scholarly journals Lord’s paradox in latent change score modeling: an example involving facilitating longitudinal effects between intelligence and academic achievement

2021 ◽  
Author(s):  
Kimmo Sorjonen ◽  
Bo Melin ◽  
Gustav Nilsonne
Keyword(s):  
Academic Achievement ◽  
Change Score ◽  
Outcome Variable ◽  
Initial Value ◽  
Longitudinal Effects ◽  
Effect Regression ◽  
Subsequent Measurement ◽  
The Mean ◽  
Regression Toward The Mean ◽  
Over Time

It has been claimed that intelligence causes academic achievement to increase over time, and that also, conversely, academic achievement causes intelligence to increase over time. This bidirectional facilitating longitudinal effect between intelligence and academic achievement rests on observed associations between initial intelligence and the change in academic achievement between an initial and a subsequent measurement, and vice versa. Here, we demonstrate, through simulating empirical data used in previous research, that such longitudinal associations may be due to regression toward the mean rather than a true facilitating effect. Regression toward the mean occurs due to the conditioning of change on the initial value on the outcome variable. Researchers should be aware of this fallacy and are recommended to verify their findings with analyses without adjustment for an initial value on the outcome.

Regression toward the Mean or Heuristic Processing in Detecting Deception?: Reply to Elaad (2010)

2010 ◽  
Vol 107 (2) ◽  
pp. 587-592 ◽  
Author(s):  
Jaume Masip ◽  
Eugenio Garrido ◽  
Carmen Herrero
Keyword(s):  
Information Processing ◽  
Processing Mode ◽  
Detecting Deception ◽  
The Mean ◽  
Regression Toward The Mean ◽  
Random Fluctuations ◽  
Over Time ◽  
Heuristic Processing

Masip, et al. (2009) conducted a study in which observers had to make truth–lie judgments at the beginning, middle, or end of a series of videotaped statements. They found a decline in truth judgments over time and explained this finding in terms of information processing mode. Recently, Elaad (2010) challenged this explanation and contended that the decline could be a result of regression toward the mean. In the present paper, it is argued that because Masip, et al. took multiple Moment 1 judgments over time and then averaged across judgments, regression toward the mean was extremely unlikely. Furthermore, the decrease in truth judgments was found under several separate conditions; this cannot be explained by random fluctuations alone. Finally, Masip, et al.'s data were re-analyzed adjusting for the effects of regression toward the mean. The outcomes of these analyses were the same as those reported in the original article.

scholarly journals Constancy of the angle between the Frankfort horizontal plane and the sella-nasion line: A nine-year longitudinal study

2013 ◽  
Vol 84 (2) ◽  
pp. 286-291 ◽  
Author(s):  
Young Jae Huh ◽  
Kyung-Hoe Huh ◽  
Hong-Kyun Kim ◽  
Shin-Eun Nam ◽  
Hye Yoon Song ◽  
...  
Keyword(s):  
Longitudinal Study ◽  
Horizontal Plane ◽  
Annual Change ◽  
Mixed Effect ◽  
Effect Regression ◽  
The Mean ◽  
Frankfort Horizontal Plane ◽  
Mixed Effect Regression Model ◽  
Over Time ◽  
Observation Period

ABSTRACT Objective: To investigate the constancy of the angle between the Frankfort horizontal plane (FH) and the sella-nasion line (SN) using longitudinal data. Materials and Methods: Longitudinal lateral cephalometric data of 223 children (116 girls and 107 boys) from 6 to 14 years of age were used. The angle between FH and SN (SNFH), the distance from FH to the nasion (NFH), the distance from FH to the sella (SFH), and the differences between the NFH and SFH (Δ) were also measured. All data were analyzed statistically using independent t-tests and mixed-effect regression model analysis. Results: The mean SNFH values showed some minor fluctuations, ranging from 9.26° to 9.74° in girls and 8.45° to 8.95° in boys. The mean NFH and SFH values gradually increased according to age irrespective of sex. There were statistically significant differences by sex for all measurements at several ages. The annual change in SFH and Δ showed sexual dimorphism. Conclusions: There are variations among individuals in the angle between the FH and SN. However, within an individual, the angle does not vary significantly over time during the observation period.

scholarly journals The impact of hearing impairment on early academic achievement in Aboriginal children living in remote Australia: a data linkage study

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Jiunn-Yih Su ◽  
Steven Guthridge ◽  
Vincent Yaofeng He ◽  
Damien Howard ◽  
Amanda Jane Leach
Keyword(s):  
Academic Achievement ◽  
Hearing Loss ◽  
Hearing Impairment ◽  
Academic Outcomes ◽  
School Attendance ◽  
Outcome Variable ◽  
Hearing Level ◽  
The Mean ◽  
Aboriginal Children ◽  
The Impact

