First-stage Sample Research Articles

A Review of Blockchain-Rooted Energy Administration in Networking

Energy Administration (EA) in networking involves improving energy efficiency by managing energy. The blockchain framework involves a chain of associated blocks that obviously protects the genuineness, upholds accountability, and upholds disguised-anonymity of its transactions/entries with the help of peer-to-peer consensus techniques and cryptographic mechanisms. Driven by the fact that existing surveys do not focus on the EA in the broad scope of networking, we review diverse blockchain-rooted EA solutions, where we recognize 7 roles of blockchain in EA and explore them in detail with regard to EA techniques, EA approaches, blockchain-linked factors, network-linked factors, and such. We assembled a first-stage sample of 80 document citations by appraising the articles for qualification criteria hunted from E-libraries operating a detailed and prolonged process. Considering the review, in blockchain-rooted EA, blockchain can facilitate storing and exchanging data in a trustworthy manner, operate energy-efficient consensus approaches, act as an energy manager, provide authentication and access control for EA, facilitate secure offloading for EA, and provide automated EA tasks operating smart contracts. Detailed exploration shows that from blockchain-rooted EA, 32.5% operate blockchain to store and exchange data for an EA task, 95% operate uniform blockchain, 30% operate PoW consensus, 82.5% operate fully decentralized EA, 57.5% operate cross-layer EA, and 10% operate in IoT networks. Finally, we debate the possibilities and barriers to the conception of blockchain-rooted EA and then present guidance to vanquish them.

Development of a 10-m resolution maize and soybean map over China: Matching satellite-based crop classification with sample-based area estimation

Spatially explicit information on crop distribution is essential for market information, food security, and agricultural sustainability. However, high-resolution crop maps are unavailable for most countries of the world. In this study, we developed an operational workflow and produced the first openly-available 10-m resolution maize and soybean map over China. We also derived area estimates for maize and soybean extent for 2019 using a stratified, two-stage, cluster sampling design and ground data collected for the entire country. We developed a multi-scale, multi-temporal procedure for mapping, in which field data were used as training to map maize and soybean over the first-stage sample of 10 km × 10 km equal-area blocks with PlanetScope and Sentinel-2 data. Then, the classified blocks were used as training to map maize and soybean for the country with wall-to-wall Sentinel-2 data using a random forests approach. We used all available Sentinel-2 surface reflectance data acquired between April and October 2019, applied quality assurance, including cloud and shadow masking, and created monthly image composites as inputs for the random forests analysis. We derived maize and soybean area estimates using the field sample data and a regression estimator. Utilizing the probability output layer of the random forests models, we found and applied empirical probability thresholds that matched map-based crop area estimates with sample-based area estimates. Maize area in China in 2019 was estimated to be 330,609 ± 34,109 km2 (± value is the standard error), and soybean area was estimated to be 78,107 ± 12,969 km2. Validated using the field sample data as reference, our crop map had an overall accuracy of 91.8 ± 1.2%. The user's and producer's accuracies for the maize class were 93.9 ± 2.5% and 79.2 ± 3.6%, and for the soybean class were 63.6 ± 12.1% and 61.9 ± 11.8%. Our map-based maize and soybean area estimates had close agreement with government reports at the provincial and prefectural levels, with r2 of 0.90 and 0.92 for maize, and 0.93 and 0.94 for soybean, respectively. Our workflow can generate internally consistent results for crop area estimation and crop mapping simultaneously. As Sentinel-2 data are being acquired consistently and very-high-resolution commercial satellite data are increasingly available, our established workflow may be applied in an operational setting for annual crop mapping in China and other countries.

Influence of multi-stage heat treatment on the microstructure and mechanical properties of TC21 titanium alloy

Duplex-structured TC21 alloy samples were first solution-treated at a higher temperature in the α + β region (940°C) with furnace cooling (FC), air cooling (AC), and water cooling (WC), followed by a second-stage solution treatment at a lower temperature in the α + β region (900°C), and then finally aged at 590°C. The effects of the morphology and quantity of α phases on the structure and properties of the TC21 alloy after the different heat treatments were analyzed. The in-situ tensile deformation process and crack propagation behavior were observed using scanning electron microscopy (SEM). The quantity of equiaxed α phases as well as the thickness of lamellar α phases reduced, the tensile strength increased firstly and then decreased, the elongation decreased with the increasing cooling rate after the first-stage solution treatment. The amount and size of lamellar α phases increased after the second-stage solution treatment because of sufficient diffusion of the alloying elements, thereby leading to increased tensile strength. The amount of dispersed α phases increased after the third-stage aging treatment owing to the increase in the nucleation rate, resulting in a noteworthy strengthening effect. After the third-stage aging treatment, the first-stage FC sample exhibited better mechanical properties because it contained more equiaxed α and βtrans phases than the first-stage AC and WC samples.

