Nonparametric Methods

This paper proposes a nonparametric test in order to establish the level of accuracy of the foreign trade statistics of 17 Latin American countries when contrasted with the trade statistics of the main partners in 1925. The Wilcoxon Matched-Pairs Ranks test is used to determine whether the differences between the data registered by exporters and importers are meaningful, and if so, whether the differences are systematic in any direction. The paper tests for the reliability of the data registered for two homogeneous products, petroleum and coal, both in volume and value. The conclusion of the several exercises performed is that we cannot accept the existence of statistically significant differences between the data provided by the exporters and the registered by the importing countries in most cases. The qualitative historiography of Latin American describes its foreign trade statistics as mostly unusable. Our quantitative results contest this view.

This paper investigates the evolution of firm distributions for entrant manufacturing firms in Canada using functional principal components analysis. This method is nonparametric. It describes the dynamics of marginal densities and illustrates the efficacy of functional principal components to analyze firm distributions. We modify the method proposed in Kneip and Utikal (2001, JASA) to allow for the inclusion of qualitative information in the form of discrete variables such as industry and region. The results indicate that there are substantial differences in the dynamics of firm size, labour productivity, and leverage distributions between two entry cohorts. We also utilize a bootstrap test for the null hypothesis that the distributions are time-invariant. The null hypothesis is rejected for all variables and both cohorts when ignoring the qualitative information. However when accounting for industry and regional effects, the null is not rejected for size and leverage, while rejection occurs for labour productivity in both cohorts. These results show the importance of including qualitative information to account for potential heterogeneity when applying functional principal component analysis.

Parametric tests make certain conditions about the parameters of population. The most important assumptions of parametric tests are 1) the data must be independent, 2) the data must be normally distributed, 3) the populations must have the same variance, 4) the measurement must be in an interval or ratio scale and 5) there must be a linear relationship between the data. In general, parametric tests are more powerful than nonparametric tests because these

Climate change causes changes in the flow of rivers by causing changes in temperature and precipitation. Therefore, river flow simulation is important as a prerequisite for some environmental and engineering issues. In the current research, the effect of climate change on the Mahabad's river flow in the future periods (2045-2026) was predicted using machine learning models. First, two input scenarios were compiled, in which the first scenario included temperature and precipitation parameters and the second scenario included temperature, precipitation, and flow parameters one month ago. In the following, the performance of two ANN and ANN-PSO models in estimating the flow rate in the base period (1992-2014) was compared to select the best scenario and the best model for predicting the flow in the future period under the three scenarios SSP1.26, SSP2.45 and SSP5.85 of the CMIP6. The results of the error evaluation criteria showed that the ANN-PSO model makes the best estimation of the river flow using the second scenario and with the criteria (NSE=0.77, RMSE=6.4 MCM, MAE=3.4 MCM for the test data) and it was chosen to predict the flow in the future period (2026-2045). The results of investigating the effect of climate change on each of the meteorological parameters showed that climate change causes an increase in temperature and creates a fluctuating pattern in precipitation. The results of the climate change survey on flow showed that under the SSP1.26 scenario, there will not be much changes in flow in almost months, but in the SSP2.45 and SSP585 scenarios, there will be an increase in the discharge in December, and in May and April, the greatest decrease in discharge will be (16.50 MCM) and (13.33 MCM) respectively.

Copula is a method that examines the relationship pattern between variables. Copula is characterized as a nonparametric method with several benefits, i.e., it is independent of the assumption of the distribution, accommodates nonlinear relationship among variables, and is convenient in building joint distribution. This study investigates the relationship and prediction analysis using the copula approach. The method is applied to the monthly data of oil palm production and the amount of rainfall. The results show that the model of Frank Copula is the best model for rainfall and oil palm production relationship.

We describe and experimentally investigate a method to construct forecasting algorithms for stationary and ergodic processes based on universal measures (or so-called universal data compressors). Using some geophysical and economical time series as examples, we show that the precision of thus obtained predictions is higher than that of known methods.

We address the issue of building consistent specification tests in econometric models defined through multiple conditional moment restrictions. In this aim, we extend the two methodologies developed for testing the parametric specification of a regression function to testing general conditional moment restrictions. Two classes of tests are proposed, which can be both interpreted as M-tests based on integrated conditional moment restrictions. The first class depends upon nonparametric functions that are estimated by kernel smoothers. The second type of test is built as a functional of a marked empirical process. For both tests, a simulation procedure for obtaining critical values is shown to be asymptotically valid. Comparison of finite sample performances of the tests are investigated by means of several Monte-Carlo experiments.

In this study, spatio-temporal variations of evapotranspiration (ET) in the southern part of Aras River basin were investigated. For this purpose, FLDAS Noah gridded ET data with a horizontal resolution of 0.1*0.1 degrees for 38 years (1982-2019) were used. After validating the data, first the average annual ET values for the basin were determined. Then the monthly and seasonal distribution of ET was analyzed spatially. Next, the changes and anomalies of ET in the basin were evaluated yearly. Then, the spatial distribution of the occurrence of ET was investigated by considering the absolute thresholds of 50, 80, 100, and 120 mm for the basin. The results showed that annual ET is higher in the east of the basin than in the west. On a seasonal scale, spring and summer have the highest ET values. On a monthly scale, May, June, April and March have the highest ET values. Autumn and winter months have the lowest average values of ET. During the study period, the Aras River basin has experienced three specific periods of ET changes. In the eastern and western parts of the basin, despite similar behavior in the second and third periods, a prominent difference was observed in the first period. The findings also indicate the existence of a positive anomaly after 2002 in the entire basin, the highest values of which occurred in the west of the basin in 2018. Examining the frequency of occurrence of absolute thresholds of ET on the basin, shows the high frequency of occurrence of ET in all thresholds in the east of the basin. A 4-decade study of ET values in the Aras River basin has shown an increase in ET values in the last two decades in the entire basin, which can consider it to be a result of global warming.

