• Journal of the Korean Data and Information Science Society
• /
• 제18권2호
• /
• pp.525-534
• /
• 2007

It is a common practice in many research areas that multiple range tests for a between subject factor such as Tukey are applied to a within subject factor in a repeated measures design. Tukey procedure, however, sometimes detects no pairs with different means even when the hypothesis of all equal level means is rejected. This study attempts to provide a rationale for the proposition that Tukey is inappropriate post hoc procedure for a within subject factor in which the observations are correlated. We introduce two multiple range tests, Bonferroni and Scheffe, for a within subject factor and show that Bonferroni is more appropriate than Scheffe for pairwise multiple comparisons. Subsequent simulation study indicates that Tukey has significantly less power than Bonferroni in detecting actual difference between means of some pairs when the observations of a within subject factor are highly correlated.

• 응용통계연구
• /
• 제2권1호
• /
• pp.18-34
• /
• 1989

서로 같은 분산을 가지며 정규분포를 따르는 4개의 처리평균의 대응비교에 관한 연구로서, 삼중 t-분포를 이용하여 동시포함 범위 확률값이 정확히 $1-\alpha$를 갖는 통계적 계산방법과 기법을 고찰하였다. 이 기법을 이용하여 처리사이의 표본 갯수를 변화시켜 대응되는 정확한 신뢰구간을 구하며 기존의 신뢰구간의 길이 비교, 실험적 오차 비, 효율성을 조사하였다.

• Communications for Statistical Applications and Methods
• /
• 제24권6호
• /
• pp.627-640
• /
• 2017

A common interest in gene expression data analysis is to identify genes that present significant changes in expression levels among biological experimental conditions. In this paper, we develop a Bayesian approach to make a gene-by-gene comparison in the case with a control and more than one treatment experimental condition. The proposed approach is within a Bayesian framework with a Dirichlet process prior. The comparison procedure is based on a model selection procedure developed using the discreteness of the Dirichlet process and its representation via Polya urn scheme. The posterior probabilities for models considered are calculated using a Gibbs sampling algorithm. A numerical simulation study is conducted to understand and compare the performance of the proposed method in relation to usual methods based on analysis of variance (ANOVA) followed by a Tukey test. The comparison among methods is made in terms of a true positive rate and false discovery rate. We find that proposed method outperforms the other methods based on ANOVA followed by a Tukey test. We also apply the methodologies to a publicly available data set on Plasmodium falciparum protein.

• Communications for Statistical Applications and Methods
• /
• 제16권1호
• /
• pp.75-83
• /
• 2009

단순선형 회귀모형의 기울기에 대한 평행성 검정법을 제안하였다. 세 군 이상에서 기울기에 대하여 Tukey (1953)가 제안한 HSD방법을 이용한 모수적 검정법과 Kruskal-Wallis (1952) 검정법을 이용한 비모수적 검정법을 각각 제안하였다. 또한 모의실험을 통하여 기존의 검정법과 제안한 검정법의 검정력을 비교하였다.

• 응용통계연구
• /
• 제30권6호
• /
• pp.1027-1036
• /
• 2017

일원배치모형에서 세 개 이상의 처리 간에 차이 유무를 검정하여 귀무가설이 기각됐다면, 어떤 것이 통계적으로 유의한 결과인지 확인하기 위해서는 다중비교 방법이 필요하다. 대표적인 모수적 검정법으로는 Tukey (1953), 비모수적 검정법으로는 Kruskal-Wallis (1952)의 검정에 기초한 방법이 있다. 이 방법은 전체 자료에 대한 혼합표본에 순위를 부여한 후 세 개 이상의 각 처리별 평균 순위를 이용한 검정방법이다. 본 논문에서는 Chung과 Kim (2007)이 제안한 결합위치 검정법을 확장하여 일원배치모형에서 새로운 비모수적 다중비교 방법을 제안하였다. 또한 모의실험(Monte Carlo simulation)을 통해 기존의 검정방법들과 제안한 방법의 family wise error rate (FWE)와 검정력을 비교하였다.

• Communications for Statistical Applications and Methods
• /
• 제19권4호
• /
• pp.591-595
• /
• 2012

We frequently use Tukey's boxplot to identify outliers in the batch of observations of the continuous variable. In doing so, we implicitly assume that the underlying distribution belongs to the family of normal distributions. Such a practice of data handling is often superficial and improper, since in reality too many variables manifest the skewness. In this short paper, we build a modified boxplot and set the outlier identification procedure by assuming that the observations are generated from the skew normal distribution (Azzalini, 1985), which is an extension of the normal distribution. Statistical performance of the proposed procedure is examined with simulated datasets.

• Clinics in Shoulder and Elbow
• /
• 제25권1호
• /
• pp.42-48
• /
• 2022

Background: Total shoulder arthroplasty (TSA) has been demonstrated to be an effective treatment for multiple shoulder pathologies. The purpose of our study was to compare the relative value units (RVUs) per minute of surgical time for primary and revision TSA. Methods: The American College of Surgeons National Surgical Quality Improvement Program database was queried to identify patients that underwent primary TSA, one-component revision TSA, and two-component revision TSA between January 1, 2015 and December 31, 2017 using current procedure terminology codes. RVUs were divided by mean operative time for each procedure to determine the amount of revenue generated per minute. Rates were compared between the groups using a one-way analysis of variance with post-hoc Tukey test. Statistical significance was set at p<0.05. Results: When dividing compensation by surgical time, we found that two-component revision generated more compensation per minute compared to primary TSA (0.284±0.114 vs. 0.239±0.278 RVU per minute or $10.25±$4.11 vs. $8.64±$10.05 per minute, respectively; p=0.001). Conclusions: The relative value of revision TSA procedures is weighted to account for the increased technical challenges and time associated with these procedures. This study confirms that reimbursement is higher for revision TSA compared to primary TSA.

