Exact P-value Research Articles

Predictors of Mortality in Paediatric Myocarditis.

Paediatric myocarditis can present as mild flu like symptoms to fulminent form. Early identification of the severity of illness and prioritization of intensive care is helpful especially in developing countries with limited resources. To know the factors at admission that can predict mortality in paediatric myocarditis. This was an observational study which enrolled children who presented with fever of acute onset (less than 15 days in duration), and were diagnosed as suspected myocarditis on the basis of clinical features, Troponin I and echocardiography, according to Expanded criteria for myocarditis in Paediatric ward at our institute over a period from August 2014 to December 2015. Their clinical features, cardiac biomarkers and echocardiography findings were compared between survivors and non-survivors. All statistical analysis was done using graphpad Prism 5 and SPSS statistical software. A Fisher exact p-value <0.05 was regarded as significant. Multivariate Logistic Regression was carried out to quantify the relationship between cardiac death and other predictor variables. The logistic coefficients for the predictor variables and their exponents, that is, log odds were calculated. Statistical significance of these predictor variables was interpreted by p-values. A 17.7% (n=11/62) patients of paediatric myocarditis died in this study. New York Heart Association (NYHA) class IV dyspnea (p=0.0115) and hypotension (p=0.0174) were more in patients who did not survive. The mean value of Troponin I was more in the non-survivor group (0.958 ± 1.13ng/ml); (p=0.0074). More number of patients who died had Brain Natriuretic Peptide (BNP) levels increased in their plasma (p=0.0087) with higher mean value (p=0.0175). LV ejection fraction was decreased markedly in non survivor group with mean value of 37±8.09 % as compared to survivor group with mean value of 46.6±10.5%, (p=0.0115). On multivariate analysis, NYHA class IV dyspnea (p=0.0113), BNP (p=0.015) and ejection fraction (p = 0.0284) independently are the predictors of mortality in our study group. Children with myocarditis having hypotension, raised Troponin I, BNP and decreased ejection fraction are more prone to die. NYHA IV dyspnea, higher levels of BNP and decreased EF are independently related to worst outcome.

Permutation P-values for Inter-rater Agreement Measures

Permutation p-values are provided for the agreement measures for multivariate interval data among many raters. Three agreement measures, Berry and Mielke's measure, Janson and Olsson's measure, and Um's measure are described and compared. Exact and resampling permutation methods are utilized to compute p-values and empirical quantile limits for three measures. Comparisons of p-values demonstrate that resampling permutation methods provide close approximations to exact p-values, and Berry and Mielke's measure and Um's measure show similar performance in terms of measuring agreement.

Independent Association of Postdoctoral Training with Subsequent Careers in Cancer Prevention.

The purpose of this study was to examine the career paths of alumni from the National Cancer Institute (NCI) Cancer Prevention Fellowship Program (CPFP), a structured in-house postdoctoral training program of 3–4 years duration, and specifically what proportion of the alumni were currently performing cancer prevention-related activities. The analyses here included 119 CPFP alumni and 85 unsuccessful CPFP applicants, all of whom completed postdoctoral training between 1987–2011 and are currently employed. Postdoctoral training experiences and current career outcomes data were collected via online surveys. Differences between groups were assessed using chi-square and Fisher’s exact test p-values and subsequent regression analyses adjusted for differences between the groups. Compared to 15.3% of unsuccessful CPFP applicants, 52.1% of CPFP alumni (odds ratio [OR] = 4.99, 95% confidence interval [95% CI): 1.91–13.0) were currently spending the majority of their time working in cancer prevention. Among those doing any cancer prevention-focused work, 54.3% of CPFP alumni spent the majority of their time performing cancer prevention research activities when compared to 25.5% of unsuccessful applicants (OR = 4.26, 95% CI: 1.38–13.2). In addition to the independent effect of the NCI CPFP, scientific discipline, and employment sector were also associated with currently working in cancer prevention and involvement in cancer prevention research-related activities. These results from a structured postdoctoral training program are relevant not only to the cancer prevention community but also to those interested in evaluating alignment of postdoctoral training programs with available and desired career paths more broadly.

