Multivariate Discriminant Analysis Research Articles

Snow avalanche hazard prediction using machine learning methods

Snow avalanches are among the most destructive natural hazards threatening human life, ecosystems, built structures, and landscapes in mountainous regions. The complexity of snow avalanche modelling has been discussed in many studies, but its modelling is not well-documented. Snow avalanche modeling in this study was done using three main categories of data, including avalanche occurrence locations, meteorological factors, and terrain characteristics. Two machine learning models, namely support vector machine (SVM) and multivariate discriminant analysis (MDA), were employed. A ratio of 70 to 30 of data was considered for calibrating and validating the models. Results indicated that both models had an excellent performance in snow avalanche modeling (area under curve, AUC > 90), although hits and misses analysis demonstrated the superior performance of MDA. Sensitivity analysis indicated that the topographic position index, slope, precipitation, and topographic wetness index were the most effective variables for modeling. A snow avalanche map indicated that the high snow avalanche hazard zone was mostly near the streams and was matched with hillsides around the water pathways. Findings of study can be helpful for land use planning, to control snow avalanche paths, and to prevent the probable hazards induced by it, and it can be a good reference for future studies on modeling snow avalanche hazards.

Estrés cotidiano infantil y factores ligados al aprendizaje escolar como predictores del rendimiento académico

Background and objectivesWithin the broad spectrum of variables that influence learning and consequently academic achievement, affective-motivational factors related to daily stress are particularly important. The aim of this study was to analyze associations between daily childhood stress, learning strategies and academic motivation, by analyzing how they differ across 3 achievement groups (low, medium and high), and the predictive-ability of these groupings. MethodNon-experimental methodology in a cross-sectional, descriptive, correlational, inferential and multivariate study. A total of 535 primary school students from Cantabria, Spain, aged 9 to 12 (M=10.72; SD=0.67), participated in the study. They completed the Inventario de Estrés Cotidiano Infantil [Children's Daily Stress Inventory] and the Diagnóstico Integral del Estudio [Comprehensive Diagnosis of Study], and their school grades were recorded for the subjects of Language Arts, English as a Foreign Language, and Mathematics. ResultsThe results showed positive, significant relationships between all the variables pertaining to learning and academic achievement; each of these variables, in turn, had negative, significant relationships with global daily stress (as well as with health, school and family stress). The multivariate discriminant analysis explained the predictive role of complementary strategies, school stress, attitude toward study and self-concept, in different levels of general academic achievement. ConclusionsThere is a need for interventions in self-regulated learning strategies that would serve as a preventive measure, and in development of coping strategies for stressful situations inside and outside the educational context.

Unhealthy Diet in Children with Cancer: A Case-Reference Study

AbstractObjective: To explore the dietary intake of a children’s cohort with cancer incomparison with an age-matched cohort of healthy children. MethodsWe enrolled children with a confirmed diagnosis of cancer (solid tumors, brain and blood malignancies) aged 1-18 years and agematched children as controls. A 3-days standardized food record was collected by a dietician blinded to the diagnosis. Differences of consumptions of nutrients were compared by parametric andnon-parametric tests, as appropriate. A multivariate discriminant analysis was used to identify the most effective nutrients to discriminate between the patients and controls.Results The diet of patients with solid tumors differed from that of the controls: they consumed a lower level of monounsaturated fats, a higher level of potential renal acid load and had a lower intake of vitamin E and B6. Children with blood malignancies showed greater differences with controls: they consumed lower quantities of calories, proteins, carbohydrates, monounsaturated fats, fibers and higher quantities of potential renal acid load and cholesterol. A multivariate analysis iscriminated blood malignancy patients by controls, with 90% efficiency, by a lower intake of vitamin E, B6, saturated fats, starch and a higher intake of sodium andvitamin A. Conclusions This extensive analysis of nutrients showed imbalances from recommended dietary intake in children affected by cancer, with significantly less protective nutrients.

