Theses
Browse
Browsing Theses by Subject "Agricultural Statistics and Informatics"
Now showing 1 - 6 of 6
Results Per Page
Sort Options
ThesisItem Open Access DEVELOPMENT OF ZERO-INFLATED COUNT TIME SERIES MODELS FOR FORECASTING YELLOW STEM BORER (Scirpophaga incertulas) POPULATIONS OF RICE(PROFFESSOR JAYASHANKAR TELANGANA STATE AGRICULTURAL UNIVERSITY, 2023-01-28) Nanda Kumar Reddy, B.; Santosha RathodAim of this study was to develop the reliable statistical model to forecast the yellow stem borer pest data. Count time series modelling is a popular statistical approach in which auto-correlated discrete count observations are considered as dependent variables, and the observations are assumed to be derived from Poisson or negative Binomial distributions. Crop pest modelling is one of the major areas of count time series modelling wherein daily or weekly counts of insects (pests) are considered as dependent variables of interest. As the pest population does not occur regularly on a daily basis there used to be many zeros in weekly count data under such conditions the classical count time series models may not yield better results alternatively zero excess count models can be used to model the data with excess zeros. In this study, the rice Yellow Stem Borer (YSB) populations recorded using a light trap with an incandescent bulb along with weather parameters of major centres generated under All India Coordinated Rice Improvement Project (AICRIP) from 2013-2021 were considered. The residuals of the fitted models namely, Integer-valued Generalized Autoregressive Conditional Heteroscedastic (INGARCH), Zero Inflated Poisson Autoregressive (ZIPAR), Zero Negative Binomial Autoregressive (ZINBAR) models were found significant for most of the centres. Therefore, to correct the classical model a two stage count time series methodology is proposed in this study. In the first stage, the YSB populations are modelled using the count time series models and diagnostically tested using the multivariate Box-Pierce test. If this test is not significant, the procedure ends. In the second stage, when the residuals are significant, the BDS test is used to test for the nonlinearity of the residuals. If the residuals are found to be significant, the ANN model is fitted to the residuals to obtain the predicted values. Finally, the ANN fitted residuals are combined with the count time series fitted values to obtain the final YSB population forecast. The proposed two stage methodology performed better thanclassical count time series models in both training and testing data sets, further, two stage zero inflated models outperformed all models which as it provides lowest root mean square error values. The proposed methodology for an efficient early warning system to predict the YSB population could greatly contribute to the sustainable site-specific pest management strategies to avoid significant riceyield losses.ThesisItem Open Access RICE YIELD GAPS IN SELECTED DISTRICTS OF TELANGANA: A STATISTICAL PERSPECTIVE(PROFESSOR JAYASHANKAR TELANGANA STATE AGRICULTURAL UNIVERSITY, 2021-01-07) BHANU SREE, D; SRINIVASA CHARY, DA Study on “RICE YIELD GAPS IN SELECTED DISTRICTS OF TELANGANA: A STATISTICAL PERSPECTIVE” was carried out at Karimnagar, Medak and Mahbubnagar districts of Telangana state for 30 years (1992 to 2021). The main aim of this study was to simulate the potential yields of rice in selected districts using crop simulation models like DSSAT and APSIM and to quantify the yield gaps. The weather and soil information for this analysis was collected from NASA power website and ISRIC website respectively. The potential yields simulated by DSSAT and APSIM were in the range of 8533-7881 kg/ha and 10241- 9208 kg/ha respectively. In this study it was observed that DSSAT model performed better then APSIM as DSSAT model considers all the weather parameters but APSIM rely mostly on the rainfall during simulation. Attainable yield data was collected from the ICAR-IIRR reports and PJTSAU Vyavasaya panchangam. Average farmers yield for 30 years was collected from DES (Directorate of Economics and Statistics), Telangana. Rice yield gaps were quantified in the three selected districts. There was no much variation in the yield gap I and we have noticed negative trends in yield gap II and total yield gaps. It has been observed that, in Telangana the production of rice has increased over the years, still there are yield gaps in rice. These gaps have to be filled so that productivity will be boosted in the study area.ThesisItem Open Access SHORT AND LONG TERM PROJECTIONS OF AREA, PRODUCTION AND PRODUCTIVITY OF GROUNDNUT IN ANDHRA PRADESH(ANDHRA PRADESH AGRICULTURAL UNIVERSITY HYDERABAD, 1991) SEETHA RAMI REDDY, S; KRISHNA KANTH, G.The present study entitled "Short and long term projections of area, production and productivity of groundnut in Andhra Pradesh" has been attempted to measure the growth rates and to estimate short term projections from 1986-87 to 1994-95 and long term projections from 1995-96 to 1999-2000, with a view to provide certain guidelines for policy implications which would bring balanced agricultural development. The investigation was carried out for all districts, regions and Andhra Pradesh state as a whole. An attempt had also been made to assess the growth in area, production and productivity of groundnut. Five formulae viz., three linear and two multiple regression