This paper proposes a new approach to multi-object tracking by semantic topic discovery. We dynamically cluster frame-by-frame detections and treat objects as topics, allowing the application of the Dirichlet process mixture model. The tracking problem is cast as a topic-discovery task, where the video sequence is treated analogously to a document. It addresses tracking issues such as object exclusivity constraints as well as tracking management without the need for heuristic thresholds. Variation of object appearance is modeled as the dynamics of word co-occurrence and handled by updating the cluster parameters across the sequence in the dynamical clustering procedure. We develop two kinds of visual representation based on super-pixel and deformable part model and integrate them into the model of automatic topic discovery for tracking rigid and non-rigid objects, respectively. In experiments on public data sets, we demonstrate the effectiveness of the proposed algorithm.

This paper proposes a new approach to multi-object tracking by semantic topic discovery. We dynamically cluster frame-by-frame detections and treat objects as topics, allowing the application of the Dirichlet Process Mixture Model (DPMM). The tracking problem is cast as a topic-discovery task where the video sequence is treated analogously to a document. This formulation addresses tracking issues such as object exclusivity constraints as well as cannot-link constraints which are integrated without the need for heuristic thresholds. The video is temporally segmented into epochs to model the dynamics of word (superpixel) co-occurrences and to model the temporal damping effect. In experiments on public data sets we demonstrate the effectiveness of the proposed algorithm.

This paper proposes a new approach to multi-object tracking by semantic topic discovery. We dynamically cluster frame-by-frame detections and treat objects as topics, allowing the application of the Dirichlet process mixture model. The tracking problem is cast as a topic-discovery task, where the video sequence is treated analogously to a document. It addresses tracking issues such as object exclusivity constraints as well as tracking management without the need for heuristic thresholds. Variation of object appearance is modeled as the dynamics of word co-occurrence and handled by updating the cluster parameters across the sequence in the dynamical clustering procedure. We develop two kinds of visual representation based on super-pixel and deformable part model and integrate them into the model of automatic topic discovery for tracking rigid and non-rigid objects, respectively. In experiments on public data sets, we demonstrate the effectiveness of the proposed algorithm.

In this paper we report on a number of speaker identification experiments that assume a phonetic-oriented segmentation scheme exists such as to motivate the extraction of psychoacoustically-motivated phase and pitch related features. MFCC features are also considered for benchmarking. An emphasis is given to an innovative shift-invariant phase-related feature that is closely linked to the glottal source. A very simple statistical modeling is proposed and adapted in order to highlight the relative discrimination capabilities of different feature types. Results are presented for individual features and a discussion is also developed regarding possibilities of fusing features at the speaker modeling stage, or fusing distances at the speaker identification stage. Ferreira, A. First Experiments on Speaker Identification Combining a New Shift-invariant Phase-related Feature (NRD), MFCCs and F0 Information.

The great majority of current voice technology applications relies on acoustic features characterizing the vocal tract response, such as the widely used MFCC of LPC parameters. Nonetheless, the airflow passing through the vocal folds, and called glottal flow, is expected to exhibit a relevant complementarity. Unfortunately, glottal analysis from speech recordings requires specific and more complex processing operations, which explains why it has been generally avoided. This review gives a general overview of techniques which have been designed for glottal source processing. Starting from fundamental analysis tools of pitch tracking, glottal closure instant detection, glottal flow estimation and modelling, this paper then highlights how these solutions can be properly integrated within various voice technology applications.

Given an iid sample of a distribution supported on a smooth manifold M ⊂ R d , which is assumed to be absolutely continuous w.r.t the Hausdorff measure inherited from the ambient space, we tackle the problem of the estimation of the level sets of the density f. A consistent estimator in both Hausdorff distance and distance in measure is proposed. The estimator is the level set of the kernel-based estimator of the density f. We prove that the kernel-based density estimator converges uniformly to the unknown density f , the consistency of the level set and the consistency of the boundary of the level set estimator. The performance of our proposal is illustrated through some simulated examples.

The paper analyzes a number of competing approaches to modeling efficiency in panel studies. The specifications considered include the fixed effects stochastic frontier, the random effects stochastic frontier, the Hausman-Taylor random effects stochastic frontier, and the random and fixed effects stochastic frontier with an AR(1) error. I have summarized the foundations and properties of estimators that have appeared elsewhere and have described the model assumptions under which each of the estimators have been developed. I discuss parametric and nonparametric treatments of time varying efficiency including the Battese-Coelli estimator and linear programming approaches to efficiency measurement. Monte Carlo simulation is used to compare the various estimators and to assess their relative performances under a variety of misspecified settings. A brief illustration of the estimators is conducted using U. S. banking data.

The paper analyzes a number of competing approaches to modeling efficiency in panel studies. The specifications considered include the fixed effects stochastic frontier, the random effects stochastic frontier, the Hausman-Taylor random effects stochastic frontier, and the random and fixed effects stochastic frontier with an AR(1) error. I have summarized the foundations and properties of estimators that have appeared elsewhere and have described the model assumptions under which each of the estimators have been developed. I discuss parametric and nonparametric treatments of time varying efficiency including the Battese-Coelli estimator and linear programming approaches to efficiency measurement. Monte Carlo simulation is used to compare the various estimators and to assess their relative performances under a variety of misspecified settings. A brief illustration of the estimators is conducted using U. S. banking data.

The paper describes a nonparametric analog of Cohen's d, Q. It is established that a confidence interval for Q can be computed via a method for computing a confidence interval for the median of D = X1 − X2, which in turn is related to making inferences about P(X1 < X2).

The paper constructs environmental efficiency indexes for a sample consisting of high-and low-income countries using nonparametric production frontier techniques and then establishes an environmental Kuznets relationship for environmental efficiency by Nadaraya-Watson kernel estimation methodology.