Dietary resource partitioning among age-sex classes of Agama agama (Squamata: Agamidae) assessed by fecal pellet analysis

Dietary resource partitioning among age-sex classes of Agama agama (Squamata: Agamidae) assessed by fecal pellet analysis. Dietary analysis is critical to understand the ecological roles of lizards, especially of species of Agama that are colonizing continents and islands from which they were previously absent. The foraging habits of four groups—viz., adult females, adult males, and young and juveniles (of both sexes)—of Agama agama in Nigeria were observed to assess the diet of the lizards and the contribution of the diet to separating age-sex classes. The claim that fying arthropods are less likely to be eaten by lizards was tested, and the hypothesis of dietary opportunism was explored. Sets (3–5 pellets) of 1453 fecal pellets collected during a 2-yr period were linked to individual lizards. Multivariate discriminant analysis of individual food items showed 61% lizards were correctly classifed to age-sex. However, items pooled into composite food groups, yielded fewer (43%) correctly classifed lizards. Cluster Analysis indicated that individual foods were less common (46.3%) to lizard classes than composite foods (76.1%). Thus, lizard age-sex classes are better differentiated when prey item is identifed at the lowest possible taxonomic level. Overall, arthropods are the largest, composite food for all lizard classes but, the relative amounts of different arthropod taxa varies signifcantly, and is highest for Diptera. Other foods include plants, seeds, and non-arthropod animal material. Differing coeffcients of variation accentuate dietary disparities within classes. Proportions of most individual and composite diet items differ signifcantly by month, season, and study site. Although consumed by lizards, no traces of white mold were found in the feces; this underscores the value of combining fecal analysis with surveillance of foraging habits of Agama agama.

Fourier Transform Infrared Spectroscopy (FTIR) coupled with multivariate calibration and discriminant analysis for authentication of extra virgin olive oil from rambutan seed fat

The adulteration practice in pharmaceutical industries, especially in fats and oils used as a vehicle in some pharmaceutical products must be identified to assure its quality. In this study, Fourier Transform Infrared Spectroscopy (FTIR) in combination with chemometrics techniques of multivariate calibration and discriminant analysis (DA) were used for the authentication of extra virgin olive oil (EVOO) from rambutan seed fat (RSF). EVOO, RSF, and the mixture of EVOO-RSF were scanned using FTIR spectrophotometer at mid-infrared region (4000-650 cm-1 ). The results showed that normal FTIR spectra at wavenumbers region of 1446.8-1409.7 cm-1 and 2368.6-1769.9 cm-1 combined with principle component regression (PCR) offered the best quantitative model for prediction of RSF levels in EVOO. The coefficient of determination (R2 ) values obtained for the relationship between actual values of RSF and predicted values were of 0.9955 and 0.9915 in calibration and prediction models, respectively. The errors in calibration and prediction models were relatively low, accounting of 2.17% and 3.68%, respectively. The classification model between unadulterated or pure EVOO and adulterated EVOO with RSF was successfully carried out using DA at wavenumbers of 3100-1000 cm-1 without any samples mistakenly classified into the wrong group. FTIR spectroscopy in combination with chemometrics offered effective tools for authentication of EVOO against the adulteration practice.

Lipid and Metabolite Profiles in Human Plasma and Associations with the Microbiome and Functional Gastrointestinal Disorders (P20-033-19)

