Jackknife Procedure Research Articles

Analysis of the Association Between the Incidence of Two Spatially Aggregated Foliar Diseases of Strawberry

ABSTRACT Association of the incidence of leaf blight (caused by Phomopsis obscurans) and leaf spot of strawberry (caused by Mycosphaerella fragariae) was assessed at multiple scales in perennial plantings at several commercial farms over 3 years (1996 to 1998). For each field, the presence or absence of each disease was recorded from n = 15 leaflets in each of N approximately 70 evenly spaced sampling units, and the proportion of leaflets with blight, spot, and total disease (blight or spot) was determined. Individual diseases and total disease incidence were all well described by the beta-binomial distribution but not by the binomial distribution, indicating overdispersion of disease. The Jaccard similarity index was used to measure disease co-occurrence at the leaflet, sampling-unit, and field scales. Standard errors of this index for the lower two scales were obtained using the jackknife (resampling) procedure, and data randomizations were used to determine the expected Jaccard index for an independent arrangement of the two diseases, conditioned on the incidence and spatial heterogeneity of the observed disease data. Results based on these statistics showed that only 4 of 52 data sets at the leaflet level and no data sets at the sampling-unit level had Jaccard index values significantly different from that expected under an independent rearrangement of the two diseases. Rank correlation and cross-correlation statistics were calculated to determine the degree of covariation in incidence between the two diseases. Additionally, covariation between diseases was tested using a new procedure in the Spatial Analysis by Distance IndicEs (SADIE) class of tests. Covariation was detected in 21% of the data sets using rank correlation methods and in 15% of the data sets using the SADIE-based approach. The discrepancy between these two methods may be due to the rank correlation procedure not taking into account the effects of spatial pattern of disease incidence. There was no relationship between mean disease incidence per field of spot and blight or between degree of heterogeneity of the two diseases (as measured by theta of the beta-binomial distribution), demonstrating lack of covariation at the field scale. Incidence of leaflets with either disease (total disease incidence) could be well predicted using a linear combination of the estimated probabilities of leaf blight and leaf spot incidence based on independence of the two diseases. Heterogeneity of total disease incidence, measured with the estimated theta parameter of the beta-binomial distribution, could also be well predicted using a linear combination of the weighted theta values for leaf blight and leaf spot, with weights proportional to incidence of the individual diseases.

A two-factor empirical deterministic response surface calibration model for site-specific predictions of lime requirement.

This paper describes the development of an empirical deterministic two-factor response surface model for the Woodruff lime-requirement buffer (WRF). The model may be used to produce variable-rate lime requirement maps, or to predict lime requirements in real-time. Hence it may be suitable as a component of a decision support system (DSS) for the site-specific management of acid soil. The models' predictions were compared to those of a one-factor response surface, and those of a linear regression. The models tested were validated against soil-CaCO3 incubations using a statistical jackknifing procedure for error and bias estimations. The Akaike Information Criterion (AIC) was used to ascertain the best model in terms of goodness of fit and parsimony. The two-factor response surface model produced the best lime requirement estimates, followed by the single-factor model, then the conventional linear regression. The advantages of the response surface models are their improved prediction accuracy, and their flexibility in the choice of any target pH (from pH 5.5 to 7) without the need for excessive calibrations. The uncertainty of the model was assessed using data from an agricultural field in Kelso, New South Wales, Australia. Block kriged maps of soil pH measured in 0.01 M CaCl2 (pHCaCl2), WRF buffer pH (pHbuffer) and lime requirements to a target pH of 7 were produced, to compare their spatial distributions. Finally the economic and agronomic benefits of site-specific liming were considered.

Cascaded multiple classifiers for secondary structure prediction.

We describe a new classifier for protein secondary structure prediction that is formed by cascading together different types of classifiers using neural networks and linear discrimination. The new classifier achieves an accuracy of 76.7% (assessed by a rigorous full Jack-knife procedure) on a new nonredundant dataset of 496 nonhomologous sequences (obtained from G.J. Barton and J.A. Cuff). This database was especially designed to train and test protein secondary structure prediction methods, and it uses a more stringent definition of homologous sequence than in previous studies. We show that it is possible to design classifiers that can highly discriminate the three classes (H, E, C) with an accuracy of up to 78% for beta-strands, using only a local window and resampling techniques. This indicates that the importance of long-range interactions for the prediction of beta-strands has been probably previously overestimated.

