In the article, hypothesis test for coefficients in high dimensional regression models is considered. I develop simultaneous test statistic for the hypothesis test in both linear and partial linear models. The derived...In the article, hypothesis test for coefficients in high dimensional regression models is considered. I develop simultaneous test statistic for the hypothesis test in both linear and partial linear models. The derived test is designed for growing p and fixed n where the conventional F-test is no longer appropriate. The asymptotic distribution of the proposed test statistic under the null hypothesis is obtained.展开更多
Statisticians have recently proposed some methods for ranking the gene variables with outlier expressions. The major attraction of these methods is their ability to select the variables which show systematic decrease ...Statisticians have recently proposed some methods for ranking the gene variables with outlier expressions. The major attraction of these methods is their ability to select the variables which show systematic decrease or increase in only a subset of samples in the disease group. In order to fully account for the outliers, in this article, we truncate the expression values and propose an alternative method to rank the variables with systematic increase or decrease. The proposed statistic is very simple to implement. Simulations and real data study show that the proposed statistic has a more powerful ability to rank the variables than some methods in literature.展开更多
文摘In the article, hypothesis test for coefficients in high dimensional regression models is considered. I develop simultaneous test statistic for the hypothesis test in both linear and partial linear models. The derived test is designed for growing p and fixed n where the conventional F-test is no longer appropriate. The asymptotic distribution of the proposed test statistic under the null hypothesis is obtained.
文摘Statisticians have recently proposed some methods for ranking the gene variables with outlier expressions. The major attraction of these methods is their ability to select the variables which show systematic decrease or increase in only a subset of samples in the disease group. In order to fully account for the outliers, in this article, we truncate the expression values and propose an alternative method to rank the variables with systematic increase or decrease. The proposed statistic is very simple to implement. Simulations and real data study show that the proposed statistic has a more powerful ability to rank the variables than some methods in literature.
