No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Goal Oriented Measurement with the IRES questionnaire: A critical interim statement
Abstract
This paper gives a critical view on "Goal Oriented Measurement" (ZOE, Zielorientierte Ergebnismessung) with the IRES (Indicators of Rehabilitation Status) questionnaire. Gerdes (1998) proposed this method for individualizing outcome measurement in rehabilitation research. The rationale of Goal Oriented Measurement is described and differentiated from Goal Attainment Scaling and Patient Preferences. Subsequently, important shortcomings of Goal Oriented Measurement are pointed out: insufficient validity with regard to selecting clinically relevant problems, possible regression artifacts, unsuitably aggregated scores, possible reactivity, possible changes of individual problems, possible deteriorations in problems not initially selected, and plurality as well as small size of subsamples. Overall, Goal Oriented Measurement has to undergo substantial improvement.
... The method of benefit assessment used in the PBI is grounded on the method of goal attainment scaling and the goal-oriented outcome measurement. [29][30][31][32][33] These methods have been expanded to the PBI concept based on the German requirements by the German Pharmaceuticals Market Reorganisation Act (AMNOG), which was introduced in 2011. This implies the patient relevant benefit to be a primary target of benefit assessment. ...
Purpose
Allergic rhinoconjunctivitis (ARC) is one of the most common diseases worldwide. Allergen immunotherapy (AIT) is the only causal treatment available so far. Due to health policy provisions, the assessment of treatment benefit from the patient’s perspective is of high relevance. To date, no instrument for assessing treatment needs and benefits of patients with ARC who receive AIT has been published. The aim of the study was to validate an instrument to assess the patient-relevant treatment benefit of patients with ARC who receive AIT.
Methods
We developed the Patient Benefit Index questionnaire for AIT (PBI-AIT), consisting of 33 items. Longitudinal data of patients with ARC were used to test feasibility, reliability and validity. The PBI was compared between the beginning of the study (t1) and the end of the study (t5).
Results
N = 279 patients with AIT completed the PBI-AIT at t1, n = 333 at t5; n = 226 at both timepoints. Mean number of missing values per patient was 0.7 in the Patient Needs Questionnaire (PNQ) at t1 and 1.2 in the Patient Benefit Questionnaire (PBQ) at t5. The internal consistencies measured by Cronbach’s alpha were 0.98 (PNQ) and 0.99 (PBQ). The mean PBI of the patients with AIT was significantly lower at t1 and improved at t5. The PBI-AIT correlated with all tested external criteria at t5. The correlation between PBI-AIT and satisfaction with previous treatment (r = −0.57, p < 0.001) was higher than the correlation between PBI-AIT and current disease severity (r = −0.26, p < 0.001).
Conclusion
The results indicate feasibility, reliability, convergent and discriminant validity as well as sensitivity to change of the PBI-AIT.
... Zielkriterium der "Response" ist somit der Anteil an Patienten in %, bei denen ein PBI ≥ 1 erreicht wurde. Dieses Vorgehen stellt eine Erweiterung der Vorarbeiten zur zielorientierten Ergebnismessung [22] unter Berücksichtigung einschlägiger Kritik [23] dar. ...
Hintergrund: Die Verbesserung der Lebensqualität und die Generierung eines hohen patientenseitigen Nutzens sind die Hauptziele der Akne-Therapie.
Zielsetzung: Erhebung des Nutzens und der Verträglichkeit einer topischen Kombination aus Clindamycin und Benzoylperoxid bei Akne vulgaris an einer großen bundesweiten Stichprobe.
Methoden: Die Nutzenbewertung erfolgte im Zuge einer offenen, nicht kontrollierten Beobachtungsstudie an konsekutiv n = 906 Patienten, die bundesweit von insgesamt 205 Dermatologen behandelt wurden. Messzeitpunkte waren der Therapiebeginn sowie nach 3 – 5 (im Mittel: 4) Wochen sowie nach 10 – 12 Wochen. Klinische Zielparameter waren der „lesion count” aller Akneläsionen sowie die Globalurteile von Arzt und Patient. Die Lebensqualität wurde mit dem Acne Disability Index ermittelt, der patientenseitige Nutzen mit dem „Patient benefit index” (PBI).
Ergebnisse: In allen klinische Outcomes fanden sich unter der topischen Kombinationstherapie nach 4 wie auch nach 10 – 12 Wochen signifikante Besserungen (p < 0.01). Die Lebensqualität verbesserte sich ebenfalls signifikant. Die Patienten äußerten vor Therapie ein breites Spektrum an für sie bedeutsamen Therapiezielen. Der Anteil an Patienten mit relevantem definierten Nutzen (PBI > 1) lag nach 4 Wochen bereits bei 90,2 %, nach 10 – 12 Wochen bei 93,0 %. Fazit: Die Kombinationstherapie aus Clindamycin und Benzoylperoxid-Gel ist eine effektive und gut verträgliche Therapieoption der leichten und mittelschweren Akne vulgaris. Die Behandlung geht bei einem Großteil der Patienten mit relevanten Verbesserungen des patientendefinierten Nutzens einher.
... Da die beiden Beschwerden nicht für alle Patienten relevant waren, wurde für die Ergebnisdarstellung ein duales Verfahren gewählt: Einerseits wurden die Effektgrößen konventionell für alle Patienten mit 5 Messungen ermittelt (Tab. 6, Zeile 2a und 3a), andererseits wurden die Effektgrößen auch nach dem Verfahren der zielorientierten Ergebnismessung (ZOE) nach Gerdes [18,56] bestimmt (Tab. 6, Zeilen 2b und 3b). ...
