Lenth's Method for the Analysis of Unreplicated Experiments

Author(s):  
Russell V. Lenth
1989 ◽  
Vol 21 (3) ◽  
pp. 202-212 ◽  
Author(s):  
W. Robert Stephenson ◽  
Frederick L. Hulting ◽  
Karen Moore

Weed Science ◽  
1982 ◽  
Vol 30 (1) ◽  
pp. 125-126

Manuscripts about weeds, herbicides, growth regulators, or related topics will be considered for publication in Weed Science. Each manuscript should contain original material that constitutes a logical unit of related subject matter. Progress reports, unreplicated experiments, and field experiments not repeated in time are not acceptable. Each acceptance is made with the understanding that the manuscript has not been and will not be published elsewhere other than as an abstract.


2013 ◽  
Vol 67 ◽  
pp. 95-104 ◽  
Author(s):  
Christopher T. Franck ◽  
Dahlia M. Nielsen ◽  
Jason A. Osborne

2015 ◽  
Author(s):  
Tsung Fei Khang ◽  
Ching Yee Lau

Background: A common research goal in transcriptome projects is to find genes that are differentially expressed in different phenotype classes. Biologists might wish to validate such gene candidates experimentally or use them for downstream systems biology analysis. Producing a coherent differential expression analysis from RNA-seq count data requires an understanding of how numerous sources of variation such as the replicate size, the hypothesized biological effect, and the specific method for making differential expression calls interact. We believe an explicit demonstration of such interactions in real RNA-seq data sets is of practical interest to the biologist. Results: Using two large public RNA-seq data sets - one representing strong, and another mild, biological response, we simulated different replicate size scenarios and tested the performance of several commonly-used methods for calling differentially expressed genes in each of them. Our results suggest that if the biological response of interest in the different phenotype classes is expected to be mild, then RNA-seq experiments should focus on validation of differentially expressed gene candidates. At least triplicates must be used, and the differentially expressed genes should be called using methods with high positive predictive value such as NOISeq or GFOLD. In contrast, for strong biological response, differentially expressed genes mined from unreplicated experiments using NOISeq, ASC and GFOLD had between 30 to 50% mean positive predictive value, an increase of more than 30-fold compared to the case of mild biological response. Among methods with good positive predictive value performance, having triplicates or more substantially improved mean positive predictive value to over 90% for GFOLD, 60% for DESeq2, 50% for NOISeq, and 30% for edgeR. We found DESeq2 to be the most reasonable method to call differentially expressed genes for systems level analysis as it showed the best PPV and sensitivity trade-off (mean PPV and mean sensitivity ∼ 65% at replicate size of six). Conclusion: When biological effect size is strong, NOISeq and GFOLD are effective tools for detecting differentially expressed genes in unreplicated RNA-seq experiments for validation work. Having triplicates or more enables DESeq2 to detect sufficiently large numbers of reliable gene candidates for downstream systems level analysis. When biological effect size is weak, systems level investigation is not possible, and no meaningful result can be obtained in unreplicated experiments. Nonetheless, NOISeq or GFOLD may yield limited numbers of candidates with good validation potential when triplicates or more are available.


2015 ◽  
Author(s):  
Tsung Fei Khang ◽  
Ching Yee Lau

Background: A common research goal in transcriptome projects is to find genes that are differentially expressed in different phenotype classes. Biologists might wish to validate such gene candidates experimentally or use them for downstream systems biology analysis. Producing a coherent differential expression analysis from RNA-seq count data requires an understanding of how numerous sources of variation such as the replicate size, the hypothesized biological effect, and the specific method for making differential expression calls interact. We believe an explicit demonstration of such interactions in real RNA-seq data sets is of practical interest to the biologist. Results: Using two large public RNA-seq data sets - one representing strong, and another mild, biological response, we simulated different replicate size scenarios and tested the performance of several commonly-used methods for calling differentially expressed genes in each of them. Our results suggest that if the biological response of interest in the different phenotype classes is expected to be mild, then RNA-seq experiments should focus on validation of differentially expressed gene candidates. At least triplicates must be used, and the differentially expressed genes should be called using methods with high positive predictive value such as NOISeq or GFOLD. In contrast, for strong biological response, differentially expressed genes mined from unreplicated experiments using NOISeq, ASC and GFOLD had between 30 to 50% mean positive predictive value, an increase of more than 30-fold compared to the case of mild biological response. Among methods with good positive predictive value performance, having triplicates or more substantially improved mean positive predictive value to over 90% for GFOLD, 60% for DESeq2, 50% for NOISeq, and 30% for edgeR. We found DESeq2 to be the most reasonable method to call differentially expressed genes for systems level analysis as it showed the best PPV and sensitivity trade-off (mean PPV and mean sensitivity ∼ 65% at replicate size of six). Conclusion: When biological effect size is strong, NOISeq and GFOLD are effective tools for detecting differentially expressed genes in unreplicated RNA-seq experiments for validation work. Having triplicates or more enables DESeq2 to detect sufficiently large numbers of reliable gene candidates for downstream systems level analysis. When biological effect size is weak, systems level investigation is not possible, and no meaningful result can be obtained in unreplicated experiments. Nonetheless, NOISeq or GFOLD may yield limited numbers of candidates with good validation potential when triplicates or more are available.


2000 ◽  
Vol 32 (3) ◽  
pp. 276-283 ◽  
Author(s):  
Eric D. Schoen ◽  
Enrico A. A. Kaul

2013 ◽  
Vol 50 (2) ◽  
pp. 137-149 ◽  
Author(s):  
Stanisław Mejza ◽  
Iwona Mejza

Summary This paper deals with the problems of selection in the early stages of a breeding program. During the improvement process, it is not possible to use an experimental design that satisfies the requirement of replicating all the treatments, because of the large number of genotypes involved, the small amount of seed and the low availability of resources. Hence unreplicated designs are used. To control the real or potential heterogeneity of experimental units, control (check) plots are arranged in the trial. There are many methods of using the information resulting from check plots. All of the usually applied adjusting methods for unreplicated experiments are appropriate for some specific structure of soil fertility. Their disadvantage is the fact that, before and also after the experiment, we usually do not know what a kind of soil structure is present in the experiment. Hence we cannot say which of the existing methods is appropriate for a given experimental situation. The method of inference presented below avoids this disadvantage. It is always appropriate, because of the fact that a trend of soil variability is identified and estimated. In the paper the main tool used to explore this information will be based on a response surface methodology. To begin with we will try to identify a response surface characterizing the experimental environments. We assume that observed yield (or another trait) results directly from two components, one of them due to soil fertility and the other due to the genotype effect. This means that difference between observed yield and forecast can be treated as the estimate of a genotype effect. The obtained response surface will then be used to adjust the observations for genotypes. Finally, the data so adjusted are used for inferences concerning the next stage of the breeding program. The theoretical considerations are illustrated with an example involving yields of spring barley.


Sign in / Sign up

Export Citation Format

Share Document