ObjectivesMetabolomic profiling of plasma provides a biochemical fingerprint of the circulating metabolites from the host and microbiome, and may assist with understanding mechanisms underlying functional gastrointestinal (GI) disorders such as Irritable Bowel Syndrome (IBS). In a case-control study, we aimed to identify microbial and host factors in plasma to provide mechanistic insights into functional GI disorders and increase the predictability of phenotypes for use in nutrition intervention studies. MethodsPlasma samples from 246 individuals with functional GI disorders (cases) or asymptomatic (controls), consisting of 93 healthy controls, 54 with functional constipation (C) or IBS-C, 60 with functional diarrhoea (D) or IBS-D, and 39 diagnosed as IBS-mixed or awaiting diagnosis. Plasma was subjected to biphasic extraction and global metabolite profiling was performed using three separate untargeted liquid chromatography high resolution mass spectrometry analysis (LC-MS) methods (polar, semi-polar and non-polar chromatography). ResultsPlasma metabolomic profiles differed considerably between the IBS phenotypes and those of the control subjects. Multivariate partial least squares discriminant analysis of 428 annotated lipid species highlighted significant differences (P < 0.001) between IBS-C and healthy control subjects. Univariate analysis revealed significant differences in the concentrations of 48 lipid species (P < 0.05) between the two groups, including elevated concentrations of many sphingolipids and phospholipids in the IBS-C group. Biochemical network analysis also revealed major perturbations in amino acid, bile acid and lipid metabolism, and highlighted key metabolic pathways included microbial related pathways. ConclusionsPerturbations of plasma lipid concentrations in the IBS subjects suggest changes may occur with both host and microbial lipid metabolism. Future efforts to investigate these links will utilize a systems biology approach integrating metabolomic and fecal metagenomic datasets to further identify key pathways and biomarkers that characterize functional GI disorders and how nutrition can improve GI health and function. Funding SourcesFunded by the New Zealand National Science Challenge High-Value Nutrition program.

Multivariate Discriminant Analysis of Single Seed Near Infrared Spectra for Sorting Dead-Filled and Viable Seeds of Three Pine Species: Does One Model Fit All Species?

Seed lots of pine species are composed of viable, dead-filled and empty seeds, and the success of complete sorting of dead-filled seeds using the conventional method (Incubation, Drying and Separation in water) is difficult to achieve; leaving a considerable scope for upgrading the sorting efficiency. The objective of this study was to evaluate the prospect of sorting viable and dead-filled seeds of pine species using Near Infrared (NIR) spectroscopy. To demonstrate this, dead-filled and viable seeds of Mason’s pine, slash pine and loblolly pine were incubated in moist medium for three days, dried for six hours and scanned by XDS Rapid Content Analyzer from 780–2500 nm. Orthogonal Projection to Latent Structure-Discriminant Analysis was used to develop discriminant models for each species separately and for all species combined. The results showed that the sensitivity (the model’s ability to correctly classify members of a given class) and the specificity (the model’s ability to reject non-members of a given class) were 100% for each species model and 98%–99% for combined species model. The overall classification accuracy was 100% and 99% for individual species and combined species models, respectively. The absorption band in the 1870–1950 nm with a major peak at 1930 nm, which is related to water, was responsible for discrimination as dead-filled seeds dried quicker than viable seeds during the drying process. Our study is the first attempt to simultaneously discriminate dead-filled and viable seeds of pines by NIR spectroscopy. The results demonstrates that a global calibration model of seed lots of several pine species can be equally effective as the individual species model to discriminate viable and dead-filled seeds by NIR spectroscopy, thereby ensuring precision sowing (also known as single seed sowing) in nurseries.

Applicability and reliability of foramen magnum for sex determination in contemporary Western Indian population: A computed tomographic study

Abstract Establishing sex of fragmentary skeletal remains is a critical issue in forensic anthropology and is of prime importance, since it helps to significantly narrow down the number of potential victims. Forensic anthropologists have always advocated for population specific sex discriminant formula for each population using different skeletal parts. Till date Gujarati population of India has not have any discriminant formulae for sex determination from fragmentary crania. So, the current research aims to examine the usefulness of foramen magnum variables in sex estimation of Western Indian (Gujarati) population and to provide population data which can be used as reference in cases of establishing identity in unknown fragmentary skulls. A total of 553 adult individuals [♂ = 291, ♀ = 262] of Gujarati origin with age range 18–60 years were subjected to Computed Tomography (CT) scan of skull. Length and width of foramen magnum were measured and based on these, three other variables (areas by Radinsky and Teixeria formulae and foramen magnum index) were calculated. Descriptive and discriminant function analysis was performed using SPSS 20.00. Significant difference was observed in all variables except foramen magnum index, but sexing accuracy didn't exceed 69.1%, even after using multivariate discriminant analysis. It is concluded that the foramen magnum region is not suitable for sexing Gujarati population in forensic context.