Hintergrund: Ziel der Davoser-Outcome- Studie (DOS) war es, die kurz- und längerfristigen Effekte stationärer Heilbehandlungen in der Hochgebirgsklinik Davos (Schweiz) zu untersuchen. Methodik: Die prospektive einarmige Beobachtungsstudie beinhaltete patientenseitig 5 schriftliche Datenerhebungen (Aufnahme, Entlassung, Nachbefragungen 6, 12 und 24 Monaten nach Entlassung) und arztseitig 2 Messungen (zu Beginn und am Ende der Intervention). Im Untersuchungszeitraum nahmen 61% der Neuaufnahmen an der Studie teil; die Erfassungsquoten bei den 3 Nacherhebungen lagen bei 80,4%, 73,4% und 65,8%. Stichprobe: Die Ausgangsstichprobe umfasste 896 Patienten mit unterschiedlichen pneumologischen (ca. 70%) und dermatologischen Diagnosen (ca. 30%). Das Durchschnittsalter der Patienten lag bei 49,1 Jahre, knapp 60% der Patienten waren Frauen, die durchschnittliche Behandlungsdauer betrug 27,4 Tage. Bei den Patienten lag mehrheitlich eine ausgeprägte Chronifizierung der Beschwerden vor. Etwa 70% der Studienteilnehmer waren Erwerbspersonen. Kennzeichnend ist weiterhin ein eher höheres Bildungsniveau (44,3% hatten einen höheren Schulabschluss) und eine mittlere bis gehobene berufliche Stellung. Die Stichprobe kann als weitgehend repräsentativ für den Beobachtungszeitraum angesehen werden: Ergebnisse: Konstant über alle Messzeitpunkte hinweg zeigten sich bemerkenswert hohe patientenseitige Nutzenbewertungen der Heilbehandlung sowie eine konstant hohe Zufriedenheit mit der Behandlung. Bei Entlassung konnte eine beachtliche Besserung des gesundheitlichen Befindens (ES = 1,26) beobachtet werden, die sich im weiteren zeitlichen Verlauf zwar etwas abschwächte, 2 Jahre nach Entlassung aber noch eine gute Nachhaltigkeit zeigte (ES = 0,60). Mittels zielorientierter Ergebnismessung (ZOE nach Gerdes) konnten weiterhin nachhaltige Besserungen der Atem- und Hautbeschwerden festgestellt werden. Auch bei den überprüften indikativen Ergebnisparametern (1-Sekundenkapazität, spezifischer Atemwegswiderstand, PASI-Index und SCORAD-Index) waren bei Entlassung zum Teil imposante positive Veränderungen zu verzeichnen. Ebenso zeigten sich in Vorher-Nachher-Vergleichen auch Reduktionseffekte hinsichtlich der kostenrelevanten Merkmale Anzahl der Notarztrufe und Notfalleinlieferungen (im zweiten Jahr nach der Intervention waren Reduktionen von 54% bzw. 26% zu verzeichnen). Ein äußerst günstiges Bild konnte auch hinsichtlich der Return- to-work-Quoten beobachtet werden, die den Anteil der Patienten beziffern, die vor Beginn der Intervention berufstätig waren und auch noch 6, 12 und 24 Monate danach berufstätig sind (92,2% 1/2 Jahr nach Entlassung und 87,1% 2 Jahre nach Entlassung). Schlussfolgerungen: Die Ergebnisse zeigen, dass stationäre Heilbehandlungen in der Hochgebirgsklinik Davos – größtenteils Rehabilitationsmaßnahmen – zu moderaten bis deutlichen kurz- und längerfristigen Verbesserungen bei Patienten mit Atemwegserkrankungen und Hauterkrankungen führen. Die vorliegenden Resultate deuten eine zufriedenstellende Nachhaltigkeit der Effekte an, sie bestätigen frühere Evaluationsstudien in großem Maße. Abschließend wird die Studie unter methodischen Gesichtspunkten diskutiert.
... This procedure is an extension of previous work on goal attainment scaling (GAS) [7,9,13,18,19] and on goal-oriented measurement of outcomes (zielorientierte Ergebnismessung, ZOE) [11,17] taking pertinent criticism into account [8,22]. It is an economical solution between individualized and generic recording, whereby two diVerent but related constructs (goal importance and goal attainment) are questioned at two diVerent time points. ...
Evaluation of therapeutic benefits from the patient's perspective is important in medical decision-making and reimbursement. This study aimed at developing and validating an instrument on patient-defined needs and benefits in dermatology. The questionnaire was developed according to international guidelines. The benefit assessment consists of two steps: before treatment, every patient defines his treatment needs according to a standardized list. After treatment, the patient rates the degree of benefits achieved. A "patient benefit index" (PBI) is calculated by averaging the preference-weighed results of all items. The PBI questionnaire was validated in a sample of 500 patients with ten skin diseases and in a treatment study on 906 patients with acne. The patients defined a broad spectrum of needs and treatment benefits, indicating disease-specific patterns. The PBI showed good feasibility, reliability (Cronbach's alpha >0.91) and construct validity, high responsiveness, and discrimination between subgroups. The PBI permits valid evaluation of patient-relevant benefits in dermatological treatment.
Background: The aim of the Davos Outcome Study (DOS) was to investigate short and longer-term effects of inpatient treatment in the Alpine Clinic Davos (Switzerland). Methods: The prospective single-arm observational study included 5 data collections for patients (admission, discharge, three followups 6, 12 and 24 months after discharge) and 2 measurements for clinicians (at the beginning and end of the intervention). During the study period, 61% of admissions participated in the study; the participation rates in the three follow-up surveys were 80.4%, 73.4% and 65.8%. Sample: The initial sample consisted of n = 896 patients with different pulmonary (70%) and dermatological diagnoses (about 30%). The average age of the patients was 49.1 years, almost 60% of the patients were women, the average duration of treatment was 27.4 days. The majority of patients had chronic complaints. Approximately 70% of study participants belonged to the working population (employed or unemployed). Furthermore, characteristic was a rather higher level of education (44.3% had a high school education) and a middle to high occupational status. The sample can be considered as broadly representative for the observation period. Results: At the patient level all measurements showed remarkably high benefit assessments as well as a consistently high satisfaction with the treatment. At discharge a very distinctive short-term improvement of health perception (ES = 1.26) was observed, which showed a good sustainability two years later (ES = 0.60). By means of goal-oriented outcome measurement (ZOE according to Gerdes) sustainable improvements of the respiratory and skin complaints also could be detected. Moreover, partly very striking positive effects at discharge were also found at the level of indicative outcome measures (1-second capacity, specific airway resistance, PASI- and SCORAD index). Similarly, reduction effects were seen in beforeand- after comparisons of the cost-related variables ‘number of ambulance calls’ and ‘emergency admissions’ (in the second year after the intervention reductions of 54% and 26% were recorded). A very favorable result could also be observed regarding of returnto- work rates, which represent the proportion of patients who were employed before the intervention and were employed also 6, 12 and 24 months thereafter (92.2% 1/2 year after discharge and 87.1% 2 years after release). Conclusions: The results show that inpatient medical treatments in Alpine clinic Davos – mostly rehabilitation – are associated with moderate to considerable short-term and longer-term improvements in patients with respiratory diseases and skin diseases. The present results indicate a satisfactory sustainability of these effects, they confirm previous evaluation studies to a great extent. Finally, the study is discusses under methodological point of view.
