Discuss Methods of Validity in Test Construction

In 2002, Boholst constructed a Life Position Scale for the purpose of finishing his dissertation. The construct life position was one of the variables he studied in his doctoral dissertation titled, The Influence of Life Scripts and Life Positions on Psychopathology and Positive Mental Health: A Structural Equation Modeling. He had to construct this scale because there was no available one at the time. In 2005, he and two other authors wrote another article that found modest correlations between Life Positions and Attachment Stylesâ??validating the scale by establishing the relationship between life positions and a variable that was theoretically argued to have conceptual parallels or to be â??similarâ? with it. In 2012, Isgor and two other authors translated the Life Position Scale into Turkish and established its reliability and validity.This is often a realistic scenario where a tool slowly attains credibility by a gradual validation process across the yearsâ??often by different authors. For example, in 2004, Weisner wrote his doctoral dissertation in the University of North Texas on the relationship between Affective Traits and Life Positions. Hadzi-Pesic and others more recently (2014) validated the Life Position Scale and found correlations with alcohol addictsâ?? personality. For this task, write a paper that addresses the following:Discuss the different types of validity that have been employedâ??whether implicitly or explicitly to validate the life position scale. It is ideal therefore to read articles in chronological order starting with the A Life Position Scale, Life Positions and Attachment: A Canonical Correlation Analysis, and Life Positions Scale Language Equivalence, Reliability and Validity Analysis.Length: 7-10 pages, not including title and reference pagesYour assignment should demonstrate thoughtful consideration of the ideas and concepts presented in the course by providing new thoughts and insights relating directly to this topic. Your response should reflect scholarly writing and current APA standards. Upload your document and click the Submit to Dropbox button


Don't use plagiarized sources. Get Your Custom Essay on
Discuss Methods of Validity in Test Construction
Just from $13/Page
Order Essay


