The use of marketing research panels are a more and more frequently used source of information for studies within many different branches. The purpose of this report is to investigate the demographic composition of panels and compare it with the population of Sweden, a possible change in behaviour of respondents, and if the source of recruitment is the cause of possible differences in study results. The study was commissioned by Norstats Linkoping office. Sources for the data material include Norstat’s recruitment process and their two main panels with different recruitment sources. To enable a deeper investigation of behaviour we also constructed a survey that was sent to 2,714 members of Norstat’s internet panels. The statistical analysis includes contingency table analysis, multiple logistic regression, and Poisson regression. The results show that the demographic composition does not fully cover all the aspects of the Swedish population and some groups are less represented than others. The behaviour tends to differ between panel members that have responded to three or less surveys compared to members that have responded to twenty or more surveys. Source of recruitment does not seem to affect the results of studies, but it has some effect on the demographic composition of marketing research panels. / Användandet av paneler som källa vid undersökningar har den senaste tiden blivit en allt vanligare företeelse. Denna rapport har för avsikt att undersöka panelers demografiska sammansättning och överensstämmande med Sveriges befolkning, eventuell ändring av svarsbeteende samt huruvida rekryteringskällan ger upphov till kvalitetsskillnader hos medlemmar i en panel. Företaget Norstat har med sitt kontor i Linköping figurerat som uppdragsgivare till arbetet. Datamaterialet till studien har uppkommit från Norstats rekryteringsprocess samt från företagets två huvudpaneler med olika rekryteringskällor. För att djupare undersöka svarsbeteende konstruerade vi även en enkätundersökning som skickades ut till 2 714 medlemmar i Norstats internetpaneler. Den statiska analysen innefattar χ2-test, multipel logistisk regression samt Poissonregression. Resultaten påvisade att den demografiska sammansättningen i panelen inte fullt ut speglade Sveriges befolkning samt att vissa grupper undertäcks i högre utsträckning än andra. Svarsbeteendet hos medlemmar i paneler har en tendens att ändras från det att medlemmen har svarat på en till tre undersökningar, till det att den har svarat på tjugo undersökningar eller fler. Rekryteringskällan till en panel verkar inte ge upphov till några större skillnader i svarsresultat, men däremot finns vissa skillnader i demografisk sammansättning.

Scandinavian Airlines has a large database containing their Eurobonus members. In order to analyze which customers they should target with direct marketing, such as emails, uplift models have been used. With a binary response variable that indicates whether the customer has bought or not, and a binary dummy variable that indicates if the customer has received the campaign or not conclusions can be drawn about which customers are persuadable. That means that the customers that buy when they receive a campaign and not if they don't are spotted. Analysis have been done with one campaign for Sweden and Scandinavia. The methods that have been used are logistic regression with Lasso and logistic regression with Penalized Net Information Value. The best method for predicting purchases is Lasso regression when comparing with a confusion matrix. The variable that best describes persuadable customers in logistic regression with PNIV is Flown (customers that have own with SAS within the last six months). In Lassoregression the variable that describes a persuadable customer in Sweden is membership level1 (the rst level of membership) and in Scandinavia customers that receive campaigns with delivery code 13 are persuadable, which is a form of dispatch.

In this thesis, a binary decision tree is used as an approximation of a nonparametric regression curve. The best fitted decision tree is estimated from data via least squares method. It is investigated how and under which conditions the estimator converges. These asymptotic results then are used to create asymptotic convergence regions.

The aim of the study was to evaluate dierent types of logistic regression to find the optimal model to predict the gender of hospitalized COVID-19 patients. The models were based on COVID-19 case series data from Pakistan using a set of 18 explanatory variables out of which patient age and BMI were numerical and the rest were categorical variables, expressing symptoms and previous health issues.  Compared were a logistic regression using all variables, a logistic regression that used stepwise variable selection with 4 explanatory variables, a logistic Ridge regression model, a logistic Lasso regression model and a logistic Elastic Net regression model.  Based on several metrics assessing the goodness of fit of the models and the evaluation of predictive power using the area under the ROC curve the Elastic Net that was only using the Lasso penalty had the best result and was able to predict 82.5% of the test cases correctly.

No description available.

This paper examines the impact of several macroeconomic variables on property prices in Sweden. Linear regression is used to construct severalmathematical models relating the macroeconomic variables to property prices. Using methods of variables selection and goodness of fit measures,two final models are selected and subsequently compared, resulting in one final model. From this model, we conclude that GDP per capita, unemployment rate, inflation and repo interest rate have a significant relationship with property price changes in Sweden. Unemployment, GDPper capita, and inflation have positive relationships with property price changes, while repo interest rate has a negative relationship with propertyprice changes. However, as to what extent these variables affect property prices, no certain conclusions can be drawn from this study. / Följande studie undersöker inverkan av sex makroekonomiska variabler på bostadspriser i Sverige. Linjär regressionsanalys används för att skapaflera matematiska modeller som relaterar makroekonomiska variabler till bostadspriser. Vidare används variabelselektion och statistikor för modellevaluering för att välja ut två slutgiltiga modeller. Dessa två modeller jämförs och en slutgiltig modell väljs ut. Studiens slutsatser dras fråndenna modell. BNP per capita, arbetslöshetsgrad, inflationstakt, och reporänta har enligt den slutgiltiga modellen signifikanta förhållandentill bostadspriser i Sverige. Vidare har arbetslöshet, BNP per capita, och inflation positiva förhållanden till bostadsprisförändringar, medan reporänta har ett negativt förhållande. Studien kan inte dra några slutsatser om till vilken grad dessa variabler påverkar bostadspriser i Sverige.