The Link between Facets of Impulsivity and Aggression in Extremely Violent Prisoners

Evidence is growing that aggressive behavior and impulsivity have subgroups. The subscales of the Urgency, Premeditation, Perseverance and Sensation seeking (UPPS) impulsivity scale and the Bryant and Smith shortened and refined version of the Aggression Questionnaire were used to describe and compare impulsive and aggressive behavior in extremely violent and aggressive male inmates and non-violent healthy male controls. The Mann-Whitney test showed that there was a significant difference (p < 0. 006) in the total UPPS impulsivity scale scores between the aggressive inmates and the controls. The subscales revealed that this difference was based mainly on the urgency score (p < 0. 003). On the aggression subscales, the inmates scored significantly higher for physical aggression than the controls (p < 0.001), but no significant difference was seen between inmates and controls for verbal aggression, anger and hostility, although the exact p-value was very close to statistical significance at 0.054. Regression analysis revealed a strong relationship between urgency and the aggression subscales hostility (p = 0.0004) and anger (p = 0.003) and that urgency was also linked to symptoms of anxiety (p = 0.008). Finally, a statistically significant link was found between both hostility (p = 0.0003) and anger (p = 0.002) and symptoms of anxiety. The highly selected subgroup of extremely violent criminals in this study were more physically aggressive than non-violent controls, with urgency as the driving feature in their impulsive behavior, and hostility, anger and symptoms of anxiety as underlying traits.

Saddlepoint [formula omitted]-values for two-sample bivariate tests

A double saddlepoint approximation for the exact p-values of a class of two-sample bivariate tests is derived. The saddlepoint method approximates the underlying permutation distributions of the tests. Some widely used bivariate tests are shown to be in this class. Extensive simulation studies are used to evaluate the performance of the saddlepoint approximation. The saddlepoint approximation is compared with the asymptotic approximation and shows great improvement in accuracy over the asymptotic normal approximation.

Abstract A2-61: Functional enrichment and pathway analysis of the transcriptome related to lymphovascular invasion and recurrence in axillary-node negative breast cancer

Abstract We previously reported that the presence of Lymphovascular invasion (LVI) is an independent predictor of recurrence in axillary node-negative breast cancer (ANNBC). We produced a unique set of gene expression microarrays specifically designed to identify genes with altered expression in LVI+ tumors (n= 37) compared to LVI- tumors (n = 68). We further examined expression differences in a second analysis designed to discover, within LVI+ tumors alone, clinically relevant genes involved in early recurrence (n = 4, smaller than 4 years) vs. no recurrence for at least 10 years (n = 41). To identify genes and pathways involved in LVI and recurrence in ANNBC, we performed a functional analysis of the expression data. We used the publicly available database tool via WebGestalt to perform a web-based enrichment analysis including Gene ontology, KEGG and the Cytogenetic band. In parallel, using Ingenuity pathway® (IPA), we identified networks, upstream regulators and canonical pathways. IPA provides the probability that the association between the genes in the dataset and the canonical pathways could be explained by chance alone through a right-tailed Fisher's exact test p-value. IPA use a z-score algorithm for predicting activation which reduces the chance that random data will generate significant predictions. In LVI+ vs LVI- analysis, the top IPA activated biofunctions are related to proliferation and migration. In LVI+REC+ vs LVI+REC- analysis, they are related to cell survival and migration as well as lipid synthesis and metabolism. The subset of genes identified in both comparisons include those involved in polarization of cells, oxidation of lipids, cellular homeostasis and growth of the lymphatic system component, with decreased cell death and apoptosis biofunctions. Our bioinformatics analyses are consistent with a migratory phenotype for cancer cells associated with LVI. In addition, we observed that inflammation related pathways are enriched in the LVI+ subgroup that undergoes early recurrence. In the upstream regulator IPA analysis, TGFb NFKb and PI3K are involved in the LVI+ in respect to LVI tumors as well as in LVI+REC+ tumors in respect to LVI+REC- tumors. The results suggest important pathways as well as upstream regulators associated with LVI and recurrence that are involved in invasion and cell fate biofunctions. The findings are currently being evaluated through mRNA and protein validation as well as functional studies. Citation Format: Mathieu Blais, Shelley B. Bull, Dushanthi Pinnaduwage, Irene L. Andrulis. Functional enrichment and pathway analysis of the transcriptome related to lymphovascular invasion and recurrence in axillary-node negative breast cancer. [abstract]. In: Proceedings of the AACR Special Conference on Translation of the Cancer Genome; Feb 7-9, 2015; San Francisco, CA. Philadelphia (PA): AACR; Cancer Res 2015;75(22 Suppl 1):Abstract nr A2-61.