models were tried . Formulae having maximum R2 values were used for projection purpose. Out of these exponential function was used for long term projections and the multiple regression model involving standard deviations of groundnut prices as one variable was used for short term projections. for the 1985-86. coastal The secondary data was collected and analysed period of 30 years covering from 1956-57 to Almost all the Rayalaseema districts and some districts showed positive growth in area, production and productivity but negative in most of the Telangana districts. Short term projections of area, production and productivity declined in most of the districts but long term projections showed increasing trendsThesisItem Open Access STABILITY ANALYSIS OF THE HYBRIDS OF RICE AND THE VARIETIES OF GROUNDNUT EVOLVED BY ACHARYA N.G. RANGA AGRICULTURAL UNIVERSITY(ACHARYA N.G. RANGA AGRICULTURAL UNIVERSITY, RAJENDRANAGAR, HYDERABAD, 1998) MURALI KRISHNA RAJU, B; NAGESWARA RAO, GThe present investigation aimed at studying the mean perfrv-J-irl.‘ and stability of some prereleased hybrids of rice alongwith commo:variety and some released and pre released varieties of groundnut ; by Acharya N.G. Ranga Agricultural University. The data for the stu;;. given by Eberhart and Russell (1966) and Perkins and Jinks (196E) __ used to evaluate the mean performance and stability for the genotypes .V under different environments. AMMI (Additive main effects and multipgaj ‘3 interaction) model was carried out to study the genotypes x envirr,;»l-,Vl.:;.:. interaction. Evaluation of mean performance of different rice genotypes Tina-3:4 that MTU HR—2034 was superior among all the test genotypes follOi.-..;;;-; MTU FIR-2037 followed by common check variety MTU—2067. The 1-1,: yield was recorded by MTU 1—1R—2024. Study on stability of different rice genotypes tested over? environments revealed that the hybrids MTU HR-2035 and MTU Eli-gin were stable. (23 ( II Evaluation of mean performance of different groundnut varjiw showed that in k/ICII"if-l990, the genotype K—l34 topped among all tl.:5 i2=t genotypes followed by lCGS—ll followed by lCG (FDRS)-4. The lowest yield was recorded by TCGS—l. In khan/L199] also K—l34 registered highest yield and lCG(FDRS)-10 recorded the lowest yield. Studies on stability of different groundnut genotypes tested over eight locations during kharijll990 revealed that the genotypes K- 134 and SVGS—l were stable and TCGS—3 was having good adaptability but with low mean yield. The genotypes JL—24 and SVGS—l were having good stability with high mean yields among the IS genotypes tested over 12 locations during kharI'f—l99l. Here TCGS—l was also stable with mean yield nearer to grand mean. For all the three studies (hybrid rice /r/)a/‘[f—1995, groundnut kl'zarif-IQQO ' and groundnut klzarIf-199l) ANOVA revealed significant G x E interaction. By partitioning the G x E interaction, both linear and non linear components were found to be significant. Moreover the non linear component was higher in magnitude than the linear component Evaluation of rice hybrids over five locations during k/zarifll‘JQS using AMMl model showed that the hybrids MTU HR—2028, MTU HR—ZOZQ, MTU FIR-2032, MTU HR-2018 and MTU HR—2033 were differing with the genotypes MTU HR—2037, MTU HR-2034 and MTU-2067 for main effects. The hybrids MTU HR-2026, MTU HR—ZOZS, MTU HR—2032, MTU HR-2018 and MTU HR—2033 differed with the hybrids MTU [TR—2034, MTU HR-2036 and MTU HR-2037 both for main and interaction effects. The environment E2 and the hybrids MTU HR-2024 and MTU ELK—2029 had very small interaction effects. The environments E4 and E5 had positive interaction with the genotypes MTU HR-2026, MTU FIR-2028, MTU HR-2032, MTU HR—2033, MTU HR—2018 and common check MTU-2067 and negative interaction with other hybrids, The interaction becomes vice versa for the environments E1 and E3. Evaluation of groundnut genotypes over eight environments during klzarif—l990 showed that the genotypes TMV-B. TCGS-l, SVGS-l and TPT—2 were differing with the genotypes Girnar—l, lCG(FDRS)-4 and [CG (FDRS)—l0 for their interaction effects, The environment E6 and the genotype TPT—l were having small interaction effects. The environments E4, E7 and E8 were having positive interaction with the genotypes TPT—l, TPT—Z, K—134, SVGS-l, TCGS-l, TCGS-3, JL—24 and TMV—2 and negative interaction with other genotypes. The interaction becomes vice versa for E1, E2, E3 and E5. Evaluation of groundnut genotypes over 12 locations during klrarif1991 showed that the genotypes lCG (FDRSWL lCG (FDRS)—10 differed with Girnar-l, ICGS-‘l‘l 811d JL-24 for their interaction effects. The genotypes TPT~1, TPT-2, ICGS'3, SVGS-l, ICGS—ll and JL—24 differed among themselves neither for main effects nor for interaction effects. The environments E2 and E6 and the genotype Kadiri—3 had very less interaction effects The environments E7, E8, E9, E10 and E12 had positive interaction with the genotypes lCG (FDRS)-4, ICG(FDRS)—|O, K—134, lCGS—l and lCGV-86699 and negative interaction with others. The interaction becomes vice versa for the remaining environments. Comparision of three models revealed that the AMMI model is accurate in partitioning the G x E interaction and it is facilitating the yield estimation. Regarding the evaluation of stability Eberhart and Russell (1966) and Perkins and Jinks (1968) models were good.ThesisItem Open Access A