A unifying model for Critical Heat Flux (CHF) prediction has been elusive for over 60 years. With the release of the data utilized in the making of the 2006 Groeneveld Lookup table (LUT), by far the largest public CHF database available to date, data-driven predictions on a large variable space can be performed. The popularization of machine learning techniques to solve regression problems allows for deeper and more advanced tools when analyzing the data. We compare three different machine learning algorithms to predict the occurrence of CHF in vertical, uniformly heated round tubes. For each selected algorithm (ν-Support vector regression, Gaussian process regression, and Neural network regression), an optimized hyperparameter set is fitted. The best performing algorithm is the Neural network, which achieves a standard deviation of the prediction/measured factor three times lower than the LUT, while the Gaussian process regression and the ν-Support vector regression both lead to two times lower standard deviation. All algorithms significantly outperform the LUT prediction performance. The neural network model and training methodology are designed to prevent overfitting, which is confirmed by data analysis of the predictions. Additionally, a feasibility study of transfer learning and uncertainty quantification is performed, to investigate potential future applications.

The possible effects of the General Data Protections Regulations (GDPR) have been widely discussed among policymakers, stakeholders and ordinary people who are the objective for data collection. The purpose of GDPR is to protect people’s integrity and increase transparency for how personal data is used. Up until May 25th, 2018 personal data could be sampled and used without consent from users. Many argue that the introduction of GDPR is good, others are reluctant and argue that GDPR may harm data-driven companies. The report aims to answer how GDPR affects sales at the flight search engine Flygresor.se. By examining how and to what extent these regulations impact revenue, it is hoped for that these findings will lead to a deeper understanding of how these regulations affect businesses. Multiple linear regression analysis was used as the framework to answer the research question. Numerous models were constructed based on data provided by Flygresor.se. The models mostly included categorical variables representing time indicators such as month, weekday, etc. After carefully performing data modifications, variable selections and model evaluation tests three final models were obtained. After performing statistical inference tests and multicollinearity diagnostics on the models it could be concluded that an effect from GDPR could not be statistically proven. However, this does not mean that an actual effect of GDPR did not occur, only that it could not be isolated and proven. Thus, the extent of the effect of GDPR is statistically inconclusive. / De möjliga följderna av införandet av General Data Protections Regulations (GDPR) har varit väl omdiskuterat bland beslutsfattare, intressenter och människor som är målet för datainsamlingen. Syftet med GDPR är att skydda människors integritet samt öka insynen för hur personlig data används. Fram tills den 25 maj 2018 har det varit möjligt att samla in och använda personuppgifter utan samtyckte från användare. Många menar att införandet av GDPR är nödvändigt medans andra är mer kritiska och menar att GDPR kan skada lönsamheten för data beroende verksamheter. Denna rapport syftar till att svara på huruvida GDPR har påverkat försäljningen på flygsökmotorn Flygresor.se. Genom att undersöka om och i vilken utsträckning dessa regler påverkat intäkterna, är förhoppningen att dessa resultat kan leda till en djupare förståelse för hur GDPR påverkar företag. Multipel linjär regressionsanalys användes som ramverk för att svara på frågeställningen. Flera modeller utformades baserat på data som tillhandahölls av Flygresor.se. Modellerna var främst baserade på kategoriska variabler som representerade tidsaspekter så som månad, veckodag etc. Efter ett grundligt genomförande av data modifieringar, variabelselektion och modellutvärdering kunde tre modeller konstateras. Efter att ha genomfört signifikanstester och korrelationstester på modellerna kunde det fastställas att en effekt från GDPR inte kunde statistiskt säkerställas. Dock betyder detta inte att GDPR inte har haft en faktisk effekt, utan att en effekt inte kunde isoleras och bevisas.

