The main focus of this diploma thesis is productivity estimation of the company using economic indicators. The thesis is focused on evaluating data of timelines using proportional indicators and regressive analysis which estimate the trend and future development. The main point of this thesis is the analysis of results and recommendations for future improvement of the situation.

The diploma thesis evaluates economic status of selected company by analysis of main financial indicators. The analysis is made by regression analysis method and forecast of time series is made by using selected regression function. The thesis result is evaluation of executed analysis and list of recommendations for improvement of the current economic company status.

Bakgrund: Enligt den makroekonomiska kvantitetsteorin påverkar penningmängdstillväxten prisnivån i en ekonomi. Mer specifikt säger kvantitetsteorin att ett positivt samband finns mellan tillväxten av penningmängden och prisnivån. I detta arbete undersöks om penningmängdstillväxten i penningmängdsdefintionen M3 har en påverkan på tillgångspriser i form av aktiepriser. Syfte: Studiens syfte är att undersöka om penningmängdstillväxten har en påverkan på aktiepriser.Metod Studien är kvantitativ. För att besvara studiens syfte användes statistisk analys i form av tidsserieregression. Resultat: I tre regressionsmodeller visade sig penningmängdstillväxten vara en signifikant variabel. Hypotesprövningar indikerade också på att ett samband föreligger mellan penningmängdstillväxt och prisnivån på OMXS30. Slutsats: Den sammantagna slutsatsen är att det inte kan uteslutas att penningmängdstillväxten har en påverkan på aktiepriser. / Background: According to the macroeconomic quantity theory of money, the growth in money affects the price level in an economy. More precisely, the quantity theory of money suggests that there is a positive relationship between the growth of money and price level. This study examines whether the money growth has an impact on asset prices in the form of stock prices.  Purpose: The purpose of this study is to examine if money growth has an impact on stock prices.Method The study is quantitative. To answer the purpose of the study, statistical analysis in the form av time series regression wasused.  Results: The variable for money growth was determined to be significant in three different regression models. Hypothesis tests also indicated that a relationship between money growth and the price level of OMXS30 was present.  Conclusion: The general conclusion is that the notion of money growth’s impact on stock prices cannot be ruled out.

The Swedish real estate market has, and arguably still continues to, endure a crisis in terms of increased interest rate followed by uncertainties on a global scale. Both the residential and commercial real estate market has been affected, seeing prices and transaction volumes decrease as a consequence. The commercial real estate market is largely dependent on financing, which is further strengthened by the large amount of the Swedish banks’ total lending that is directed towards the commercial real estate sector. These aspects combined proves the need of accurately forecasting the real estate market, partly in the aspect of investment decision making but also in relation to the development of the overall economy.  To connect the real estate market with the economy as a whole, this study will analyze five different macroeconomic variables’ effect on the transaction price on commercial real estate in Sweden, as well as making forecasts on the future outlook of real estate prices in relation to the development of the variables. This is conducted with the time series regression model ARIMAX, which utilizes lagged versions of previous commercial real estate prices along with macroeconomic variables in terms of GDP, KIX (the krona index), real interest rate, the Euro/SEK exchange rate as well as the unemployment rate. The model is conducted in relation to the commercial real estate market in Sweden, with a dataset of commercial transactions ranging from 1996 until 2023. Additionally, an analysis of a subset of solely the industrial segment is investigated.  Lastly, the forecasting of real estate prices was conducted in relation to a scenario analysis. The analysis was built on multiple market outlooks by utilizing a predictive movement of the independent variables in relation to three scenarios: pessimistic, base and optimistic. The results of the scenario analysis depicts a fairly modest difference in predicted outcomes on the transaction price in December 2024 in relation to the different scenarios. / Den svenska fastighetsmarknaden har genomgått, och enligt vissa prognoser genomgår, en kris i form av höjda räntor följt av osäkerheter på global nivå. Både bostadsfastigheter och kommersiella fastigheter har påverkats och priserna och transaktionsvolymerna har sjunkit som en följd av detta. Den kommersiella fastighetsmarknaden är till stor del beroende av finansiering, vilket ytterligare förstärks av att en stor del av de svenska bankernas totala utlåning är riktad mot den kommersiella fastighetssektorn. Dessa aspekter sammantaget visar på behovet av att kunna göra korrekta prognoser för fastighetsmarknaden, dels för att kunna fatta investeringsbeslut men också för att kunna bedöma utvecklingen av ekonomin överlag.  För att koppla samman fastighetsmarknaden med ekonomin i stort kommer denna studie att analysera fem olika makroekonomiska variablers effekt på transaktionspriset på kommersiella fastigheter i Sverige, samt göra prognoser om fastighetsprisernas framtidsutsikter i förhållande till variablernas utveckling. Detta görs med tidsserieregressionsmodellen ARIMAX, som utnyttjar laggade versioner av tidigare kommersiella fastighetspriser tillsammans med makroekonomiska variabler i form av BNP, KIX (kronindex), realränta, växelkursen Euro/SEK samt arbetslöshet. Modellen genomförs i relation till den kommersiella fastighetsmarknaden i Sverige, med ett dataset av kommersiella transaktioner från 1996 till 2023. Dessutom genomförs en analys av enbart industrisegmentet. Slutligen genomfördes en prognostisering av fastighetspriserna med hjälp av en scenarioanalys. Analysen byggde på flera marknadsutsikter genom att använda den förutspådda förändringen av de oberoende variablerna i förhållande till tre scenarier: pessimistisk, bas och optimistisk. Resultatet av scenarioanalysen visar på en svag men noterbar skillnad i förväntat utfall för transaktionspriset i december 2024 i förhållande till de olika scenarierna.