• The Journal of Advanced Prosthodontics
• /
• 제3권4호
• /
• pp.177-185
• /
• 2011

PURPOSE. The aim of this study was to evaluate the effect of dimensional stability of splinting material on the accuracy of master casts. MATERIALS AND METHODS. A stainless steel metal model with 6 implants embedded was used as a master model. Implant level impressions were made after square impression copings were splinted using 5 different techniques as follows. (1) Splinted with autopolymerizing resin and sectioned, reconnected to compensate polymerization shrinkage before the impression procedure. (2) Splinted with autopolymerizing resin just before impression procedure. (3) Primary impression made with impression plaster and secondary impression were made over with polyether impression material. (4) Splinted with impression plaster. (5) Splinted with VPS bite registration material. From master model, 5 impressions and 5 experimental casts, total 25 casts were made for each of 5 splinting methods. The distortion values of each splinting methods were measured using coordinate measuring machine, capable of recordings in the x-, y-, z- axes. A one-way analysis of variance (ANOVA) at a confidence level of 95% was used to evaluate the data and Tukey's studentized range test was used to determine significant differences between the groups. RESULTS. Group 1 showed best accuracy followed by Group 3 & 4. Group 2 and 5 showed relatively larger distortion value than other groups. No significant difference was found between group 3, 4, 5 in x-axis, group 2, 3, 4 in y-axis and group 1, 3, 4, 5 in z-axis (P<.0001). CONCLUSION. Both Splinting impression copings with autopolymerizing resin following compensation of polymerization shrinkage and splinting method with impression plaster can enhance the accuracy of master cast and impression plaster can be used simple and effective splinting material for implant impression procedure.

• The Journal of Advanced Prosthodontics
• /
• 제9권4호
• /
• pp.257-264
• /
• 2017

PURPOSE. To evaluate the adhesion to CAD/CAM feldspathic blocks by failure analysis and shear bond strength test (SBSt) of different restorative systems and different surface treatments, for purpose of moderate chipping repair. MATERIALS AND METHODS. A self-adhering flowable composite (Vertise Flow, Kerr) containing bi-functional phosphate monomers and a conventional flowable resin composite (Premise Flow, Kerr) applied with and without adhesive system (Optibond Solo Plus, Kerr) were combined with three different surface treatments (Hydrofluoric Acid Etching, Sandblasting, combination of both) for repairing feldspathic ceramics. Two commercial systems for ceramic repairing were tested as controls (Porcelain Repair Kit, Ultradent, and CoJet System, 3M). SBSt was performed and failure mode was evaluated using a digital microscope. A One-Way ANOVA (Tukey test for post hoc) was applied to the SBSt data and the Fisher's Exact Test was applied to the failure analysis data. RESULTS. The use of resin systems containing bi-functional phosphate monomers combined with hydrofluoric acid etching of the ceramic surface gave the highest values in terms of bond strength and of more favorable failure modalities. CONCLUSION. The simplified repairing method based on self-adhering flowable resin combined with the use of hydrofluoric acid etching showed high bond strength values and a favorable failure mode. Repairing of ceramic chipping with a self-adhering flowable resin associated with hydrofluoric acid etching showed high bond strength with a less time consuming and technique-sensitive procedure compared to standard procedure.

• Restorative Dentistry and Endodontics
• /
• 제39권4호
• /
• pp.303-309
• /
• 2014

Objectives: Hydrogen peroxide ($H_2O_2$) surface treatment of fiber posts has been reported to increase bond strength of fiber posts to resin cements. However, residual oxygen radicals might jeopardize the bonding procedure. This study examined the effect of three antioxidant agents on the bond strength of fiber posts to conventional and self-adhesive resin cements. Materials and Methods: Post spaces were prepared in forty human maxillary second premolars. Posts were divided into five groups of 8 each: G1 (control), no pre-treatment; G2, 10% $H_2O_2$ pre-treatment; G3, G4 and G5. After $H_2O_2$ application, Hesperidin (HES), Sodium Ascorbate (SA) or Rosmarinic acid (RA) was applied on each group respectively. In each group four posts were cemented with Duo-Link conventional resin cement and the others with self-adhesive BisCem cement. Push-out test was performed and data were analyzed using 2-way ANOVA and tukey's post-hoc test (${\alpha}=0.05$). Results: There was a statistically significant interaction between the cement type and post surface treatment on push-out bond strength of fiber posts (p < 0.001, F = 16). Also it was shown that different posts' surface treatments significantly affect the push-out bond strength of fiber posts (p = 0.001). $H_2O_2$ treated posts (G2) and control posts (G1) cemented with Duo-link showed the highest ($15.96{\pm}5.07MPa$) and lowest bond strengths ($6.79{\pm}3.94$) respectively. Conclusions: It was concluded that $H_2O_2$ surface treatment might enhance the bond strength of fiber posts cemented with conventional resin cements. The effect of antioxidants as post's surface treatment agents depends on the characteristics of resin cements used for bonding procedure.