Hintergrund: Das SGB IX hat die Fragen nach Wirksamkeit und Nutzen unseres Systems der medizinischen Rehabilitation (einer komplexen multimodalen, multidisziplinären und verhaltensmedizinisch orientierten Behandlungsmethode) intensiviert, auch - aber nicht nur - in Hinblick auf chronische Rückenschmerzen. Auf diese Indikationsgruppe entfielen 2002 rund 29 % aller medizinischen und sonstigen Rehabilitationsleistungen der gesetzlichen Rentenversicherung. In einer systematischen Literaturübersicht wurde für den Zeitraum 1980 bis Mitte 2001 eine möglichst vollständige Erfassung und Bewertung von bislang in Deutschland durchgeführten Studien zu den Effekten stationärer medizinischer Rehabilitation bei chronischen Rückenschmerzen vorgelegt. Ziel des vorliegenden Beitrages ist es, diese Übersicht bis Ende 2003 zu aktualisieren und kritisch zu diskutieren. Methodik: In enger Anlehnung an das Vorgehen im ersten Review erfolgten eine mehrgleisige Studiensuche (elektronische Datenbanken, Handsuche, Befragung), eine Bewertung der methodischen Studienqualität (nach Empfehlungen der Cochrane Back Review Group) und die Extraktion von zentralen Studienmerkmalen. Für sechs Outcomeparameter wurden Effektstärken nach einer Formel für Prä-Post-Vergleiche berechnet und mit prognostisch relevanten Studien- und Probandenmerkmalen in Beziehung gesetzt. Die Einzeleffektstärken wurden zu kurz- wie längerfristigen Gesamt-Effektstärken zusammengefasst und mit den Befunden aus internationalen Studien verglichen. Ergebnisse: Die Literatursuche für den Zeitraum Juli 2001 bis Dezember 2003 führte zum Einschluss von 16 Untersuchungen. Kontrollierte Studien, die bei chronischen Rückenschmerzen kurz- und längerfristige Effekte einer stationären multimodalen Behandlung mit „keiner” Behandlung bzw. der „normalen” medizinischen Grundversorgung vor Ort vergleichen, fehlen weiterhin. Eine Steigerung der Studienqualität war im Vergleich zum Vorzeitraum nicht zu beobachten. Kurzfristig werden je nach Outcomeparameter kleine (z. B. Funktionskapazität) bis große Effekte (z. B. Vitalität) erzielt. Verglichen mit den älteren Studien liegen die Gesamteffektstärken der neueren Studien teils höher (z. B. Depressivität), teils niedriger (z. B. Schmerzintensität) oder auf gleichem Niveau (Katastrophisieren). Die mittelfristigen Gesamteffektstärken fallen in den neuen Studien bei fünf der sechs Parameter geringer aus und erreichen höchstens kleine positive Effekte. Diskussion und Schlussfolgerung: Die Größe der beobachteten längerfristigen Effekte weist auf ein Grundproblem der stationären medizinischen Rehabilitation bei chronischen Rückenschmerzen hin: eine unbefriedigende Nachhaltigkeit. Der Vergleich mit internationalen Befunden eines Cochrane-Reviews unterstreicht diesen Befund. Unter zwei Gesichtspunkten wird dieses Problem diskutiert: Zum einen werden verschiedene inhaltliche Gründe für eine geringe Nachhaltigkeit angeführt, zum anderen werden aus methodischer Sicht unterschiedliche Varianten einer „maskierten” Nachhaltigkeit identifiziert. Überzeugende Evidenz für eine generelle Wirksamkeit stationärer Rehabilitation bei chronischen Rückenschmerzen lässt sich auch nach den neuesten nationalen Studien nicht finden.
Abstract
Regression to the mean
The evaluation of rehabilitation programs may be distorted by regression to the mean: In a group of patients with extreme measurement values, these values tend to be less extreme on a following point in time due to merely random components and regardless of a ‘true’ treatment effect. If this effect is not taken into account, the effectiveness of rehabilitation programs may be estimated wrongly. In this paper regression to the mean is explained comprehensively and common misunderstandings are clarified. It is shown, which conditions are crucial for regression to the mean to arise and which factors determine its strength. Furthermore it is shown how regression to the mean should be controlled in repeated measurement designs.
Goals:
It is widely known that goals and goal agreement are important components of a modern approach to medical rehabilitation. The present work gives an overview of the current state of research regarding patient goals for medical rehabilitation by reviewing relevant German pub-lications between 2000 and 2010. This review focused on (1) data collection methods of rehabilitation goals, (2) patient goals, and (3) agreement between the goals of patients and their clinicians.
Methods:
A search strategy combining electronic databases and hand search was applied. A priori inclusion and exclusion criteria were applied. A self-developed goal-catalogue was used to synthesize the literature.
Results:
A total of 20 publications were included, 11 of which explored both patient and clinicians perspectives. ad (1): Only 4 goal-assessment instruments in the field of medical rehabilitation exist, but none has been established as a standard. The instruments differ in how differentiate they depict different goals areas. ad (2): The goal structure of medical rehabilitation patients corresponds to the respective indications. The 3 top goals in all patient groups included physical and/or psychosocial objectives. Information and occupational goals are rarely represented among the 3 top goals mentioned. ad (3): Patients have more numerous as well as differing goals then their treating clinicians. Goals of physical functions (e. g., enhancement of stamina) and superior rehabilitation goals (e. g., return to work) have the best agreement. Mental and maintenance goals are more frequently mentioned by the patients while pain and symptom-related goals are more frequently mentioned by the doctors. There are indication-specific differences for goals regarding information.
Conclusion:
Rehabilitation goals are highly valuable in the rehabilitation process. Finding only 20 relevant publications, generalizability of study results is limited. Due to high variability in methodological approach and presentation of results, comparisons of results across studies reviewed are severely limited. Developing survey standards and using uniform metrics could contribute to standardizing study endpoints. The goals of patients and clinicians are formed in individual life or work contexts, which are influenced by numerous factors (e. g., knowledge, illness/health concepts, assumptions regarding rehabilitation treatment), representing individual expertise that complement one another. Since compatible goals are essential for successful rehabilitation treatment, an exchange of goals and expectations as well as the establishment of joint target agreements should precede any rehabilitation programme.
The quality assurance programme of the statutory health insurance funds (QS-Reha®-Programme) is presented. In autumn 2005 about 200 rehabilitation centers with nearly all indications of medical rehabilitation are participating in this comprehensive external quality assurance programme. In each center, structural, process and outcome quality, including patient satisfaction, are measured. Results concerning short-term and mediumterm effects show significant effects immediately after rehabilitation. Medium-term effects 6 months after rehabilitation are less favourable. Effect sizes concerning health-related quality of life range between 0.20 und 0.30. But one have to take into consideration that in many cases goal-oriented outcome assessment (analyses based on subgroups of patients for whom the corresponding outcome represents a rehabilitation goal) results in higher effect sizes. This is valid even after adjusting for regression to the mean by a residualized change score.
