Using Planned Comparisons in Management Research: A Case for the Bonferroni Procedure

1993 ◽  
Vol 19 (3) ◽  
pp. 707-724 ◽  
Author(s):  
Maria B. Castaiieda ◽  
Joel R. Levin ◽  
Randall B. Dunham
Keyword(s):  
Repeated Measures ◽  
Multivariate Analyses ◽  
A Priori ◽  
Comparison Method ◽  
Multiple Comparison ◽  
Management Research ◽  
Bonferroni Procedure ◽  
Sequential Hypothesis ◽  
Sequential Hypothesis Testing ◽  
Post Hoc

This article describes the Bonferroni multiple-comparison procedure, and makes a case for researchers’ more frequent and appropriate use of it. The procedure is discussed as a test that facilitates investigation of precise and powerful a priori multiple comparisons. Characteristics of the Bonferroni procedure are described in relation to the more familiar Scheffe post hoc multiple-comparison method, and a step-by-step guide for comparing and choosing between the two is provided. The Bonferroni procedure is discussed in detail in the context of one-factor analysis-of-variance designs. Application of the technique is then considered in the context of factorial designs, analyses of covariance, univariate repeated-measures analyses, multivariate analyses of variance, and recent sequential hypothesis-testing extensions. To aid the presentation, an example from the field of management is included.

Repeated Measures Multiple Comparison Procedures: Effects of Violating Multisample Sphericity in Unbalanced Designs

1988 ◽  
Vol 13 (3) ◽  
pp. 215-226 ◽  
Author(s):  
H. J. Keselman ◽  
Joanne C. Keselman
Keyword(s):  
Repeated Measures ◽  
Type I Error ◽  
Multiple Comparison ◽  
Type I ◽  
Type I Errors ◽  
Unbalanced Designs ◽  
Bonferroni Procedure ◽  
Weighted Means ◽  
Multiple Comparison Procedures ◽  
Multisample Sphericity

Two Tukey multiple comparison procedures as well as a Bonferroni and multivariate approach were compared for their rates of Type I error and any-pairs power when multisample sphericity was not satisfied and the design was unbalanced. Pairwise comparisons of unweighted and weighted repeated measures means were computed. Results indicated that heterogenous covariance matrices in combination with unequal group sizes resulted in substantially inflated rates of Type I error for all MCPs involving comparisons of unweighted means. For tests of weighted means, both the Bonferroni and a multivariate critical value limited the number of Type I errors; however, the Bonferroni procedure provided a more powerful test, particularly when the number of repeated measures treatment levels was large.

Affective-Symbolic Connotations of the Rorschach Inkblots: Fact or Fantasy

1983 ◽  
Vol 56 (1) ◽  
pp. 287-295
Author(s):  
Judith D. Wallach
Keyword(s):  
Analysis Of Variance ◽  
Repeated Measures ◽  
A Priori ◽  
Multiple Comparison ◽  
Male Students ◽  
Point Scale ◽  
Comparison Test ◽  
Multiple Comparison Test ◽  
Repeated Measures Analysis ◽  
Error Terms

The Rorschach inkblots were rated for their similarity to 40 concepts by 111 female and 116 male students. A 5-point scale was used to compare the inkblots with eight concepts in each of five categories: psychoanalytic affective-symbolic connotations, an alternate set of affective-symbolic connotations, “popular” Rorschach responses, affectively toned concepts, and randomly selected nouns. A one-way repeated-measures analysis of variance for each inkblot provided the error terms for Dunn's multiple-comparison test. Although results varied considerably from inkblot to inkblot, the cards were rated over-all more similar to the derived concepts than to their traditionally assumed connotations. These findings and the results of other studies suggest that reliance on any set of hypothesized a priori meanings in Rorschach interpretation may be hazardous or, at best, premature.

scholarly journals Detecting variable responses within fMRI time-series of volumes-of-interest using repeated measures ANOVA

F1000Research ◽  
2016 ◽  
Vol 5 ◽  
pp. 563 ◽  
Author(s):  
Paul M. Macey ◽  
Philip J. Schluter ◽  
Katherine E. Macey ◽  
Ronald M. Harper
Keyword(s):  
Repeated Measures ◽  
A Priori ◽  
Brain Regions ◽  
Response Patterns ◽  
Whole Brain ◽  
Repeated Measures Analysis ◽  
Average Signal Intensity ◽  
Respiratory Challenge ◽  
Post Hoc