Deciding the optimal media advertisement spending is a complex issue that many companies today are facing. With the rise of new ways to market products, the choices can appear infinite. One methodical way to do this is to use Marketing Mix Modelling (MMM), in which statistical modelling is used to attribute sales to media spendings. However, many problems arise during the modelling. Modelling and mitigation of uncertainty, time-dependencies of sales, incorporation of expert information and interpretation of models are all issues that need to be addressed. This thesis aims to investigate the effectiveness of eight different statistical and machine learning methods in terms of prediction accuracy and certainty, each one addressing one of the previously mentioned issues. It is concluded that while Shapley Value Regression has the highest certainty in terms of coefficient estimation, it sacrifices some prediction accuracy. The overall highest performing model is the Bayesian hierarchical model, achieving both high prediction accuracy and high certainty.

The new growth theory establishes, among other things, that government expenditure can manipulate economic growth of a country. This study attempts to explain whether government expenditure increases or decreases economic growth in the context of Sri Lanka. Results obtained applying an analytical framework based on time series and second degree polynomial regressions are generally consistent with previous findings: government expenditure and economic growth are positively correlated; excessive government expenditure is negatively correlated with economic growth; and an open economy promotes growth. In a separate section, the paper examines Armey's (1995) idea of a quadratic curve that explains the level of government expenditure in an economy and the corresponding level of economic growth. The findings confirm the possibility of constructing the Armey curve for Sri Lanka, and it estimates the optimal level of government expenditure to be approximately 27 per cent. This paper adds to the literature indicating that the Armey curve is a reality not only for developed economies, but also for developing economies.(author's abstract) / Series: SRE - Discussion Papers

The analysis of financial statements of Norgren CZ Company based on statistical methods and comparing with Festo Company, which is one of the best competitors this concern, is the object of presented thesis. Used methods are financial analysis and time series analysis. Suggest part of thesis is focused on inventory management, cost reduction and looking for new markets opportunities. The thesis contains theoretical background needed for full understanding of the analytical part, analysis and recommendations, which after putting themselves into practice contribute to the betterment of present condition as well.

The master’s thesis deals with the assessment of the financial performance of the company using statistical methods. The theoretical part describes the issues necessary for the practical part, financial indicators, time series, regression analysis and correlation analysis. In the practical part of the work is a calculation of selected financial indicators, then statistical methods are used to predict future developments and to detect dependencies between the indexes. The last section contains suggestions for improving the current situation.

In an increasingly polarizing world, the debate on the importance of public opinion in shaping foreign policy decisions has been raging over. This study explores the interactions between Chinese investment and credit and public opinion about China in Ecuador from 2012 to 2021 through two classical international relations theories: the realist and liberal hypotheses. Ecuador was selected as a case study because it is among the four Latin American countries that have received the most significant amounts of Chinese loans in the 21st century. We use a mixed methods approach combining a time series regression model to explore the evolution of Ecuadorian public opinion, as well as media content analysis of mainstream Ecuadorian news on Chinese investments. To run the regression model, we draw upon Latin American Public Opinion Project (LAPOP) survey waves. LAPOP is a unique survey exploring public opinion on foreign policy in Latin America in general and in Ecuador in particular. The media content analysis was based on top three newspapers in Ecuador by circulation: El Comercio, El Telégrafo, and El Universo. Research findings suggest that a realist approach contributes more to understanding attitudes of Ecuador’s foreign policymakers regarding Chinese investments over the years. In effect, Ecuadorian foreign policymakers seemingly ignore local public opinion when defining the country’s relations with China. The realist perspective allows to interpret the untangling between public opinion and Ecuadorian foreign policy because of the volatility of Ecuadorian public opinion about China, as evidenced by LAPOP surveys. Another explaining factor is the limited influence of Ecuadorian citizens living in provinces with a strong Chinese economic presence. Finally, the combined results of our newspaper content analysis and our regression study demonstrate that despite being systematically exposed to mainstream news which are predominantly negative regarding Chinese finance in Ecuador, a high proportion of Ecuadorian newspaper readers maintain a positive opinion about China. Further research on Chinese public diplomacy efforts in the country is needed to fully disaggregate the impact of Chinese loans and investments on public opinion about China in Ecuador. This could provide timely information about the complex dynamics of public perceptions and foreign relations in a moment where political and economic hegemonies are being rapidly reshaped.

Time series prediction is one of the main areas of statistics and machine learning. In 2018 the two new algorithms higher order hidden Markov model and temporal convolutional network were proposed and emerged as challengers to the more traditional recurrent neural network and long-short term memory network as well as the autoregressive integrated moving average (ARIMA). In this study most major algorithms together with recent innovations for time series forecasting is trained and evaluated on two datasets from the theme park industry with the aim of predicting future number of visitors. To develop models, Python libraries Keras and Statsmodels were used. Results from this thesis show that the neural network models are slightly better than ARIMA and the hidden Markov model, and that the temporal convolutional network do not perform significantly better than the recurrent or long-short term memory networks although having the lowest prediction error on one of the datasets. Interestingly, the Markov model performed worse than all neural network models even when using no independent variables.