Diverse methods are available for evaluation of (medical) interventions. In each case one has to decide on a specific method. Our aim was to analyze typical problems involved in the measurement of change. Different methods are delineated, and their specific pros and cons are set out. Subsequently, empirically derived recommendations are outlined on which method should be employed for which problem and under which circumstances. A characteristic of rehab treatment is that as a rule a multitude of problems are addressed, and accordingly, treatment goals are heterogenic. Straightforward recommendations for one or the other method cannot be given.
© Georg Thieme Verlag KG Stuttgart · New York.
Empirical evidence of the efficacy of drugs and therapeutic procedures becomes more important in industrial countries. The assessment of patient benefit from the patient's perspective is of particular relevance. The Patient Benefit Index (PBI) for skin diseases is a validated instrument to assess patient-relevant benefit in patients with skin diseases. So far, no instrument for the assessment of patient-relevant needs and benefits in patients with psoriasis has been published. Objective of the study was the validation of an instrument to assess patient benefit in psoriasis treatment. Patient-relevant treatment needs and benefits in psoriasis patients were recorded with the PBI questionnaire in two studies conducted in 2007. Treatment goals and benefits were used to calculate an importance-weighted PBI. Data of n = 2,009 patients in the cross-sectional study and n = 93 patients in the longitudinal study were used to test validity, feasibility and reliability of the PBI. The PBI was feasible with a rate of missing values ≤1.5 % in PNQ and ≤2.0 % in PBQ. The subscales of the PBI were internally consistent (Cronbach's alpha = 0.68-0.87). The PBI showed convergent validity regarding the quality of life, psoriasis area and severity index, and two single questions on treatment benefit used in the longitudinal study. The PBI is a suitable instrument for the assessment of patient-reported benefit in the treatment of psoriasis.
The question of which methods should be used to assess the effects of medical rehabilitation has a long and controversial history. With regard to this background the project "Outcome measurement in medical rehabilitation" aimed at developing a better understanding of the process of change and its assessment. We also looked into possible causes for discrepancies between the results of direct and indirect measures of change. Aims of our study were: (1) to picture trajectories of change in a simple and descriptive way, (2) to compare the resulting solutions, (3) to highlight relations with direct measurement of change and/or global estimation of effects, (4) to compare the predictive value of different measurements of change.
We used available data from rehabilitation research which covered direct and indirect measurement of change as well as global measurement of effects and which therefore enabled us to compare different methods of outcome measurements. The well documented record includes data from n=466 patients with chronic back pain. Different trajectories (3 and 5 groups) were defined using their pre/post data.
Depending on limits chosen for positive or negative courses and chosen outcome 20% to almost 40% of the patients showed improvements over the follow-up period. About the same percentages changed for the worse. However, two-thirds of the patients improved at least in one outcome. Compared with those, who did not experience improvements in any outcome, this group indicated better global rehabilitation effects. The different types of trajectories (3 and 5 groups) substantially contribute to the explained variance of catamnestic status at 12 months beyond other predictors as well as beyond initial status. The same applies to the prediction of disability days.
The description of trajectories of change yields useful results. In contrast to complex statistical methods we were able to identify groups of patients that can easily be described.
Assessing therapeutic benefit of any drug and medical device is essential in registration and cost reimbursement decisions in Germany and in many nations. In this study, a method for the assessment of patient-relevant benefits in wound therapy was developed and validated. A total of 83 items on treatment benefit from the patients' perspective were collected in an open survey, including n = 50 patients with chronic wounds. The item pool was compiled to a list of 22 items by an interdisciplinary panel of experts including patients. The item list is presented prior to therapy to assess patient-relevant treatment needs and during or after therapy to establish if benefits have been attained. A weighed patient benefit index (PBI) is calculated from the items of both questionnaires. The instrument was examined for practical feasibility, reliability, and validity in a prospective study involving n = 172 patients with acute or chronic wounds treated by vacuum-assisted therapy. Validation criteria were: change in generic and disease-specific quality of life; judgment of efficacy by patients and physicians; treatment satisfaction; patients' willingness to recommend the therapy to others. Construct validity was given for all criteria applied. Cronbach's alpha was 0.88. The instrument was well-accepted by patients and rated relevant for the assessment of benefit in wound treatment.
Goal setting is regarded as a key element in the rehabilitation process. Information about current goal setting practice is limited. However, there is potential for further improvement, e. g. as far as patient participation in the goal setting process is concerned. The study reports results of a survey on the current practice of goal setting in medical rehabilitation, focusing on development potential. The study examines acceptance and requirements for goal setting as well as patients' and professionals' experiences regarding goal setting during the rehabilitation process, with an emphasis on patient participation.
A total of n=40 rehabilitation professionals and n=210 inpatients with a diagnosis of chronic back pain, diabetes mellitus type 2 or coronary heart disease were surveyed at six rehabilitation centres using a questionnaire. Questionnaires contained predominantly closed-ended items regarding the current practice of goal setting. Several items were identical for both groups. In addition to the quantitative evaluation by means of frequency analyses free text data were evaluated.
Rehabilitation professionals saw various benefits in goal setting with patients. Many professionals experienced patients to have personal goals for their rehabilitation, and most of them believed that patient participation in goal setting is possible. Also, barriers and requirements for goal setting were identified. A consistent concept for goal setting, involvement of and exchange between the different occupational groups and an elaborate handling of information in the context of goal setting seem to be realised at least partially. Professionals and patients reported similar frequencies of talks on goal setting at different times during the rehabilitation course. Patient participation seems to be realised to some extent but not comprehensively. The results show slight discrepancies between patients' and professionals' statements.
Current practice of goal setting in inpatient rehabilitation of patients with the diagnoses named above is altogether on a relatively advanced level in the rehabilitation centres taking part in the study. The study identifies potential for development concerning a comprehensive implementation of goal setting, the realisation of patient participation, goal documentation and their integration into rehabilitation. Moreover, deeper involvement of the rehabilitation team and a stronger conceptual integration of the subject within the centres seem desirable. This can be taken up within the scope of interventions.
