Tests for comparing elements of a correlation matrix.

Steiger, James H.

doi:10.1037/0033-2909.87.2.245

Cited by 4,026 publications

(3,037 citation statements)

References 14 publications

Supporting

Mentioning

2,961

Contrasting

Unclassified

Order By: Relevance

“…The standard deviation of the true score correlations was smaller for organizational-targeted behaviors, but it was not much different for individual-targeted behaviors, (SD ϭ .07 and SD ϭ .12, respectively) compared with the overall analysis (SD ϭ .11). A Hotelling-Williams test, recommended when comparing nonindependent correlations that share a variable (see Steiger, 1980), showed that the two correlations were significantly different from each other. Whether LMX and citizenship behavior ratings were provided by the same source substantially influenced the meta-analytic correlation between the two constructs: The estimate for samesource ratings was ϭ .54, whereas the meta-analytic correlation between these constructs was ϭ .32 when different raters provided the two construct scores.…”

Section: Resultsmentioning

confidence: 99%

Leader-member exchange and citizenship behaviors: A meta-analysis.

Ilies¹,

Nahrgang²,

Morgeson³

2007

Journal of Applied Psychology

940

771

View full text Add to dashboard Cite

This article provides a meta-analytic review of the relationship between the quality of leader-member exchanges (LMX) and citizenship behaviors performed by employees. Results based on 50 independent samples (N ϭ 9,324) indicate a moderately strong, positive relationship between LMX and citizenship behaviors ( ϭ .37). The results also support the moderating role of the target of the citizenship behaviors on the magnitude of the LMX-citizenship behavior relationship. As expected, LMX predicted individual-targeted behaviors more strongly than it predicted organizational targeted behaviors ( ϭ .38 vs. ϭ .31), and the difference was statistically significant. Whether the LMX and the citizenship behavior ratings were provided by the same source or not also influenced the magnitude of the correlation between the 2 constructs.

show abstract

Section: Resultsmentioning

confidence: 99%

Leader-member exchange and citizenship behaviors: A meta-analysis.

Ilies¹,

Nahrgang²,

Morgeson³

2007

Journal of Applied Psychology

940

771

View full text Add to dashboard Cite

show abstract

“…6). Steiger’s Z-Test 39 shows that activity inequality is more strongly correlated with obesity than the average volume of steps recorded in a country (r = 0.79 vs. −0.62; N = 46; t = 2.86; p < 0.01). For example, even though the United Kingdom has higher average daily steps than Germany and France (5444 vs. 5205 and 5141), it exhibits higher obesity prevalence (19.5% vs. 14.3% and 8.9%).…”

Section: Methodsmentioning

confidence: 99%

Large-scale physical activity data reveal worldwide activity inequality

Althoff

Sosič

Hicks

et al. 2017

Nature

786

556

View full text Add to dashboard Cite

Understanding the basic principles that govern physical activity is needed to curb the global pandemic of physical inactivity1–7 and the 5.3 million deaths per year associated with in-activity2. Our knowledge, however, remains limited owing to the lack of large-scale measurements of physical activity patterns across free-living populations worldwide1, 6. Here, we leverage the wide usage of smartphones with built-in accelerometry to measure physical activity at planetary scale. We study a dataset consisting of 68 million days of physical activity for 717,527 people, giving us a window into activity in 111 countries across the globe. We find inequality in how activity is distributed within countries and that this inequality is a better predictor of obesity prevalence in the population than average activity volume. Reduced activity in females contributes to a large portion of the observed activity inequality. Aspects of the built environment, such as the walkability of a city, were associated with less gender gap in activity and activity inequality. In more walkable cities, activity is greater throughout the day and throughout the week, across age, gender, and body mass index (BMI) groups, with the greatest increases in activity for females. Our findings have implications for global public health policy and urban planning and highlight the role of activity inequality and the built environment for improving physical activity and health.

show abstract

“…The correlations were calculated separately from planar dGEMRIC map-dependent data and planar map-independent data, and 95% confidence intervals and p values were presented for each using the Fisher Z-transformation approach. We tested whether the correlations with versus without the use of the planar maps differed from each other using methods in either Meng et al [16] or Steiger [20] depending on whether the pairs of correlated measures being compared had one measure in common. When comparing the planar map-dependent and map-independent Beck-Outerbridge correlations as well as map-dependent and map-independent Beck-dGEMRIC correlations, the same Beck's grades are used in every correlation and so the methods of Meng et al were used.…”