Abstract B2-15: Functional enrichment and pathway analysis of the transcriptome related to lymphovascular invasion and recurrence in axillary-node negative breast cancer

Abstract We previously reported that the presence of Lymphovascular invasion (LVI) is an independent predictor of recurrence in axillary node-negative breast cancer (ANNBC). We produced a unique set of gene expression microarrays specifically designed to identify genes with altered expression in LVI+ tumors (n= 37) compared to LVI- tumors (n = 68). We further examined expression differences in a second analysis designed to discover, within LVI+ tumors alone, clinically relevant genes involved in early recurrence (n = 4, smaller than 4 years) vs. no recurrence for at least 10 years (n = 41). To identify genes and pathways involved in LVI and recurrence in ANNBC, we performed a functional analysis of the expression data. We used the publicly available database tool via WebGestalt to perform a web-based enrichment analysis including Gene ontology, KEGG and the Cytogenetic band. In parallel, using Ingenuity pathway® (IPA), we identified networks, upstream regulators and canonical pathways. IPA provides the probability that the association between the genes in the dataset and the canonical pathways could be explained by chance alone through a right-tailed Fisher's exact test p-value. IPA use a z-score algorithm for predicting activation which reduces the chance that random data will generate significant predictions. In LVI+ vs LVI- analysis, the top IPA activated biofunctions are related to proliferation and migration. In LVI+REC+ vs LVI+REC- analysis, they are related to cell survival and migration as well as lipid synthesis and metabolism. The subset of genes identified in both comparisons include those involved in polarization of cells, oxidation of lipids, cellular homeostasis and growth of the lymphatic system component, with decreased cell death and apoptosis biofunctions. Our bioinformatics analyses are consistent with a migratory phenotype for cancer cells associated with LVI. In addition, we observed that inflammation related pathways are enriched in the LVI+ subgroup that undergoes early recurrence. In the upstream regulator IPA analysis, TGFb NFKb and PI3K are involved in the LVI+ in respect to LVI tumors as well as in LVI+REC+ tumors in respect to LVI+REC- tumors. The results suggest important pathways as well as upstream regulators associated with LVI and recurrence that are involved in invasion and cell fate biofunctions. The findings are currently being evaluated through mRNA and protein validation as well as functional studies. Citation Format: Mathieu Blais, Dushanthi Pinnaduwage, Shelley B. Bull, Irene L. Andrulis. Functional enrichment and pathway analysis of the transcriptome related to lymphovascular invasion and recurrence in axillary-node negative breast cancer. [abstract]. In: Proceedings of the AACR Special Conference on Computational and Systems Biology of Cancer; Feb 8-11 2015; San Francisco, CA. Philadelphia (PA): AACR; Cancer Res 2015;75(22 Suppl 2):Abstract nr B2-15.

ATCT-14CHEMOSENSITIVITY OF PRIMARY AND METASTATIC CNS TUMORS TO 4-DEMETHYL-4-CHOLESTERYLOXYCARBONYLPENCLOMEDINE (DM-CHOC-PEN) AND TEMOZOLOMIDE

