scholarly journals Testing Mean Differences among Groups: Multivariate and Repeated Measures Analysis with Minimal Assumptions

2018 ◽  
Vol 53 (3) ◽  
pp. 348-359 ◽  
Author(s):  
Arne C. Bathke ◽  
Sarah Friedrich ◽  
Markus Pauly ◽  
Frank Konietschke ◽  
Wolfgang Staffen ◽  
...  
2011 ◽  
Vol 35 (3) ◽  
pp. 136-141 ◽  
Author(s):  
Shangbin Liu ◽  
Walter Bitterlich ◽  
Chris J. Cieszewski ◽  
Michal J. Zasada

Abstract Three dendrometers are used to measure dbh. Two of the devices are the well-known and widely used d-tape and caliper. The third device is the lesser-known sector fork. In this study, measurements of dbh were collected from each dendrometer for each tree in nine plots, with each of the three plots nested in one of the diameter classes (small, medium, and large). The results from repeated-measures analysis of variance show that different dendrometers, the interaction between the dendrometer and diameter class, and the interaction between the dendrometer and plot significantly affected the dbh measurements. Statistically significant differences were detected in most of the comparisons of dbh measured by the three dendrometers. However, the actual mean differences and limits of agreement (Bland, J.M., and D.G. Altman. 1986. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet 1:307–310) were small enough to support the claim that the dbh measurements made by the three dendrometers agree well in measurements of the small and medium trees (in this study, dbh of <16 in.). Thus, these statistically significant differences are not biologically and/or practically important. For the large trees (dbh 16 in. or more), the dbh measured by d-tape and caliper still agreed well. The sector fork should be used cautiously in measuring large trees.


2013 ◽  
Vol 24 (08) ◽  
pp. 660-670 ◽  
Author(s):  
Kristi Oeding ◽  
Michael Valente

Background: SoundTracker is an algorithm in Widex's Compass fitting software that could potentially be used to estimate a patient's aided sensation level (SL). SoundTracker's accuracy of estimating a patient's SL has never been verified in comparison to SL measured with commercially available real-ear analyzers. Purpose: Determine whether statistically significant differences are present between the estimated SL of the Widex SoundTracker software application and the measured SL of the Audioscan Verifit and Frye 6500 real-ear analyzers at 500, 1000, 2000, and 4000 Hz. Research Design: This study used a randomized repeated measures design to determine differences in SL between SoundTracker and the Verifit and 6500. Study Sample: Ten subjects (N = 20 ears) were recruited who were experienced users of behind-the-ear hearing aids with conventional vented earmolds and had bilateral sensorineural hearing loss that was >30 dB HL below 1000 Hz and ≤70 dB HL to 4000 Hz. Data Collection and Analysis: Real-ear in-situ thresholds (dB sound pressure level [SPL]) and real-ear aided responses (REAR; dB SPL) were measured at 500, 1000, 2000, and 4000 Hz to determine differences in SL between SoundTracker, Verifit, and 6500. A three-factor repeated measures analysis of variance (ANOVA) was utilized to determine differences between method (real-ear analyzers and SoundTracker), analyzer (Verifit and 6500), and frequency (500, 1000, 2000, and 4000 Hz). Results: Mean differences in measured SL for the Verifit and 6500 were ≤2 dB when compared to the estimated SL using SoundTracker. A statistically significant difference in SL was present between the Verifit and SoundTracker at 2000 Hz (p < 0.01), but no significant differences were present at 500, 1000, and 4000 Hz. A statistically significant difference in SL was present between the 6500 and SoundTracker at 4000 Hz (p < 0.01), but no significant differences were present at 500, 1000, and 2000 Hz. Mean differences in measured SL between the real-ear analyzers (difference of SoundTracker SL minus Verifit SL compared to the difference of SoundTracker SL minus 6500 SL) were ≤2 dB with a statistically significant difference present at 2000 Hz (p < 0.01), but no statistically significant differences were present at 500, 1000, or 4000 Hz. Conclusions: Nearly 85% of the differences between the estimated SoundTracker SL and the measured SLs of the Verifit and 6500 were ≤2 dB. Despite some limitations of this study, SoundTracker could be useful as a counseling tool to illustrate to patients which sounds are audible or inaudible when unaided and aided.


2015 ◽  
Vol 86 (3) ◽  
pp. 358-364 ◽  
Author(s):  
Dan L. Romanyk ◽  
Andrew George ◽  
Yin Li ◽  
Giseon Heo ◽  
Jason P. Carey ◽  
...  

