|
|
Analysis of Wages and Salaries in the Pardubice Region
Hanuš, Pavel ; Löster, Tomáš (advisor) ; Šimpach, Ondřej (referee)
This bachelor thesis deals with the study of changes in income of the economically active population in the given region. The main aim of the thesis is to analyze the wage and salary sphere of the population in the Pardubice region and to compare the size of wages and salaries by category. These include age groups, gender, highest education and type of profession. The partial aim is to predict the evolution of hourly earnings using appropriately selected statistical methods. The main benefit of this thesis is to provide a comprehensive overview of the size of the personal income in the Pardubice region for 2015 and 2016.
|
|
|
Analysis of salaries and wages in the capital city of Prague
Jermář, Martin ; Löster, Tomáš (advisor) ; Šimpach, Ondřej (referee)
The aim of the bachelor thesis is to analyse the development of wages and salaries in Prague, the capital city of the Czech Republic by using statistical methods. The thesis includes a general description of terms of salary and wage sphere, time series and selected applied statistical methods. In practical part the analysis of development of wages and salaries in Prague will be performed using the rates of dynamics. Further, time series predictions will be created using adaptive methods. The analysis should familiarize the reader with wage and salary developments for the period from 2011 to 2016 and outline the predictions of possible values in 2017. The results of the thesis show a higher increase in average and median monthly earnings in a wage sphere, increasing disproportions in monthly earning between men and women and bigger disproportions in monthly earnings in the wage sphere. Based on predictions performed the growth of wages and salaries is expected in 2017.
|
|
|
An influence of offline advertising on website traffic
Solnický, Vojtěch ; Löster, Tomáš (advisor) ; Šimpach, Ondřej (referee)
The time series of sessions on web site is investigated in the paper with using box and line plots. On organic traffic, which is part of the main time serie of sessions, is aplicated F-test of seasinality which proves presence of seasonality. The seasonality is removed from time searie by X-13 ARIMA method. The influence of offline advertising on organic traffic of the website is investigated in the second part of this work by using ADL model, but firstly all time series are tested on stacionarity by Dickey-Fuler test which proves, that they are all stacionary. The final model is tested on heteroscedasticity by ARCH test with no prove of it, on autocorelation by BG test also with no prove of it and by Jarque-Bera test on normal distribution of residuals, which proves that they follow normal distribution. The result from test says, that the time searie of organic traffic of the website is influenced by television advertising and by lagged organic trafic itslef with lag of one month.
|
|
|
The consumer loans analysis using statistical methods
Božíková, Barbora ; Löster, Tomáš (advisor) ; Šimpach, Ondřej (referee)
Consumer loans are part of loan products provided by bank institutions. This diploma thesis is focused on possibility of identifying risk clients with the consumer loans, using available data set. In the first part of the work was briefly mentioned the credit process and also theoretical basis of statistic methods used in empirical part of the work. In the second part were investigated dependencies, and was described the clients structure. Then the discriminant analysis was applied, with the aim to identify the sorting criteria, which could recognize the risk and unproblematic clients. Subsequently the results of the analysis were evaluated and described the identified connections.
|
|
|
Analysis of marriage rate, divorce rate and live births outside marriage
Birčáková, Barbora ; Arltová, Markéta (advisor) ; Löster, Tomáš (referee)
The main goal of the thesis is to analyze the basic indicators of marriage rate, divorce rate and the proportion of live births outside marriage. The first part is focused on the evaluation of the past and present development of the selected indicators. The thesis also includes a prediction of the future development of these indicators by using the Box-Jenkins methodology. The last part is dedicated to an international comparison of marriage, divorce and non-marital fertility indicators in the selected countries of the European Union. Moreover, the last part also includes a cluster analysis, where countries are divided into homogeneous groups according to the selected indicators.
