Reliability and Validity
Type of reliability and validity used
Reliability refers to the degree to which an instrument produces reliable results when administered to the test population. For the VMQ, internal consistency reliabilities were used (Cronbach's Alpha). This means that rather than comparing multiple populations, it was determined if similar respondents gave similar types of answers when tested, reflecting a consistent pattern. The reliability was not assessed by subjecting different or the same populations to subsequent retests. According to the results, 8 of the 11 categories fell within the standard achievement measure of reliability, meaning that three of the measures should be assessed with caution.
Regarding validity, which means that the test measures what it purports to measure, the various scales for different attributes were found to operate independently of one another, suggesting that different scales had different levels of validity. Construct validity overall was used, in which the test's results were compared with other tests that attempted to measure similar types of indications. A sample of 59 psychology undergraduates took a similar, already-established test instrument (the MAPP), which was compared to the VMI. Then, a sample of 100 MBA students attending a prestigious London Business School completed both the VMI and the 16PF version 5 to compare with the final results of the VMI independently.
Q2. Areas of concern and strength: (e.g., low coefficients, or weaknesses, and high coefficients, or strengths).
The areas of greatest concern are those pertaining to the Moral and Independence scales which fall below acceptable ranges of reliability. And the Achievement scale exhibited a Standard Error of Measurement in a range which, according to the test's own designers, should be viewed with caution.
Q3. Articulate how sample size and nature of population may influence the constructs purportedly measured by the test, observing any strengths and weaknesses in these areas.
The sample size was relatively small: for example, gender results were calculated based upon the mean score differences between 68 male and 87 female students. Another disadvantage regarding the validity of the analysis regarding gender was that the results between the two gendered groups were calculated based upon a mean, which meant that one or two respondents with scores could have a considerable effect, skewing the results in one direction or another.
The two sample groups of 59 psychology students and 100 MBA students were relatively small and select as well. Using these populations is also of concern given the degree to which they are relatively homogeneous in terms of the test-taker's backgrounds, ages, and education.
Q4. Form an opinion of the test using the information you provide in your report
You’re 69% through this paper. Sign up to read the full paper.
Sign Up Now — Instant Access Already a member? Log inAlways verify citation format against your institution’s current style guide requirements.