BACKGROUND: The efficacy of TMZ in the treatment of high-grade astrocytomas is limited by drug-resistance mediated by O6-methylguanine-DNA methyltransferase (MGMT). Brain metastases are difficult to treat and currently no standard chemotherapeutic therapies exist. 4-Demethyl-4-cholesteryloxycarbonylpenclomedine (DM-CHOC-PEN) is a polychlorinated pyridine cholesteryl carbonate whose mechanism of action is via alkylation of DNA at N7-guanine. This agent has had early therapeutic success in treating both primary and metastatic CNS malignancies in Phase I and Phase II clinical trials. METHODS: To better understand the sensitivity and mechanisms of resistance in primary and metastatic CNS tumors, we collected tissue from subjects (n = 38) enrolled between March 2014 - January 2015 for chemosensitivity studies. These included high-grade astrocytomas (9), metastatic brain tumors (6) meningiomas (6), and other more benign tumors such as pituitary adenomas (4), hemangioblastoma (1), and chondrosarcoma (1). Using viable tumor cell explants from surgery, cells were grown under standard conditions (RPMI/FBS, 5%CO2, 37°C), in vitro chemosensitivity profiles were obtained comparing DM-CHOC-PEN vs. TMZ and other commonly used anti-cancer agents. RESULTS: Tumor cells exhibited higher susceptibility to DM-CHOC-PEN than to TMZ (RR = 3.19, p = 0.0029, 95% confidence interval [CI], 1.3-7.8 vs. TMZ). In a subgroup analysis of high-grade astrocytomas, atypical meningiomas, and secondary metastases in this cohort, an association was noted between TMZ-resistance (µIC50 = 3.3, S.D. = 0.46) and DM-CHOC-PEN-sensitivity (µIC50 = 1.0, S.D = 0.26) using two-sample independent, Student's t-test with Fisher's exact P-value (p = 0.0001, t(23.72) = 4.5, df = 27.17). CONCLUSIONS: These preliminary results suggest that DM-CHOC-PEN may promote cell death in tumors possessing acquired MGMT-mediated drug-resistance. Furthermore, it supports roles for this promising new agent in the treatment of primary and metastatic brain tumors and in treatment of high-grade astrocytomas, either in combination with TMZ or alone in cases of TMZ-resistance.

Exact Inference for Hardy-Weinberg Proportions with Missing Genotypes: Single and Multiple Imputation.

This paper addresses the issue of exact-test based statistical inference for Hardy−Weinberg equilibrium in the presence of missing genotype data. Missing genotypes often are discarded when markers are tested for Hardy−Weinberg equilibrium, which can lead to bias in the statistical inference about equilibrium. Single and multiple imputation can improve inference on equilibrium. We develop tests for equilibrium in the presence of missingness by using both inbreeding coefficients (or, equivalently, χ2 statistics) and exact p-values. The analysis of a set of markers with a high missing rate from the GENEVA project on prematurity shows that exact inference on equilibrium can be altered considerably when missingness is taken into account. For markers with a high missing rate (>5%), we found that both single and multiple imputation tend to diminish evidence for Hardy−Weinberg disequilibrium. Depending on the imputation method used, 6−13% of the test results changed qualitatively at the 5% level.

Calculating Exact P-Values from the McNamara Transmission/Disequilibrium Test Statistic

The transmission/disequilibrium test (TDT) is a popular method for analyzing genetic data in studies of complex disease. It is often assumed that the P-values for the test are well-calculated using the asymptotic, chi-squared distribution. However, that is not always an accurate assumption. A formula is derived for the exact P-value of the TDT McNemar statistic and we show that the asymptotic P-values for the McNemar statistic can often depart considerably from the exact P-values, even when sample sizes are relatively large. Notably, the asymptotic P-values can be either too large or too small, leading to either false positive or false negative results. Since the exact P-value for this statistic is simple to calculate, it will be preferable to do so. We also anticipate that our derivation may find utility in other applications of the McNemar statistic where the underlying variables are binomially-distributed.

Abstract 3886: Comparing the mutational landscape of African American and Caucasian lung cancers