Novel Motor Imagery-Based Brain Switch for Patients With Amyotrophic Lateral Sclerosis: A Case Study Using Two-Channel Electroencephalography

This article presents a brain switch for patients with amyotrophic lateral sclerosis (ALS). The firststage extract sample entropy (SampEn) features are from 30-channel electroencephalography (EEG) signals. Fisher's separability criterion is then performed in the second stage to select the top two EEG channels for each patient. Features of the top two channels are sent into the last stage for classification, where a motor imagery detector based on an adaptive support vector machine (ASVM) is used to keep the false positive rate (FPR) below a near-zero threshold and gain a high true positive rate (TPR). The results on five patients with ALS demonstrated the superior performance of the brain switch in both validation and follow-up sessions.

Predicting suicide attempts among soldiers who deny suicidal ideation in the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS)

Most nonfatal suicide attempts and suicide deaths occur among patients who deny suicidal ideation (SI) during suicide risk screenings. Little is known about risk factors for suicidal behaviors among such patients. We investigated this in a representative sample of U.S. Army soldiers who denied lifetime SI in a survey and were then followed through administrative records for up to 45 months to learn of administratively-recorded suicide attempts (SA). A novel two-stage risk assessment approach was used that combined first-stage prediction from administrative records to find the subsample of SI deniers with highest subsequent SA risk and then used survey reports to estimate a second-stage model identifying the subset of individuals in the high-risk subsample at highest SA risk. 70% of survey respondents denied lifetime SI. Administrative data identified 30% of this 70% who accounted for 81.2% of subsequent administratively-recorded SAs. A relatively small number of self-report survey variables were then used to create a prediction model that identified 10% of the first-stage high-risk sample (i.e., 3% of all soldiers) at highest SA risk (accounting for 45% of SAs in the total sample). We close by discussing potential applications of this approach for identifying future SI deniers at highest SA risk.

붓스트랩방법을 이용한 등분산 검정의 다중비교

사후분석(post-hoc analysis) 혹은 다중비교(multiple comparison)는 분산분석(analysis of variance)에서 귀무가설(null hypothesis)을 기각시켰을 때 관심대상인 집단들 간의 개별적인 비교를 위한 절차이다. Baek, Park(2013)은 두 집단씩 짝을 지어 t-통계량을 구한 후 붓스트랩방법(bootstrapping method)을 사용하여 Holm(1979)의 순차적 기각방법(sequentially rejective method)을 근간으로 검정하는 다중비교방법을 제안하였는데 이 때, 등분산 여부를 검정하는데 있어 원 자료의 등분산 검정(homogeneity of variance test)을 고려하였다. 본 연구에서는 평균차이 검정(test for mean differences)을 등분산 검정과 연동해서 수행하기 위해 t-통계량을 통한 평균차이 검정을 적용하기 전에 분산의 동일성 여부를 붓스트랩방법과 순차적 기각방법으로 알아보고자 한다. 이를 통해 얻어진 주어진 표본의 분산의 동일성 여부로부터 최종적인 평균차이 검정을 수행하기 위하여 이중(double) 붓스트랩방법을 제안한다. 본 연구에서는 사례분석을 통해 제안한 방법을 적용하였다. 그 결과, 검정순서에서 차이가 발생하고 결과적으로 상이한 의사결정이 이루어질 수 있음을 확인하였다.Multiple comparison is a comparison of differences between groups used when the null hypothesis is rejected in the analysis of variance. Baek, Park (2013) proposed a multiple comparison that uses t-statistic, followed by a sequentially rejective method of Holm (1979) using the bootstrapping methods. In Baek, Park (2013), however, only the traditional homogeneity of variance test was used in the homogeneity of variance test before using t -statistic. In this paper, both the test of mean difference and the homogeneity of variance test are simultaneously taken into account by employing the bootstrapping method and the sequentially rejective method. In order to check the homogeneity of variances between groups, we propose a double bootstrapping method, where the second-stage bootstrap samples re-sampled from a certain first-stage bootstrap sample are utilized in terms of variance and, consequently, the results about the variances are considered to the final decision on the significance of mean differences. As a result of applying the proposed method through the case analysis, it is confirmed that there is a possibility of different decision making by the difference of the test sequence.