Multivariate analysis reveals significant diuron-related changes in the soil composition of different Brazilian regions

Sorption and desorption determine the amount of an herbicide in soil solution. Therefore, knowledge of the sorption and desorption coefficients in different soils is an essential factor to estimate the potential for environmental contamination by herbicides. We evaluated the feasibility of multivariate and linear discriminant analyses to predict the sorption and desorption capacity of a soil for diuron, one of the most used herbicides on sugarcane plantations. The adsorptive capacity in twenty-seven Brazilian soil samples was estimated using the sorption constant (Kfs) and desorption constant (Kfd) obtained by the Freundlich isotherms. The regression model was created from the sorbed and nonsorbed concentrations of diuron in soils. Ultra-performance liquid chromatography was applied to quantify the diuron concentrations. The multivariate analysis separated the soils into four groups considering the similarity of the following attributes: pH, organic matter, clay, and base saturation. The groups showed a similar pattern of sorption and desorption for diuron: Lom-Lclay: low sorption (5.9 ± 1.2) and high desorption (10.9 ± 0.6); Lclay: low sorption (7.5 ± 1.1) and high desorption (11.4 ± 1.3); Hom-Hclay: high sorption (11.2 ± 1.2) and low desorption (13.8 ± 1.2); HpH-Hclay: high sorption (10.1 ± 1.1) and medium desorption (11.5 ± 1.4). Linear discriminant analysis of these soil attributes was used to classify other soils described in the literature with adsorption capacity. This analysis was able to identify soils with high and low sorption using the pH, organic matter, clay, and base saturation, demonstrating the enormous potential of the technique to group soils with different contamination risks for subterranean waters. Sugarcane crops in northeastern Brazil showed a higher pollution risk through the leaching of diuron. Multivariate analysis revealed significant diuron-related changes in the soil composition of different Brazilian regions; therefore, this statistical analysis can be used to improve understanding of herbicide behavior in soils.

Bankruptcy prediction for Japanese corporations using support vector machine, artificial neural network, and multivariate discriminant analysis

This study predicted the bankruptcy risk of companies listed in Japanese stock markets for the entire industry and individual industries using multiple discriminant analysis (MDA), artificial neural network (ANN), and support vector machine (SVM) and compared the methods to determine the best one. The financial statements of the companies listed in the Tokyo Stock Exchange in Japan were used as data. The data of 244 companies that went bankrupt between 1991 and 2015 were used. Additionally, the data of 64,708 companies that did not go bankrupt between 1991 and 2015 (24 years) were used. The data was acquired from the Nikkei NEEDS database. It was found from the results of empirical analysis that the SVM is more accurate than the other models in predicting the bankruptcy risk of companies. In the ANN analysis and MDA, bankruptcy prediction could be made accurately only for some individual industries. In contrast, the SVM could predict the bankruptcy risk of companies almost perfectly for either entire and individual industries. This bankruptcy prediction model can help customers, investors, and financiers prevent losses by focusing on the financial indicators before finalizing transactions.

