• Journal of Power System Engineering
• /
• v.15 no.5
• /
• pp.72-76
• /
• 2011

In this work, the parameter optimization for thermal-sprayed Al/SiC composites have been designed by $L_9(3^4)$ orthogonal array and analysis of variance(ANOVA). Al/SiC composites were fabricated by flame spray process on steel substrate. The hardness of composites were measured using micro-vickers hardness tester, and these results were analyzed by ANOVA. The ANOVA results showed that the oxygen gas flow, powder feed rate and spray distance affect on the hardness of the Al/SiC composites. From the ANOVA results, the optimal combination of the flame spray parameters could be extracted. It was considered that experimental design using orthogonal array and ANOVA was efficient to determine optimal parameter of thermal-sprayed Al/SiC composites.

• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.337-354
• /
• 2002

This paper derives three estimation methods for the between group variance component for serially correlated random model. To compare their estimation capability, three designs having different degree of unbalancedness are considered. The so-called empirical quantile dispersion graphs(EQDGs) used to compare estimation methods as well as designs. The proposed conditional ANOVA estimation is robust for design unbalancedness, however, ML estimation is preferred to the conditional AOVA and REML estimation regardless of design unbalancedness and correlation coefficient.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2001.10a
• /
• pp.97-115
• /
• 2001

cDNA microarray technology allows the monitoring of expression levels for thousands of genes simultaneously. Many statistical analysis tools become widely applicable to the analysis of cDNA microarray data. In this talk, we consider a two-way ANOVA model to differentiate genes that have high variability and ones that do not. Using this model, we detect genes that have different gene expression profiles among experimental groups. The two-way ANOVA model is illustrated using cDNA microarrays of 3,800 genes obtained in an experiment to search for changes in gene expression profiles during neuronal differentiation of cortical stem cells.

• Advances in concrete construction
• /
• v.11 no.4
• /
• pp.285-298
• /
• 2021

This study focused on experimental evaluation of mechanical properties of pervious concrete mixtures with the aim of achieving higher values of strength while considering the associated costs. The effectiveness of key parameters, including cement content, water to cement ratio (W/C), aggregate to cement ratio (A/C), and sand replacement was statistically analyzed using paired-samples t-test, Taguchi method and one-way ANOVA. Taguchi analysis determined that in general, the role of W/C was more significant in increasing strength, both compressive and flexural, than cement content and A/C. It was found that increase in replacing percent of coarse aggregate with sand could undermine specimens to percolate water, though one-way ANOVA analysis determined statistically significant increases in values of strength of mixtures. Cost analysis revealed that higher strengths did not necessarily correspond to higher costs; in addition, increasing the cement content was not an appropriate scenario to optimize both strength and cost. In order to obtain the optimal values, response surface method (RSM) was carried out. RSM optimization helped to find out that W/C of 0.40, A/C of 4.0, cement content of about 330 kg/m3 and replacing about 12% of coarse aggregate with sand could result in the best values for strength and cost while maintaining adequate permeability.

• Advances in concrete construction
• /
• v.6 no.6
• /
• pp.611-629
• /
• 2018

The objective of present study is to investigate the effect of granulated blast furnace slag (GBS) as partial substitution of natural sand on behaviour of cement mortar. For this, the methods of factorial design with water cement (w/c) ratio and incorporation percentages of GBS as replacement of natural fine aggregate i.e., GBS(%) as factors are followed. The levels of factor w/c ratio are fixed at 0.4, 0.45, and 0.5 and the levels of factor GBS(%) are kept fixed as 0%, 20%, 40%, 60%, 80% and 100%. The compressive strength (CS) of mortar after 3, 7, 14, 28, 56 and 90 days, and water absorption (WA) are chosen as responses of the study. Analysis of variance (ANOVA) of experimental results has been carried out and those are illustrated by ANOVA tables, main effect and interaction plots. The results of study depict that the selected factors have substantial influence on the strength and WA of mortar. However, the interaction of factors has no substantial impact on CS and WA of mixes.

• Journal of Pharmaceutical Investigation
• /
• v.24 no.2
• /
• pp.49-55
• /
• 1994

Bioequivalence test of commercially available rifampicin capsules was performed. Sixteen volunteers were divided into 2 groups and the reference and test drug were given orally (450 mg) by cross-over design. Statistical evaluation of AUC, $C_{max}\;and\;T_{max}$ involved an analysis of variance (ANOVA). The differences of mean value in AUC, $C_{max}\;and\;T_{max}$ between the reference and test drug were within 20% with reference drug. ANOVA showed no significant differences for ‘between group’, ‘drug’ and ‘period’, but not for ‘between subjects’. The power of test $(1-{\beta})\;of\;AUC\;and\;$C_{max}$ was larger than 0.8 and the confidence of bioavailability was $within\;{\pm}20%$. From these results, it was concluded that the two preparations were bioequivalent for AUC and $C_{max}$, but was not for $T_{max}$.

• Journal of Pharmaceutical Investigation
• /
• v.24 no.2
• /
• pp.67-72
• /
• 1994

Bioequivalence (BE) test of biphenyl dimethyl dicarboxylate (DDB) tablets was performed. Normal healthy male volunteers (n = 20) were randomly divided into 2 groups, and reference $(Nissel{\circledR})$ and test $(Livital{\circledR})$ tablets of DDB $(25mg{\times}8\;Tab.\;= \;200\;mg)$ were given orally by balanced two-period cross-over design. The serum concentration was determined by high performance liquid chromatography. The pharmacokinetic parameters, AUC, $C_{max}$, and $T_{max}$ obtained after drug administration were statistically analyzed. Statistical evaluation of the data involved an analysis of variance (ANOVA) for cross-over design. The results were within 20% differences of mean value in AUC, $C_{max}$, and $T_{max}$ between reference and test tablets. The results of ANOVA showed no significant differences for "between group or subject" and "period". The test tablet was bioequivalent with the reference tablet in the AUC, $C_{max}$, and $T_{max}$.

