On Closed Testing Procedures with Special Reference to Ordered Analysis of Variance

Marcus, Ruth; Peritz, Eric; Gabriel, K. R.

doi:10.2307/2335748

Cited by 293 publications

(397 citation statements)

References 0 publications

Supporting

Mentioning

393

Contrasting

Unclassified

Order By: Relevance

“…Pvalues were calculated by a permutation procedure (SAS s PROC NPAR1WAY, SAS Institute, 1997) rather than relying on the asymptotic w 2 distribution of the Savage statistic. In an effort to reduce Type I error rate, the closed testing procedure of Marcus et al (1976) was used. Accordingly, if the global null hypothesis was rejected at Po0.05 (distribution of abnormal counts same in all groups), a pairwise null hypothesis of the form Group A ¼ Group B would be rejected at Po0.05 only if the three-way hypotheses (Group A ¼ B ¼ C and Group A ¼ B ¼ D) were also rejected at Po0.05.…”

Section: Experimental Designmentioning

confidence: 99%

Micromolar Brain Levels of Kynurenic Acid are Associated with a Disruption of Auditory Sensory Gating in the Rat

Shepard

Joy

Clerkin

et al. 2003

Neuropsychopharmacol

127

View full text Add to dashboard Cite

Brain levels of kynurenic acid (KYNA), an endogenous antagonist of glycine B /NMDA and a-7 nicotinic acetylcholine receptors, are elevated in individuals with schizophrenia. Both receptors are broadly implicated in the pathophysiology of this disease, particularly in the deficits many patients show in filtering the sensorium. In the present study, we sought to determine whether elevated brain levels of KYNA disrupt auditory gating in anesthetized rats. A mid-latency evoked potential was recorded from the hippocampus in response to a pair of auditory tones. Gating was assessed by determining the ratio of the amplitude of test and conditioning responses (T/C ratio) in rats that had received KYNA's precursor L-kynurenine (KYN; 150 mg/kg, i.p.) together with probenecid (PBCD; 200 mg/kg, i.p.) 2 h prior to the start of the recording session. KYNA levels in the hippocampus of KYN+PBCD-treated rats were increased 500-fold, and accompanied by a significant increase in T/C ratio consistent with a disruption in sensory gating. PBCD alone increased hippocampal KYNA 12-fold, but did not significantly elevate T/C ratio. L-701,324 (3-30 mg/kg, i.v.), a centrally acting glycine B site antagonist, also failed to disrupt gating; however, large quantities of the competitive NMDA receptor antagonist DL-2-amino-5-phosphopentanoate (200 nmol, i.c.v.) markedly increased T/C ratio. Thus, while total blockade of NMDA receptors disrupts auditory gating, partial blockade achieved by antagonism of its glycine coagonist binding site does not. These observations indicate that the disruption in auditory processing in rats with greatly elevated KYNA levels is not attributable to the compound's antagonist actions at the glycine B receptor.

show abstract

Section: Experimental Designmentioning

confidence: 99%

Micromolar Brain Levels of Kynurenic Acid are Associated with a Disruption of Auditory Sensory Gating in the Rat

Shepard

Joy

Clerkin

et al. 2003

Neuropsychopharmacol

127

View full text Add to dashboard Cite

show abstract

“…Under a normal model assumption, O'Brien derived an ordinary least-squares test statistic and a generalized least-squares test statistic that are more powerful than Hotelling's T 2 statistic in the case of related endpoints. Lehmacher et al (1991) apply O'Brien's test in combination with the closure principle of Marcus et al (1976). They point out that the Bonferroni test, and by extension, stepdown tests based on the maximum test statistic (Romano and Wolf, 2005), are useful for detecting one highly significant difference, or treatment effect, among a group of otherwise barely significant or nonsignificant differences.…”

Section: Introductionmentioning

confidence: 99%

Optimal testing of multiple hypotheses with common effect direction

Bittman¹,

Romano²,

Vallarino³

et al. 2009

Biometrika

View full text Add to dashboard Cite

SUMMARYWe present a theoretical basis for testing related endpoints. Typically, it is known how to construct tests of the individual hypotheses, but not how to combine them into a multiple test procedure that controls the familywise error rate. Using the closure method, we emphasize the role of consonant procedures, from an interpretive as well as a theoretical viewpoint. Surprisingly, even if each intersection test has an optimality property, the overall procedure obtained by applying closure to these tests may be inadmissible. We introduce a new procedure, which is consonant and has a maximin property under the normal model. The results are then applied to PROactive, a clinical trial designed to investigate the effectiveness of a glucose-lowering drug on macrovascular outcomes among patients with type 2 diabetes.

show abstract

“…The Kruskal-Wallis test was performed as a global test to calculate between group comparisons. In case of a statistical difference between the groups, pair-wise comparisons with the Mann-Whitney U test were calculated applying the closed testing procedure [23]. A twotailed p value less than 0.05 was considered significant.…”

Section: Discussionmentioning

confidence: 99%

Injection of a polymerized hyaluronic acid/collagen hydrogel matrix in an in vivo porcine disc degeneration model

et al. 2012

View full text Add to dashboard Cite

Introduction Disc degeneration and re-herniation after nucleotomy procedures are common problems. Simultaneous application of hyaluronic acid (HA)-based matrix has been proposed to limit disc degeneration. This, however, is hampered by loss of the substituted matrix out of the disc. Hence, in situ polymerization of the injected matrix with ultraviolet light (UVL) directly used after injection may be useful. Therefore, this study evaluates a new HA/collagen hydrogel matrix with in situ polymerization after implantation in an established porcine nucleotomy model. Materials and methods 12 mature minipigs were used. A total of 60 lumbar discs were analyzed. 36 discs underwent partial nucleotomy with a 16G biopsy needle. Of those, 24 discs received matrix (porcine nucleus pulposus collagenous scaffold component and chemically modified HA) which was in situ polymerized using UVL immediately after transplantation. 12 nucleotomized discs and 24 non-nucleotomized discs served as controls. After 24 weeks, animals were killed. X-rays, MRIs, histology, and gene expression analysis were done. Results Disc height was reduced equally after sole nucleotomy and nucleotomy with HA treatment and in MRIs signal intensity decreased. For both nucleotomy groups, the nucleus histo-degeneration score showed a significant increase compared to controls. In histology, HA treatment resulted in more scarring and inflammation in the annulus. Gene expression of catabolic MMPs was up-regulated, whereas IFN-gamma, IL-6, and IL-1b were unchanged. Conclusion Although nucleotomy and administration of the implant material did not cause generalized inflammation of the disc, localized annular damage with annulus inflammation and scarring resulted in detrimental degenerative disc changes. As a result, therapeutic strategies should strongly focus on the prevention of annular damage or techniques for annular repair to remain disc integrity.

show abstract

On Closed Testing Procedures with Special Reference to Ordered Analysis of Variance

Cited by 293 publications

References 0 publications

Micromolar Brain Levels of Kynurenic Acid are Associated with a Disruption of Auditory Sensory Gating in the Rat

Micromolar Brain Levels of Kynurenic Acid are Associated with a Disruption of Auditory Sensory Gating in the Rat

Optimal testing of multiple hypotheses with common effect direction

Injection of a polymerized hyaluronic acid/collagen hydrogel matrix in an in vivo porcine disc degeneration model

Contact Info

Product

Resources

About