Auditory steady-state EEG response across the schizo-bipolar spectrum

Deviant auditory steady-state responses (aSSRs) in the gamma range (30–90 Hz) may be translational biomarkers for schizophrenia (SZ). This study tests whether aSSR deviations are (i) specific to SZ across the psychosis dimension, (ii) specific to particular frequency bands, and (iii) present in bipolar I disorder without psychosis (BDNP). MethodsBeta (20-), low- (40-), and high-gamma (80-Hz) aSSRs were measured with EEG and compared across 113 SZ, 105 schizoaffective disorder (SAD), 99 bipolar disorder with psychosis (BDP), 68 BDNP, and 137 healthy comparison subjects (HC). Standard aSSR measures (single-trial power [STP] and inter-trial phase coherence [ITC]), as well as evoked responses to stimulus onsets/offsets and pre-stimulus power, were quantified. Multivariate canonical discriminant analysis was used to summarize variables that efficiently and maximally differentiated groups. Results(i) Psychosis groups showed reduced responses on ITC 20 Hz, STP/ITC 40 Hz, STP/ITC 80 Hz, indicating dimensional reductions in aSSR across the psychosis spectrum not specific to aSSR frequency. For the 40- and 80-Hz ITCs there was greater reduction in SZ compared to SAD, possibly indexing cortical disruptions linked to psychosis without mood symptoms. (ii) All probands had elevated pre-stimulus power, possibly compromising neural entrainment to the steady-state stimuli. (iii) Onset/Offset and 80 Hz ITC responses were most important for group discrimination and showed dimensional reduction across the schizo-bipolar spectrum. ConclusionsDeviant aSSRs were found across the schizo-bipolar spectrum at multiple frequencies with psychosis status and severity linked to greatest reductions at low and high gamma.

Multivariate product adapted grading of Scots Pine sawn timber for an industrial customer, part 2: Robustness to disturbances

ABSTRACTHolistic-subjective automatic grading (HSAG) of sawn timber by an industrial customer's product outcome is possible through the use of multivariate partial least squares discriminant analysis (PLS-DA), shown by part one of this two-part study. This second part of the study aimed at testing the robustness to disturbances of such an HSAG system when grading Scots Pine sawn timber partially covered in dust. The set of 308 clean planks from part one of this study, and a set of 310 dusty planks, that by being stored inside a sawmill accumulated a layer of dust, were used. Cameras scanned each plank in a sawmill's automatic sorting system that detected selected feature variables. The planks were then split and processed at a planing mill, and the product grade was correlated to the measured feature variables by partial least squares regression. Prediction models were tested using 5-fold cross-validation in four tests and compared to the reference result of part one of this study. The tests showed that the product adapted HSAG could grade dusty planks with similar or lower grading accuracy compared to grading clean planks. In tests grading dusty planks, the disturbing effect of the dust was difficult to capture through training.

Consolidated Biochemical Profile of Subacute Stage Traumatic Brain Injury in Early Development.

Traumatic brain injury (TBI) in general has varied neuropathological consequences depending upon the intensity and biomechanics of the injury. Furthermore, in pediatric TBI, intrinsic developmental changes add further complexity, necessitating a biochemical dimension for improved TBI characterization. In our earlier study investigating the subacute stage TBI metabolome (72 h post-injury) in a developmental rat model, significant ipsilateral brain biochemical changes occurred across 25 metabolite sets as determined by metabolite set enrichment analysis (MSEA). The broad metabolic perturbation was accompanied by behavioral deficits and neuronal loss across the ipsilateral hemisphere containing the injury epicenter. In order to obtain a consolidated biochemical profile of the TBI assessment, a subgrouping of the 190 identified brain metabolites was performed. Metabolites were divided into seven major subgroups: oxidative energy/mitochondrial, glycolysis/pentose phosphate pathway, fatty acid, amino acid, neurotransmitters/neuromodulators, one-carbon/folate and other metabolites. Subgroups were based on the chemical nature and association with critically altered biochemical pathways after TBI as obtained from our earlier untargeted analysis. Each metabolite subgroup extracted from the ipsilateral sham and TBI brains were modeled using multivariate partial least square discriminant analysis (PLS-DA) with the model accuracy used as a measurable index of TBI neurochemical impact. Volcano plots of each subgroup, corrected for multiple comparisons, determined the TBI neurochemical specificity. The results provide a ranked biochemical profile along with specificity of changes after developmental TBI, enabling a consolidated biochemical template for future classification of different TBI intensities and injury types in animal models.