With this study the suitability of two instruments for assessing changes in the quality of life was examined. Data were collected in mother-child rehabilitation centres. The Kiddy-KINDL (n=727), a parent-based instrument for assessing health related quality of life in children (age 4 to 7 years) and the Kid-KINDL (n=716), a self-report questionnaire for children (age 8-12 years) were used at the beginning and the end of rehabilitation. In addition in a subgroup of n=420 children the Child Behavior Checklist was used in order to identify behavioral and emotional problems. The psychometric analyses revealed that both instruments were well accepted by mothers and children. The reliabilities of the sum scores as well as the convert validity were sufficient. The results of the Kid-KINDL were affected by low reliabilities and ceiling effects on subscales. Thus, in repeated measurements only changes of sum scores can be interpreted with sufficient accuracy. However, the use of the self-report questionnaires can be recommended because the known-group validity was high. Both versions of the KINDL are suitable for assessing treatment effects of preventive measures in rehabilitation clinics, considering the low reliabilities of subscales for the Kid-KINDL.
Georg Thieme Verlag KG Stuttgart.New York.
Supportive skin care for irritated and inflamed skin is one of the most important measures in the prevention and treatment of eczema and sensitive skin.
To develop and validate an instrument for the evaluation of patient-relevant benefit in the supportive care of irritated skin with nonpharmacological topical agents.
Patient-defined treatment objectives and benefits of supportive skin care were determined in an open survey of patients with irritated skin. A pilot questionnaire was constructed according to the Patient Benefit Index (PBI). The questionnaire was tested for feasibility and validity in 1,886 patients with various irritated skin conditions.
From a total of 90 characteristics of basic therapy benefit, a 23-item questionnaire was constructed. This questionnaire ('PBI-k') proved to be feasible, reliable and was associated with a high level of patient acceptance in the surveillance field. The questionnaire showed good internal consistency, distribution characteristics and convergent validity with patient satisfaction.
The PBI-k is the first specific instrument developed for the evaluation of patient-defined benefit in supportive skin care with nonpharmacological topical agents. Feasibility and psychometric properties make this questionnaire suitable for application in studies involving patients with irritated, sensitive skin.
Benefit assessment of drugs and medical products has become a legally established feature of medical research. A standardized assessment of benefits using scientifically sound and valid methods is essential.
Development, validation and practical evaluation of an instrument to record patient benefit in treatment of acne.
In open interviews with n = 50 patients, possible benefits of the therapy from the patients' point of view were recorded. The item pool thus generated was reviewed by a panel of dermatologists, psychologists and patients and transferred to a 23-item questionnaire. This is used prior to therapy to assess patients' desired benefits and after therapy to record the perceived benefits. The therapy goals and the resulting benefits are then used to generate a weighted 'Patient Benefit Index' (PBI). The procedure has been tested for its validity and feasibility in n = 923 patients with acne.
Patients accepted the instrument and deemed it to be easily understandable. Additionally, the method proved itself to be internally consistent, constructively valid and sensitive to changes.
The Patient Benefit Index (PBI) is a valid and highly accepted practical instrument for recording patient benefit. The PBI permits an individualized, patient-weighted assessment of the benefits of acne therapy.
Measuring the results of rehabilitation interventions presents a number of issues regarding content and method, two of which have been selected for discussion in view of the findings of current research--the significance of patient orientation and the relation to the International Classification of Functioning, Disability and Health, ICF. Compilation of patients' treatment goals, expectations and preferences, patient participation in the development of assessment instruments, compilation of patients' evaluations of treatment results and consideration of the subjectivity of the physician as well as interaction between patient and physician were discussed with respect to involving patients in measuring results. The ICF is a terminology system presenting a uniform international classification for describing health conditions that could assume the function of a common language for the members of various occupations involved in medical rehabilitation. Orienting the measurement of results to the ICF is an obvious next step. This can promote patient orientation, as the categories used by the ICF--in particular for the domains of activities and participation--are formulated in terms relevant to daily routine and are thus pertinent to the patients' lifestyle. The consequences resulting from this overview concern future research needs on the one hand, and on the other hand tips for carrying out a patient-oriented, ICF-based measurement of results. The need for research becomes especially clear regarding the measurement of results based on patient preferences, the determination of the participation relevance perceived by the patient as a criterion for "patient significance" (analogous to "clinical significance"), the integration and weighting of patient and physician assessments of success, the consideration of physicians' subjective concepts and patients' communication preferences, and the design of new, ICF-oriented assessment instruments.
In addition to clinical efficacy, patient-defined benefit assessment has become an important outcome parameter. Thus far, no such instrument has been developed for vitiligo.
Development and validation of a patient-defined benefit questionnaire in the therapy of vitiligo.
Open questioning of 50 vitiligo patients generated 110 benefit items, which were converted into a 26-item questionnaire by a panel of dermatologists, psychologists and patients. This was used to record patient-defined needs prior to therapy and to evaluate patient benefit attained after therapy. A 'patient benefit index' (PBI) was formed on the basis of both. Validation was based on data of n = 1,023 vitiligo patients.
The questionnaires were feasible in clinical practice, Cronbach's alpha (patient need questionnaire) was 0.94. The PBI showed convergent and discriminant validity with respect to quality of life and patient satisfaction.
The PBI for vitiligo is a valid instrument, which is highly accepted in practice for recording patient-reported benefit.
A mental health enterprise may be described by either (a) rather general philosophical total mental health goals, or (b) highly diverse and individualized patient-therapist goals. Goals a. have not provided a workable framework for program evaluation. This paper proposes that evaluation be done in the framework of goals b. by setting up, before treatment, a measurable scale for each patient-therapist goal, and specifying, for each patient, a transformation of his overall goal attainment into a standardized T-score. This method, together with random assignment of patients to treatment modes, was devised to permit comparison of treatment modes within a program, but it also provides a good basis for a judgmental evaluation of the total program.
Rehabilitation erhebt den Anspruch einer ganzheitlichen, interdisziplinär angelegten Diagnostik und Therapie. Sie soll vom individuellen Rehabilitationsbedarf ausgehen, die aktive Mitwirkung der Rehabilitanden fördern und gleichermaßen die körperliche, psychische und soziale Ebene der jeweiligen Gesundheitsstörung und ihrer Folgen berücksichtigen (VDR 1996). Behandelt werden in erster Linie chronische Erkrankungen, die multifaktoriellen Einflüssen unterliegen. Zugrunde gelegt wird letztlich ein „bio-psycho-soziales“ Modell, wie es v. a. in der Psychosomatik entwickelt wurde (vgl. z. B. Engel 1977). Behandlungskonzepte in der Rehabilitation versuchen deshalb, eine Vielzahl unterschiedlicher Maßnahmen oder Therapiebausteine zu integrieren und individuell auf den jeweiligen Patienten abzustimmen. Sie sind multimethodal und komplex ausgelegt und erfordern die intensive Zusammenarbeit von Fachkräften aus sehr unterschiedlichen Disziplinen (Ärzte, Psychologen, Pflegekräfte, Pädagogen, Sozialarbeiter, Physiotherapeuten etc.).