Unformatted Attachment Preview

A Life Position Scale
Fredrick A. Boholst
This article describes the construction of
a Life Position Scale developed by the author. Initial items representing four convictions articulated by Berne (1972)-I’m OK
(1), I’m not-OK (1-),You’re OK (U), and
You’re not-OK (U-)-were administered to
95 participants. The top five items for each
conviction, with item-total correlations that
reached an alpha level of p < .05, were retained for a subsequent factor analysis. An exploratory type of factor analysis constraining the process to two factors yielded a factor neatly containing all "I" items and another factor containing "You" items, with the OK items taking on opposite loadings to the not-OK items. Underlying factors seem to be I and You factors, not factors representing OK and not-OK. The final items are presented with suggestions for future research and a question for future theory development. Readers are free to administer the scale in their clinical and research practice but are encouraged to establish norms based on their culture and locale. In an effort to measure life positions for my doctoral dissertation, I constructed a Life Position Scale (LPS). A life position is a psychological stance that a child takes about the self and the rest of the world. It derives from a basic conviction that individuals develop when they are young. Convictions are firm decisions about the OKness or not-OKness of the self (I) and others in general (V). Convictions are presumably influenced by early script programming (referred to in transactional analysis as the "protocol") during the nursing period and within the context ofa two-handed transaction, usually between mother and child (Berne, 1972). In developing these convictions, and depending on what they were constantly made to believe about themselves, people may conclude about themselves: I'm smart, I'm stupid, I'm 28 nice, I'm nasty, I'm as good as anybody else, I'm inadequate, and so on (James & Jongeward, 1971/1978). When deciding about others, people may conclude: People can't be trusted, People are wonderful, It's a dog-eatdog world, or Everybody's on to something. These convictions can be summarized as: I'm OK, I'm not-OK, You're OK, or You're notOK. Using the symbols () for OK and (-) for not-OK, the convictions can be represented as 1 or 1- and V or V-. Convictions form the basis for the life position the person takes in relation to the self and others. Positions can be any of the following: 1. 1. "I'm OK, You're OK" is a healthy position. People taking this position solve problems in a constructive and realistic manner and have a generally positive outlook on life. This is the position a transactional analysis therapist should take in a therapeutic relationship; in fact, it is the basis of transactional analysis as a contractual therapy (Blackstone, 1993). 2.1 V-. "I'm OK, You're not-OK" is a projective or "get-rid-of' position. People taking this position are described as arrogant and antisocial. At worst, they can be killers who justify eradication ofthe minority; at best, they may be meddlers who go out of their way in a "holierthan-thou" attitude to convince others to change. Clinically, this is the position of the paranoid (Berne, 1966) or the narcissist (MeFarren, 1998). 3. 1- V. "I'm not-OK, You're OK" is the depressive position. Colloquially, these are the people who live on "If onlys," and "I should haves" (Berne, 1972) and tend to denigrate themselves (Hunt-Cohn, 1994). The "I'm notOK, You're OK" position is the existential basis for the feeling of shame (Erskine, 1994). Individuals in this position experience melancholia and in severe clinical cases may resort to suicide (Berne, 1972). 4.1- U-. "I'm not-OK, You're not-OK," also known as the futility position, is taken by those Transactional Analysis Journal A LIFE POSITION SCALE who lose interest in living. Clinically, they exhibit schizoid or schizophrenic behavior. If those taking the third position feel that "Life isn't worth living," those taking the fourth feel "Life isn't worth anything at all" (Berne, 1972). Migdow (1994), in her conceptual analysis of abuse, suggested that this position also seems to be the one taken by child abuse perpetrators, whose own traumatic experiences led them to "conclude that life is not precious" (p. 180). For the Life Position Scale I developed, ten items were constructed for each of the four convictions discussed by Berne (1972): I'm OK (1), I'm not-OK (1-), You're OK (U), and You're not-OK (U-). To these the test takers were to answer "All of the time," "Most of the time," "Half of the time," "Sometimes," or "Never." The initial scale was administered to 95 college students, and a corrected item-total correlation was performed. A corrected item-total correlation is the Pearson r between the total score for each conviction and each item, with the particular item score deducted from the total score. This is also known as item-whole or item-remainder coefficient (Spector, 1994) and is done to avoid inflation of the correlation coefficient due to the presence ofthe particular item. The top five items for each conviction had item-total correlations ranging from .39 to .57, with a probability level of p < .05. This indicated that the chances are less than five in a hundred that these correlations were spurious. The items were then retained for a subsequent factor analysis. A Short Note on Factor Analysis Factor analysis is a mathematical technique used to summarize a large set of data by reducing it into fewer dimensions or factors. Basically, it reduces the data or clusters them based on their intercorrelations. The grouped data can then be named and can even be presumed to be a function of"some underlying, latent, and hypothetical set of factors" (Hair, Anderson, Tatham, & Black, 1995, p. 367). For example, a researcher may have 20 sets oftest scores from 100 students. Obviously, it would be cumbersome to process and analyze these individual test scores, so the researcher Vol. 32. No. I. January 2002 runs a factor analytic procedure and extracts two factors: one containing students' scores in math and another containing verbal test scores. It so happens that these two sets of tests cluster together because the data within each dimension or factor are interrelated. Students' scores can then be thought ofas functions ofthese two underlying dimensions, which the researcher may call verbal and mathematical intelligences. The factor analytic procedure includes rotating the axes on which the data are plotted to maximize the variance in the data set that each