1-Introduction
Climate change is an essential issue of the current era (Jiang et al., 2019: 2). Impacts on water resources are considered an effect of climate change (Motamed Vaziri et al., 2020: 102). Understanding climatic changes, their behavior in future periods, and their effects in different fields, particularly in water resources, is specifically important in macro and strategic planning (Haji Mohammadi, 2018: 144). The volume of surface runoff is one of the main components in sustainable development; therefore, predicting the level and trend of its changes is important in the issue of water resources management (Goodarzi et al., 2015, 176). Due to the importance and necessity of the issue, therefore, the effects of climate change on surface water fluctuations were frequently studied in the Aras basin, northwest of Iran. Climate change and its effects on the basin runoff were investigated in several studies (Fatehi and Shahoui, 2020: 294; Zahbioun et al., 2011: 43). The use of general atmospheric models HadCm3 and LARS-WG on the microscale and using the SWAT method have been of interest in evaluating the climate change effect on the basin hydrology. In a study, Babaian et al. (2015: 907) observed climate change effects on water resource behavior in the basin. They reported that precipitation would decrease and temperature would increase in the basin by climate change effects on the hydro-climatic variables in part of the basin of the important Darghaz River. Moreover, Jahanbakhsh et al (2016: 107) investigated the climate change effect on temperature and precipitation in a study on the Shahr Chay River basin in Urmia and concluded that the precipitation in this basin would decrease by 9 mm in the coming period. Zhang et al. (2012: 2199) examined the climate change effect on water resources in North China using the SWAT model. They concluded that climate change increased blue and green water resources, and human activities did not significantly affect the change in these resources. Located in the northwest of Iran, the Aras basin is a common boundary basin with Turkey, Azerbaijan, and Armenia. In terms of the political divisions of Iran, it includes parts of the three provinces, West Azarbaijan, East Azarbaijan, and Ardabil. With an area of 39,534 km2, the basin is geographically located between 44° 1′ 42" to 48° 42′ 33" E and 37° 46′ 10" to 39° 47′ 7" N (Hafezparast, 2015: 63).
2-Methodology
The Aras River basin forms the northernmost hydrological area of Iran between 38° and 40° northern latitudes. From a macro-scale climatology point of view, this basin features the characteristics of the temperate regions of the earth's middle latitudes (Talabi, 2019: 2004).
1.2 Climate simulation and downscaling of data
The future climate was simulated using the statistical data of seven selected synoptic meteorological stations in the Aras basin in the 1985-2014 period. In this research, the output of the Hadcm3 model was extracted from the AOGCM model subset related to the fifth assessment report in 2021-2050 and 1985-2014 as the future and base periods, respectively, under the RCP8.5 emission scenario. In previous studies comparing the efficiency of atmospheric general circulation models, Hadley Center models, especially Hadcm3, are known to be appropriate for fitting temperature and precipitation in Iran and have the closest results to observational data compared to other models.
2.2 Introduction of the SWAT model
Developed by the United States Agricultural Research Service, SWAT is a comprehensive and complete model on the basin scale to predict the effect of different management methods on flow, sediment, nutrients, and chemical balance in basins with different soil, land use, and management conditions for long periods (Nich et al., 2002: 88). It is a time-continuous, semi-distributive, physically based hydrologic model developed by USDA-ARS (Arnold et al., 1998: 73).
3-Results and Discussion
1.3 Downscaling and simulation data generation
Simulated data were generated for the future period (2021-2050) after choosing the Hadcm3 climate model and determining the RCP8.5 scenario. Then, the model outputs for each climate change were averaged monthly to compare simulated and observational data.
2.3 Validation and calibration of the prediction model of climatic parameters
Based on the statistical evaluation criteria, namely root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE) coefficient, bias coefficient, and coefficient of determination (R2) of base period climatic data and observations with simulation data, the RMSE value 
is higher for precipitation, which can be attributed to the nature of the precipitation parameter. The error rate of the maximum, minimum, and average temperature data is more than 0.8, indicating the minimum error in the predicted data. The correlation coefficient of the data is close to 1, suggesting the appropriate correlation of the data.
3.3 Model validation results for runoff estimation
The distribution of observed and recorded discharges of the Aras basin hydrometric station is closer to 1, indicating the clustered distribution of discharge in stations. According to map 10 of Moran's analysis in the observational condition of the Aras River basin, the high-high cluster status of the clusters is high with a positive spatial correlation at the 99% confidence level in the estuaries of the main river sub-basins. A cluster with a low-high outlier critical status is not observed in the Aras River basin.
4-Conclusions
In this research, possible changes in average climatic parameters and surface runoff were evaluated as statistical indicators that are mostly relied on in water resources management. The scientific goals include forecasting changes in temperature and precipitation in this region and evaluating climate change effects on the status of surface water resources in the basin area. The practical goals of this research include the scientific development of the conceptual rainfall-runoff model framework (SWAT), the climate change effect on the fluctuations of surface water sources, evaluating changes in surface runoff at different periods using approved global parameters, using the LARS-WG model, downscaling the studied variables, and predicting climate changes and surface water changes in the long term. The results of this research demonstrate significant changes in climatic and hydrological variables of the Aras basin in the future forecast period. The comparison of the observed and simulated climate components by this climate model in the 2021-2050 period shows that the temperature of the region increases by 0.9 °C in different months compared to the base period. Precipitation also decreases by 7.9 mm, except in rain-free months. This increase in both temperature and evapotranspiration and, consequently, the decrease in precipitation can influence the available water level, peak time, and extreme events. According to the statistical analysis of the recorded and simulated climatology and hydrology data of the studied area, climate change and temperature increase have occurred in the studied area. Furthermore, although mountainous lands still provide the discharge of existing rivers up to the hillsides of the mountains, permanent rivers cannot be supplied and refilled in plain lands. However, the effects of drought are still slightly observed on the Ares river discharge due to the topographical and geopolitical features of its basin. The results of the research indicate an increase in the temperature of the basin in the future, which can lead to an increase in evaporation and transpiration, a decrease in snowfall, and a rise in torrential rains and
floods. This can, in turn, result in a decrease in the water reserve and supply of the basin, an increase in damages caused by torrential rains, and fertile soil washing.
Keywords: Climate Change, Surface Runoff, WG-LARS, SWAT, Aras Basin, Northwest of Iran.