Adaptive designs: The Swiss Army knife among clinical trial designs?

There has been considerable progress in the development and implementation of adaptive designs over the past 30 years. A major driver for this class of novel designs is the possibility to increase the information value of clinical trial data to enable better decisions, leading to more efficient drug development processes and improved late-stage success rates. In the first part of this article, we review the development of adaptive designs from different perspectives. We trace back key historical papers, report on landmark adaptive design clinical trials, review major cross-industry collaborations, and highlight key regulatory guidance documents. In the second, more technical part of this article, we address the question of whether it is possible to define factors which guide the choice between a fixed or an adaptive design for a given trial. We show that in non-linear regression models with a moderate variance of the responses, the first-stage sample size of an adaptive design should be chosen sufficiently large in order to address variability in the interim parameter estimate. In conclusion, the choice between an adaptive and a fixed design depends in a sensitive manner on the specific statistical problem under investigation.

1422TiP - Phase II, singlearm, nonrandomized, and multicenter clinical trial of regorafenib (REG) as a single agent in the firstline setting for patients with metastatic and/or unresectable KIT/PDGFR wild-type GIST. A GEIS and ISG study

Approximately 10-15% of adults with GIST lack KIT or PDGFRA mutations. This KIT/PDGFRA wild-type (wt) GIST is considered a separate pathological entity and is highly clinically heterogeneous. Because most KIT/PDGFRA wt-GISTs do not respond to imatinib, new treatment approaches are needed. REG is an oral multikinase inhibitor that has been shown to improve progression-free survival (PFS) and disease control rate (DCR) vs placebo in patients with advanced GIST progressing after failure of imatinib and sunitinib (Demetri et al. Lancet 2013). This study was designed to assess the effectiveness of REG in patients with metastatic and/or unresectable KIT/PDGFR wt-GIST in the first-line setting. Trial design: Patients ≥18 years of age with histologically confirmed unresectable and/or metastatic KIT/PDGFR wt-GIST (lack of mutations in KIT exons 11,9,13,17 and PDGFR exons 12,18 confirmed by next-generation sequencing) are eligible. Other inclusion criteria include ≥1 measurable lesion (RECIST v1.1), ECOG PS 0-1, adequate bone marrow, liver, and renal function, not fulfilling any exclusion criteria, and written informed consent. FFPE-tumor blocks are to be provided. Collection of blood and fresh tumor samples for a translational substudy is optional. REG 160 mg will be administered once daily in a 3-weeks on, 1-week off schedule until disease progression, unacceptable toxicity, or investigator/patient decision to withdraw. Thirtythree patients (+ 20%) are to be recruited according to Simon Minmax 2stage Phase II design. Main endpoint is DCR relative to the historical control of imatinib in wt-GIST. Hypothesis 0: p0 = 73% (0% CR + 23% PR + 50% SD). Hypothesis 1: achieving a DCR of p1 = 90% with REG. Using error rates of a = 0.05 and b = 0.20, the first-stage sample size is 31 patients, with 26 patients as the upper limit for firststage drug rejection. Secondary outcomes include PFS, overall survival, response (CHOI criteria), correlation with translational research, early metabolic response by PETscan, and safety (CTCAE 4.03). Clinical trial identification: EudraCT Number: 2015-001048-12 Legal entity responsible for the study: Grupo Español de Investigación en Sarcomas (GEIS)

Boundary problem in Simon’s two-stage clinical trial designs

ABSTRACTThe activity of a new treatment in clinical trials with binary endpoints can be assessed by comparing the observed response rate to the target response rate. Traditionally, a one-sided hypothesis is used to make statistical inference, and the actual Type I error rate has to be computed over the parameter space of the null hypothesis. The monotonicity property is a fundamental property that guarantees the actual Type I error rate occurring at the boundary. One-arm two-stage designs are considered in this article. We theoretically proved this important property when the final threshold value of a design is less than the first-stage sample size together with another weak condition being satisfied. The method used in this article may finally lead to the final complete proof of this property in the future. We also numerically proved that the monotonicity property is satisfied for designs with the first-stage and the second-stage sample sizes from 10 to 100.