Abstract Background: The overall death rate from lung cancer is higher in African-Americans (AA) compared to Caucasians (CAU). Understanding differences in the prevalence and type of somatic alterations between races may illuminate differences in prognosis and lead to the reduction of outcome disparities by more precisely targeting patients’ treatment. Methods: Formalin-fixed paraffin embedded tumor samples were collected from Baptist Cancer Center, Memphis, TN. DNA was extracted and sonicated to 250 bp following Covaris FFPE DNA Extraction &amp; Purification protocol and further purified using Agencourt AMPure XP beads. The OncoPanel_v2 target enrichment panel (Agilent SureSelect) was used for hybrid capture of 502 cancer-related genes. Samples were pooled and sequenced on an Illumina HiSeq2500 to a mean depth of coverage of 210x. Tumors with &amp;gt;30x sequencing depth over &amp;gt;80% of targeted bases were considered for analysis. MuTect and SomaticIndelDetector were used to identify somatic single nucleotide variants (SNVs) and short insertions or deletions (indels), respectively. As matched normal DNA was not available for these samples, analysis was limited to variants previously observed in tumors as described in the Catalogue of Somatic Mutations in Cancer (COSMIC) database, and variants were excluded if found in the germline dataset of the Exome Sequencing Project (ESP). Results: 510 tumor specimens from 242 Black and 268 White patients (with self-reported race) were analyzed including 320 adenocarcinomas and 142 squamous cell carcinomas. Pathological classification was independently reviewed and confirmed for 374 of 472 cases for an overall concordance rate of 79%. Using principle component analysis (PCA) on germline SNVs, we observed that the biological ancestry was different than the self-reported race for 1.5% of patients. Mutational frequencies for genes with known roles in adenocarcinoma such as KRAS and EGFR were not significantly different between tumors from Black and White patients (Fisher's exact p-value &amp;gt; 0.05). Amplification rates for NKX2-1, MET, MDM2, and MYC and homozygous deletion rates for CDKN2A were also not significantly different between populations. Translocations involving ALK and ROS1 were detected in tumors from Black patients demonstrating that these events are present in both populations. Similarly, mutational frequencies for genes such as PIK3CA and PTEN were not significantly different across populations in squamous cell carcinomas. Conclusions: These results demonstrate that lung cancers from Black patients are more similar to Whites than East Asians with respect to genes such as EGFR, and suggest that clinical trials of targeted therapies could significantly benefit patients in both populations. Citation Format: Joshua Campbell, Christopher Lathan, Lynette Sholl, Matthew Ducar, Mikenah Vega, Ling Lin, Aaron Thorner, Nick Faris, Paul van Hummelen, Raymond Osarogiagbon, Matthew Meyerson, Laura MacConaill. Comparing the mutational landscape of African American and Caucasian lung cancers. [abstract]. In: Proceedings of the 106th Annual Meeting of the American Association for Cancer Research; 2015 Apr 18-22; Philadelphia, PA. Philadelphia (PA): AACR; Cancer Res 2015;75(15 Suppl):Abstract nr 3886. doi:10.1158/1538-7445.AM2015-3886

Randomization tests in recursive response-adaptive randomization procedures

In a randomized clinical trial, response-adaptive randomization procedures use the information gathered, including the previous patients' responses, to allocate the next patient. In this setting, we consider randomization-based inference. We provide an algorithm to obtain exact p-values for statistical tests that compare two treatments with dichotomous responses. This algorithm can be applied to a family of response adaptive randomization procedures which share the following property: the distribution of the allocation rule depends only on the imbalance between treatments and on the imbalance between successes for treatments 1 and 2 in the previous step. This family includes some outstanding response adaptive randomization procedures. We study a randomization test to contrast the null hypothesis of equivalence of treatments and we show that this test has a similar performance to that of its parametric counterpart. Besides, we study the effect of a covariate in the inferential process. First, we obtain a parametric test, constructed assuming a logit model which relates responses to treatments and covariate levels, and we give conditions that guarantee its asymptotic normality. Finally, we show that the randomization test, which is free of model specification, performs as well as the parametric test that takes the covariate into account.