1-Introduction
There are different degrees of flooding, flood risks, and types of flooding on different alluvial fans, and engineering protection must be done for each unique set of alluvial fans (Jonathan et al., 2018). Flood propagation models are a useful tool for floodplain management. This ability to predict floods has been very useful in reducing the flood damage potential and preventing construction in the flood plain area (De Baldasar, 2012). HEC-RAS hydraulic model can be used to identify and investigate flood risk zoning. Pardisan town of Qom is expanding rapidly. The location of this area of Qom city in the area of flood and its vulnerability is necessary to conduct comprehensive studies. Having a slope, a favorable climate, access to transportation routes, and a smooth urban development space, it is important to pay attention to the future of this region in a logical and principled way. The purpose of this research is to answer whether the location of human phenomena in the study area is based on geographical features. To answer this question, it is necessary to evaluate the situation of Pardisan town in the Sialab region.
2-Methodology
In this research, it is considered desirable to carry out the necessary measures and mechanisms to improve the desired research environment. For this purpose, satellite images, reports, land use maps, and topography of the region are among the important sources used in this research. HEC-RAS-6 and ARC GIS software are the most important tools used in this research. The hydraulic model of HEC-RAS shows the flood reality better due to the one-dimensional and two-dimensional modeling mechanisms and the integration of these two models. Due to the lack of hydrometric stations in the study area, the SCS method has been used to analyze the required factors and parameters (Relation1).
This method is usually developed in large natural basins with different areas and is widely used by hydrologists (Safavi, 2018).
(1) Q_p=0.2083AR/t_p
(2) T_p=√(T_c )+0.6T_c
(3) Tc=0.000142L^0.8 〖(25400/CN-228.6)〗^0.7 S^(-0.5)
(4) R=〖(P-0.2S)〗^2/(P+0.8S)
(5) S=25400/CN-254
(6) 〖 P〗_6T=P_24T/1.48

3- Results and Discussion
It is necessary to add human elements to the RAS field map to determine the flood trend concerning the alluvial fan system in the geographical space, as well as the sensitivity of each to the filling and deviation of the path. By locating the human phenomena in the Pardisan region, the problems in the flow path design and the performance of bridges and dams during the passage of the 100-year flood flow are identified. Monitoring measures are also effective for unloading the sediment load and the correct design of dams by the responsible organizations in stabilizing the routes. Also, embankments and sediment reservoirs have a positive role in stabilizing the flow and flow of debris, and mismanagement conditions can also be a factor in the formation of instability in an area. It is necessary to add human elements to the RAS field map to determine the flood trend in connection with the alluvial fans flood system in the geographical space, as well as the sensitivity of each one to the filling and deviation of the path. By placing human phenomena in the environment of the background map with the 100-year return period flood, it was found that the location of construction projects in different parts of the Pardisan region, especially along the streams, has caused a large change in the sedimentation of debris. In some aspects, with the strengthening of the nearby flow, it has become difficult to predict the flow in the lower parts of the alluvial fan. There are also problems in the flow path design at some points. Flow modeling shows well that after strengthening the flow at one level, the sedimentation process in the lower parts undergoes  changes,  leading  to  turbulence  in  the  spatial  landscape  of  the  Pardisan 
waterway network. In addition, bridges and dams cause hydraulic changes in the flow path by changing the volume and speed of the flow. Regulatory measures to unload the sediment load and the correct design of dams by the responsible organizations are effective in stabilizing the routes. Embankments and sediment reservoirs play a positive role in stabilizing the flow and flow of debris. The Pardisan region's embankments are one factor that can perform a good function in different conditions. In addition, the lack of coherent organizational supervision in the location of structures and the lack of supervision of sedimentation reservoirs has caused spatial anomalies in the location and development of human phenomena in the region.
4-Conclusions
Pardisan town of Qom has a high potential for floods due to its location on the alluvial fans. For this reason, we focused on flood zoning with a return period of 100 years with the Hec-ras-6 hydraulic model. In this research, an effort was made to locate all human phenomena by measuring them in the RAS field map to provide favorable results in flood simulation. By placing the phenomena in the geographical space of Pardisan, it was found that the location operation for establishing the Pardisan settlement was not done correctly. As a result, some areas have been damaged, and flood problems, including the upper part of Pardisan and agricultural lands. In general, the urban design and the investigation and modification of the next route are not compatible with the geographical characteristics of the region, and the perspective of instability has prevailed in the geographical space of the area.
Keywords: Human phenomena, Alluvial fan, Flood, HEC-RAS, Pardisan Qom.
5-References
Dawdy, D., 1979. Flood frequency estimates on alluvial fans, Journal of Hydraulic Engineering, 105(11) 1407-1413.
Di Baldassarre, G. (2012). Floods in a changing climate: Inundation modeling (Vol.3). Cambridge University Press. Doi. Org/101017/CBO9781139088411
FEMA (2009). Guide to Flood Maps Using the Flood Map to Improve Your Understanding of Risk FEMA.
Hirabayashi, Y., & Kanae, S. (2009). The first estimate of the future global population at risk of flooding. Hydrological research letters, 3(6)9-25
Jonathan E. Fuller David P. Meyer. (2018). Case Studies of Flood Impacts on Development of Active Alluvial Fans in Central Arizona, Arizona Geological Survey Contributed Report CR-18-j107.Tucson AZ.
Safavi, H. (2009). Engineering Hydrology, Second Edition, Isfahan, Isfahan University Press. 
Wilby, R.L., Keenan, R. (2012). Adapting to flood risk under climate change. Progress in Physical Geography, 36(3), 348-378
Wohl, E.E. (2000). Inland Flood Hazards (Human, Riparian, and Aquatic Communities). Cambridge University Press, Geomorphology, 46(s 3-4)311-313.