Financial Failure Prediction Using Financial Ratios: An Empirical Application on the Saudi Stock Exchange

The objective of this research is to predict financial failure of few selected companies using financial ratios. In addition, the goal of this review is to look at the segregating power of monetary crisis utilizing the factors of the Altman's Z-score display and build up a reasonable model for Saudi Arabia, which could give detect ahead of time about the budgetary pain of companies. To build up the model the review has classified the chosen factors from year 2013 to 2016 two bad performing and two good performing companies. Multivariate Discriminant Analysis (MDA) has been utilized as the logical strategy and synchronous estimation technique used to enter the factors in the research. The results show that all the company's fall within the gray are, which indicates a weakness in performance and inability to make satisfactory profits for shareholders. Companies results reveal that most of them suffer from sever stagnation and that most of them do not distribute any profits at all or distribute very little profits. The two good performing companies continue to remain in the market while the two bad performers have quit the market. Keywords: Financial ratios, Saudi Arabia, Stock Market DOI : 10.7176/RJFA/10-9-07 Publication date :May 31 st 2019

The efficiency of collagen III, metalloproteinase 1, carcinoembryonic antigen, and carbohydrate antigen 19.9 for colon cancer diagnosis

Background: Currently, blood markers are noninvasive methods for the diagnosis of patients with colorectal cancer (CRC). We evaluated four biomarkers (Carcinoembryonic antigen (CEA), carbohydrate antigen 19.9 (CA19.9), collagen III, and metalloproteinase 1 (MMP-1)) and their combination as a substitute method to enhance diagnosis of CRC. Subjects and methods: one hundred ninety-five patients who had undergone colonoscopy examination were included in the study (135 CRC and 60 benign growths). Also, 45 healthy individuals were included. Multivariate discriminant analysis (MDA) and area under the receiver operating characteristic curve (AUC) were applied for evaluating the diagnostic power of single and their combination. Results: levels of collagen III, CEA, and CA 19.9 increased while MMP-1 decreased with the progression of CRC (stages, positive lymph node invasion, distant organ metastasis, and high grades) with a significant difference (P P < 0.0001). Combination of MMP-1, CEA, CA 19-9, and Collagen III yielded MC3 index had diagnostic power greater than every single marker could achieve alone. When differentiating colon cancer from benign growth, the AUC of MC3 index was 0.91 yielded 85.2% sensitivity and 86.7% specificity. Moreover, the MC3 index for patients with late stages, lymph node invasion, organ metastasis, and high-grade had AUC = 0.81, 0.82, 0.80, and 0.80 higher than CEA and CA19.9.Conclusion: MC3 index is can be used as an effective index for early detection of CRC.

Predicting Corporate Failures Using Multi Discriminant Analysis and Current Ratio: An Empirical Application to Philippines Stock Exchange

Predicting Corporate Failures Using Multi Discriminant Analysis and Current Ratio: An Empirical Application to Philippines Stock Exchange

Implimentasi Sistem Bunga dan Bagi Hasil Terhadap Kinerja Keuangan Perbankan

This research is aimed to know difference of the financial performance of the conventional banking and the syariah banking. Financial is measured by using ratios: ratio of capital to asset deliberated by according to risk, ratio of earning asset which classified to earning asset (KAP. I), ratio of allowance for possible earning losses to classified earning asset ( KAP.II), ratio of net operating income to operating income (NPM) representing proxy from management, ratio of profit before interest and tax to total asset ( ROA), ratio of operating expenses to operating income (BOPO), ratio of current assets to current liabilities and ratio of loan to deposit (LDR). This research use the saturated simple, that all bank of state of the public ownerships (BUMN) and bank of the Muamalat Indonesia, by using data of the secondary publicized by the Bank Indonesia each of semester, between period 2003-2011. The analysis instruments used was Multivariate Discriminant Analysis (MDA). Results of this research indicate that the CAMEL approach can determine banking financial performance. Pursuant to statistical test really there was financial performance difference between conventional banking and syariah banking, where conventional banking has better finance performance from syariah banking. This research found that CAR dan LDR; significantly differentiate conventional banking finance performance and syariah banking, in which the CAR was the most dominant