Abstract P2-03-08: Mutational landscape of metaplastic breast carcinomas

Abstract Introduction: Metaplastic breast carcinoma (MBC) is an aggressive histologic type of breast cancer, which preferentially displays a triple-negative phenotype. These tumors are characterized by the presence of malignant cells exhibiting differentiation towards squamous epithelium or mesenchymal elements, including spindle, chondroid, osseous and rhabdoid differentiation. Unlike other rare histologic types of breast cancer such as adenoid cystic and secretory carcinomas, which are underpinned by the MYB-NFIB and ETV6-NTRK3 fusion genes respectively, pathognomonic genetic alterations have not been identified in MBC. It has been suggested, however, that the frequency of PIK3CA somatic mutations would be significantly higher in MBCs than in other forms of triple-negative disease. Here we sought to characterize the mutational landscape of MBCs by means of high-depth whole exome sequencing analysis. Material and Methods: Twenty-one triple-negative MBCs were retrieved from the authors’ institutions. Representative sections from frozen blocks were microdissected to ensure tumor cell content greater than 50%. DNA samples extracted from microdissected tumor and matched peripheral blood leukocytes were subjected to high-depth (250x) whole exome sequencing on an Illumina GAIIx or HiSeq2000. Somatic point mutations were called using MuTect and somatic insertions and deletions (indels) were called using Strelka, Varscan2 and Haplotype Caller. Potentially pathogenic mutations were predicted using computational algorithms including PolyPhen-2, Mutation Taster, Mutation Assessor, CHASM and FATHMM. Significantly mutated genes were identified using MutSigCV. Pathway and network enrichment analysis of mutations was performed with Ingenuity Pathway Analysis and HOTNET. The genomic landscape of MBCs was compared with that of triple-negative breast cancers (TNBCs) analyzed as part of The Cancer Genome Atlas project. Results: A mean of 135 somatic non-synonymous point mutations and indels were identified per MBC. The most frequently mutated gene was TP53, found in 12/21 cases (57%), and the only significantly mutated gene as defined by MutSigCV (q&amp;lt;0.01). The repertoire of somatic mutations found in MBCs was qualitatively similar to that of TNBCs of no special type, and recurrently mutated genes were altered at similar frequencies in MBCs and TNBCs of no special type. When somatic mutations were annotated in pathways and networks, MBCs were found to have potentially pathogenic mutations affecting genes directly related to the PI3K pathway, including pathogenic non-synonymous mutations affecting PIK3CA, PIK3R1, PIK3R2, PIK3C2B, PIK3C2G and PTEN, significantly more frequently than TNBCs of no special type (10 out of 21 MBCs vs. 11 out of 62 TNBCs; Fisher's exact test p-value=0.0099). Conclusion: The majority (57%) of MBCs harbored non-synonymous mutations affecting TP53. While the frequencies of mutations affecting recurrently mutated genes in MBCs are similar to those found in other forms of TNBCs, MBCs significantly more frequently harbor mutations affecting PI3K pathway-related genes than TNBCs of no special type. Citation Format: Charlotte KY Ng, Britta Weigelt, Salvatore Piscuoglio, Y Hannah Wen, Maria R De Filippo, Luciano G Martelotto, Rachael Natrajan, Raymond Lim, Edi Brogi, Larry Norton, Anne Vincent-Salomon, Jorge S Reis-Filho. Mutational landscape of metaplastic breast carcinomas [abstract]. In: Proceedings of the Thirty-Seventh Annual CTRC-AACR San Antonio Breast Cancer Symposium: 2014 Dec 9-13; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2015;75(9 Suppl):Abstract nr P2-03-08.

A robust mathematical model for a loophole-free Clauser–Horne experiment

Recent experiments (Giustina et al 2013 Nature 497 227–30; Christensen et al 2013 Phys. Rev. Lett. 111 130406) have reached detection efficiencies sufficient to close the detection loophole, testing the Clauser–Horne version of Bell's inequality. For a similar future experiment to be completely loophole-free, it will be important to have discrete experimental trials with randomized measurement settings for each trial, and the statistical analysis should not overlook the possibility of a local state varying over time with possible dependence on earlier trials (the ‘memory loophole’). In this paper, a mathematical model for such an experiment is presented, and a method for statistical analysis that is robust to memory effects is introduced. Additionally, a new method for calculating exact p-values for martingale-based statistics is described; previously, only non-sharp upper bounds derived from the Azuma–Hoeffding inequality have been available for such statistics. This improvement decreases the required number of experimental trials to demonstrate non-locality. The statistical techniques are applied to the data of Giustina et al (2013 Nature 497 227–30) and Christensen et al (2013 Phys. Rev. Lett. 111 130406) and found to perform well.

Disagreement of ICD-10 codes between a local hospital information system and a cancer registry.

