Unreliability of difference scores: A paradox for measurement of change.

1975 ◽  
Vol 82 (1) ◽  
pp. 85-86 ◽  
Author(s):  
John E. Overall ◽  
J. Arthur Woodward
Keyword(s):  
Difference Scores ◽  
Measurement Of Change

Long-term quality of life and work status after high-dose spinal cord stimulation in patients with failed back surgery syndrome: a secondary analysis of real-world data

2020 ◽  
pp. 1-9
Author(s):  
Lisa Goudman ◽  
Ann De Smedt ◽  
Koen Putman ◽  
Maarten Moens ◽  
_ _
Keyword(s):  
Normal Population ◽  
Failed Back Surgery Syndrome ◽  
Work Status ◽  
High Dose ◽  
Difference Scores ◽  
Failed Back Surgery ◽  
Back Surgery ◽  
Vas Scores ◽  
Utility Scores

OBJECTIVEIn recent years, the use of high-dose spinal cord stimulation (HD-SCS) as a treatment option for patients with failed back surgery syndrome (FBSS) has drastically increased. However, to the authors’ knowledge a thorough evaluation of health-related quality of life (HRQOL) and work status in these patients has not yet been performed. Moreover, it is unclear whether patients who are treated with HD-SCS can regain the same levels of HRQOL as the general population. Therefore, the aims of this study were to compare the HRQOL of patients who receive HD-SCS to HRQOL values in an age- and sex-adjusted population without FBSS and to evaluate work status in patients who are receiving HD-SCS.METHODSHRQOL, measured with the 3-level EQ-5D (EQ-5D-3L), and work status were evaluated in 185 FBSS patients at baseline (i.e., before SCS) and at 1, 3, and 12 months of treatment with HD-SCS. Difference scores in utility values between patients and an age- and sex-adjusted normal population were calculated. One-sample Wilcoxon tests were used to assess the EQ-5D-3L difference scores. Mixed models were used to evaluate the evolution over time in EQ-5D-3L utility scores and EQ-5D visual analog scale (VAS) scores in patients and matched controls. Quality-adjusted life-years (QALYs) were calculated using the area under the curve method.RESULTSAn overall significant increase in EQ-5D-3L utility scores and EQ-5D VAS scores was found over time in the patient group. Wilcoxon tests indicated that the difference scores in utility values between patients and the normal population were significantly different from zero at all time points. The median incremental QALY after 12 months of HD-SCS was 0.228 (Q1–Q3: 0.005–0.487) in comparison to continued conservative treatment. At 12 months, 13.75% of patients resumed work.CONCLUSIONSHD-SCS may lead to significantly increased HRQOL at 12 months in patients with FBSS. Despite the increase, reaching the HRQOL level of matched controls was not achieved. Only a limited number of patients were able to return to work. This finding indicates that specialized programs to enhance return to work may be beneficial for patients undergoing SCS.

scholarly journals Genetic factors explain a significant part of associations between adolescent well-being and the social environment

2021 ◽  
Author(s):  
Margot P. van de Weijer ◽  
Dirk H. M. Pelt ◽  
Catharina E. M. van Beijsterveldt ◽  
Gonneke Willemsen ◽  
Meike Bartels
Keyword(s):  
Family Conflict ◽  
Generalized Estimating Equations ◽  
Leisure Time ◽  
Genetic Factors ◽  
Well Being ◽  
Causal Association ◽  
Difference Scores ◽  
The Social ◽  
Time Variables ◽  
Genetic Contributions

AbstractSocio-environmental factors play an important role in adolescent well-being, but potential genetic contributions to these associations are rarely assessed. To address this gap in the literature, associations between well-being and family conflict and functioning, number of friends, friendship importance and satisfaction, and leisure time variables were studied in N =  ~ 4700 twin pairs from the Netherlands Twin Register, us ing generalized estimating equations and twin-difference scores. When twin-difference scores indicated a role for genetic factors, we used bivariate genetic models to quantify genetic and environmental contributions to these associations. We identify significant associations between well-being and family functioning, family conflict, different leisure time activities, number of friends, and satisfaction with friendships. Additionally, we find evidence for large (73–91%) genetic influence on the associations between well-being and family conflict and functioning, leisure time sport/scouting clubs, and satisfaction with friendships. Finally, findings support the hypothesis of a causal association between well-being and family conflict and functioning. These findings have important implications for research into the social correlates of well-being in adolescence, as not taking genetic factors into account leads to overestimations of the influence of identified correlates and consequently to recommendations of these correlates as intervention targets.

scholarly journals Controlling response dependence in the measurement of change using the Rasch model

2017 ◽  
Vol 27 (12) ◽  
pp. 3709-3725 ◽  
Author(s):  
David Andrich
Keyword(s):  
Rasch Model ◽  
Real Data ◽  
Repeated Measurements ◽  
Measurement Of Change ◽  
Location Parameters ◽  
Response Dependence ◽  
The Individual ◽  
First Time ◽  
The Rasch Model ◽  
Research And Policy

The advantages of using person location estimates from the Rasch model over raw scores for the measurement of change using a common test include the linearization of scores and the automatic handling of statistical properties of repeated measurements. However, the application of the model requires that the responses to the items are statistically independent in the sense that the specific responses to the items on the first time of testing do not affect the responses at a second time. This requirement implies that the responses to the items at both times of assessment are governed only by the invariant location parameters of the items at the two times of testing and the location parameters of each person each time. A specific form of dependence that is pertinent when the same items are used is when the observed response to an item at the second time of testing is affected by the response to the same item at the first time, a form of dependence which has been referred to as response dependence. This paper presents the logic of applying the Rasch model to quantify, control and remove the effect of response dependence in the measurement of change when the same items are used on two occasions. The logic is illustrated with four sets of simulation studies with dichotomous items and with a small example of real data. It is shown that the presence of response dependence can reduce the evidence of change, a reduction which may impact interpretations at the individual, research, and policy levels.

Caution in the Use of Difference Scores in Consumer Research

1993 ◽  
Vol 19 (4) ◽  
pp. 655 ◽  
Author(s):  
J. Paul Peter ◽  
Gilbert A. Churchill, Jr. ◽  
Tom J. Brown
Keyword(s):  
Consumer Research ◽  
Difference Scores

The Sensitivity of the Beck Depression Inventory to Changes of Symptomatology

1974 ◽  
Vol 125 (585) ◽  
pp. 184-185 ◽  
Author(s):  
D. A. W. Johnson ◽  
B. B. Heather
Keyword(s):  
General Practice ◽  
Clinical Research ◽  
Beck Depression Inventory ◽  
Depressive Mood ◽  
Measurement Of Change ◽  
Practice Population ◽  
Absolute Measure

Despite the popularity of the Beck Depression Inventory (Beck et al., 1961), only Salkind (1969) has attempted to validate this instrument for a general practice population. For some purposes, particularly clinical research, measurement of change in a depressive mood is more important than an absolute measure. So far only Little and McPhail (1973) have considered this aspect of use.

The Reliability of Difference Scores When Errors Are Correlated

1977 ◽  
Vol 37 (3) ◽  
pp. 679-689 ◽  
Author(s):  
Richard H. Williams ◽  
Donald W. Zimmerman
Keyword(s):  
Difference Scores
Sign in / Sign up

Export Citation Format

Share Document