Application of curve resolution based methods to kinetic data

Two methods for estimating reaction rate constants from spectral data are compared. The first method is a weighted curve resolution method. The second method is an improved curve resolution method. If some of the pure spectra of species in a reacting system are known, this can be incorporated into the second algorithm. Hence, spectral information that is known a priori is used. Both methods are applied to UV–VIS recorded spectra of the two-step consecutive reaction of 3-chlorophenylhydrazonopropane dinitrile, which is an uncoupler of oxidative phosphorylation in cells, with 2-mercaptoethanol in order to estimate the reaction rate constants involved. In order to perform quality assessment, upper and lower error bounds of estimates of reaction rate constants were estimated using a jackknife procedure. Application of the second method led to lower standard deviations of the estimated reaction rate constants, compared to the first method, due to extra spectral information that is used in this second method.

Quadrat Sample Precision and Cost with a High-vacuum Insect Sampling Machine in Cotton Ecosystems

Accurate and reliable insect samplers must be used in an effective manner if predators are to be used in the integrated pest management (IPM) decision-making process for complex ecosystems; therefore, optimum sampling procedures were evaluated for a high-vacuum insect sampling machine (Insectavac) for use in cotton, Gossypium hirsutum L. A total of 15 adult and immature insect groups was collected from 3 cotton fields, 12 times over a 3-yr period with an Insectavac. These data were used to evaluate the effect of quadrat size and number on the cost and precision of sampling in a cotton ecosystem. We sampled 340, 30.5-m quadrats end to end and 250, 61.0-m quadrats were sampled in a randomized complete block design over a 3-yr period. Data were analyzed using analysis of variance (ANOVA) and jackknife procedures. Variances obtained from the jackknife procedure were essentially the same as those obtained from the ANOVA. We concluded that sampling biases caused by patchy or clumped distributions of insects were not significant and the resulting estimates were unbiased. Because the insect populations were not significantly clumped, nothing was gained by the use of the jackknife procedure. Large quadrats resulted in significantly greater sampling variability because the extreme values from uneven distributions were higher than with smaller quadrat sizes. Advantages of small quadrats include a greater number of quadrats sampled for similar labor input which results in more degrees of freedom, better coverage of habitats within a field, and better representation of average insect densities.

Identification of Influential Cases in Structural Equation Models Using the Jackknife Method

Relatively little attention has been given to detecting influential cases (ICs) when estimating structural equation models (SEMs). Most techniques examine individual cases using covariance-based techniques such as the Mahalanobis distance, which examine the distributional characteristics of the cases but ignore the model. Cases identified using such model-free techniques are usually referred to as out-liers. In SEM, however, the model is of central importance. The characteristics of the model (number of latent variables, etc.) have an effect on which cases are influential. The authors propose applying the well-known jackknife procedure to detect model-based ICs, which may be influential with respect to overall fit, particular model parameters, or both. The procedure is illustrated by two studies—one using simulated data, the other empirical data.

Discriminant power of combined cerebrospinal fluid τ protein and of the soluble interleukin-6 receptor complex in the diagnosis of Alzheimer's disease

Alzheimer's disease (AD) still can only be definitively diagnosed with certainty by examination of brain tissue. There is a great need for a noninvasive, sensitive and specific in vivo test for AD. We combined cerebrospinal fluid analyses of τ protein (levels were significantly increased in AD patients [ p=0.0001]), a putative marker of neuronal degeneration, with components of the soluble interleukin-6 receptor complex (sIL-6RC: IL-6, soluble IL-6 receptor and soluble gp130), putative markers of neuroregulatory and inflammatory processes in the brain. A stepwise multivariate discriminant analysis revealed that τ protein and soluble gp130 (levels were significantly reduced in AD subjects [ p=0.007]), the affinity converting and signal-transducing receptor of neuropoietic cytokines, maximized separation between the investigated groups. The discriminant function predicted 23 of 25 clinically diagnosed AD patients (sensitivity 92%) with mild to moderate dementia correctly as having AD. Furthermore, 17 of 19 physically and cognitively healthy age-matched control subjects (specificity 90%) were accurately distinguished by this test. Later predicting with the jackknife procedure each case in turn through the remaining patient group, the discriminant function remained stable. Our data suggest that multivariate discriminant analysis of combined CSF τ protein and sIL-6RC components may add more certainty to the diagnosis of AD, however, the method will need to be extended to an independent group of patients, comparisons and control subjects to assess the true applicability.

Argyrophilic nucleolar organizer region (AgNOR) technique: a helpful tool for differential diagnosis in urinary cytology.