STUDY ON THE ASSESSMENT OF TRAINING NEEDS AND JOB PERFORMANCE OF ICDS SUPERVISORS WORKING IN TELANGANA REGION OF ANDHRA PRADESH(ANDHRA PRADESH AGRICULTURAL UNIVERSITY RAJENDRANAGAR, HYDERABAD, 1992) VIJAYALAKSHMI, V; NARASIMHA REDDY, MThe supervisors occupy a key position in the hierarchial structure of !CDS scheme a-nd act as the most important catalysts for delivering the various services envisaged under the scheme. The achievement of this programme with regard to child development is greatly influenced by the job performance of these supervisors. Training is another major input which upgrades the job performance of these functionariies. As the supervisors attitude to training in conditioned by the. ir performance in job, an assessment of both these aspects can help the administrators of !CDS take corrective measures and ensure successful implementation of the programme. The present study makes an attempt to assess both training needs and job performance of !CDS supervisors working in Telengana region of Andhra Pradesh by following ex-post-facto research design. The training needs and job performance of supervisors was assessed by a combination of self, superior and subordinate ratings. The total sample comprised of 45 supervisors, 9 CDPOs (superiors) and 90 AWWs (subordinates). The data was collected with the help of an interview schedule developed for the study. Appropriate statistical tests were used to analyse the collected data. Following .findings emerged out of the study: Majority of the supervisors (53% and 76%) belonged to medium category with respect to their knowledge and skill training needs. Sixty s~ven per cent of supervisors performed their jobs to an average level. Significant associations were found among the supervisors, CDPOs and AWWs in assessment of training needs and job performance of supervisors. Training was perceived needful in certain aspects of the training areas, preschool education, nutrition and health, communiity involvement and community education and management. Job areas like service delivery, evaluation and helping AWWs were found to b~ comparitively performed at a lower level by the supervisors. While age, training undergone · and job rience showed a negative relationship, education a positive relationship with both knowledge and training needs of supervisors. expeshowed skill The variables, age, job experience, persistence disposition, and extension climate showed a positive relationshiip with job performance of supervisors. Education received by the supervisors was found to be negatively related with their job performance. Training undergone by the supervisors, their aspirations and attitude towards work showed a positive increase in the performance of their job. Suggestions given by the three categorieis of respondents to satisfy the training needs of supervisors include involvement of locals in the training programmes of supervisors and organisation of joint trainings for the functionariies of !CDS and officials from alli : ed departments. The present study emphasises the need for conducting refresher training programmes for the supervisors more frequently than before. It also suggests for the recruitment of Home science/Social work graduates as supervisors of !CDS programme to increase the output of work. In view of the above findings, the administrators and poliicy makers of !CDS programme need to take appropriate measures to organise need based training programmes for supervisors and improve their job performance by imparting skills in interpersonal relations, communication and supportive supervision and motivating them to perform better by creating more avenues through awards and rewards.ThesisItem Open Access TRENDS IN AREA,PRODUCTION AND PRODUCTIVITY OF MAIZE—AN INTER—DISTRICT ANALYSIS IN TELANGANA REGION OF ANDHRA PRADESH(Professor Jayashankar Telangana State Agricultural University, 2001) SURESHBABU, P.; KRISHNAKANTH, G.The present study entitled “Trends in area, production andproductivity ofmaize —Aninter-district analysis in Telangana region of AndhraPradesh”hasbeenattempted‘rtoexaminetheinter-districtdisparities ofarea,productionandproductivityofmaizeandshorttermprojectionsfrom 1999-2000to2008-2009andlongtermprojectionsfrom2009-2010to2013-. 2014,withaviewtoprovidecertainguidelinesforpolicyimplicationswhich wouldbringbalancedagriculturaldevelopment. The investigation was carried out for all the districts of TelanganaregionandforthestateofAndhraPradeshasawhole. Anattempt hadalsobeenmadetoassessthegrowthinarea,productionandproductivity ofmaize. Sevenformulaeviz.,fivelinearandtwomultipleregressionmodels wereattempted. Outofthesesevenmodels, fivemodelswereusedforshort term projections. Formulaehaving maximum R2 values were used for projectionpurpose. Outofthesemodels,exponentialfunctionwasusedfor longtermprojectionsandthemultipleregressionmodelinvolvingstandard deviationsofmaizepricesasonevariablewasusedforshorttermprojections asithashighR2value. Thesecondarydatawascollectedandanalysedfortheperiodof44 years coveringfrom 1955-56 to 1998-99. Almost all the districts of TelanganaregionofAndhraPradeshandalsothestateofAndhraPradeshasa wholeshowedpositivegrowthinarea,productionandproductivity. Shorttermprojectionsofarea,productionandproductivityofmaize in most ofthe diStricts had shown decreasing trend because they dependsuponlaggedvaluesandpricevariationsbutlongtermprojections showedanincreasingtendency.