Genom att analysera kortegenskaperna hos Magic the Gathering-kort harmodeller tagits fram för att bestämma deras inverkan på kortpriset. Tidigarestudier har inte fokuserat på spel-egenskaperna, vilket är vad som särskiljer dettaarbete från tidigare forskning. För att modellera effekten av spel-egenskapernahar dessa kvantifierats och undersökts med hjälp av Minsta-kvadratmetoden ochLasso-regression, med hjälp av programmeringsspråket R. Resultaten indikeraratt faktorer direkt kopplade till samlarbarhet och spelbarhet har den störstainverkan på priset för Magic the Gathering-kort. Dessa resultat har diskuteratsmed utgångspunkt från olika perspektiv, såsom Wizards of the Coast (utgivarenav Magic the Gathering), spelare, samlare och investerare. Genom att fokusera påspel-egenskaperna har denna studie bidragit till området på ett sätt som tidigareforskning inte har gjort, vilket ger en mer helhetsbild av Magic the Gathering-kortsvärde. / By analyzing the card properties of Magic the Gathering cards, models have beendeveloped to determine their impact on card prices. Previous studies have notfocused on gameplay properties, which distinguishes this work from previousresearch. To model the effect of gameplay properties, they have been quantifiedand examined using Least Squares Method and Lasso Regression, with the helpof the programming language R. The results indicate that factor directly relateradto collectability and playability have the greatest impact on the price of Magic theGathering cards. These results have been discussed from various perspectives,such as Wizards of the Coast (the publisher of Magic the Gathering), players,collectors, and investors. By focusing on gameplay properties, this study hascontributed to the field in a way that previous research has not, providing a morecomprehensive understanding of the value of Magic the Gathering cards.

A variety of complex data has broadened in many research fields such as epidemiology, genomics, and analytical chemistry with the development of science, technologies, and design scheme over the past few decades. For example, in epidemiology, the matched case-crossover study design is used to investigate the association between the clustered binary outcomes of disease and a measurement error in covariate within a certain period by stratifying subjects' conditions. In genomics, high-correlated and high-dimensional(HCHD) data are required to identify important genes and their interaction effect over diseases. In analytical chemistry, multiple time series data are generated to recognize the complex patterns among multiple classes. Due to the great diversity, we encounter three problems in analyzing those complex data in this dissertation. We have then provided several contributions to semiparametric and nonparametric methods for dealing with the following problems: the first is to propose a method for testing the significance of a functional association under the matched study; the second is to develop a method to simultaneously identify important variables and build a network in HDHC data; the third is to propose a multi-class dynamic model for recognizing a pattern in the time-trend analysis. For the first topic, we propose a semiparametric omnibus test for testing the significance of a functional association between the clustered binary outcomes and covariates with measurement error by taking into account the effect modification of matching covariates. We develop a flexible omnibus test for testing purposes without a specific alternative form of a hypothesis. The advantages of our omnibus test are demonstrated through simulation studies and 1-4 bidirectional matched data analyses from an epidemiology study. For the second topic, we propose a joint semiparametric kernel machine network approach to provide a connection between variable selection and network estimation. Our approach is a unified and integrated method that can simultaneously identify important variables and build a network among them. We develop our approach under a semiparametric kernel machine regression framework, which can allow for the possibility that each variable might be nonlinear and is likely to interact with each other in a complicated way. We demonstrate our approach using simulation studies and real application on genetic pathway analysis. Lastly, for the third project, we propose a Bayesian focal-area detection method for a multi-class dynamic model under a Bayesian hierarchical framework. Two-step Bayesian sequential procedures are developed to estimate patterns and detect focal intervals, which can be used for gas chromatography. We demonstrate the performance of our proposed method using a simulation study and real application on gas chromatography on Fast Odor Chromatographic Sniffer (FOX) system. / Doctor of Philosophy / A variety of complex data has broadened in many research fields such as epidemiology, genomics, and analytical chemistry with the development of science, technologies, and design scheme over the past few decades. For example, in epidemiology, the matched case-crossover study design is used to investigate the association between the clustered binary outcomes of disease and a measurement error in covariate within a certain period by stratifying subjects' conditions. In genomics, high-correlated and high-dimensional(HCHD) data are required to identify important genes and their interaction effect over diseases. In analytical chemistry, multiple time series data are generated to recognize the complex patterns among multiple classes. Due to the great diversity, we encounter three problems in analyzing the following three types of data: (1) matched case-crossover data, (2) HCHD data, and (3) Time-series data. We contribute to the development of statistical methods to deal with such complex data. First, under the matched study, we discuss an idea about hypothesis testing to effectively determine the association between observed factors and risk of interested disease. Because, in practice, we do not know the specific form of the association, it might be challenging to set a specific alternative hypothesis. By reflecting the reality, we consider the possibility that some observations are measured with errors. By considering these measurement errors, we develop a testing procedure under the matched case-crossover framework. This testing procedure has the flexibility to make inferences on various hypothesis settings. Second, we consider the data where the number of variables is very large compared to the sample size, and the variables are correlated to each other. In this case, our goal is to identify important variables for outcome among a large amount of the variables and build their network. For example, identifying few genes among whole genomics associated with diabetes can be used to develop biomarkers. By our proposed approach in the second project, we can identify differentially expressed and important genes and their network structure with consideration for the outcome. Lastly, we consider the scenario of changing patterns of interest over time with application to gas chromatography. We propose an efficient detection method to effectively distinguish the patterns of multi-level subjects in time-trend analysis. We suggest that our proposed method can give precious information on efficient search for the distinguishable patterns so as to reduce the burden of examining all observations in the data.