factor accounts for or "captures." This, however, is quite involved and beyond the scope of this article. Those who wish more information may look up Hair et al.'s (1995) Multivariate Data Analysis with Readings for a conceptual discussion offactor analysis or Tabachnick and Fidell's (1989) Using Multivariate Statistics (2nd ed.) for a more mathematically oriented discussion. Factor Analysis of the Life Position Scale An initial unconstrained (in terms of the number offactors) exploratory factor analysis was performed on the items that were retained after the item-whole correlation analysis. However, this yielded 12 factors, which I found to be unwieldy and difficult to interpret in light of the theory. The next step was to rerun the analysis, but this time constrain the extraction to two factors. This was done based on the hypothesis that there should be two underlying factors the items represented. However, I was not sure whether the two hypothesized factors would represent two polarities of OKness and not-OKness or two factors that would represent I and U. Results To my surprise and delight, the results of a VARIMAX-rotated factor analytic procedure extracted one factor that neatly contained all the I items, with the 1 and 1- having opposite loadings, and another factor of U items, with U and U- having opposite loadings (see Table 1 for the factor loadings and communalities). The results may shed some light on a plausible assumption ofIlU factors and not underlying OKness and not-OKness. The rotated 29 FREDRICK A. BOHOLST Table 1 Factor Analysis of the Life Position Scale (VARIMAX Rotation) Item I like myself. I don't feel good about myself. I am proud of who I am. I feel helpless. I feel confident about myself. I am aware of my positive traits. I wish I hadn't been born into this world. I feel I won't reach my dreams. I think others dislike me. I believe I am basically good. I wish some people were dead. I find it easy to appreciate others. Others are basically OK. Item I get irritated with other people. I distrust people. I feel suspicious of other people's intentions. I am impatient with other people's mistakes. Most people can be trusted. People can do a good job. I look forward to meeting other people. solution shows the I factor with an eigenvalue of 4.79, explaining only 24% of the item variance. The second factor, the V factor, has an eigenvalue of3.65, which explains 13.3% of the item variance. Although only 37.3% ofthe total variance has been accounted for, which prompted me to add more factors, the theoretical interpretability of the two-factor solution was deemed enough to stop the factor extraction. Table 2 presents the retained items for the LPS. This will be administered to 150 participants for my proposed dissertation entitled "The Influence of Scripts and Life Positions on Psychopathology and Positive Mental Health: A Structural Equation Modeling." Extracting the Life Position Pretesting the LPS among "normal" participants, the Life Position Scale used a 5-point Likert scale (5 = All of the time, 4 = Most of the time, 3 = Half of the time, 2 = Sometimes, and 1 = Never). To extract an individual's life position (i.e., 1, I-V, 1, or I-V-), the 1scores were reversed and the total score was added to the 1 scores, creating a global score 30 Communalities Factor I Factor U .71 -.68 .67 -.63 .62 .58 -.58 -.57 -.52 .33 .02 .05 -.00 .33 .02 .06 .26 .17 .21 -.29 .513 .447 .197 .347 .384 .334 .360 .450 .409 .463 .73 -.64 -.62 .277 .391 .408 Factors I Factors U Communalities .04 -.12 -.02 -.02 .17 .18 .26 .62 .63 .55 .51 -.49 -.48 -.44 .283 .272 .388 .549 .399 .262 .310 -.14 .04 -.05 for 1.Presumably, the higher the score the more OK the person feels about himself or herself. The median was then computed and used as the cut-off point between the OK and the not-OK convictions. This placed the upper 50% in the 1 and the lower 50% in the 1-. The same procedure was applied to the V conviction. The V- scores were reversed and added to the V scores, creating a global score for V. The median was computed with the upper 50% placed as V and the lower 50% as U-. Such a strategy was deemed best since the study data were gathered from a nonclinical sample of college students, which statistically "forced" them to take on a life position. Table 3 shows the descriptive statistics of the I and V global scores, N = 95. (Note: Initial exploration of the data did not show reliable differences among sex, age, and the courses majored in while attending college.) Discussion The objective of this article is to present the Life Position Scale I developed in the hope that readers might find it useful in research and Transactional Analysis Journal A LIFE POSITION SCALE Table 2 Life Position Scale Items 1 I like myself. I am proud of who I am. I feel confident about myself. I am aware of my positive traits. I believe I am basically good. U I find it easy to appreciate others. Others are basically OK. Most people can be trusted. People can do a good job. I look forward to meeting other people. clinical settings. In light of this, there are three issues that need to be addressed. The first relates to the assignment of a life position. The data in Table 3 come from the 95 pretest students who participated in the LPS construction. I have used the LPS subsequently in workshops as an indicator of participants' life positions, and the results seem to have been validated by workshop participants' phenomenological reports. The median can be used as a cut-off point to categorize the test-taker's life position. For example, if a person scores I 37 and U 37, then he or she would be categorized as 1-U or ''I'm not-OK, You're OK" because the median score for I is 38 and the median score for U is 36. This might not pose a problem if this were a research situation because the researcher could proceed to plot the scores and compute mathematical means in a nomothetic research. However, in the clinical field, the person's opinion and reflection about his or her life position should be taken into account and discussed in a safe and therapeutic environment. Moreover, the mean and the standard deviation have also been useful in providing insight into the test-taker's degree of OKness or not-OKness based on how far he or she is from the mean. In the clinical setting, this seems to be a better approach to exploring a person's life position than the previous categorical assignment on the basis ofthe median. This is because varying degrees of OKness and not-OKness can be explored in an idiographic and phenomenological light. Vol. 32, No. I, January 2002 II don't feel