Análises estatísticas com abordagem na gestão pública : um caso de responsabilidade fiscal dos restos a pagar

• Ano de defesa: 2019
• Autor(a) principal: CAVALCANTI, Rodrigo Luiz Costa
• Orientador(a): CUNHA FILHO, Moacyr
• Banca de defesa: CUNHA FILHO, Moacyr, MOREIRA, Guilherme Rocha, SILVA, Alexandre Stamford da
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal Rural de Pernambuco
• Programa de Pós-Graduação: Programa de Pós-Graduação em Biometria e Estatística Aplicada
• Departamento: Departamento de Estatística e Informática
• País: Brasil
• Palavras-chave em Português: Análise estatística; Orçamento público; Regressão segmentada; Restos a pagar
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::PROBABILIDADE E ESTATISTICA
• Link de acesso: http://www.tede2.ufrpe.br:8080/tede2/handle/tede2/8160

The concern about the fiscal responsibility has drowned attention to the execution of the remaining balances. Due to their legal and accounting characteristics, the remaining balances have their financial and budgetary effect at different times. Hence, to reduce uncertainty about the fiscal result, it is necessary to know their behavior. The objective of this dissertation was to find out the optimal period of time when the remaining balances should be kept because once the cancellation is late and the remaining balances are still available, this situation creates unnecessary uncertainty for the government’s fiscal result. Moreover, if the cancellation occurs in a period of time before its probable liquidation, it will generate budget losses. Different methods were used to analyze that situation: linear, segmented and non-linear regressions (growth models). Tests were performed using several data transformations, where the variable of interest was the proportion of the quantity already paid, considering the financial value of the remaining balances available in relation to their period of time classified as remaining balances. The segmented regressions showed positive results for trend-changing data. By using an approach that takes in account both simple and segmented regressions of two straight lines, it was possible to estimate the behavior of the remaining balances in all groups of variables. It was noticed that the behavior of the payments of the capital commitments are significantly different from the behavior of the financial resources available for the universities and the institutes’ expenses which, in turn, are also different from the other expenses of the Ministry of Education (MEC) and its auxiliary bodies. The figures indicate that, if the balances of the three groups were to be canceled in the periods of time considered for this study, the yearly amount of remaining balances would decrease 5.13 billion reals – not considering the estimated use of 726 million reals. It is to say that – in the studied periods of time, considering the available amount of resources – only 14.1% will be paid versus the 85.9% of the remaining balance that only generates unnecessary uncertainty in the fiscal result. It is of paramount importance that the norms that have impacts on the budget execution – such as the Decree 93.872/86 that limits the validity of the remaining balances up to 18 months – be accompanied by a study of possible impacts and expected results. The current omission of the remaining balance execution decree in terms of the expense groups will lead to a loss of capital resources from the yearly budget that could be executed and unnecessary costing commitments.