Examines regression effects in longitudinal sequences of observations by formulating expectations (Es) for later observations conditioned on an initial selection score value. The Es are developed for several variations of classical test theory and autocorrelation models. Es based on the general concept of regression are seen not only to depart from those depicted in the psychometric lore but to vary considerably from one underlying model to another, particularly when moving from the 2-occasion to a multiple-occasion measurement framework. Regression toward the mean is not a ubiquitous phenomenon, nor does it always continue across occasions. It is necessary to specify the characteristics of model assumptions to understand the when, how, and extent of regression toward the mean. Past interpretations have been incomplete and to an extent incorrect because they focused largely on a limited circumstance: 2-occasions of measurement and simplexlike correlation matrices. (23 ref) (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Explicates the fundamental nature of regression toward the mean, which is frequently misunderstood by developmental researchers. While errors of measurement are commonly assumed to be the sole source of regression effects, the latter also are obtained with errorless measures. The conditions under which regression phenomena can appear are first clearly defined. Next, an explanation of regression effects is presented which applies both when variables contain errors of measurement and when they are errorless. The analysis focuses on cause and effect relationships of psychologically meaningful variables. Finally, the implications for interpreting regression effects in developmental research are illustrated with several empirical examples. (21 ref.) (PsycINFO Database Record (c) 2012 APA, all rights reserved)
The measurement of individual change is approached from the standpoint of individual time paths and statistical models for individual change. The authors consider both statistical and psychometric properties of measures of individual change and examine measures of change for data with more than 2 observations on each individual. It is noted that many conclusions conflict with previous behavioral science literature. (63 ref) (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Given a series of consecutive measurements on a random sample of individuals, it is often of interest to investigate whether there exists a relationship between the rate of change and the initial value. Assuming that the observations deviate in a random manner from the true values, straightforward regression computations will yield biased results. It is shown that, in the case of the normal distribution, the maximum likelihood (ML) estimates of the second-order moments of the true slope and the true initial value are obtained by simple adjustments of the corresponding moments of the estimated quantities. An asymptotic formula for the standard error of the regression coefficient of slope on initial value is derived, and the methods are applied to longitudinal blood pressure data. The case with concomitant variables is discussed briefly.
Wie in Kap. 2.4 erläutert wurde, waren sowohl im Patientenfragebogen als auch im Arztbogen eine Vielzahl möglicher Zielparameter vorgegeben, aus denen bei Reha-Beginn je nach individueller Situation der Patienten die jeweils für den Einzelfall relevanten und aussagekräftigen Parameter ausgewählt werden sollten. Von dieser Möglichkeit ist in den Kliniken in unterschiedlicher Weise Gebrauch gemacht worden, und zwar so, daß ganz typische Unterschiede sowohl zwischen den Indikationsgebieten als auch zwischen den verschiedenen Zieldimensionen (über alle Indikationen hinweg) sichtbar werden. Wir meinen deshalb, daß es sich lohnt, diese Unterschiede aufzuzeigen und einige Interpretationen dazu zur Diskussion zu stellen.
In den 60er Jahren brachte die Einführung der staatlichen Mental Health Programs in den USA der Evaluationsforschung einen beträchtlichen Aufschwung. Die Forderungen nach Effektivitätsnachweisen für die neuartigen Versorgungssysteme und die verschiedenen Einrichtungsformen ließen eine Reihe von verschiedenen Evaluationsmodellen und -techniken entstehen. Als ein zentraler Diskussionspunkt in der wissenschaftlichen Auseinandersetzung wurde die Frage nach der Adäquatheit von Erfolgskriterien für die Evaluation der einzelnen Programme thematisiert. Zugleich ergab sich eine wachsende Unzufriedenheit mit der relativen Unflexibilität standardisierter und normativer Meßinstrumente, die der Verschiedenartigkeit der individuellen Probleme nur wenig gerecht werden konnten. Auf dem Hintergrund dieser Entwicklungen wurde die Technik des Goal Attainment Scaling (GAS) erstmalig von Kiresuk u. Sherman (1968) als Evaluationsinstrument vorgestellt. Ausgehend von den Bemühungen der Arbeitsgruppe um Kiresuk im Program Evaluation Ressource Center (PERC) in Minneapolis erlangte das Verfahren eine rasche Popularität durch zahlreiche Anwendungen in den verschiedenen Bereichen.
Grawe and Braun (1994) proposed a computerized procedure for evaluating therapy effects, which is based on difference scores. However, in this procedure a post-pre-difference which is due only to measurement error may look as big as a post-pre-difference based on perfectly reliable measurements. Therefore, we propose two simple alternative indices which take into account the problem of measurement error. The first allows a simple evaluation of the statistical significance of change, the second serves to describe the degree of change in units of the pretest standard deviation. Finally, we present a simple modification of these indices taking into account not only the problem of measurement error, but also the problem of situational and/or interactional effects.
The simplex model is used to correct for attenuation in the correlation of status with gain for a variety of academic skills. Implications of the results for the study of the determinants of academic growth are discussed and also some possible implications for classroom instruction.
This study compares the responsiveness of three instruments of functional status: two disease-specific questionnaires (Oswestry and Roland Disability Questionnaires), and a patient-specific method (severity of the main complaint). We compared changes over time of functional status instruments with pain rated on a visual analog scale. Two strategies for evaluating the responsiveness in terms of sensitivity to change and specificity to change were used: effect size statistics and receiver-operating characteristic method. We chose global perceived effect as external criterion. A cohort of 81 patients with non-specific low back pain for at least 6 weeks assessed these measures before and after 5 weeks of treatment. According to the external criterion 38 patients improved. The results of both strategies were the same. All instruments were able to discriminate between improvement and non-improvement. The effect size statistics of the instruments were higher in the improved group than in the non-improved group. For each instrument the receiver-operating characteristic curves showed some discriminative ability. The curves for the Roland Questionnaire and pain were closer to the upper left than the curves for the other instruments. The sensitivity to change of the rating of Oswestry Questionnaire was lower than that of the other instruments. The main complaint was not very specific to change. The two strategies for evaluating the responsiveness were very useful and appeared to complement each other.