good about myself. I feel helpless. I wish I hadn't been born into this world. I feel I won't reach my dreams. I think others dislike me. UI wish some people were dead. I get irritated with other people. I distrust people. I feel suspicious of other people's intentions. I am impatient with other people's mistakes. The second point relates to the use of this scale in research. Researchers who wish to use the scale are encouraged to establish their own norms and cut-off points based on their own population and cultural peculiarities. Once this is done, the life positions may then be placed under investigation as independent variables influencing dependent variables or as dependent variables being affected by antecedent independent variables that, to the researcher, may be theoretically sound. This will enhance the scale's validity as well as the validity oflife position as a construct. For example, the scale's validity could be strengthened by using known groups that can theoretically be argued to fit certain life positions. As mentioned earlier, depressives for instance, would presumably be categorized as I-U, while antisocial, paranoid (Berne, 1972), and narcissistic individuals (McFarren, 1998) might take the I position. Schizoid individuals, schizophrenics (Berne, 1972), and perhaps child abuse perpetrators (Migdow, 1994), on the other hand, are argued to be taking the I-U- position. The third issue seems serendipitous. If the reader recalls, the results of the factor analysis came up with two factors, one containing all the I items and the other all the U items. Note that the factors extracted were IJU factors and not underlying factors of OK and not-OK. This highlights questions that I do not have answers to and that readers might want to theorize on: Why are there two underlying factors bearing the "I" and the "U" and not those regarding a 31 FREDRICK A. BOHOLST Table 3 Descriptive Statistics for the I and U Global Scores Statistics I U Mean 37.30 34.96 Standard Deviation 5.50 5.39 Median 38.00 36.00 Lowest Score 12.00 11.00 Highest Score 50.00 43.00 sense of OKness and not-OKness? Of what theoretical importance might this finding have? Answers to these questions might shed light on the developmental aspects of transactional analysis theory, particularly as it relates to differentiation or the infant's development of a sense of "I" as a separate entity from "Â¥ou." Fredrick Boholst, an ITAA Associate Member, has a master's degree in psychology with a major in industrial/organizational psychology. He is a doctoral candidate in clinicalpsychology at Ateneo de Manila University and a faculty member in the Department ofPsychology at the University of San Carlos. Please send reprint requests to him at the Department ofPsychology, University ofSan Carlos, P. del Rosario St., Cebu City 6000, Philippines; email: montoya37@hotmail.com REFERENCES Berne, E. (1966). Principles of group treatment. New York: Grove Press. Berne, E. (1972). What do you say after you say hello?: The psychology ofhuman destiny. New York: Grove Press. Blackstone, P. (1993). The dynamic child: Integration of second-order structure, object relations, and self psychology. Transactional Analysis Journal; 23, 216-234. Erskine, R. G. (1994). Shame and self-righteousness: Transactional analysis perspectives and clinical interventions. Transactional Analysis Journal, 24, 86-102. Hair, 1. F., Anderson, R. E., Tatham, R. L., & Black, W. C. (1995). Multivariate data analysis with readings. Upper SadIe River, NJ: Prentice-Hall. Hunt-Cohn, M. (1994). Loneliness and the four life positions. Transactional Analysis Journal, 24, 293-294. James, M., & Jongeward, D. (1978). Born to win: Transactional analysis with gestalt experiments. New York: Penguin Books USA. (Original work published 1971) McFarren, C. (1998). Narcissism: "I'm OK, you're not!" Transactional Analysis Journal, 28. 244-250. Migdow, J. (1994). Silencing the child. Transactional Analysis Journal, 24, 178-184. Spector, P. (1994). Summated rating scale construction: An introduction. In M. S. Lewis- Beck, (Ed.), Basic measurement (pp. 229-300). London: Sage Publications. Tabachnick, B. G., & Fidel!, L. S. (1989). Using multivariate statistics (2nd ed.). New York: HarperCol!ins. ITAA Website: www.itaa-net.org The ITAA website provides comprehensive information about every aspect of the ITAA. Recent additions to the web site include links to upcoming international, national, and regional activities and membership information. If you would like your website to be linked from the ITAA site, please forward the site address (URL) to elaine@itaa-net.org . Also forward any suggestions/feedback/information for upcoming events, and share the website address with nonmembers. 32 Transactional Analysis Journal Life Positions and Attachment Styles: A Canonical Correlation Analysis Boholst, Fredrick A;Boholst, Giselle B;Mende, Michael Mark B Transactional Analysis Journal; Jan 2005; 35, 1; ProQuest Central pg. 62 Reproduced with permission of the copyright owner. Further reproduction prohibited without permission. Reproduced with permission of the copyright owner. Further reproduction prohibited without permission. Reproduced with permission of the copyright owner. Further reproduction prohibited without permission. Reproduced with permission of the copyright owner. Further reproduction prohibited without permission. Reproduced with permission of the copyright owner. Further reproduction prohibited without permission. Reproduced with permission of the copyright owner. Further reproduction prohibited without permission. Available online at www.sciencedirect.com Procedia - Social and Behavioral Sciences 47 (2012) 284 â?? 291 CY-ICER 2012 Life positions scale language equivalence, reliability and validity analysis Isa Yucel Isgor a *, Canani Kaygusuz b, ** Ahmet Ragip Ozpolat c a b ncan 2400, Turkey c Abstract Life positions scale developed by Boholst in 2002 consists of four sub-dimensions and 24 items. The language adaptation of the found significant at the level of p<.05, that is .79 for the whole scale, .77 for the I am Ok sub scale. For the sub scale I am not Ok, the result is .69, .76 for the You are OK subscale, and .70 for the You are not OK subscale.During the reliability studies, the scale w Kasier-Mayer-Olkin (KMO) value was observed and the result was .89. The coefficient of the internal consistency of the items was (a) .84. Principal components factor analysis was also used for the construct validity and the data were subjected to varimax axis convert.Results showed that the ... Purchase answer to see full attachment