Conditions for Effective Application of Analysis of Symmetrically-Predicted Endogenous Subgroups

Several analytic strategies exist for opening up the “black box” to reveal more about what drives policy and program impacts. This article focuses on one of these strategies: the Analysis of Symmetrically-Predicted Endogenous Subgroups (ASPES). ASPES uses exogenous baseline data to identify endogenously-defined subgroups, keeping the analysis of some postrandomization choice, event, or milestone grounded in the strength of experimental design. Building on lessons from prior applications of ASPES and also adding some new analyses, this article focuses on four specific practical considerations: first-stage prediction success, assumption credibility, data availability, and sample size. Discussion implies the optimal conditions for effective application of ASPES and points to future research that can enhance the overall tool kit of “what works” analyses.

COPD Surveillance—United States, 1999-2011

This report updates surveillance results for COPD in the United States. For 1999 to 2011, data from national data systems for adults aged ≥ 25 years were analyzed. In 2011, 6.5% of adults (approximately 13.7 million) reported having been diagnosed with COPD. From 1999 to 2011, the overall age-adjusted prevalence of having been diagnosed with COPD declined (P = .019). In 2010, there were 10.3 million (494.8 per 10,000) physician office visits, 1.5 million (72.0 per 10,000) ED visits, and 699,000 (32.2 per 10,000) hospital discharges for COPD. From 1999 to 2010, no significant overall trends were noted for physician office visits and ED visits; however, the age-adjusted hospital discharge rate for COPD declined significantly (P = .001). In 2010 there were 312,654 (11.2 per 1,000) Medicare hospital discharge claims submitted for COPD. Medicare claims (1999-2010) declined overall (P = .045), among men (P = .022) and among enrollees aged 65 to 74 years (P = .033). There were 133,575 deaths (63.1 per 100,000) from COPD in 2010. The overall age-adjusted death rate for COPD did not change during 1999 to 2010 (P = .163). Death rates (1999-2010) increased among adults aged 45 to 54 years (P < .001) and among American Indian/Alaska Natives (P = .008) but declined among those aged 55 to 64 years (P = .002) and 65 to 74 years (P < .001), Hispanics (P = .038), Asian/Pacific Islanders (P < .001), and men (P = .001). Geographic clustering of prevalence, Medicare hospitalizations, and deaths were observed. Declines in the age-adjusted prevalence, death rate in men, and hospitalizations for COPD since 1999 suggest progress in the prevention of COPD in the United States.

Replication of Association between Schizophrenia and Chromosome 6p21-6p22.1 Polymorphisms in Chinese Han Population

Chromosome 6p21-p22.1, spanning the extended major histocompatibility complex (MHC) region, is a highly polymorphic, gene-dense region. It has been identified as a susceptibility locus of schizophrenia in Europeans, Japanese, and Chinese. In our previous two-stage genome-wide association study (GWAS), polymorphisms of zinc finger with KRAB and SCAN domains 4 (ZKSCAN4), nuclear factor-κB-activating protein-like (NKAPL), and piggyBac transposable element derived 1 (PGBD1), localized to chromosome 6p21-p22.1, were strongly associated with schizophrenia. To further investigate the association between polymorphisms at this locus and schizophrenia in the Chinese Han population, we selected eight other single-nucleotide polymorphisms (SNPs) distributed in or near these genes for a case-control association study in an independent sample of 902 cases and 1,091 healthy controls in an attempt to replicate the GWAS results. Four of these eight SNPs (rs12214383, rs1150724, rs3800324, and rs1997660) displayed a nominal difference in allele frequencies between the case and control groups. The association between two of these SNPs and schizophrenia were significant even after Bonferroni correction (rs12000: allele A>G, P = 2.50E-04, odds ratio [OR] = 1.27, 95% confidence interval [CI] = 1.12–1.45; rs1150722: allele C>T, P = 4.28E-05, OR = 0.55, 95% CI = 0.41–0.73). Haplotype ATTGACGC, comprising these eight SNPs (rs2235359, rs2185955, rs12214383, rs12000, rs1150724, rs1150722, rs3800324, and rs1997660), was significantly associated with schizophrenia (P = 6.60E-05). We also performed a combined study of this replication sample and the first-stage GWAS sample. The combined study revealed that rs12000 and rs1150722 were still strongly associated with schizophrenia (rs12000: allele G>A, P combined = 0.0019, OR = 0.81; rs1150722: allele G>A, P combined = 3.00E-04, OR = 0.61). These results support our findings that locus 6p21-p22.1 is significantly associated with schizophrenia in the Chinese Han population and encourage further studies of the functions of these genetic factors.