Section: Methodsmentioning

confidence: 99%

Planar dGEMRIC Maps May Aid Imaging Assessment of Cartilage Damage in Femoroacetabular Impingement

Bulat

Bixby

Siversson

et al. 2016

Clinical Orthopaedics &Amp; Related Research

View full text Add to dashboard Cite

Background Three-dimensional (3-D) delayed gadolinium-enhanced MRI of cartilage (dGEMRIC) helps quantify biochemical changes in articular cartilage that correlate with early-stage osteoarthritis. However, dGEMRIC analysis is performed slice by slice, limiting the potential of 3-D data to give an overall impression of cartilage biochemistry. We previously developed a computational algorithm to produce unfolded, or ''planar,'' dGEMRIC maps of acetabular cartilage, but have neither assessed their application nor determined whether MRI-based grading of cartilage damage or dGEMRIC measurements predict intraoperative findings in hips with symptomatic femoroacetabular impingement (FAI). Questions/purposes (1) Does imaging-based assessment of acetabular cartilage damage correlate with intraoperative findings in hips with symptomatic FAI? (2) Does the planar dGEMRIC map improve this correlation? (3) Does the planar map improve the correlation between the dGEMRIC index and MRI-based grading of cartilage damage in hips with symptomatic FAI? (4) Does the planar map improve imaging-based evaluation time for hips with symptomatic FAI? Methods We retrospectively studied 47 hips of 45 patients with symptomatic FAI who underwent hip surgery between 2009 and 2013 and had a 1.5-T 3-D dGEMRIC scan within 6 months preoperatively. Our cohort included 25 males and 20 females with a mean ± SD age at surgery of 29 ± 11 years. Planar dGEMRIC maps were generated from isotropic, sagittal oblique TrueFISP and T1 sequences. A pediatric musculoskeletal radiologist with experience in hip MRI evaluated studies using radially reformatted sequences. 123Clin Orthop Relat Res (2016) 474:467-478 DOI 10.1007 Clinical Orthopaedics and Related Research ® A Publication of The Association of Bone and Joint Surgeons® map and 13 without the map, and total evaluation times were recorded. Results There were no meaningful differences in the correlations obtained with versus without referencing the planar maps. Planar map-independent Outerbridge grades had a notable (p \ 0.05) Spearman's rank correlation (q) with Beck's grades that was moderate in AP, SC, and PC (0.3\q \ 0.5) and strong in SP (q [ 0.5). For map-dependent Outerbridge grades, q was moderate in AP, AC, and SC and strong in SP. Map-independent dGEMRIC indices had a q with Beck's grades that was moderate in AP and SC (À0.3[ q [ À0.5) and strong in SP (q \ À0.5). For map-dependent dGEMRIC indices, q was moderate in SC and strong in SP. Similarly, there were no meaningful, map-dependent differences in the correlations. When comparing Outerbridge grades and dGEMRIC indices, there were notable correlations across all subregions. Without the planar map, q was moderate in AC and PC and strong in AP, SP, SC, and PP. With the map, q was strong in all six subregions. In AC, there was a notable map-dependent improvement in this correlation (p \ 0.001). Finally, referencing the planar dGEMRIC map during evaluation was associated with a decrease in mean evaluation time, from 207 ± 32 seconds to 152 ±...

show abstract

Tests for comparing elements of a correlation matrix.

Abstract: small-sample performance and computational efficiency. Several techniques are illustrated with numerical examples.-Pjl? -Pjft 2 -Pkl?)-(3)

Cited by 4,026 publications

References 14 publications

Leader-member exchange and citizenship behaviors: A meta-analysis.

Leader-member exchange and citizenship behaviors: A meta-analysis.

Large-scale physical activity data reveal worldwide activity inequality

Planar dGEMRIC Maps May Aid Imaging Assessment of Cartilage Damage in Femoroacetabular Impingement

Contact Info

Product

Resources

About