Abstract Objective:  To investigate the influence of a rotational second-order bracket-archwire misalignment on the loads generated during third-order torque procedures. Specifically, torque in the second- and third-order directions was considered. Materials and Methods:  An orthodontic torque simulator (OTS) was used to simulate the third-order torque between Damon Q brackets and 0.019 × 0.025-inch stainless steel archwires. Second-order misalignments were introduced in 0.5° increments from a neutral position, 0.0°, up to 3.0° of misalignment. A sample size of 30 brackets was used for each misalignment. The archwire was then rotated in the OTS from its neutral position up to 30° in 3° increments and then unloaded in the same increments. At each position, all forces and torques were recorded. Repeated-measures analysis of variance was used to determine if the second-order misalignments significantly affected torque values in the second- and third-order directions. Results:  From statistical analysis of the experimental data, it was found that the only statistically significant differences in third-order torque between a misaligned state and the neutral position occurred for 2.5° and 3.0° of misalignment, with mean differences of 2.54 Nmm and 2.33 Nmm, respectively. In addition, in pairwise comparisons of second-order torque for each misalignment increment, statistical differences were observed in all comparisons except for 0.0° vs 0.5° and 1.5° vs 2.0°. Conclusion:  The introduction of a second-order misalignment during third-order torque simulation resulted in statistically significant differences in both second- and third-order torque response; however, the former is arguably clinically insignificant.


2021 ◽  
pp. 105566562110515
Author(s):  
Tim Bressmann

The Nasometer is a popular instrument for the acoustic assessment of nasality. In light of the currently ongoing COVID-19 global pandemic, clinicians may have wondered about the infection control procedures for the Nasometer. The current research investigated whether nasalance scores are affected if the Nasometer 6450 microphone casings are covered with a material such as rolled polyvinyl chloride household wrap. For the experiment, pre-recorded sound files from two speakers were played back through a set of small loudspeakers. Nasalance scores from two baselines and three wrap cover conditions were compared. While there was no statistically significant condition effect in a repeated-measures analysis of variance, the within-condition cumulative differences in nasalance scores were 2 for the initial baseline, 42 for wrap cover 1, 24 for wrap cover 2, 78 for wrap cover 3, and 8 for the final baseline. Mean differences between the wrap cover and the baseline conditions were 8.2 to 15.3 times larger, and cumulative differences were 8.3 to 16.6 times larger than between the two baselines. Based on the higher cumulative and mean differences observed, clinicians should not cover Nasometer microphones with household wrap as this increases variability of nasalance scores. Since there is evidence that the COVID-19 virus can survive for some time on metal surfaces, clinicians should be mindful of the fact that the Nasometer microphone housings can only be cleaned superficially and should be handled with gloves to minimize any possible risk of touch transfer of pathogens to the next speaker or the clinician.


2021 ◽  
Vol 2021 ◽  
pp. 1-5
Author(s):  
Özgür Genç Şen ◽  
Özgür İlke Ulusoy ◽  
Yelda Nayır Paltun ◽  
Çağrı Ulusoy

The purpose of this study was to evaluate the effect of metal orthodontic brackets on the accuracy of electronic apex locator (EAL). The actual canal lengths (ACL) of 40 mandibular incisor teeth were determined. Then, the teeth were randomly divided into two groups ( n = 20 ). Orthodontic metal brackets were applied in the first group, and no brackets, in the second group. The working length of each tooth was measured with an EAL under 3 test conditions according to the distance between the lip clip and sample tooth. Data were analyzed using one-way repeated measures analysis of variance and Tukey’s post hoc tests ( p = 0.05 ). In the bracketed samples, when the lip clip was located at 1 cm and 2 cm from the samples. The mean differences between the EAL measurements and ACLs were statistically higher than those when the samples were located 3 cm from the lip clip ( p < 0.05 ). There were also statistically significant differences between EAL measurements and ACLs in the bracketed samples located 1 and 2 cm from the lip clip ( p < 0.05 ). In the nonbracketed group, the differences between EAL measurements and ACLs were not statistically significant in the samples located 1, 2, and 3 cm from the lip clip ( p > 0.05 ). Use of orthodontic metal brackets can negatively influence the accuracy of the electronic apex locator when the distance between the lip clip and bracket was short. A minimum of 3 cm distance should be kept between the lip clip and tooth in order to make consistent electronic measurements.


2020 ◽  
Vol 20 (09) ◽  
pp. 2040003
Author(s):  
MOON-SEOK KWON ◽  
YU-RI KWON ◽  
YOON-HYEOK CHOI ◽  
GWANG-MOON EOM ◽  
JUNGHYUK KO ◽  
...  