Abstract Background The prevalence of otitis media (OM) and related hearing loss has remained persistently high among some groups of Australian Aboriginal children who are also reported to have poor academic outcomes. The general literature remains inconclusive about the association between OM-related hearing loss and academic performance in primary school. This study aimed to investigate this association in Aboriginal children living in the Northern Territory (NT) of Australia. Methods A retrospective, observational cohort study was conducted for 2208 NT Aboriginal children, aged about 8 years, living in remote and very remote communities. The explanatory variable was audiometrically determined hearing level as recorded in the Remote Hearing Assessment dataset. The outcome variable consisted of scale scores in the five domains of the National Assessment Program – Literacy and Numeracy (NAPLAN) for Year 3. Other linked datasets used in the study included school attendance records, perinatal records and community level information on relative remoteness, socioeconomic disadvantage and housing crowdedness. Fixed effects linear regression models were used for statistical analyses. Results Compared with children with normal hearing and after controlling for a range of covariates, children with mild hearing impairment (HI) scored lower in Writing and Spelling by 15.0 points (95% CI: − 22.4 to − 7.6, p < 0.0005) and 5.0 points (95% CI: − 9.6 to − 0.3, p = 0.037), equivalent to 7.3 and 2.1% of the mean score, respectively. Children with moderate or worse HI scored lower in Writing and Numeracy by 13.4 points (95% CI, − 24.8 to − 1.9, p = 0.022) and 15.2 points (95% CI, − 27.6 to − 2.7, p = 0.017), both equivalent to 6.3% of the mean score the respective domain. Other factors associated with poorer NAPLAN results included being male, lower Year 2 school attendance, low birthweight, average household size> 5 persons, living in a very remote community and speaking English as a second language. Conclusions OM-related HI was independently associated with poorer early year academic achievement in Aboriginal children living in remote NT communities. Interventions to improve academic outcomes for Aboriginal children must incorporate actions to address the negative impact associated with HI through early detection, effective treatment and ongoing support for affected children.

Truth Bias and Regression toward the Mean Phenomenon in Detecting Deception

2010 ◽  
Vol 106 (2) ◽  
pp. 641-642 ◽  
Author(s):  
Eitan Elaad
Keyword(s):  
Information Processing ◽  
Alternative Explanation ◽  
Systematic Information ◽  
Truth Bias ◽  
Detecting Deception ◽  
The Mean ◽  
Regression Toward The Mean ◽  
Systematic Information Processing ◽  
Increase In Accuracy ◽  
Over Time

A 2009 study by Masip, et al. contended that the truth bias appears in brief communications. They demonstrated a strong truth bias when truth–lie judgments were made at the beginning of the judged statement. Over time, a decrease in the truth bias and an increase in accuracy were observed. The improvement was explained by systematic information processing. The present paper suggests an alternative explanation, which rests on the phenomenon of regression toward the mean.

Averaging to Minimize or Eliminate Regression toward the Mean to Measure Pure Experimental Effects

2008 ◽  
Vol 102 (3) ◽  
pp. 665-677 ◽  
Author(s):  
Rex S. Toh ◽  
Michael Y. Hu
Keyword(s):  
Large Scale ◽  
Real Life ◽  
Diary Data ◽  
Initial Values ◽  
The Mean ◽  
Regression Toward The Mean ◽  
Spontaneous Reaction ◽  
Use Categories ◽  
Over Time

This paper explains how regression toward the mean can contaminate diary data, making it difficult to measure the pure effects of an experimental variable over time. Using a large scale real-life database collected by AT& T, a method of measuring this mathematical artifact is advanced. It is shown to manifest very quickly as a result of a spontaneous reaction toward happenstance, with the most extreme initial values gravitating most toward the mean. Then averaging over longer and longer periods of time to define use categories is shown to dilute happenstance increasingly, and therefore progressively minimizes or eliminates regression toward the mean. Finally, regression toward the mean is very pervasive and very persistent.

scholarly journals Dangers of including outcome at baseline as a covariate in latent change score models

2021 ◽  
Author(s):  
Kimmo Sorjonen ◽  
Gustav Nilsonne ◽  
Bo Melin
Keyword(s):  
Structural Equation ◽  
Change Score ◽  
Published Data ◽  
Regression To The Mean ◽  
Initial Value ◽  
Equation Modelling ◽  
Measuring Change ◽  
The Mean ◽  
Latent Change Score ◽  
Matrix Reasoning

Latent change score modelling is a version of structural equation modelling for measuring change between measurements. It seems quite common to regress change on the initial value included in the calculation of the change score (i.e. ΔY (= Y2 – Y1) is regressed on Y1). However, similarly as in simpler regression analyses, this procedure may make findings susceptible to the influence of regression to the mean. This suspicion was verified in the present simulations. An empirical application, including re-analyses of previously published data, indicated that previously claimed reciprocal promoting effects of vocabulary and matrix reasoning on each other’s longitudinal development may actually be due to regression to the mean. Researchers are recommended not to regress change on the initial value included in the calculation of the change score when employing latent change score modelling, or at least to verify findings with analyses omitting this parameter.

Reversion Toward the Mean Independently of Regression Toward the Mean

Methodology ◽  
2009 ◽  
Vol 5 (1) ◽  
pp. 3-6 ◽  
Author(s):  
Merton S. Krause
Keyword(s):  
Random Error ◽  
Evaluation Studies ◽  
Internal Validity ◽  
Intervention Evaluation ◽  
Population Mean ◽  
Experimental Intervention ◽  
Sample Data ◽  
The Mean ◽  
Regression Toward The Mean

There is another important artifactual contributor to the apparent improvement of persons subjected to an experimental intervention which may be mistaken for regression toward the mean. This is the phenomenon of random error and extreme selection, which does not at all involve the population regression of posttest on pretest scores but involves a quite different and independent reversion of subjects’ scores toward the population mean. These two independent threats to the internal validity of intervention evaluation studies, however, can be detected and differentiated on the sample data of such studies.

Early Social Competence and Academic Achievement: Relations Over Time

2006 ◽  
Author(s):  
Ashley C. Gibb ◽  
John E. Bates ◽  
Jackson A. Goodnight ◽  
Kenneth A. Dodge ◽  
Gregory S. Pettit
Keyword(s):  
Academic Achievement ◽  
Social Competence ◽  
Over Time
Sign in / Sign up

Export Citation Format

Share Document