Types of reliability and validity used in the “Values and Motives Manual”
One type of testing reliability used in the article is the inter-rater reliability. The researchers have used the inter-rater reliability in the literature review (Values and Motives Manual, n.d.). Inter-rater reliability integrates the agreement between different judges (Phelan & Wren, 2006).
The researchers have used the internal consistency reliability method. The internal consistency method ensures that each item is positively associated with their score on the scale. They have used Cronbach’s Alpha co-efficient to measure reliability (Values and Motives Questionnaire, n.d.). A high alpha coefficient indicates that the scores are more reliable.
The researchers have also used the parallel forms reliability test. It involves using different scales for the same test (Kaplan & Saccuzzo, 2009). The researchers have used two scales for the same sample. The correlation coefficient is calculated for the different scores from different constructs (Values and Motives Questionnaire, n.d.). A scale is a construct such as VMI, OPP, and MAPP.
One form of validity that the researchers have used is sampling validity. They have used samples from different populations. They have used MBA students as well as undergraduate from different institutions (Values and Motives Questionnaire, n.d.).
The researchers have also used construct validity. Construct validity examines if the scores are “consistent with scores from the other major test which measure similar construct, and dissimilar from those which measure different constructs” (Values and Motives Questionnaire, n.d., p. 15). For example, the researchers have elaborated the difference between VMI and 16PF constructs. The construct’s scores have less similarity.
Areas of concern and strength
The relationship between VMI and MAPP shows that the constructs can be used interchangeably. A correlation coefficient that ranges between -/+0.3 to -/+0.5 is considered a moderate correlation.
A correlation coefficient above -/+ 0.5 is a strong correlation. A correlation coefficient that is above 0.7 means that the two construct can be used interchangeably (Values and Motives Questionnaire, n.d.). Most of the values between the two constructs are strongly correlated.
VMI and 16PF constructs are different. Validity requires dissimilar constructs to give different scores (Values and Motives Questionnaire, n.d.). The social desirable correlation coefficient for the two constructs is 0.4. It is a modest correlation.
Examples of valid scores shown by the correlation co-efficient between VMI affection and 16PF are ‘privateness’ with a coefficient of -0.41, social desirability/ impression management with a correlation coefficient of 0.4, and those with higher values (Values and Motives Questionnaire, n.d., p. 23, table 5).
VMI and OPP constructs indicate two scores having a correlation coefficient of 0.7. It indicates that the scores are strongly related. As a result of strong correlation, the social desirable coefficient for the two constructs is 0.58, and a central responding correlate of 0.75.
Correlation coefficients that are less than 0.5 (normal) are invalid. For VIM/OPP, the valid scores are altruism/ cynical-trusting (0.51), traditional/ detailed-flexible (-0.58), affiliation/ reserved-gregarious (0.73) among others (Values and Motives Questionnaire, n.d., p. 25, table 6).
Sample size and nature of population
The larger the sample size, the lower the standard error. A high value in the standard error reduces the validity of the test. It may indicate that the scores are different from those in the population. The samples have been selected from a population which tends to have a higher education index than the overall population in the country.
The population is more sophisticated because it mainly consists of undergraduate and postgraduate students. The research outcome may be different if the sample if drawn from the country’s population (Values and Motives Questionnaire, n.d.).
An opinion about the test
The test is valid and reliable if it used to interpret values among college students. It includes both undergraduate and postgraduate students. However, it cannot be used to make conclusions about the country’s population.
Works Cited
Kaplan, R., & Saccuzzo, P. (2009). Psychological Testing: Principles, Applications, and Issues (7th ed.). Belmont: Wadsworth Cengage Learning.
Phelan, C., & Wren, J. (2006). Exploring Reliability in Academic Assessment. Retrieved from https://chfasoa.uni.edu/reliabilityandvalidity.htm
Values and Motives Questionnaire. (n.d.). “Lecture notes”.