Gait assessment is important for identification of potential faller among the elderly populations. Slope walking is associated with fall risk factor and elderly women have higher fall rate compared with elderly men. Therefore, this study investigated gait characteristics of elderly women in overground and slope walkway conditions. Thirty healthy elderly women (15 younger-elderly women and 15 older-elderly women) walked along the linear walkway including three walking conditions (overground, ascent and descent conditions). Temporal gait variables and normalized peak vertical GRF (ground reaction force) variables were derived from commercial motion analysis software. Repeated-measures analysis of variance (ANOVA) was evaluated to compare mean differences of the three conditions and mean difference between younger and older elderly women. All gait characteristics were significantly different from the slope walking conditions ([Formula: see text]). Elderly women walked with longer loading response and mid stance phase during descent walking. Also, ascent walking induced a longer terminal stance phase. Interactions of age and walkway conditions were also significant in vertical GRF, where older-elderly women were greater than younger-elderly women in ascent walkway condition ([Formula: see text]) and in descent walkway condition ([Formula: see text]). These findings suggest that specific-walkway condition should be considered for fall prevention and clinical interventions in elderly women.


1970 ◽  
Vol 1 (2) ◽  
Author(s):  
Irma Nurbaeti ◽  
Kustati Budi Lestari

Pemberian Air Susu Ibu (ASI) masih merupakan masalah bagi pemenuhan kebutuhan nutrisi bayi baru lahir. Dukungan agar ibu menyusui bayi merupakan hal penting dalam menginisiasi dan mempertahankan pemberian ASI. Strategi dibutuhkan untuk mendukung keberhasilan menyusui. Tujuan penelitian adalah menganalisis efektivitas comprehensive breastfeeding education terhadap keberhasilan pemberian (ASI) pada periode postpartum. Jenis penelitian ini menggunakan kuasi eksperimen one group pre post test repeated measured design. Jumlah sampel sebanyak 22 ibu dengan menggunakan teknik accidental sampling. Pengumpulan data dilaksanakan pada bulan September–Oktober 2013 di Puskesmas wilayah Kota Tangerang Selatan. Intervensi dilakukan selama 30 menit. Pengumpulan data dilakukan sebelum intervensi, 3 hari setelah intervensi (post1), dan 10 hari setelah intervensi (post 2). Pengumpulan data menggunakan kuesioner dan observasi. Keberhasilan pemberian ASI berdasar pada parameter pengetahuan, langkah menyusui, perlekatan bayi, dan kecukupan ASI. Analisis data menggunakan general linear model repeated measureANOVA. Hasil penelitian menunjukkan adanya signifikansi comprehensive breastfeeding education (p=0.001). Rata-rata keberhasilan pemberian ASI sebelum dan setelah intervensi meningkat. Sebesar 93,9% intervensi memengaruhi tingkat keberhasilan. Rata-rata sebelum intervensi 56,74 (SD 5,92), post 1 sebesar 60,83 (SD 6,38) dan post2 sebesar 74,55 (SD 5,32). Subvariabel yang memiliki efek secara signifikan setelah intervensi adalah pengetahuan (p=0.001) dan langkah menyusui (p=0.001), sedangkan subvariabel perlekatan bayi (p=0.061) dan kecukupan ASI (p=0.162) tidak secara signifikan berbeda antara sebelum dan setelah intervensi. Pelaksanaanbreastfeeding education disarankan pada ibu agar dapat melakukan posisi perlekatan bayi yang benar sehingga dapat mengurangi masalah-masalah berkaitan dengan perlekatan yang tidak sesuai seperti puting perih, lecet atau berdarah, dan bayi kurang puas dalam menyusu yang bisa mengakibatkan gagalnya program ASI ekslusif.Kata kunci:Menyusui, pendidikan, perlekatan, postpartum AbstractBreastfeeding have still been problem for adequate newborn nutrition. Adequate breastfeeding support is essential for mothers to initiate and maintain optimal breastfeeding practices. A strategic needed to support successful breastfeeding. The purpose of research is to analyze the effectiveness comprehensive breastfeeding education on successful breastfeeding at postpartum periods. A quasi-experimental one group pretest, post test, repeated mesaured was used. This study was conducted at public health in Tangerang Selatan municipality in September–October 2013 among 22 postpartum mothers, convenience sampling methods. Intervention was done 30 minute. Data were collected before intervention (pretest), third day after intervention (post 1) and tenth day after intervention (repeated/post 2) using four parameter, that are knowledge, breastfeeding steps, proper lacth-on and adequate breastmilk. Using repeated measures analysis of variance there was a significant increase (p=0.001) in the overall Successful breastfeeding mean. Around 93,9% the effectiveness of intervention influence on successful. The mean before intervention is 56,74 (SD 5,92), increased at post 1:60,83 (SD 6,38) and post 2:74,55 (SD 5,32). Subvariable which has effect significantly after intervention is knowledge (p=0.001) and breastfeeding steps (p=0.001), in contrary, proper latch-on (p=0,061) and adequate breastmilk (p=0.162) have no significant effect after intervention. Suggestion to support breastfeeding education and counselling proper latch-on adequately that can decrease the problem such as painful, creaks or bloody putting.Key words: Breastfeeding, education, latch-on, postpartum


2021 ◽  
pp. bjophthalmol-2020-317664
Author(s):  
Carly SY Lam ◽  
Wing Chun Tang ◽  
Paul H Lee ◽  
Han Yu Zhang ◽  
Hua Qi ◽  
...  

