Ensuring content validity of patient-reported outcomes: a shadow-test approach to their adaptive measurement

Purpose

Most computerized adaptive testing (CAT) applications in patient-reported outcomes (PRO) measurement to date are reliability-centric, with a primary objective of maximizing measurement efficiency. A key concern and a potential threat to validity is that, when left unconstrained, individual CAT administrations could have items with systematically different attributes, e.g., sub-domain coverage. This paper aims to provide a solution to the problem from an optimal test design framework using the shadow-test approach to CAT.

Methods

Following the approach, a case study was conducted using the PROMIS^® (Patient-Reported Outcomes Measurement Information System) fatigue item bank both with empirical and simulated response data. Comparisons between CAT administrations without and with the enforcement of content and item pool usage constraints were examined.

Results

The unconstrained CAT exhibited a high degree of variation in items selected from different substrata of the item bank. Contrastingly, the shadow-test approach delivered CAT administrations conforming to all specifications with a minimal loss in measurement efficiency.

Conclusions

The optimal test design and shadow-test approach to CAT provide a flexible framework for solving complex test-assembly problems with better control of their domain coverage than for the conventional use of CAT in PRO measurement. Applications in a wide array of PRO domains are expected to lead to more controlled and balanced use of CAT in the field.

     

Measurement invariance,the lack thereof,and modeling change

Purpose

Measurement invariance issues should be considered during test construction. In this paper, we provide a conceptual overview of measurement invariance and describe how the concept is implemented in several different statistical approaches. Typical applications look for invariance over things such as mode of administration (paper and pencil vs. computer based), language/translation, age, time, and gender, to cite just a few examples. To the extent that the relationships between items and constructs are stable/invariant, we can be more confident in score interpretations.

Methods

A series of simulated examples are reported which highlight different kinds of non-invariance, the impact it can have, and the effect of appropriately modeling a lack of invariance. One example focuses on the longitudinal context, where measurement invariance is critical to understanding trends over time. Software syntax is provided to help researchers apply these models with their own data.

Results

The simulation studies demonstrate the negative impact an erroneous assumption of invariance may have on scores and substantive conclusions drawn from naively analyzing those scores.

Conclusions

Measurement invariance implies that the links between the items and the construct of interest are invariant over some domain, grouping, or classification. Examining a new or existing test for measurement invariance should be part of any test construction/implementation plan. In addition to reviewing implications of the simulation study results, we also provide a discussion of the limitations of current approaches and areas in need of additional research.

     

Motives for Filing a False Allegation of Rape

The list of motives by Kanin (1994) is the most cited list of motives to file a false allegation of rape. Kanin posited that complainants file a false allegation out of revenge, to produce an alibi or to get sympathy. A new list of motives is proposed in which gain is the predominant factor. In the proposed list, complainants file a false allegation out of material gain, emotional gain, or a disturbed mental state. The list can be subdivided into eight different categories: material gain, alibi, revenge, sympathy, attention, a disturbed mental state, relabeling, or regret. To test the validity of the list, a sample of 57 proven false allegations were studied at and provided by the National Unit of the Dutch National Police (NU). The complete files were studied to ensure correct classification by the NU and to identify the motives of the complainants. The results support the overall validity of the list. Complainants were primarily motivated by emotional gain. Most false allegations were used to cover up other behavior such as adultery or skipping school. Some complainants, however, reported more than one motive. A large proportion, 20% of complainants, said that they did not know why they filed a false allegation. The results confirm the complexity of motivations for filing false allegations and the difficulties associated with archival studies. In conclusion, the list of Kanin is, based on the current results, valid but insufficient to explain all the different motives of complainants to file a false allegation.