1-Introduction
The most important parameter of water resources management among the various components of the hydrological cycle of a watershed is the river discharge; the pattern of water consumption in different sectors of industry, urban and domestic, agriculture, etc., is affected by changes in river discharge. On the other hand, soil deposition and erosion are the world's biggest environmental concerns; erosion is the primary source of sediments that pollute rivers and settle in dams. Determining the discharge rate and sediment changes is crucial in prioritizing catchment management. In recent years, sediment and river discharge changes have become an important issue worldwide. Many researches have been done to analyze the trend of climate change variables such as precipitation, temperature and hydrological components of the basin, such as sediment and runoff, as well as water quality parameters (Bayati Khatibi et al., 2014: 93 & Haji et al., 2017: 121). One of the best methods to assess the hydro-climatic conditions of catchments is to analyze the trend of change.
This method is often used to examine changes in a variable over time. Based on the presented materials, it can be concluded that analysis of river sedimentation trends and runoff time series in watershed management is very important. This article aims to analyze the trend of monthly, seasonal and annual changes in the flow and sediment of the Mordaghchai River.
2-Methodology
Mordaghchai watershed (Mordochai) is one of the main tributaries of Zarrinehrud in the eastern part of Lake Urmia. Residents of the area use this river as an important source of water. This paper investigates the trend of gradual and rapid changes in flow rate (1974-2017) and sediment load (1977-2016) of Mordaghchai River in East Azerbaijan province.

This study was carried out in Gheshlagh Amir hydrometric station on three-time scales: annual, seasonal and monthly, using non-parametric methods. To analyze the trend of changes, the Modified Mann-Kendall test was used to analyze runoff and sediment data of the Gheshlagh-Amir hydrometric station. Also, the Sen's slope estimator was used to estimate the slope of the trend line and the non-parametric Pettitt test was used to investigate the abrupt changes in the runoff and sediment time series.
3-Results and Discussion
The results show that annual, monthly and spring, summer and winter discharges significantly decrease at the level of 5%. The annual and all-season sediment load data significantly decreased by 5%. Also, there is a significant decrease in sediment load in all months except March, April and October. The results of the Pettit test show that the average annual discharge in the period after the breaking point (1998) has decreased by 45% compared to the period before the breaking point. Also, the average annual sediment load after the breaking point (1996) has decreased by about 52% compared to the previous period.
4-Conclusions
This study examines the trend of monthly, seasonal and annual changes in the flow and sediment of the Mordeghchai River in East Azerbaijan using non-parametric Modifies Mann-Kendall, Sen's slope estimator and Pettit tests. The results show that annual, monthly and spring, summer and winter discharges significantly decrease at the level of 5%. The annual and all-season sediment load data significantly decreased by 5%. Also, there is a significant decrease in sediment load in all months except March, April and October. The results of the Pettitt test show that the average annual discharge in the period after the breaking point (1998) has decreased by 45% compared to the period before the breaking point. Also, the average annual sediment load after the breaking point (1996) has decreased by about 52% compared to the previous period.
Based on this, managers must manage the water resources of the basin by adopting appropriate strategies in the future because the decrease in flow will cause severe environmental consequences in the watershed.
Keywords: Runoff, Sediment, Modified Man-Kendall, Sen’ slope estimator, Pettitt test, East Azerbaijan province.

5-References
Bayati Khatibi, M., Shahbazi, M., & Heidari, M.A., (2015). Speculations and Analysis on the Changes in Water Quality of Ahar River and its Impacts on Human Health, Hydrogeomorphology, 1(1): 93-109.
Haji, Kh., Mirzaei, Sh., Mostafazadeh, R., & Nazarnejad, H. (2018). The Monthly Changes of Surface Runoff Intensity and Concentration in the Gorgan-Roud River, Golestan Province, Hydrogeomorphology, 4(13): 121-146.

We present novel methodology to assess undergraduate students' performance. The proposed methods are based on measures of diversity and on the decomposability of quasi U-statistics to define average distances between and within groups. They have been employed as an alternative to the classic analysis of variance especially when the assumption of normality is not met. The quasi U-statistics nonparametric method can handle tests for interaction and uses jackknife to get p-values for the tests. The nonparametric method also results in smaller error variances, illustrating its robustness against model misspecication.

Building upon state-of-the-art algorithms for pedestrian detection and multi-object tracking, and inspired by sociological models of human collective behavior, we automatically detect small groups of individuals who are traveling together. These groups are discovered by bottom-up hierarchical clustering using a generalized, symmetric Hausdorff distance defined with respect to pairwise proximity and velocity. We validate our results quantitatively and qualitatively on videos of real-world pedestrian scenes. Where human-coded ground truth is available, we find substantial statistical agreement between our results and the human-perceived small group structure of the crowd. Results from our automated crowd analysis also reveal interesting patterns governing the shape of pedestrian groups. These discoveries complement current research in crowd dynamics, and may provide insights to improve evacuation planning and real-time situation awareness during public disturbances.

Given an iid sample of a distribution supported on a smooth manifold M ⊂ R d , which is assumed to be absolutely continuous w.r.t the Hausdorff measure inherited from the ambient space, we tackle the problem of the estimation of the level sets of the density f. A consistent estimator in both Hausdorff distance and distance in measure is proposed. The estimator is the level set of the kernel-based estimator of the density f. We prove that the kernel-based density estimator converges uniformly to the unknown density f , the consistency of the level set and the consistency of the boundary of the level set estimator. The performance of our proposal is illustrated through some simulated examples.

