are high or low in construct validity?
Why or why not? (4 points).
Rubric: 0 – 2 points: Student defines construct validity and provides their own unique, apt
example.
0 – 2 points: Student provides a sufficient explanation as to why these self-esteem
items are high or low in construct validity.

Construct validity measures the extent to which the test performed measures what it was
intended to. In this type of validity, independent and dependent variables are observed to
enquire how much the study truly represents the hypothetical values that they are
interested in. Should we use the previous example, the test’s construct validity would be
the extent to which happiness, joy, excitement, and positivity are assessed, as opposed to
anger, sadness, or upset emotions. As the Rosenberg scale measures both positively and
negatively phrased questions regarding self-esteem, it contains two constructs that are
both correlated to self-esteem, therefore making it high in construct validity.

4. The highlighted responses indicate a participant’s answers on each item of this measure.
First, what is meant by internal consistency? Next, using split half reliability, do you
believe the items on this measure are internally consistent? Why or why not? Be sure to
include your arithmetic, that is, show your work, how you came up with your answer. (4
points).
Rubric: 0 – 1 point: Student properly defines internal consistency.
0 – 3 points: Student properly uses split half reliability to determine whether or not
the answered items on the measure are internally consistent, and shows their calculations
(i.e., how they came up with the proper solution).

Internal consistency measures the agreement and correlation between multiple responses
to questions regarding a specific concept or construct. Should we split the values of the
Rosenberg Scale into even and odd, the items are not internally consistent.
Even: 6+3+2+1+2 = 23
Odd: 5+1+6+5+6 = 14

Because of this differential, the items are not considered to be internally consistent. If the
measure was internally consistent, the values for odd and even split would be closer
together, or preferably the same number.

You might also like