On the efficiency of two‐stage response‐adaptive designs

In this paper, we investigate the efficiency of response-adaptive locally optimum designs. We focus on two-stage adaptive designs, where after the first stage the accrued data are used to determine a locally optimum design for the second stage. On the basis of an explicit expansion of the information matrix, we compare the variance of the maximum likelihood estimates obtained from a two-stage adaptive design and a fixed design without adaptation. For several one-parameter models, we provide explicit expressions for the relative efficiency of these two designs, which is seen to depend sensitively on the statistical problem under investigation. In particular, we show that in non-linear regression models with moderate or large variances the first-stage sample size of an adaptive design should be chosen sufficiently large in order to address variability in the interim parameter estimates. These findings support the results of recent simulation studies conducted to compare adaptive designs in more complex situations. We finally present an application to a real clinical dose-finding trial aiming at the estimation of the smallest dose achieving a certain percentage of the maximum treatment effect by using a three-parameter Emax model.

Polymorphisms in the glial glutamate transporter SLC1A2 are associated with essential tremor

Sporadic, genetically complex essential tremor (ET) is one of the most common movement disorders and may lead to severe impairment of the quality of life. Despite high heritability, the genetic determinants of ET are largely unknown. We performed the second genome-wide association study (GWAS) for ET to elucidate genetic risk factors of ET. Using the Affymetrix Genome-Wide SNP Array 6.0 (1000K) we conducted a two-stage GWAS in a total of 990 subjects and 1,537 control subjects from Europe to identify genetic variants associated with ET. We discovered association of an intronic variant of the main glial glutamate transporter (SLC1A2) gene with ET in the first-stage sample (rs3794087, p = 6.95 × 10(-5), odds ratio [OR] = 1.46). We verified the association of rs3794087 with ET in a second-stage sample (p = 1.25 × 10(-3), OR = 1.38). In the subgroup analysis of patients classified as definite ET, rs3794087 obtained genome-wide significance (p = 3.44 × 10(-10), OR = 1.59) in the combined first- and second-stage sample. Genetic fine mapping using nonsynonymous single nucleotide polymorphisms (SNPs) and SNPs in high linkage disequilibrium with rs3794087 did not reveal any SNP with a stronger association with ET than rs3794087. We identified SLC1A2 encoding the major glial high-affinity glutamate reuptake transporter in the brain as a potential ET susceptibility gene. Acute and chronic glutamatergic overexcitation is implied in the pathogenesis of ET. SLC1A2 is therefore a good functional candidate gene for ET.

Two-Stage Adaptive Optimal Design with Fixed First-Stage Sample Size

In adaptive optimal procedures, the design at each stage is an estimate of the optimal design based on all previous data. Asymptotics for regular models with fixed number of stages are straightforward if one assumes the sample size of each stage goes to infinity with the overall sample size. However, it is not uncommon for a small pilot study of fixed size to be followed by a much larger experiment. We study the large sample behavior of such studies. For simplicity, we assume a nonlinear regression model with normal errors. We show that the distribution of the maximum likelihood estimates converges to a scale mixture family of normal random variables. Then, for a one parameter exponential mean function we derive the asymptotic distribution of the maximum likelihood estimate explicitly and present a simulation to compare the characteristics of this asymptotic distribution with some commonly used alternatives.

Comparison of field sampling methods for assessing coarse woody debris and use of airborne laser scanning as auxiliary information

Coarse woody debris (CWD) has been recognized as one of the strongest indicators of forest biodiversity and its assessment has been emphasized in the development of new inventory methods. In this study, the most commonly referenced probability sampling methods were tested in a field area of 305.8 ha to gain comparative information on their performance and efficiency. Simple random sampling (SRS), systematic sampling and cluster sampling with fixed sized circular sample plots were tested, as well as strip sampling, transect relascope sampling and adaptive cluster sampling (ACS). Point relascope sampling and line intersect sampling were also tested for inventories of downed dead wood volumes. In addition, the amount of standing dead wood was assessed by means of traditional small angle relascope sampling. In general, the use of additional information in the inventory process has shown promising results. A new method for using data derived from airborne laser scanning (ALS) as a source of auxiliary information in the assessment of CWD volumes is presented, using probability proportional to size (PPS) sampling for the selection of the first-stage sample units in ACS (ACS PPS) and for the placement of fixed sized plots (PLOT PPS). The sampling methods were compared in terms of the cost-effectiveness. Point relascope sampling proved the most efficient sampling method for inventorying CWD volumes. PLOT PPS and ACS PPS were more efficient than the inventory of fixed sized plots (PLOT SRS) and ACS (ACS SRS) where sample units were selected with SRS. However, these methods could not achieve the same efficiency as relascope samplings. Nevertheless, the use of probability layers derived from ALS data gave promising results and offers new possibilities for inventorying CWD volumes more efficiently.