We present an approach to analyzing fMRI timetrends from volumes-of-interest (VOI) within and between subject groups using repeated measures analysis of variance (RMANOVA), which allows temporal patterns to be examined without an a priori model of expected timing or pattern of response. The method serves as a complement to whole-brain voxel-based analyses, and is useful for detecting complex responses within pre-determined brain regions, or as a post-hoc analysis of regions of interest identified by whole-brain assessments. We illustrate an implementation of the technique in the statistical software package SAS. VOI timetrends are extracted from conventionally preprocessed fMRI images. A timetrend of average signal intensity across the VOI during the scanning period is calculated for each subject. The values are scaled relative to baseline periods, imported into SAS, and the procedure PROC MIXED implements the RMANOVA. The ensuing results allow determination of significant overall effects, and time-point specific within- and between-group responses relative to baseline. We illustrate the technique using fMRI data from two groups of subjects who underwent a respiratory challenge. RMANOVA allows insight into the timing of responses and response differences between groups, and so is suited to fMRI paradigms eliciting complex response patterns.

scholarly journals Efficacy of galcanezumab in patients with migraine who did not benefit from commonly prescribed preventive treatments

BMC Neurology ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Dulanji K. Kuruppu ◽  
Joshua Tobin ◽  
Yan Dong ◽  
Sheena K. Aurora ◽  
Laura Yunes-Medina ◽  
...  
Keyword(s):  
Repeated Measures ◽  
Migraine Headache ◽  
Mixed Model ◽  
Preventive Treatment ◽  
Response Rates ◽  
Toxin A ◽  
Double Blind ◽  
Preventive Medication ◽  
Onabotulinum Toxin A ◽  
Post Hoc

Abstract Background Galcanezumab is a calcitonin gene-related peptide (CGRP) monoclonal antibody (mAb) indicated for the preventive treatment of migraine. While galcanezumab has demonstrated efficacy in patients who did not respond to prior preventive medications in general, its efficacy in patients who did not benefit from individual, commonly prescribed preventive treatments due to inadequate efficacy or safety/tolerability remains unknown. Methods CONQUER was a 3-month, randomized, double-blind, placebo-controlled, phase 3b study that enrolled patients with episodic or chronic migraine who had 2 to 4 migraine preventive medication category failures in the past 10 years. Patients were randomly assigned 1:1 to receive placebo (N = 230) or galcanezumab 120 mg/month (240 mg loading dose; N = 232). Post hoc analyses were conducted to determine the efficacy of galcanezumab in patients who had not benefited from six of the most commonly prescribed migraine preventive medications. The mean change from baseline in monthly migraine headache days and ≥ 50 % response rates were assessed over months 1–3. Improvement in Migraine-Specific Questionnaire Role Function-Restrictive (MSQ-RFR) scores were assessed at month 3. The endpoints were estimated via mixed model with repeated measures. Results The most common treatment failures due to inadequate efficacy or safety/tolerability, which at least 20 % of patients reported trying without benefit, included topiramate, amitriptyline, propranolol, valproate or divalproex, onabotulinum toxin A, and metoprolol. Patients who had not previously benefited from these treatments had a greater mean reduction in monthly migraine headache days across months 1–3 in the galcanezumab group compared to placebo (all p < 0.01). More patients treated with galcanezumab experienced a ≥ 50 % reduction from baseline in monthly migraine headache days across months 1–3 compared to placebo (all p < 0.05). Galcanezumab-treated patients had a greater improvement in mean MSQ-RFR scores at month 3 compared to placebo (all p < 0.01). Conclusions In this population, galcanezumab was effective in reducing monthly migraine headache days, improving response rates, and enhancing quality of life in patients who had not previously benefited from topiramate, amitriptyline, propranolol, valproate or divalproex, onabotulinum toxin A, and/or metoprolol due to inadequate efficacy or safety/tolerability. Trial registration ClinicalTrials.gov NCT03559257 (CONQUER).

scholarly journals When Does HARKing Hurt? Identifying When Different Types of Undisclosed Post Hoc Hypothesizing Harm Scientific Progress

2017 ◽  
Vol 21 (4) ◽  
pp. 308-320 ◽  
Author(s):  
Mark Rubin
Keyword(s):  
Philosophy Of Science ◽  
Present Article ◽  
Literature Search ◽  
A Priori ◽  
Scientific Progress ◽  
Research Report ◽  
Research Results ◽  
Different Types ◽  
Replication Crisis ◽  
Post Hoc

Hypothesizing after the results are known, or HARKing, occurs when researchers check their research results and then add or remove hypotheses on the basis of those results without acknowledging this process in their research report ( Kerr, 1998 ). In the present article, I discuss 3 forms of HARKing: (a) using current results to construct post hoc hypotheses that are then reported as if they were a priori hypotheses; (b) retrieving hypotheses from a post hoc literature search and reporting them as a priori hypotheses; and (c) failing to report a priori hypotheses that are unsupported by the current results. These 3 types of HARKing are often characterized as being bad for science and a potential cause of the current replication crisis. In the present article, I use insights from the philosophy of science to present a more nuanced view. Specifically, I identify the conditions under which each of these 3 types of HARKing is most and least likely to be bad for science. I conclude with a brief discussion about the ethics of each type of HARKing.

