Survival analysis is a class of statistical method aimed at studying the occurrence and timing of events of interest. The analysis is propelled by event while time is the central operator. In medicine, event may be death, relapse, in which wise, time may be time to death and time to relapse respectively. In economics, the event may be employment while time is time to employment, that is, unemployment duration. In Civil Engineering, the event may be completion of a project while time is project duration; the event may also be appearance of a crack on a building while the time istime that lapses between project completion and appearance of the crack. It is thus, a concept applicable to virtually all aspects of human endeavour where event and time to event are clearly defined. Unemployment duration study is very important as it explains changes in the labour market situation. Such a study is capable of informing policy makers about effectiveness of policies formulated to tackle unemployment in an economy. An unemployment duration study via survival analytical approach that signifies that unemployment duration has reduced significantly will naturally be pleasing to the government. A contrary result will suggest that government approach to tackling unemployment needs to me revisited. The need for such study from time to time can therefore, not be overemphasized. A large amount of efforts has gone into survival analysis research. Although most of the efforts seem to be in the medical sciences, some applications have been made in other areas also. Leo and Go (1977) reviewed the common statistical technique employed to analyze survival data in public research; Tatsiramos (2006)studied the effect of unemployment insurance on unemployment duration and the subsequent employment stability using mixed proportional hazard model; Blanchard and Diamond (2008) examined unemployment duration dependence and suggested that this affects both the matching and the wage function. Daniela-Emanuela and Cirnu (2014) studied unemployment duration in Romania using survival methods; Novella and Duvivier (2015) examined the relationship between unemployment duration and education in Belgium;Oujezsky, Horvath, and Skorpil (2016) applied survival methods to analyze botnet command and control traffic using Kaplan-Meier estimator. Echeburua, Gomez and Freixa (2017) examined schizophrenia patients with gambling disorder using Cox survival model. These research objectives are to apply Kaplan-Meier survival model to unemployment duration data and to also compare the unemployment duration experience of males and females. The remaining part of the article is organized as follows: Section 2 presents Methodology; Section 3 presents Results and Discussion while Section 4 concludes the article and recommends.

The focus of this article was to fit a hierarchical loglinear model to data on academic performance. Data on gender, university attended for B.Sc., B.Sc. and M.Sc. grades of 116 M.Sc. graduates were collected from Department of Statistics, University of Ilorin, Ilorin, Nigeria. Model estimation was carried out by iterative proportional fitting method. Likelihood ratio statistic was utilized for goodness of fit test. The final model generating class contained University, Gender, and B.Sc.*M.Sc., and in harmony with the principle of hierarchy, also contained B.Sc. and M.Sc. grades. Significant interaction was found between B.Sc. and M.Sc. grades only. All other 2-factor and all 3-factor interactions were found not to be significant. Thus, M.Sc. grade was neither associated with gender and university nor with their interaction. The likelihood ratio statistic with p-value of 0.722 suggested model adequacy. The study concluded that only B.Sc. grade was associated with M.Sc. grade obtained by students on graduation. The need to extend study to other departments in the University was recommended.

The order of bias of the fixed effects gompertz model is studied, using Monte Carlo approach. Performance criteria are bias and root mean squared errors. For fixed N, bias is found to decrease steadily between T=5 and T=20 but exhibits a mixture of increase and decline afterwards. At each value of T involved, bias steadily decreases with increased value of N. Bias is found to be at most 123%, due to the combination of minimum of each of N and T involved. Decrease in order of bias is found to be more definite with increased N at fixed T than with increased T at fixed N.

This article compared single to combined forecasts of wind run using artificial neural networks, decomposition, Holt-Winters’ and SARIMA models. The artificial neural networks utilized the feedback framework while decomposition and Holt-Winters’ approaches utilized their multiplicative versions. Holt-Winters’ performed best of single models but ranked fourth, of all fifteen models (single and combined). The combination of decomposition and Holt-Winters’ models ranked best of all two-model combinations and second of all models. Combination of decomposition, Holt-Winters’ and SARIMA performed best of three-model combinations and ranked first, of all models. The only combination of four models ranked third of all models. The accuracy of single forecast should not be underestimated as a single model (Holt-Winters’) outperformed eleven combined models. It is therefore, evident that inclusion of additional model forecast does not necessarily improve combined forecast accuracy. In any modeling situation, single and combined forecasts should be allowed to compete.