Problem statement: In many applications two or more dependent variables are observed at several values of the independent variables, such as at time points. The statistical problems are to estimate functions that model their dependences on the independent variables and to investigate relationships between these functions. Nonparametric regression model, especially smoothing splines provide powerful tools to model the functions which draw association of these variables. Approach: Penalized weighted least-squares was used to jointly estimate nonparametric functions from contemporaneously correlated data. We apply Generalized Maximum Likelihood (GML), Generalized Cross Validation (GCV) and leaving-out-one-pair Cross Validation (CV) for estimating the smoothing parameters, the weighting parameters and the correlation parameter Results: In this study we formulated the multi-response nonparametric regression model with unequal correlation of errors and give a theoretical method for both obtaining distribution of the response and estimating the nonparametric function in the model. We also estimate the smoothing parameters, the weighting parameters and the correlation parameter simultaneously by applying three methods GML, GCV and CV. Conclusion: Distribution of responses is normal. With multiple correlated responses it is better to estimate these functions jointly using the penalized weighted least-squares.

In the paper we deal with the problem of non-linear dynamic system identification in the presence of random noise. The class of considered systems is relatively general, in the sense that it is not limited to block-oriented structures such as Hammerstein or Wiener models. It is shown that the proposed algorithm can be generalized for two-stage strategy. In step 1 (non-parametric) the system is approximated by multi-dimensional regression functions for a given set of excitations, treated as representative set of points in multi-dimensional space. 'Curse of dimensionality problem' is solved by using specific (quantized or periodic) input sequences. Next, in step 2, non-parametric estimates can be plugged into least squares criterion and support model selection and estimation of system parameters. The proposed strategy allows decomposition of the identification problem, which can be of crucial meaning from the numerical point of view. The "estimation points" in step 1 are selected to ensure good task conditioning in step 2. Moreover, non-parametric procedure plays the role of data compression. We discuss the problem of selection of the scale of non-parametric model, and analyze asymptotic properties of the method. Also, the results of simple simulation are presented, to illustrate functioning of the method. Finally, the proposed method is successfully applied in Differential Scanning Calorimeter (DSC) to analyze aging processes in chalcogenide glasses.

This dissertation explores applying nonparametric and semiparametric methods to recover latent characteristics in various settings. The first chapter studies an auction market where latent effort is selected by the bidders. Recently, states have experimented with offering nonstandard contracts through procurement auctions in an attempt to reduce long-term costs on projects. With no framework in place to study the effects of these of changes, these “innovative projects” lack the rigorous analysis needed to see widespread implementation. The effects on effort, immediate costs, and potential future costs are all relevant to policy debates about the use of nonstandard contracts. This paper formally addresses the use of nonstandard warranty contracts in procurement auctions by building latent effort choice into an auction model. Taking my model to data from Michigan, I find that warranty auctions encourage roughly 30% of the lowest cost firms to undertake higher effort work in order to r...

Given the contradictory recent reports on whether there is a decline of insect pollinators, there is a clear need to develop more sophisticated monitoring systems in order to assess the quantity and variety of pollinators in a given environment. In this work, we explore an approach to the stability/plasticity dilemma to construct bumblebees tracklets, where the detector provides a stable, learned off-line, model of the object being sought, while an adaptable tracker keeps a record of both the object and the background to fill up the gaps in case of a detector miss. Through our experiments, we showed how the performance of the detector alone was enhanced with the addition of tracking.

The paper constructs environmental efficiency indexes for a sample consisting of high-and low-income countries using nonparametric production frontier techniques and then establishes an environmental Kuznets relationship for environmental efficiency by Nadaraya-Watson kernel estimation methodology.

Stream flow forecasting on a monthly time scale is essential for optimal water resources management and planning. In this paper using the predictions obtained from the ECMWF climate model, monthly stream flow forecast was made in Shahroud river Subbasin, part of Sefidrood basin northwest of Iran. To this end, using monthly precipitation forecasts from ECMWF climate model in tandem with SVR data-driven modelling, as a rainfall-runoff model, the stream flow was predicted based on the predicted precipitations. First, the results of precipitation forecast for the desired historical period and up to a 3-month forecast horizon for the study area were obtained from the Climate Data Store. Then, by using the SVR driven model, a linked Climate-Data-driven model was developed to predict the flow up to a 3-month forecast horizon. The results showed that flow forecasting based on climate forecasting models for the forecast horizon of the next month is more accurate than that of two and three mo...

A data driven structural change detection method is described and evaluated where the data are acceleration and force measurements from a mechanical structure in the form of a vehicle. By grouping the measured signals as inputs and outputs an hypothesized MIMO linear dynamic relation between the inputs and outputs is assumed. It is assumed that baseline data are available to build statistical models for the estimated frequency function of the baseline system at selected frequencies. When new data is available, the monitoring algorithm re-estimates the non-parametric frequency function and uses a test statistic based on the statistical distance to detect possible change. To generate the frequency function estimates a non-parametric MIMO frequency function estimator based on the local rational model (LRM) method is developed. A statistical analysis of the proposed test statistic shows that it has an F-distribution for data from the baseline case. The method is evaluated on simulated data from a high fidelity full scale vehicle simulation generating both baseline data and data from a structurally changed vehicle. In the evaluation, the frequency response functions were estimated by the non-parametric LRM method, the parametric ARX estimate and the non-parametric ETFE. The results show that all three methods can detect the structural change while the LRM method is more robust with respect to the selection of the hyperparameters.

This paper examines the linear relation between Shifted Delta Cepstral (SDC) features and the dynamic of prosodic features. SDC features were reported to produce superior performance to ∆ features in Language Identification and Speaker Recognition. A selection of more correlated SDC features is used in speaker verification to evaluate its robustness to channel/handset mismatch. The experiment reflects superior performance of selected SDC features regarding to ∆ features in speaker verification using speech samples from NIST 2001 Ahumada database.

