RESUMO
In a note about the paper titled 'On the one parameter unit-Lindley distribution and its associated regression model for proportion data', Mazucheli et al. [J. Appl. Stat. 46 (2019), pp. 700-714] and Nadarajah and Chan [On moments of the unit Lindley distribution, J. Appl. Stat. (under review)] claim that 'The expressions given for the moments and incomplete moments are not correct and not in closed form'. While we agree that they are not in closed form and observe a typo in the expressions for µ k ' and T k ( t ) , k = 1 , , the expressions for µ 1 ' , µ 2 ' , µ 3 ' and µ 4 ' are, however, entirely correct.
RESUMO
ABSTRACT Pathogenic variation in Colletotrichum gloeosporioides infecting species of the tropical pasture legume Stylosanthes at its center of diversity was determined from 296 isolates collected from wild host population and selected germ plasm of S. capitata, S. guianensis, S. scabra, and S. macrocephala in Brazil. A putative host differential set comprising 11 accessions was selected from a bioassay of 18 isolates on 19 host accessions using principal component analysis. A similar analysis of anthracnose severity data for a subset of 195 isolates on the 11 differentials indicated that an adequate summary of pathogenic variation could be obtained using only five of these differentials. Of the five differentials, S. seabrana 'Primar' was resistant and S. scabra 'Fitzroy' was susceptible to most isolates. A cluster analysis was used to determine eight natural race clusters using the 195 isolates. Linear discriminant functions were developed for eight race clusters using the 195 isolates as the training data set, and these were applied to classify a test data set of the remaining 101 isolates. All except 11 isolates of the test data set were classified into one of the eight race clusters. Over 10% of the 296 isolates were weakly pathogenic to all five differentials and another 40% were virulent on just one differential. The unclassified isolates represent six new races with unique virulence combinations, of which one isolate is virulent on all five differentials. The majority of isolates came from six field sites, and Shannon's index of diversity indicated considerable variation between sites. Pathogenic diversity was extensive at three sites where selected germ plasm were under evaluation, and complex race clusters and unclassified isolates representing new races were more prevalent at these sites compared with sites containing wild Stylosanthes populations.
RESUMO
Three adult patients with acid beta-galactosidase deficiency/GM1 gangliosidosis who were from two unrelated families of Scandinavian descent were found to share a common point mutation in the coding region of the corresponding gene. The patients share common clinical features, including early dysarthria, mild ataxia, and bone abnormalities. When cDNA from the two patients in family 1 was PCR amplified and sequenced, most (39/41) of the clones showed a C-to-T transition (C-->T) at nucleotide 245 (counting from the initiation codon). This mutation changes the codon for Thr(ACG) to Met(ATG). Mutant and normal sequences were also found in that position in genomic DNA, indicating the presence of another mutant allele. Genomic DNA from the patient in family 2 revealed the same point mutation in one allele. It was determined that in each family only the father carried the C-->T mutation. Expression studies showed that this mutation produced 3%-4% of beta-galactosidase activity, confirming its deleterious effects. The cDNA clones from the patients in family 1 that did not contain the C-->T revealed a 20-bp insertion of intronic sequence between nucleotides 75 and 76, the location of the first intron. Further analysis showed the insertion of a T near the 5' splice donor site which led to the use of a cryptic splice site. It appears that the C-->T mutation results in enough functional enzyme to produce a mild adult form of the disease, even in the presence of a second mutation that likely produces nonfunctional enzyme.