The aim of this study was to investigate whether the AgNOR technique could be helpful for the cytologic diagnosis of neoplastic and non-neoplastic urinary tract lesions. We analysed the AgNOR pattern in urinary cytology in samples from 70 patients. In every case the average number of silver precipitations per nucleus was counted and the range between the minimum and maximum AgNOR value calculated. Furthermore we noted whether the AgNOR precipitations had a homogeneous or heterogeneous distribution. The diseases were classified in three groups: non-neoplastic lesions, low grade and high grade carcinoma. Linear discriminant analysis (with jack-knife procedure) was performed with the AgNOR parameters as independent variables. The final diagnosis of each patient had been established by histological analysis of bladder biopsies. We obtained a correct classification in 84.3% of the cases. All patients with normal or reactive lesions were correctly classified and only two cases of low grade malignancy were erroneously diagnosed as non-malignant. Five high grade neoplasms had been classified as low grade and four low grade carcinomas had been over-diagnosed as high grade neoplasms. We conclude that a combined qualitative and quantitative AgNOR analysis can be useful in the differential diagnosis of urinary cytology.

Identifying influential individuals in linkage analysis: application to a quantitative trait locus detected in the COGA data.

Once linkage is detected to a quantitative trait locus (QTL), the next step towards localizing the gene involved may be to identify those families, or individuals, in whom the putative mutations are segregating. In this paper, we describe a jackknife procedure for identifying individuals (and families) who contribute disproportionately to the linkage. Following initial detection of linkage to a QTL, the strategy involves sequentially removing each individual (or each family) from the analysis and recomputing the lod score associated with the linked region using data from all remaining subjects (or families). This procedure can be used to determine if particular observations have substantial impact on evidence for linkage. Identification of such observations may provide insights for further efforts to localize the QTL.

Support, Ribosomal Sequences and the Phylogeny Of The Eukaryotes

Sequences of the small subunit (SSU) ribosomal RNA are considered useful for reconstructing the tree of life because this molecule is found in all organisms and is large enough not to have become saturated with multiple mutations. However, these data sets are large, difficult to align, and have extreme biases in base compositions which makes their phylogenetic signal ambiguous. Large ambiguous data sets may have many most-parsimonious trees, and finding them all may be impossible using convential phylogenetic methods. To examine the reliability of the number and relationships of eukaryotic kingdoms proposed by previous analyses of the SSU, we calculated trees from aligned sequences from eukaryotes in the Ribosomal Database Project using parsimony jackknifing which uses a resampling procedure to rapidly search large data sets for the branches that are strongly supported and eliminates poorly supported groups. Two separate analyses were carried out: an analysis in which all bases were equally weighted, and one in which transversions only were used. The parsimony jackknife procedure was able to efficiently find trees in which most major groups of eukaryotes were supported and in which some evolutionary hypotheses proposed by previous workers were tested. The relationships of these major groups to each other were largely unresolved, indicating that the SSU data, as represented in this database, is insufficient for answering questions about these deep branches. Interestingly, the analysis of transitions differs from the results of the entire data set, primarily being less resolved. This indicates that transversional mutations are important contributors to the resolved structure of the tree.

Support, Ribosomal Sequences and the Phylogeny Of The Eukaryotes.

Sequences of the small subunit (SSU) ribosomal RNA are considered useful for reconstructing the tree of life because this molecule is found in all organisms and is large enough not to have become saturated with multiple mutations. However, these data sets are large, difficult to align, and have extreme biases in base compositions which makes their phylogenetic signal ambiguous. Large ambiguous data sets may have many most-parsimonious trees, and finding them all may be impossible using convential phylogenetic methods. To examine the reliability of the number and relationships of eukaryotic kingdoms proposed by previous analyses of the SSU, we calculated trees from aligned sequences from eukaryotes in the Ribosomal Database Project using parsimony jackknifing which uses a resampling procedure to rapidly search large data sets for the branches that are strongly supported and eliminates poorly supported groups. Two separate analyses were carried out: an analysis in which all bases were equally weighted, and one in which transversions only were used. The parsimony jackknife procedure was able to efficiently find trees in which most major groups of eukaryotes were supported and in which some evolutionary hypotheses proposed by previous workers were tested. The relationships of these major groups to each other were largely unresolved, indicating that the SSU data, as represented in this database, is insufficient for answering questions about these deep branches. Interestingly, the analysis of transitions differs from the results of the entire data set, primarily being less resolved. This indicates that transversional mutations are important contributors to the resolved structure of the tree.