In the field of cancer, the ICD-10 coding convention is based on the site of a neoplasm in the body and usually ignores the morphology, thus the same code may be assigned to tumors of different morphologic types in an organ. Nowadays, all general (provincial) and center hospitals in Thailand are equipped with the hospital information system (HIS) database. This study aimed to find the characteristics and magnitude of agreement represented by the positive predictive value (PPV) of provisional cancer diagnoses in the HIS database in Pattani Hospital in Thailand in comparison with the final cancer diagnosis of the ICD-10 codes generated from a well established cancer registry in Songklanagarind Hospital, the medical school hospital of Prince of Songkla University. Data on cancer patients residing in Pattani province who visited Pattani Hospital from January 2007 to May 2011 were obtained from the HIS database. The ICD-10 codes of the HIS computer database of Pattani Hospital were compared against the ICD-10 codes of the same person recorded in the hospital-based cancer registry of Songklanagarind Hospital. The degree of agreement or positive predictive value (PPV) was calculated for each sex and for both sexes combined. A total of 313 cases (15.9%) could be matched in the two databases. Some 222 cases, 109 males and 113 females, fulfilled the criteria of referral from Pattani to Songklanagarind Hospitals. Of 109 male cancer cases, 76 had the same ICD-10 codes in both hospitals, thus, the PPV was 69.7% (95%CI: 60.2-78.2%). Agreement in 76 out of 113 females gave a PPV of 67.3% (95%CI: 57.8-75.8%). The two percentages were found non-significant with Fisher's exact p-value of 0.773. The PPV for combined cases of both sexes was 68.5% (95%CI: 61.9-74.5%). Changes in final diagnosis in the referral system are common, thus the summary statistics of a hospital without full investigation facilities must be used with care, as the statistics are biased towards simple diseases able to be investigated by available facilities. A systematic feedback of patient information from a tertiary to a referring hospital should be considered to increase the accuracy of statistics and to improve the comprehensive care of cancer patients.

Saddlepoint p-values for a class of tests for comparing competing risks with censored data

One of the general problems in clinical trials and mortality rates is the comparison of competing risks. Most of the test statistics used for independent and dependent risks with censored data belong to the class of weighted linear rank tests in its multivariate version. In this paper, we introduce the saddlepoint approximations as accurate and fast approximations for the exact p-values of this class of tests instead of the asymptotic and permutation simulated calculations. Real data examples and extensive simulation studies showed the accuracy and stability performance of the saddlepoint approximations over different scenarios of lifetime distributions, sample sizes and censoring.

Perception of purpose and parental involvement in competitive youth sport

&lt;b&gt;Background&lt;/b&gt;&lt;br /&gt; Because of the various demanding investments, parents develop various expectations regarding their children’s sport experience. The purposes of this study were twofold: (a) to determine whether there is a discrepancy between parents and athletes in terms of perception of purpose for engaging in youth sport, and (b) to explore whether the reported discrepancies impact parental involvement.&lt;br /&gt; &lt;br /&gt; &lt;b&gt;Participants and procedure&lt;/b&gt;&lt;br /&gt; Participants included 25 club level athletes (19 girls, 6 boys), ages 13-17 (M = 14.96 years, SD = 1.49 years), and 24 pa­rents (18 women, 6 men) of these athletes, ages 39-55 (M = 48.26 years, SD = 4.44 years) from both individual and team sports. Parents and athletes completed their respective versions of both the Participation Motivation Questionnaire (PMQ) and Parental Involvement in Sport Questionnaire (PISQ). Optional individual interviews with 12 athletes and 12 parents were then conducted to further triangulate perceptions of purpose and parental involvement in youth sport.&lt;br /&gt; &lt;br /&gt; &lt;b&gt;Results&lt;/b&gt;&lt;br /&gt; Findings included four statistically significant negative correlations between the PMQ and PISQ, as well as a statistically significant discrepancy between parents and athletes on one subscale of the PMQ (p = .026). Also, statistically significant discrepancies were found between perceived and desired levels of parental involvement on three out of four subscales of the PISQ (there are 3 exact p-values since there were significant discrepancies for 3 out of the 4 subscales. They are: Directive Behavior: p &lt; .001, Praise and Understanding: p = .042 and Pressure: p = .025).&lt;br /&gt; &lt;br /&gt; &lt;b&gt;Conclusions&lt;/b&gt;&lt;br /&gt; Perceptions of parental involvement between the parents and their children were not congruent. Similarly, the parents and their children perceive why an athlete participates in sport somewhat differently. If further explored, parent-athlete relations and interactions could be improved to facilitate optimal youth sport participation.