• The Korean Journal of Applied Statistics
• /
• v.17 no.3
• /
• pp.419-430
• /
• 2004

Since cDNA microarray experiments can monitor expression levels for thousands of genes simultaneously, the experimental designs and their analyzing methods are very important for successful analysis of microarray data. The loop design is discussed for selecting differentially expressed genes among several treatments and the analysis of variance method is introduced to normalize microarray data and provide estimates of the interesting quantities. MA-ANOVA is used to illustrate this method on a recently collected loop designed microarray data at Cancer Metastasis Research Center, Yonsei University.

• Archives of Pharmacal Research
• /
• v.18 no.4
• /
• pp.237-242
• /
• 1995

For the vioequivalence study of two ceftriaxone injection formulations ($Rocephin{\circledR}$ ; Roche, and Triaxone ; Hanmi0, the HPLC analytical method for the analysis of ceftriaxone in plasma was used. Fourteen healthy volunteers completed the study and each subject were IM in jected signle doses (1 g) of the test and the reference formulations in a two-way crossover design with an one week drug free interval between doses. Following each administration, plasma concentrations of ceftrixone were monitored over a period of 24 h. Bioequivalence parameters $AUC_{24th}, {\;}T_{max}, {\;}C_{max}$ and MRT determined from the data obtained for the two formulations were examined by analyses of variance (ANOVA) and other criteria and tests for bioequivalence. Results of ANOVA and confidence limits of test/reference ratios of $AUC_{24th}, {\;}T_{max}, {\;}C_{max}$ and MRT, and statistical tests indicated the bioequivalence of the two formulations (i.e., test/reference ratio was within $100{\pm}20%$) except for $T_{max}$ The mean of $T_{max}$ showed only 6. 9% difference from the reference but the detection limit was 22.5% which is slightly over the 20% criteria. No pharmacokinetic parameters including Ka, Kel, Vd and Cl indicated significant difference in between the two fomulations. It was concluded that the data yielded fro the two cefriaxone formulations demonstrated that they were bioequivalent.

• Biomolecules & Therapeutics
• /
• v.11 no.1
• /
• pp.65-71
• /
• 2003

Terbinafine is a synthetic allylamine that is available in an oral formulation and is used at a dosage of 250mg/day. It is used as an active antifungal agent and inhibits the fungal enzyme squalene epoxidase, which leads to the accumulation of the sterol squalene, which is toxic to the organism. The purpose of the present study was to evaluate the bioequivalence of two terbinafine tablets, Lamisil (Novartis Korea Ltd.) and Terbinex (C-TRI Ltd.), according to the guidelines of Korea Food and Drug Administration (KFDA). Eighteen normal male volunteers, 26.00$\pm$2.57 year in age and 70.51$\pm$9.36 kg in body weight, were divided into two groups and a randomized 2${\times}$2 cross-over study was employed. After one tablet containing 125 mg of terbinafine was orally administered, blood was taken at predetermined time intervals and the concentrations of terbinafine in plasma were determined using HPLC with UV detector. Pharmacokinetic parameters such as AUC, $C_{max}$ and $T_{max}$ were calculated and ANOVA test was utilized for the statistical analysis of the parameters. The results showed that the differences in AUC, $C_{max}$ and $T_{max}$ between two tablets were －4.191％, 5.223％ and －25.720％, respectively when calculated against the Lamisil, tablet. The powers (1-$\beta$) for AUC, $C_{max}$ and $T_{max}$ were 81％, 87％ and below 60％, respectively. Minimum detectable differences(.il) at alpha=O.1 and 1-/3=0.8 were less than 20％ (e.g., 19.72％ and 17.77％ for AUC and $C_{max}$, respectively). But minimum detectable differences($\Delta$) at alpha=0.1 and 1-$\beta$=0.8 for $T_{max}$ were more than 20％ (e.g., 26.25％). The 90％ confidence intervals were within $\pm$20％ (e.g., －17.440∼9.06 and －6.713∼17.160 for AUC and $C_{max}$ respectively). But 90％ confidence intervals for $T_{max}$ were not within $\pm$20％ (e.g., －43.346∼8.083). Another ANOVA test was conducted for logarithmically transformed AUC and $C_{max}$. These results showed that there are no significant differences in AUC and $C_{max}$ between the two formulations: The differences between the formulations in these log transformed parameters were all for less than 20％ (e.g., －4.19％ and 5.22％ for AUC and $C_{max}$, respectively). The 90％ confidence intervals for the log transformed data were not the acceptance range of log 0.8 to log 1.25 in AUC but the acceptance range of log 0.8 to log 1.25 in $C_{max}$ (e.g., log 1.13∼log 1.50 and log 0.94-log 1.22 for AUC and $C_{max}$ respectively). The major parameters, AUC and $C_{max}$ met the criteria of KFDA for bioequivalence although $T_{max}$ did not meet the criteria of KFDA (1998 year) for bioequivalence, indicating that Onfran tablet is bioequivalent to Zofran tablet. But in another ANOVA test AUC did not meet the criteria of KFDA (2002) for bioequivalence but $C_{max}$ met the criteria of KFDA (2002 year) for bioequivalence.or bioequivalence.equivalence.equivalence.equivalence.