AimsTo determine myopia progression in children who continued to wear the defocus incorporated multiple segments (DIMS) lenses or switched from single vision (SV) to DIMS lenses for a 1-year period following a 2-year myopia control trial.Methods128 children participated in this study. The children who had worn DIMS lenses continued to wear DIMS lenses (DIMS group), and children who had worn SV lenses switched to wear DIMS lenses (Control-to-DIMS group). Cycloplegic spherical equivalent refraction (SER) and axial length (AL) were measured at 6-month interval. Historical controls were age matched to the DIMS group at 24 months and used for comparing the third-year changes.ResultsOver 3 years, SER and AL changes in the DIMS group (n=65) were −0.52±0.69D and 0.31±0.26 mm; these changes were not statistically significant over time (repeated measures analysis of variance, p>0.05).SER (−0.04±0. 38D) and AL (0.08±0.12 mm) changes in the Control-to-DIMS group (n=55) in the third year were less compared with the first (mean difference=0.45 ± 0.30D, 0.21±0.11 mm, p<0.001) and second (0.34±0.30D, 0.12±0.10 mm, p<0.001) years.Changes in SER and AL in both groups over that period were significantly less than in the historical control group (DIMS vs historical control: mean difference=−0.18±0.42D, p=0.012; 0.08±0.15 mm, p=0.001; Control-to-DIMS versus historical control: adjusted mean differences=−0.30±0.42D, p<0.001; 0.12±0.16 mm, p<0.001).ConclusionsMyopia control effect was sustained in the third year in children who had used the DIMS spectacles in the previous 2 years and was also shown in the children switching from SV to DIMS lenses.


2021 ◽  
Vol 6 (1) ◽  
pp. 4
Author(s):  
W. Guy Hornsby ◽  
Abigail L. Tice ◽  
Jason D. Stone ◽  
Justin J. Merrigan ◽  
Joshua Hagen ◽  
...  

The purpose of this longitudinal, descriptive study was to observe changes in maximal strength measured via isometric clean grip mid-thigh pull and home runs (total and home runs per game) across three years of training and three competitive seasons for four National Collegiate Athletic Association (NCAA) Division 1 baseball players. A one-way repeated measures analysis of variance (ANOVA) was performed, revealing significant univariate effects of time for peak force (PF) (p = 0.003) and peak force allometrically scaled (PFa) (p = 0.002). Increases in PF were noted from season 1 to season 2 (p = 0.031) and season 3 (p = 0.004), but season 2 was not significantly different than season 3 (p = 0.232). Additionally, increases in PFa were noted from season 1 to season 2 (p = 0.010) and season 3 (p < 0.001), but season 2 was not significantly different than season 3 (p = 0.052). Home runs per game rose from the 2009 (0.32) to 2010 season (1.35) and dropped during the 2011 season (1.07). A unique aspect of the study involves 2010 being the season in which ball-bat coefficient of restitution (BBCOR) bats were introduced to the NCAA competition.


2008 ◽  
Vol 38 (2) ◽  
pp. 247-256 ◽  
Author(s):  
Nathaniel A. Hemstad ◽  
Eric C. Merten ◽  
Raymond M. Newman

The response of fish communities and stream habitat to four riparian harvest treatments was studied in north-central Minnesota to determine if riparian harvest with two different harvest systems degrades stream systems. Treatments included control (no harvest), riparian control, cut-to-length riparian thin, and tree length riparian thin. Fish and habitat data were collected from 50 m reaches above, within, and downstream of each treatment 1 year preharvest (1997) and 3 years postharvest (1998–2000). Repeated measures analysis revealed few effects due to treatment; however, there was a 6%–10% significant reduction in canopy cover. Percent fine sediments increased significantly (15%) system-wide following forest harvest and persisted through 2000. This increase in fine sediments was correlated with a decrease in fish biotic integrity (r = –0.31). Habitat and fish variables were influenced more by year-to-year variation than by harvest treatment, suggesting that factors operating at a broader basin-wide scale may influence fish and habitat or mask any site-level harvest effects in this low-gradient stream system. Residual riparian basal areas ≥12.3m2/ha along reaches ≤200 m in length may be adequate to protect fish and habitat in these low-gradient streams, but basin-wide effects of harvest deserve more scrutiny.


Sign in / Sign up

Export Citation Format

Share Document