The Evaluation of Strategic Management Implementation in Agricultural Enterprises in: The Slovak Republic

Design /Methodology/Approach: Qualitative data have been collected from a questionnaire survey. Furthermore, using Porter’s model of five forces, an evaluation has been made of managers’ perception of choosing opportunities, threats and success factors. The presence of statistically significant differences in the perception of these ‘parameters’ in disparate production zones and between diverse groups of agricultural enterprises according to the number of employees and to the area of agricultural land in their ownership was tested using the Kruskal-Wallis test, with post-hoc testing employing the SteelDwass-Critchlow-Fligner testing procedure. The presence of a trend in the perception of these ‘parameters’ of the competitive environment was tested using the Jonckheere-Terpstra test with respect to the number of employees and the area of agricultural land belonging to the enterprise. The exact pvalue, in the case of the Kruskal-Wallis test and the Jonckheere-Terpstra test, was calculated utilizing Monte Carlo simulation (Mehta and Patel, 1996). We used the Steel-Dwass-Critchlow-Fligner testing procedure (Critchlow and Fligner, 1991) as a post-hoc test in the instance that null hypothesis can be rejected of the Kruskal-Wallis test.

Asymptotic Behavior of a Randomization Test for a Response-Adaptive Design

Response-adaptive designs allow the incorporation of ethical goals in the performance of a clinical trial, and they have been thoroughly studied assuming that treatment responses follow a population model. However, in some clinical trials, population models are not appropriate and randomization tests appear as a plausible alternative to make inference. Randomization-based tests can be devised but the calculation of their exact p-values when a response-adaptive design is used to allocate patients is either time consuming or not feasible for moderate to large sample sizes and so asymptotic results become helpful. Nevertheless, these asymptotic results are not available for response-adaptive designs with good properties. The Klein allocation rule is a response-adaptive design, with good ethical and inferential properties, that generalizes the classical Ehrenfest urn design by making the replacement policy dependent on the response of the last patient. The goal of this article is to study the asymptotic distribution of a test statistic under a randomization-based approach when patients are allocated by using the Klein allocation rule.

Prevalence of Cancer in Female Plastic Surgeons in the United States

Objective: Several female sub-populations of the healthcare industry, including radiologists, radiology technicians, and orthopedic surgeons, display an increased prevalence of breast cancer. Female plastic surgeons have a similar exposure to possible risk factors such as radiation exposure, late parturition, and overnight shifts. Therefore, this study aimed to evaluate the risk of breast cancer and overall cancer in female plastic surgeons. Methods: A two-page survey designed to collect data on respondent demographics, cancer incidence and exposure to social and occupational risk factors as identified in the current literature was mailed to 612 currently practicing female plastic surgeons identified by the American Society of Plastic Surgeons (ASPS). Prevalence rates for breast cancer and cancer in general were calculated. Only melanoma and internal cancers that were diagnosed within 15 years of the survey date were included, enabling us to compare the results with data from the National Institute’s Surveillance Epidemiology and End Results (SEER 11) Program. Standardized prevalence ratios (SPR), confidence intervals, and exact p-values were calculated. Results: Fourteen of the 352 respondents had been diagnosed with cancer, including three breast cancer cases, within 15 years preceeding the survey. These numbers are not signficantly lower than the expected prediction of 16 cancer and six breast cancer cases, based on the sex and race-specific prevalences in the general U.S. population. SPRs were 0.89 [95%CI: 0.49 to 1.5] for all cancers and 0.54 [95%CI: 0.11, 1.57] for breast cancer. Conclusion: Despite similarities to subpopulations with increased breast and overall cancer prevalence, the subpopulation of female plastic surgeons had no evdience of excess cancers compared to age and race-adjusted women in the general US population.