Generalized Cross Validation (GCV) has been considered a popular model for choosing the complexity of statistical models, it is also well known for its optimal properties. Mallow's CP criterion (MCP) has been considered a powerful tool which is used to select smoothing parameters for spline estimates with non-Gaussian data. Most of the past works applied Generalized Cross Validation (GCV) and Mallow's CP criterion (MCP) smoothing methods to time series data, this methods over fits data in the presence of Autocorrelation error. A new Smoothing method is proposed by taking the hybrid of Generalized Cross Validation (GCV) and Mallow's CP criterion (MCP). The predicting performance of the Hybrid GCV-MCP is compared with Generalized Cross Validation (GCV) and Mallow's CP criterion (MCP) using data generated through a simulation study and real-life data on all SITC export and import price index in Nigeria between the years, 2001-2018, performed by using a program written in R and based on the predictive Mean Score Error (PMSE) criterion. Experimental results obtained show that the predictive mean square error (PMSE) of the three smoothing methods decreases as the sample size and smoothing parameters increases. The study discovered that the Hybrid GCV-MCP smoothing methods performed better than the classical GVV and MCP for both the simulated and real life data.

Parametric tests make certain conditions about the parameters of population. The most important assumptions of parametric tests are 1) the data must be independent, 2) the data must be normally distributed, 3) the populations must have the same variance, 4) the measurement must be in an interval or ratio scale and 5) there must be a linear relationship between the data. In general, parametric tests are more powerful than nonparametric tests because these

Understanding pedestrian dynamics in crowded scenes is an important problem. Given highly fragmented trajectories as input, we present a novel, fully unsupervised approach to automatically infer the semantic regions in a scene. Once the semantic regions are learned, given a tracklet of a person, our model predicts the pedestrian’s starting point and destination. The method is comprised of three steps. First, the spatial domain of the scene is quantized into hexagons and a 2D orientation distribution function (ODF) is learned for each hexagon. A Time Homogenous Markov Chain Meta-tracking method is used to automatically find the sources and sinks and later find the dominant paths in the scene. In the last step, using a 3-term based trajectory clustering method, we predict the source and sink for each pedestrian. Furthermore, we introduce a 2-step trajectory reconstruction method to infer the future behavior of each individual in the scene. Qualitative and quantitative experiments on a...

Purpose  ̶  to develop an improved mathematical model for volume determination of standardized weights by geometric measurement.Methodology  ̶  the new model eliminates an assumption considered in the current model published in the OIML R 111-1 recommendation, since it considers existing deviations from the assumed shape of the weights in the current model, specifically in the so-called knob and ring sections. These deviations might originate during the manufacturing processes of the weights. Results  ̶  an improved mathematical model for the calculation of the volume of standard weights by geometric measurement was deduced. Additionally, the model has the advantage of eliminating the risk of scratching the weights, which makes it possible to extend the use of the new model to higher accuracy classes.Limitations  ̶  the proposed model involves the possibility of making geometric measurements without surface contact of the weights, for example, with an optical comparator. Findings  ̶...

The Working Paper Series seeks to disseminate original research in economics and fi nance. All papers have been anonymously refereed. By publishing these papers, the Banco de España aims to contribute to economic analysis and, in particular, to knowledge of the Spanish economy and its international environment. The opinions and analyses in the Working Paper Series are the responsibility of the authors and, therefore, do not necessarily coincide with those of the Banco de España or the Eurosystem. The Banco de España disseminates its main reports and most of its publications via the INTERNET at the following website: http://www.bde.es. Reproduction for educational and non-commercial purposes is permitted provided that the source is acknowledged.

Speaker Recognition is a multi-disciplinary branch of biometrics that may be used for identification, verification, and classification of individual speakers, with the capability of tracking, detection, and segmentation by extension. Recently, a comprehensive book on all aspects of speaker recognition was published [1]. Therefore, here we are not concerned with details of the standard modeling which is and has been used for the recognition task. In contrast, we present a review of the most recent literature and briefly visit the latest techniques which are being deployed in the various branches of this technology.

In this paper, a novel excitation source-related feature set, viz., Teager Energy-based Mel Frequency Cepstral Coefficients (T-MFCC) is proposed for the task of spoken keyword detection. Experiments are carried out on TIMIT database for spoken keyword detection. Furthermore, state-of-the-art feature set, viz., MFCC is used as the baseline spectral feature set to represent implicitly vocal tract (i.e., system) information. The idea is to exploit the vocal-source (and its nonlinear coupling with formant) and system-related information embedded in the spoken query. Experimental results show % EER of 17.23 and 22.58 for MFCC and proposed T-MFCC features, respectively. However, the significant reduction in % EER, i.e., by 1.8 % (as compared to MFCC) is observed when evidences from T-MFCC and MFCC are combined using score-level fusion; indicating that proposed feature set captures complementary linguistic information (in the spoken keyword) than MFCC alone.

Residuals are minimized in a correlated dataset by selecting a smoothing parameter with optimum performance in the smoothing spline. The selection methods utilized in this study include Generalized Maximum Likelihood (GML), Generalized Cross-Validation (GCV), Unbiased Risk (UBR), and the Proposed Smoothing Method (PSM). The aim of this study is to compare the smoothing parameter selection ability of the four parameter selection methods for a correlated dataset with autocorrelation structure in the error term. To achieve this purpose, a Monte-Carlo simulation was conducted by utilizing program written in R-4.2.2. The performance of the parameter selection methods were evaluated using predictive Mean Squared Error (PMSE). Findings from the study indicated that GCV and GML were mostly affected by the presence of auto correlation in the residual and therefore had an asymptotically similar behavioural pattern. The estimators conformed to the asymptotic properties of the smoothing parameter selection methods considered; this is noticed in all the sample sizes and at all the smoothing parameters. The result also showed that; the most consistent and efficient among the four spline smoothing parameter selection methods considered in this study based on sample size and performance in the presence of autocorrelated residual error is the proposed smoothing method (PSM) because it does not undersmooth relative to the other smoothing method especially for small sample and medium sample size of 50 and 100.