The statistical term “regression,” from a Latin root meaning “going back,” was first used by Francis Galton in his paper “Regression towards Mediocrity in Hereditary Stature.”1 Galton related the heights of children to the average height of their parents, which he called the mid- parent height (figure). Children and parents had the same mean height of 68.2 inches. The ranges differed, however, because the mid-parent height was an average of two observations and thus had its range reduced. Now, consider those parents with a mid-height between 70 and 71 inches. The mean height of their children was 69.5 inches, which was closer to the mean height of all children than the mean height of their parents was to the mean height of all parents. Galton called this phenomenon “regression towards mediocrity”; we now call it “regression towards the mean.” The same thing happens if we start with the children. For the children with height between 70 and 71 inches, the mean height of their parents was 69.0 inches. This is a statistical, not a genetic phenomenon.If we take each group of mid-parents by height and calculate the mean height of their children, these means will lie close to a straight line. This line came to be called the regression line, and hence the process of fitting such lines became known as “regression.”In mathematical terms, if variables X and Y have standard deviations sX and sY, and correlation r, the slope of the familiar least squares regression line can be written rsy/sx. Thus a change of one standard deviation in X is associated with a change of r standard deviations in Y. Unless X and Y are exactly linearly related, so that all the points lie along a straight line, r is less than 1. For a given value of X the predicted value of Y is always fewer standard deviations from its mean than is X from its mean. Regression towards the mean occurs unless r=1, perfect correlation, so it always occurs in practice. We give some examples in a subsequent note.
Given a series of consecutive measurements on a random sample of individuals, it is often of interest to investigate whether there exists a relationship between the rate of change and the initial value. Assuming that the observations deviate in a random manner from the true values, straightforward regression computations will yield biased results. It is shown that, in the case of the normal distribution, the maximum likelihood (ML) estimates of the second-order moments of the true slope and the true initial value are obtained by simple adjustments of the corresponding moments of the estimated quantities. An asymptotic formula for the standard error of the regression coefficient of slope on initial value is derived, and the methods are applied to longitudinal blood pressure data. The case with concomitant variables is discussed briefly.
Goal Attainment Scaling is an evaluation procedure directed at measuring client progress toward therapeutic goals. This critique
takes issue with the procedure conceptually and operationally and points out problems of validity and reliability. The authors
conclude that careful testing and development of the procedure is needed prior to further dissemination.
When individuals with high levels of a biological variable are given a treatment to lower these levels, it is important to be able to assess how much of any subsequent decrease is due to the treatment. The fact that individuals selected for their high levels on one occasion will (on average) show lower levels on subsequent occasions even in the absence of treatment is now recognized, and has been termed the ‘regression’ effect. The reverse is true for low levels.This paper presents a method for predicting how much change can be expected from regression, and thus a means of estimating the treatment effect. The analysis is based on measures of within-person and between-person variability, the within-person source being responsible for the regression effect. The effect that within-person variability has on misclassification of people into high-risk groups, and a means of determining how many estimates of one individual's level are required for a given precision of classification, are also derived from the same analytical approach.Examples are given using data on cholesterol levels following treatment with Clofibrate, caloric intake levels in a diet survey, and the relationship between the incidence of ischemic heart disease and systolic blood pressure level.
Available published and unpublished studies on Goal Attainment Scaling (GAS), cur rently the most popular outcome evaluation technique in the human sciences, were cri tically reviewed. Forty-one of ninety-one initial studies, which met minimal criteria of completeness of information reported and quality of research, were subjected to in-depth review. Conclusions were rather mixed and somewhat discouraging. The proliferation m the use of GAS as an evaluative technique has been accompanied by serious procedural and methodological problems. Despite numerous studies, the reliability and validity of GAS remain questionable. More optimistically, GASprocedures can serve a useful educa tional and intervention function, particularly in mental health settings, and patient in volvement in the goal-setting process as defined by GAS seems to enhance therapeutic effectiveness.
A simplex model is presented for the analysis of longitudinal academic growth variables in which only one measure is obtained at each time. When this model fits the observed data, then reliabilities and unattenuated correlations can be estimated except for the first and last periods.
The patient's capacity to identify and pursue realistic goals is often an inherent element in the admission, evaluation and treatment planning process in occupational therapy groups in mental health programs. The appropriateness, potential for realization and capacity to anticipate the steps entailed from initial goal setting through goal achievement is a critical skill that merits individualized treatment attention. This article reviews a structured system which involves the patient in stating goals in behavioral terms, in a graded sequence and is appropriate for functionally oriented task groups in partial hospitalization settings. This approach is based on Goal Attainment Scaling and lends itself to objective review of treatment outcomes.
The simplex model is used to correct for attenuation in the correlation of status with gain for a variety of academic skills. Implications of the results for the study of the determinants of academic growth are discussed and also some possible implications for classroom instruction.
Includes bibliographical references (p. 285 - 295) and index
Reviews recently proposed definitions of "reliable" raw change scores in psychotherapy that do not take into account regression toward the mean effects attributable to measurement error and explores some implications of these effects. An alternative definition that focuses on the difference between a posttreatment score and the value of this score, which would be expected because of regression toward the mean, can result in conclusions that are different from those of the raw change score definitions, and can also result in counterintuitive conclusions about treatment efficacy. Comparisons of the 2 types of definitions are made by re-expressing critical change scores of both types of definitions on a common scale. Practical problems in the use of these definitions are discussed. (PsycINFO Database Record (c) 2012 APA, all rights reserved)
a brief history of outcome assessment is offered / this is followed by some guidelines for selecting outcome measures [in clinical practice and research], followed by recommendations for assessing outcome in psychotherapy (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Goal attainment scaling is a program evaluation technique that measures program success using individualized client goals rather than the same measuring instrument for all clients. Although the reliability of the goal attainment scales is generally acceptable, such scales have not exhibited satisfactory validity. Also when clients have not been assigned to programs randomly, evaluations comparing two or more programs using goal attainment scales are potentially more biased than evaluations that use the same outcome measure for all clients. Thus since goal attainment scaling does have therapeutic value, program evaluators should adopt a multivariate assessment strategy combining goal attainment scaling with uniform measuring instruments.
In a recent paper, Vredenburg, Flett, and Krames (1993) hypothesized that the apparent instability of depressive symptom scores in college students may be due, in part, to the phenomenon known as statistical regression to the mean. This statistical principle was demonstrated in the current study. A sample of 183 university students completed the Beck Depression Inventory (BDI) at two timepoints separated by a 3-month interval. Consistent with past results, analyses revealed substantial changes in symptom scores over time with decrements being evident among many subjects with elevated symptom scores at Time 1. Examination of the amount of change over time in BDI scores indicated a pattern of findings that approximated the regression to the mean phenomenon. Statistical tests confirmed that regression to the mean accounted for a significant amount of the change in symptom scores over time. The implications of these findings are discussed in terms of the nature of depressive symptoms in students and the inappropriateness of assigning subjects to depressed or nondepressed groups on the basis of elevated scores on a self-report measure.