The effect of group discussion on interrater reliability of structured peer review.

The effect of group discussion on interrater reliability of structured peer review.

A retail failure prediction model

Financial ratios have long been used for business analysis. Researchers have formulated business failure prediction models utilizing financial ratios. This study focuses on the use of financial ratios to discriminate between failed and non-failed firms in the retail industry. Using a matched sample of sixty-six failed and sixty-six non-failed retail firms obtained from the COMPUSTAT database, multiple discriminant analysis was utilized to develop a retail prediction model which accurately classified 78 per cent of the sample firms as failed or non-failed. Hotelling's T 2 test determined that the mean vector of the discriminant function for failed firms differed from that of non-failed firms. The model was further validated using a jackknife procedure and split sample analysis. Failed or non-failed classification accuracy was found to be significantly better than chance.

The Value of PCNA and AgNOR Staining in Endoscopic Biopsies of Gastric Mucosa

The aim of the present study was to examine the usefulness of the quantification of PC10-positive-cells and of Argyrophilic Nucleolar Organizer Regions (AgNORs) in gastric biopsies for the identification of gastric mucosal proliferative lesions. Fifty seven paraffin-embedded endoscopic biopsies were classified into four histologic groups: normal, inflammatory, dysplastic and neoplastic mucosa. The percentage of PC10-positive cells was determined by immunohistochemistry. The AgNOR parameters determined included the total number of all identifiable silver precipitations in the nucleus, the mean number of silver precipitations per cluster, and the presence of morphologically heterogenous silver precipitations. Group comparisons were performed using the Kruskall Wallis and Dunn non-parametric tests with a significance level of 5%. A discriminant analysis (followed by the jack-knife procedure) was performed using the three AgNOR parameters plus the percentage of PCNA-positive cells as the independent variables and histological groups as the dependent variable. All three AgNOR parameters, as well as the percentage of PCNA-stained nuclei, showed their highest values in the carcinoma group. However, no good differentiation among the four histologic groups was obtained using only one of these parameters, since there was always considerable overlap among them. By combining all the parameters in a linear discriminant analysis, we obtained a correct classification in 48 out of 57 cases. Within the classification errors there was only one false positive carcinoma, which was in fact a dysplasia and only one false negative carcinoma erroneously classified as dysplasia. The number of cells with heterogenous AgNORs was the most important parameter for the discriminant analysis. No correlation between PCNA values and the AgNOR parameters could be found, thus indicating that they do not represent the same phenomenon in the cell cycle. We concluded that the use of a combination of various proliferation parameters in a linear discriminant analysis may be helpful for differentiating gastric mucosal lesions. The peculiar AgNOR morphology is an important variable which should be taken in consideration in quantitative studies. PCNA and AgNORs seem to represent different physiological phenomena in the cell cycle.

Estrutura de guildas e riqueza de espécies em uma comunidade de larvas de anisoptera (Odonata)

Normal 0 21 false false false MicrosoftInternetExplorer4 /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Tabela normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin:0cm; mso-para-margin-bottom:.0001pt; mso-pagination:widow-orphan; font-size:10.0pt; font-family:"Times New Roman"; mso-ansi-language:#0400; mso-fareast-language:#0400; mso-bidi-language:#0400;} Odonata larvae are important components of the littoral systems in lakes. They are considered food generalists and interact among themselves by a complex of competition und predation of the early upon the late breeders. Here, we determine the guild structure for odonates sarnpled in Lagoa Carioca. Parque Estadual do Rio Doce (PERD), MG, based on microhabitat use. We only found t wo species of the macrophyte-dweller guild to seven bottom-dweller species. Using a jackknife procedure, we found that the species richness of the areas with macrophytes were higher than the areas where the macrophytes are absent.

Empirical estimation of the reliability of ribosomal RNA alignments.

The automatic alignment of rRNA sequences can reproduce manual expert alignments with high, but not perfect, fidelity. We examine the use of empirical methods for the identification of regions of an alignment of a new sequence with an existing large alignment which can confidently be predicted to be correctly aligned. We show how to use a simple jack-knife procedure to derive an estimate of the reliability that is to be expected at each position of a large alignment of eukaryotic rRNA sequences. These reliabilities are then improved using measures that are specific to the input sequence. Regions where the sequence-specific reliability method performs particularly well are identified and seen to correspond with elements in the structure of the rRNA molecules that vary between species in the alignment. We also compare these reliability measures to an algorithmic alignment stability measure. The software is available free of charge by sending an e-mail message to emmet@chah.ucc.ie. emmet@chah.ucc.ie

Species-area curves and estimates of total species richness in an old-field chronosequence

Average species-area curves were generated for vascular plants in 20 old-fields that were sampled in 1983, 1989, and 1994. These curves were fit with a saturating function to estimate total species richness for each old-field. Additional estimates of total species richness were generated by fitting the same saturating function to subsets of the species area curves and with a first-order jackknife procedure. Estimates of total species richness were strongly correlated with observed species richness. There was limited evidence suggesting that greater sampling was necessary to identify the same proportion of species in older, more species-rich old-fields.