In this paper, we elaborate on mobile phone identification from recorded speech signals. The goal is to extract intrinsic traces related to the mobile phone used to record a speech signal. Mel frequency cepstral coefficients (MFCCs) are extracted from any recorded speech signal at a frame level. The sequences of the MFCC vectors extracted from each recording device train a Gaussian Mixture Model with diagonal covariance matrices. A Gaussian supervector is derived by concatenating the mean vectors and the main diagonals of the covariance matrices that is used as a template for each device. Experiments were conducted on a database of 21 mobile phones of various models from 7 different brands. The aforementioned database, that is called MOBIPHONE, was collected by recording 10 utterances, uttered by 12 male speakers and another 12 female speakers, randomly chosen from the TIMIT database. Three commonly used classifiers were employed, such as Support Vector Machines with different kernels, a Radial Basis Functions neural network, and a Multi-Layer Perceptron. The best identification accuracy (97.6%) was obtained by the Radial Basis Functions neural network.

This paper explores the earnings gap between the self-employed and wage earners in urban Ghana. This is important in understanding the drivers of inequality, we hypothesise that heterogeneity in informal sector earnings will have implications for the income gap between self-employed individuals and wage earners. This heterogeneity in earnings will be concealed at the mean. However, the information about who benefits and who is penalized in the informal sector can be important from the policy perspective. Furthermore, this paper investigates the possibility that result from quantile regression can depend on the assumption of the estimator about the variation due to the fixed effect. The results show that at the mean, self-employed individuals enjoy a premium, however, quantile result suggests that this is driven by the individuals at the upper end of the self-employment earning distribution. At the lower quantiles, being self-employed attracts a penalty. We note that this result beco...

Generalized Cross Validation (GCV) has been considered a popular model for choosing the complexity of statistical models, it is also well known for its optimal properties. Mallow's CP criterion (MCP) has been considered a powerful tool which is used to select smoothing parameters for spline estimates with non-Gaussian data. Most of the past works applied Generalized Cross Validation (GCV) and Mallow's CP criterion (MCP) smoothing methods to time series data, this methods over fits data in the presence of Autocorrelation error. A new Smoothing method is proposed by taking the hybrid of Generalized Cross Validation (GCV) and Mallow's CP criterion (MCP). The predicting performance of the Hybrid GCV-MCP is compared with Generalized Cross Validation (GCV) and Mallow's CP criterion (MCP) using data generated through a simulation study and real-life data on all SITC export and import price index in Nigeria between the years, 2001-2018, performed by using a program written in R and based on the predictive Mean Score Error (PMSE) criterion. Experimental results obtained show that the predictive mean square error (PMSE) of the three smoothing methods decreases as the sample size and smoothing parameters increases. The study discovered that the Hybrid GCV-MCP smoothing methods performed better than the classical GVV and MCP for both the simulated and real life data.

We decompose the Pearson correlation coefficient into two components. We recommend the first component for detecting linear relationships and the second for recognizing patterns of two parallel lines, providing robust versions to outliers. The significance of the Pearson coefficient without significant components indicates a fit of three parallel lines. Thus, we reveal the unknown aspect of the Pearson coefficient that identifies a two- or three-group association other than a group, producing Type I or III  errors. Finally, we apply the proposed coefficients with permutation tests to simulated and real data. The proposed coefficients identify two- or three-parallel line correlations or weaker but significant relationships not recognized by the Pearson coefficient. In testing correlation hypotheses with normal data, the proposed methodology minimizes the total error resulting from the Person coefficient by 4%.

In this paper we examine a class of multiple-input, singleoutput (MISO) nonlinear systems of the block-oriented structure. In particular, we focus on MISO Hammerstein systems being the cascade connection of a multivariate nonlinearity with a linear dynamical subsystem. In order to alleviate an apparent curse of dimensionality occurring in the problem of estimating the nonlinearity, we propose to a semi-parametric strategy for identification of the nonlinear system. This is carried out by projecting the d−dimensional input signal onto one dimensional subset which, in turn, is mapped by a univariate nonparametric function to an internal unobserved signal of the system. Such a parsimonious representation allows us to overcome the curse of dimensionality as the accuracy of our identification algorithms is independent of d. We identify the system via the semi-parametric version of the leastsquares. The statistical accuracy of the resulting estimates is obtained via the theory of M − estimation. These theoretical findings are verified in numerous simulation studies.

Reliable quantile estimates of annual peak flow discharges (APFDs) are needed for the design and operation of major hydraulic infrastructures and for more general flood risk management and planning. In the present study, linear higher order-moments (LH-moments) and nonparametric kernel functions were applied to APFDs at 18 stream gauge stations in Punjab, Pakistan. The main purpose of this study was to evaluate the impacts of different quantile estimation methods towards water resources management and engineering applications by means of comparing the state-of-the-art approaches and their quantile estimates calculated from LH-moments and nonparametric kernel functions. The LH-moments (η = 0, 1, 2) were calculated for the three best-fitted distributions, namely, generalized logistic (GLO), generalized extreme value (GEV), and generalized Pareto (GPA), and the performances of these distributions for each level of LH-moments (η = 0, 1, 2) were compared in terms of Anderson–Darling, Kol...

Generalized Cross Validation (GCV) has been considered a popular model for choosing the complexity of statistical models, it is also well known for its optimal properties. Mallow's CP criterion (MCP) has been considered a powerful tool which is used to select smoothing parameters for spline estimates with non-Gaussian data. Most of the past works applied Generalized Cross Validation (GCV) and Mallow's CP criterion (MCP) smoothing methods to time series data, this methods over fits data in the presence of Autocorrelation error. A new Smoothing method is proposed by taking the hybrid of Generalized Cross Validation (GCV) and Mallow's CP criterion (MCP). The predicting performance of the Hybrid GCV-MCP is compared with Generalized Cross Validation (GCV) and Mallow's CP criterion (MCP) using data generated through a simulation study and real-life data on all SITC export and import price index in Nigeria between the years, 2001-2018, performed by using a program written in R and based on the predictive Mean Score Error (PMSE) criterion. Experimental results obtained show that the predictive mean square error (PMSE) of the three smoothing methods decreases as the sample size and smoothing parameters increases. The study discovered that the Hybrid GCV-MCP smoothing methods performed better than the classical GVV and MCP for both the simulated and real life data.