Calculate your paper price
Pages (550 words)
Approximate price: -

Why Work with Us

Top Quality and Well-Researched Papers

We always make sure that writers follow all your instructions precisely. You can choose your academic level: high school, college/university or professional, and we will assign a writer who has a respective degree.

Professional and Experienced Academic Writers

We have a team of professional writers with experience in academic and business writing. Many are native speakers and able to perform any task for which you need help.

Free Unlimited Revisions

If you think we missed something, send your order for a free revision. You have 10 days to submit the order for review after you have received the final document. You can do this yourself after logging into your personal account or by contacting our support.

Prompt Delivery and 100% Money-Back-Guarantee

All papers are always delivered on time. In case we need more time to master your paper, we may contact you regarding the deadline extension. In case you cannot provide us with more time, a 100% refund is guaranteed.

Original & Confidential

We use several writing tools checks to ensure that all documents you receive are free from plagiarism. Our editors carefully review all quotations in the text. We also promise maximum confidentiality in all of our services.

24/7 Customer Support

Our support agents are available 24 hours a day 7 days a week and committed to providing you with the best customer experience. Get in touch whenever you need any assistance.

Try it now!

Calculate the price of your order

Total price:

How it works?

Follow these simple steps to get your paper done

Place your order

Fill in the order form and provide all details of your assignment.

Proceed with the payment

Choose the payment system that suits you most.

Receive the final file

Once your paper is ready, we will email it to you.

Our Services

No need to work on your paper at night. Sleep tight, we will cover your back. We offer all kinds of writing services.


Essay Writing Service

No matter what kind of academic paper you need and how urgent you need it, you are welcome to choose your academic level and the type of your paper at an affordable price. We take care of all your paper needs and give a 24/7 customer care support system.


Admission Essays & Business Writing Help

An admission essay is an essay or other written statement by a candidate, often a potential student enrolling in a college, university, or graduate school. You can be rest assurred that through our service we will write the best admission essay for you.


Editing Support

Our academic writers and editors make the necessary changes to your paper so that it is polished. We also format your document by correctly quoting the sources and creating reference lists in the formats APA, Harvard, MLA, Chicago / Turabian.


Revision Support

If you think your paper could be improved, you can request a review. In this case, your paper will be checked by the writer or assigned to an editor. You can use this option as many times as you see fit. This is free because we want you to be completely satisfied with the service offered.

Order your essay today and save 15% with the discount code DISCOUNT15