Interfacial Nanoleakage and Bonding of Self-Adhesive Systems Cured with a Modified-Layering Technique to Dentin of Weakened Roots

2013 ◽  
Vol 38 (5) ◽  
pp. E154-E165 ◽  
Author(s):  
E Mobarak ◽  
R Seyam
Keyword(s):  
Bond Strength ◽  
Repeated Measures ◽  
Adhesive Systems ◽  
Root Canals ◽  
Root Region ◽  
Modes Of Failure ◽  
Group A ◽  
Post Hoc ◽  
Vertise Flow ◽  
Self Etch

SUMMARY Objective The purpose of the study was to evaluate the nanoleakage and bond strength of different self adhesive systems cured with a modified-layering technique (MLT) to dentin of weakened roots. Methods Twenty-one maxillary incisors were decoronated and then root canals were instrumented and obturated with the cold lateral compaction technique. Weakened roots were simulated by flaring root canals until only 1 mm dentin thickness remained. Teeth were distributed into three groups. The canals were backfilled with Vertise Flow (VF group), a self-adhering system, following a modified-layering technique using two light-transmitting posts, sizes 6 and 3. DT Light Post size 2 was cemented using the same material. Remaining roots were prepared and cured in the same way as the VF group. However, in the TS/MF group, Clearfil Tri-S Bond (TS) adhesive and Clearfil Majesty Flow (MF) composite were used, while in the ED/PF group, ED primer II (ED)/Panavia F2.0 (PF) were used. After one week of storage, each root was sectioned to obtain six slices (two slices from each root third: coronal, middle and apical) of 0.9 ± 0.1 mm thickness. Interfacial nanoleakage expression was analyzed using a field emission scanning electron microscope (FEG-SEM), and the micro push-out bond strength (μPOBS) was measured at different root regions. Modes of failure were also determined using SEM. Data were statistically analyzed using two-way analysis of variance with repeated measures and Tukey post hoc test (p≤0.05). Results With MLT, all adhesive systems showed nanoleakage. For μPOBS, there was a statistically significant effect for adhesive systems (p&lt;0.001) but not for root region (p&lt;0.64) or for their interaction (p=0.99). Tukey post hoc test revealed that the bond strength of the VF group was significantly higher than the TS/MF and ED/PF groups for all root regions. Conclusion All of the tested self-adhesive systems cured using MLT had slight nanoleakage and were not sensitive to root regional differences. Self-adhering systems had higher bond strength than self-etch adhesives.

Physiological Assessment of Bagpipers: A Preliminary Study of Cardiopulmonary Parameters

2000 ◽  
Vol 15 (2) ◽  
pp. 51-54
Author(s):  
Deborah Barr ◽  
Lee Van Dusen ◽  
Steve Ess ◽  
Julie Plezbert
Keyword(s):  
Heart Rate ◽  
Repeated Measures ◽  
Vital Capacity ◽  
A Priori ◽  
Mean Values ◽  
Time Period ◽  
Impedance Cardiograph ◽  
Cardiac Adaptation ◽  
Automatic Blood Pressure ◽  
Predicted Values

This study examined pulmonary function of pipers and cardiac adaptation to the playing of the Great Highland bagpipe. Pipers (n = 13) of varying ages (31-65 years) and playing experiences (2-20+ years) were evaluated for vital capacity (VC), maximal voluntary ventilation (MVV), and forced vital capacity (FVC) using a RIKO AS-600 spirometer. Subjects were monitored by impedance cardiograph for heart rate (HR), stroke volume (SV), and cardiac output (CO) at rest and during 5 minutes of playing. An automatic blood pressure (BP) monitor collected BP values over the same time period. Eleven weeks after initial cardiac data collection, the BP and cardiac measurements were repeated using the same protocols. Mean values for HR, SV, and CO were calculated for rest and each minute (1-5) of playing. A 2 (data session) by 6 (rest, min 1–5) repeated-measures ANOVA was performed. Analysis revealed a significant overall time effect (p < 0.001) on HR. A-priori contrast comparing all playing times with rest showed significant differences at all time points. Analysis of SV and CO failed to find significance. Heart rate values calculated for percent of maximum ranged from 68% to 89% of maximum overall while playing (session 1) and from 55% to 81% of maximum (session 2). Predicted percent of maximum values for VC and MVV found 77% of players above their maximum predicted values.

Sign in / Sign up

Export Citation Format

Share Document