A general maximum likelihood approach for estimating the effects of treatments applied to samples subject to regression to the mean is outlined. Models may be specified in terms of three factors: whether the treatment effect is multiplicative or additive, whether the treatment group is above or below some truncation point and the type of sample involved. The way in which solutions may be obtained for all 16 models so defined is described.
Accurate measurement of clinically relevant change in individual patients undergoing rehabilitation has been an elusive goal. Simple, clinically meaningful, patient-centered measures of individual patient change are urgently needed. The purpose of this research was the development and testing of Improvement Scaling (Rehabilitation Version)(IMS), a new approach to measuring the progress that rehabilitation patients make during treatment.
Research and clinical staff developed the 65 IMS scales and applied them to all admissions to an an inpatient rehabilitation unit. Date were collected on 292 consecutively admitted rehabilitation patients who were aged 50 or older. An Improvement Score indicates the degree to which each patient achieves the expected level of outcome on his or her unique set of IMS goals. Improvement scores were compared to Goal Attainment Scores and to scores from more traditional measures. Interrater reliability was assessed.
IMS scores correlated r = .78 with comparable Goal Attainment Scores. IMS and Goal Attainment Scores had the same pattern of correlations with other measures. Interrater reliability of IMS scores was r = .91.
IMS appears to be a practical, reliable, valid, and clinically useful technique for measuring individual patient change. What is needed now is replication and more information on factors which may influence IMS scores. Versions of IMS are being developed for home health care and mental health. Applications of IMS for quality assurance, quality improvement, and documentation of patient change for third parties is discussed.
The study of correlates of change is the investigation of systematic individual differences in growth. Our representation of systematic individual differences in growth is built up in two parts: (a) a model for individual growth and, (b) a model for the dependence of parameters in the individual growth models on individual characteristics. First, explicit representations of correlates of change are constructed for various models of individual growth. Second, for the special case of initial status as a correlate of change, properties of collections of growth curves provide new results on the relation between change and initial status. Third, the shortcomings of previous approaches to the assessment of correlates of change are demonstrated. In particular, correlations of residual change measures with exogenous individual characteristics are shown to be poor indicators of systematic individual differences in growth.
The notion of “regression to the mean” is widely misunderstood. This paper explains the concept in simple terms and shows how it arises in studies of mental and physical development.
Der Begriff “Regression auf den Mittelwert” wird häufig mißverstanden. Diese Arbeit erklärt das Konzept in einfacher Weise und zeigt, wie es in Studien der geistigen und körperlichen Entwicklung entsteht.
La notion de “régression à la moyenne” est largement mal comprise. Ce travail explique le concept en termes simples et montre comment il survient dans des études de développement mental et physique.
The course of pain associated with temporomandibular disorders (TMD) and other chronic pain conditions is typically episodic. Its expression may influence when a person seeks treatment, for example, when the level of pain flares up or exceeds its characteristic severity. Improvement in pain status subsequent to entering treatment may be due to: (1) specific effects of treatment; (2) non-specific effects of treatment ('placebo effects'); or (3) regression to the mean. Due to regression to the mean, uncontrolled evaluation of treatment in persons self-selected by a pain flare-up may lead to erroneous conclusions concerning effects of treatment by patients, providers, and/or researchers. For this report, the magnitude of regression to the mean due to self-selection for treatment is estimated by comparing subjects who sought treatment for TMD pain (n = 147) to a random sample of subjects with TMD pain not seeking treatment (n = 95). Among subjects seeking treatment, a significant 14.7-point reduction in VAS pain intensity was observed at 1-year follow-up. A control group of TMD subjects not seeking treatment showed no mean reduction in pain intensity but reported lower pain intensity at baseline than the group seeking care. When both groups of subjects were stratified on baseline VAS pain values, the reduction in pain increased as the baseline pain level increased, but no differences between comparable treated and untreated cases in the extent of improvement were observed. The before-after differences in both groups may be attributed to regression to the mean.(ABSTRACT TRUNCATED AT 250 WORDS)
The relationship between statistically and clinically significant change has been enigmatic. Jacobson and Truax (1991) have proposed an important step toward rapprochement. However, their suggested index of clinically significant change neglects possible confounding of improvement rate estimates by regression to the mean. An alternative method is described that incorporates an adjustment that minimizes this confounding when statistical regression has been shown to be present. If regression is not present, the Jacobson and Truax method is more appropriate; if regression is present, the Edwards-Nunnally method (Edwards, Yarvis, Mueller, Zingale, & Wagman, 1978) is more appropriate. The two methods are compared, and the effects of instrument reliability and sample deviance on estimated improvement rates are demonstrated using general well-being test-retest data from a sample of older adult mental health outpatients.
We consider a regression to the mean problem with a very large sample for the first measurement and relatively small subsample for the second measurement, selected on the basis of the initial measurement. This is a situation that often occurs in screening trials. We propose to estimate the unselected population mean and variance from the first measurement in the larger sample. Using these estimates, the correlation between the two measurements, as well as an effect of treatment, can be estimated in simple and explicit form. Under the condition that the size of the subsample is of a smaller order, the new estimators for all the four parameters are as asymptotically efficient as the usual maximum likelihood estimators. Tests based on this new approach are also discussed. An illustration from a cholesterol screening study is included.
Regression to the mean arises often in statistical applications where the units chosen for study relate to some observed characteristic in the extreme of its distribution. Gardner and Heady attribute the effect of regression to the mean to measurement errors. They assume the model Yi = U + ei, where U is a fixed within-subject component and ei is the random measurement error. They suggest several replicate measurements to reduce the regression effect under the assumption that the measurement errors ei are independent within subjects. While measurement errors play an important role in regression to the mean, one should not overlook within-subject variation. In this paper, we consider a model to estimate the regression effect in the presence of correlated within-subject effects as well as independent measurement errors.
The applicability of a signal measurement strategy was compared with a traditional method of measuring outcome in osteoarthritis. The signal method detected statistically significant alterations in health status with small sample sizes and with a relative efficiency close to or at unity. The prevalence of deterioration in nonsignal items was low. Signal methods of measurement may provide an alternative approach to outcome measurement in osteoarthritis clinical trials.