Assessing sediment yield and sources using fingerprinting method in a representative catchment of the Loess Plateau, China

Quantitative assessment of sediment yield and sources is of great importance for future soil and water conservation and watershed management in erosion-prone areas. This study investigated sediment yield and sources by using a simple fingerprinting method in a dam-controlled watershed on the northern Loess Plateau. The sampling sediment profile exhibited 24 flood couplets corresponding to rainfall storms from 2001 to 2014. A total of 2.05 × 105 t sediment was trapped during the period. The annual sediment yield varied from 0 to 430 t ha−1 year−1, with an average annual sediment yield of 146.1 t ha−1 year−1. Ten sediment properties (i.e., σ13C, σ15N, TOC, TN, C/N, Xlf, Xhf, Xfd, 137Cs, 210Pb) were potentially selected to identify the sediment sources. The multivariate discriminant function analysis (DFA) test suggested that three soil properties (Χhf, TN, and 137Cs) comprised the optimum composite fingerprinting. The results demonstrated that sandstone contributed nearly 90% of sediment in 2012 and 56.1% in 2003. The contribution from arable land varied from 5.2% in 2005 to 44.6% within the period of 2013–2014. On average, approximately 74.06% of sediment originated from the weathered sandstone, followed by 15.67% from arable land, and the remaining 10.27% from uncultivated land. Our finding indicated that bare sandstone was the main sediment source, leading to relatively high sediment yield in the study area. This study provides a method with great potential for sediment yields assessment and sediment source identification in ungauged watersheds on the Loess Plateau.

Variation in Agro-morphological Traits of Some Turkish Local Pop, Flint and Dent Maize (Zea mays L.)

Turkish maize accessions collected from north of Turkey were investigated for agro-morphologic variation in three maize kernel types (flint, pop and dent) including 79 accessions. Eight agronomic and morphologic traits (ear length, ear kernel row number, ear height, leaf number, 1000 kernel weight, tassel length, leaf width and leaf length) were analysed by ANOVA and principal component analysis. Varieties and accessions were found significantly different for variance components which were made up high variance due to accessions. Positive correlations were found between agronomic and morphologic traits. Multivariate discriminant function analysis with eight traits revealed that first two of multivariate correlation covered 86.6%, and next 69% of total variation among accessions and the first multivariate discriminant function had high eigenvalue with 76.8% of total variance between varieties belonged to flint and pop maize accessions while the second multivariate variable belonged to flint and dent maize accessions. These multivariate variables correctly classify three maize varieties maintaining maize accessions for their various characteristics with agronomic and morphological traits.

Morphometric and Meristic Characterization of Common Carp, Cyprinus Carpio Strains Sourced from Jos, Bauchi and Ibadan, Nigeria

The study investigated the morphometric and meristic characterization of Common carp (Cyprinus carpio) sourced from Jos Bauchi and Ibadan (Nigeria). In comparing the morphometric and meristic characters one hundred and eighty (180) adult Common carp, Cyprinus carpio were used. Twenty four (24) morphometric and six (6) meristic characters were studied. Measurements of the morphometric features were taken to the nearest centimeter by means of a measuring board, measuring rule, pair of dividers for the length, while the weight was taken by means of a weighing scale (salter scale) to the nearest gram. ANOVA, multivariate technique principal component analysis (PCA) and discriminant function analysis were also applied to the transformed morphometric data to; classify the fish into one or several mutually exclusive groups. The Morphometric study indicated that seven parameters did not differ significantly (p&gt;0.05) between Jos (male and female), and Bauchi (male and Female) strains. The parameters are the body depth, caudal fin length, pectoral fin height, standard weight, pre dorsal distance, eye diameter and body weight. In the meristic count, only the dorsal fin spine did not differ significantly (p &gt;0.05) among the Jos, Bauchi, and Ibadan strains in all sexes. The study revealed that there was a genetic distance between male and female Carp sourced from Ibadan and that of Jos and Bauchi, where as male and female Carp from Jos and Bauchi showed genetic closeness.