Two‐stage analysis for gene‐environment interaction utilizing both case‐only and family‐based analysis

The case-only study and family-based study are two popular study designs for detecting gene-environment interactions. It is well known that the case-only analysis is efficient, but its validity relies crucially on the assumption of gene-environment independence in the study population. In contrast, the family-based analysis is robust to the violation of such an assumption, but is less efficient. We propose a two-stage study design for detecting gene-environment interactions, where a case-only study is performed at the first stage, and a case-parent/case-sibling study is performed at the second stage on a random subsample of the first-stage case sample as well as their parents/unaffected siblings. Statistical inference procedures are developed for the proposed two-stage study designs, which not only preserve the robustness property of the family-based analysis, but also utilize information from the case-only analysis to enhance estimation efficiency and testing power. Simulation results reveal both the robustness and efficiency of the proposed strategies.

Including sampling and phenotyping costs into the optimization of two stage designs for genome wide association studies

We propose optimized two-stage designs for genome-wide case-control association studies, using a hypothesis testing paradigm. To save genotyping costs, the complete marker set is genotyped in a sub-sample only (stage I). On stage II, the most promising markers are then genotyped in the remaining sub-sample. In recent publications, two-stage designs were proposed which minimize the overall genotyping costs. To achieve full design optimization, we additionally include sampling costs into both the cost function and the design optimization. The resulting optimal designs differ markedly from those optimized for genotyping costs only (partially optimized designs), and achieve considerable further cost reductions. Compared with partially optimized designs, fully optimized two-stage designs have higher first-stage sample proportion. Furthermore, the increment of the sample size over the one-stage design, which is necessary in two-stage designs in order to compensate for the loss of power due to partial genotyping, is less pronounced for fully optimized two-stage designs. In addition, we address the scenario where the investigator is interested to gain as much information as possible, however is restricted in terms of a budget. In that we develop two-stage designs that maximize the power under a certain cost constraint.

The reassessment of trial perspectives from interim data—a critical view

If an interim analysis is performed during a trial it is tempting to determine the conditional power to reach a rejection in the trial given the observed results in the interim analysis. Since the true effect size is unknown the conditional power may be calculated by using the effect size, which the study has been powered for in the planning phase or by using an interim estimate of the true size (or a combination of both). In either case the conditional power is a random variable and its density is investigated depending on the analysis time and the true effect size. Under the null hypothesis, in early interim analyses after a small proportion of sample units, the conditional power typically will be close to the overall power when the effect size from the planning stage is used for calculation. In this case the majority of observations must still be made and the small first-stage sample in general will be dominated by the hypothetical second-stage chance based on the wrong parameter value. It is shown that the conditional power in moderately underpowered studies can have a distribution symmetric around 0.5. When using the interim estimate for calculating the conditional power the density in general will be u-shaped. The impact of using conditional power to reassess the sample size using flexible two-stage combination tests is shown for a specific example in terms of overall power and average sample size as compared to the corresponding group sequential design. For small true effect sizes mid-trial sample size recalculation based on an interim estimate may lead to an overly large price to be paid in average sample size in relation to the gain in overall power. Finally, the problem is discussed in terms of estimating the true conditional power.

A Two-Stage Procedure for Selection and Assessment of Agreement of the Best Instrument with a Gold Standard

We consider a method-comparison study of assessing agreement between the gold standard and the unknown best among the k instruments under consideration. The goal is to identify the best when this agreement is close enough in terms of certain metric. We propose a two-stage procedure that employs the logarithm of the mean squared deviation as the metric for comparison and uses its large-sample properties. Our procedure has a prespecified significance level under the null hypothesis of insufficient agreement. Further, it correctly rejects the null hypothesis and selects the true best with probability no less than a prespecified level (in the asymptotic sense), when the best has sufficiently close agreement with the gold standard and is not practically equivalent to other competing instruments. For k = 2, we assume bivariate normality for the differences of paired measurements and study the small-sample properties of the procedure using simulation. We observe that a first-stage sample of size 15 is adequate for its application and illustrate the procedure using a real data set.