Development of Statistical Discriminant Mathematical Programming Model Via Resampling Estimation Techniques

AbstractThis paper uses resampling estimation techniques to develop a statistical mathematical programming model for discriminant analysis problems. Deleted‐d jackknife, deleted‐d bootstrap, and bootstrap procedures are used to identify statistical significant parameter estimates for a discriminant mathematical programming (MP) model. The results of this paper indicate that the resampling approach is a viable model selection technique. Furthermore, estimating the MP models via resampling techniques can also improve the classification performance compared to a deterministic discriminant MP model. In this study, the deleted‐d jackknife procedure was the most promising among the resampling estimation techniques examined.

Behavioral phenomenology in Alzheimer's disease, frontotemporal dementia, and late-life depression: a retrospective analysis.

Often patients in the early stages of Alzheimer's disease (AD), frontotemporal dementia (FTD), and late-life depression can be difficult to differentiate clinically. Although subtle cognitive distinctions exist between these disorders, noncognitive behavioral phenomenology may provide additional discriminating power. In 19 subjects with AD, 19 with FTD, 16 with late-life psychotic depression (LLPD), and 19 with late-life nonpsychotic depression (LLNPD), noncognitive behavioral symptoms were quantified retrospectively using the Schedules for Clinical Assessment in Neuropsychiatry (SCAN) and compared using both a one-way ANOVA and a multivariate stepwise discriminant analysis, which utilized a jackknife procedure. The FTD group showed the highest mean total SCAN score, while the AD group showed the lowest. ANOVA showed significant differences in the mean total SCAN scores between the four diagnostic groups (P < .0001). With the discriminant analysis, the four disorders demonstrated different clusters of behavioral abnormalities and were differentiated by these symptoms (P < .0001). A subset of 14 SCAN item group symptoms was identified that collectively classified the following percentages of subjects in each diagnostic category: AD 94.7%, FTD 100%, LLPD 87.5%, and LLNPD 100%. These results indicate that AD, FTD, LLPD, and LLNPD were distinguished retrospectively by the SCAN without using cognitive data. Better definition of the longitudinal course of noncognitive behavioral symptoms in different dementias and psychiatric disorders will be valuable both for diagnosis and to help define behavioral syndromes that are associated with selective neuroanatomic and neurochemical brain pathology.

A multivariate approach for estimating the random effects variance component in one-way random effects model

It is well known that the ANOVA estimator of the random effects variance component in one-way random effects model can assume negative values. It is also well known that nonnegative quadratic unbiased estimators do not exist for estimating the random effects variance component (LaMotte, 1973). LaMotte (1985) indicated the possibility that nonnegative invariant quadratic estimator of the random effects variance component uniformly better than the ANOVA estimator may exist for the balanced one-way random effects model. Mathew et al. (1992a) have shown that such estimator exists only when the number of treatments is 9 or less. As noted in Herbach (1959) (see also Thompson, 1962), a simple truncation of the ANOVA estimator at zero yields uniform improvement over the ANOVA estimator. The estimators suggested by Herbach and Thompson are, in fact, restricted maximum likelihood estimators, and they are nonquadratic by nature. In this paper, we discuss a multivariate technique which always yields positive estimate of the random effects variance component in one-way random effects model. The multivariate approach exploits the estimates of the eigenvalues of the covariance matrix of the model in estimating the variance components including the error variance. The resulting estimates are nonquadratic. The success of this multivariate approach depends on the precise estimation of the eigenvalues. Since there does not exist any unbiased estimation procedure in the small sample case for the estimation of the eigenvalues, we use a delete-d jackknife procedure to estimate them. This delete-d jackknife based multivariate approach yields better estimates (in terms of mean squared error) for the random effects variance component than the restricted maximum likelihood estimation as well as Chow and Shao's (1988) nonquadratic estimation approaches, which is shown through a simulation study for the cases with number of treatments up to 20.