|
|
|
Cluster analysis as a tool for classification of objects
Budilová, Šárka ; Löster, Tomáš (advisor) ; Šulc, Zdeněk (referee)
Cluster analysis is a popular method of multivariate statistics. Based on mutual similarities between objects this method is able to classify and divide objects into several groups or clusters. The results of the clustering can be different by using different methods, measures of distance and procedures. The main aim of this thesis is to compare the results of several methods of cluster analysis with the known classification of classes from the original data file. In total, there are 15 data files, which were analyzed and each of them contained known information about the right allocation of objects in groups. The success of clustering of each method was calculated by comparing the known classification of classes and resulted clusters. In addition to the comparison of individual methods of cluster analysis was compared the impact of standardization and correlation to the success of each method. To reflect the distance betweeen the objects within each clusters, squared Euclidean distance was used. The results of this thesis point out that better success of clustering were achieved in the case of correlated variables in data file. The succes of clustering was higher about 2 percent points than in the case when correlated variables were deleted from data set. The methods divided 69,8 % objects before standardization and 70,8 % objects after standardization. The results also show a large importance of standardization in the case of Ward´s method. After standardization this method rank the most objects into correct classification classes and were more succesful, about nine percent points. In the case of correlated variables is the succes of the method 76,4 %. Standardization positively influences also centroid method and the method of farthest neighbour. Median method, nearest neighbour method and the method of average linkage achieve higher success of clustering in the case of original, nonstandardized variables (uneven variables).
|
|
|
Statistical Analysis of Deaths for Traffic Accidents by Regions of the Czech Republic
Pfefferová, Veronika ; Arltová, Markéta (advisor) ; Löster, Tomáš (referee)
The bachelor thesis deals with the analysis of causes of deaths by regions of the Czech Republic focusing on traffic accidents. The aim of this thesis is to compare the causes of death using the rate of deaths per 100 000 population in one year intervals. With these rates regions can be compared with each other though each region has a different number of inhabitants. Further thesis will focus on forecast of time series, namely the forecast of calculated death rates using exponential smoothing - Brown's exponential smoothing, Brown (double) linear exponential smoothing and Holt's linear exponential smoothing. From these smoothings is chosen exactly that which has the smallest residual sum of squares or RSS for individual rate of deaths in each region and on a selective basis for individual regions is prepared the forecast.
|
|
|
The Comparison of Unemployment in Hradec Králové Region and Pardubice Region
Nováková, Marie ; Löster, Tomáš (advisor) ; Šimpach, Ondřej (referee)
Unemployment is a social and economic problem and almost every country in the world has to face it. The Czech Republic has to face that problem as well; hence the topic of this bachelor thesis is to compare unemployment in two regions: Hradec Králové Region and Pardubice Region. These two regions were selected for comparison as they have many geographical and demographical traits in common. The purpose of the thesis is to explain unemployment in both regions by selected demographical and other traits. In the first chapter, both regions are described. Description of different types of unemployment can be found in the second chapter and the third chapter deals with data collection methods. The fourth chapter, which is practically oriented, contains comparison of unemployment in both regions from different perspectives by using the most appropriate statistical methods. Datasets, which were used for this thesis, were obtained from the online database of the Ministry of Labour and Social Affairs and from the website of the Czech Statistical Office. The presented calculations, graphs and tables were created in MS Excel.
|
|
|
Discriminant and cluster analysis as a tool for classification of objects
Rynešová, Pavlína ; Löster, Tomáš (advisor) ; Řezanková, Hana (referee)
Cluster and discriminant analysis belong to basic classification methods. Using cluster analysis can be a disordered group of objects organized into several internally homogeneous classes or clusters. Discriminant analysis creates knowledge based on the jurisdiction of existing classes classification rule, which can be then used for classifying units with an unknown group membership. The aim of this thesis is a comparison of discriminant analysis and different methods of cluster analysis. To reflect the distances between objects within each cluster, squeared Euclidean and Mahalanobis distances are used. In total, there are 28 datasets analyzed in this thesis. In case of leaving correlated variables in the set and applying squared Euclidean distance, Ward´s method classified objects into clusters the most successfully (42,0 %). After changing metrics on the Mahalanobis distance, the most successful method has become the furthest neighbor method (37,5 %). After removing highly correlated variables and applying methods with Euclidean metric, Ward´s method was again the most successful in classification of objects (42,0%). From the result implies that cluster analysis is more precise when excluding correlated variables than when leaving them in a dataset. The average result of discriminant analysis for data with correlated variables and also without correlated variables is 88,7 %.
|
|
|
Statistical methods in R
Jiráň, Robin ; Löster, Tomáš (advisor) ; Bílková, Diana (referee)
This thesis deals with the most important statistic methods, ways of calculating and syntax in the environment of R statistic programme. The initial parts of the bachelor thesis content a brief theoretical basis for the main chapters of the practical part. In the following chapters the use of R programme itself for calculating statistic tasks is explained. The particular parts of recording functions in R programme are presented, important arguments are described and both text and graphical inputs are displayed.
|
guest ::
