Statistical Supervised Learning With Engineering Data: A Case Study of Low Frequency Noise Measured On Semiconductor Devices

Our practical motivation is the analysis of potential correlations between spectral noise current and threshold voltage from common on-wafer MOSFETs. The usual strategy leads to the use of standard techniques based on Normal linear regression easily accessible in all statistical software (both free or commercial). However, these statistical methods are not appropriate because the assumptions they lie on are not met. More sophisticated methods are required. A new strategy based on the most novel nonparametric techniques which are data-driven and thus free from questionable parametric assumptions is proposed. A backfitting algorithm accounting for random effects and nonparametric regression is designed and implemented. The nature of the correlation between threshold voltage and noise is examined by conducting a statistical test, which is based on a novel technique that summarizes in a color map all the relevant information of the data. The way the results are presented in the plot makes it easy for a non-expert in data analysis to understand what is underlying. The good performance of the method is proven through simulations and it is applied to a data case in a field where these modern statistical techniques are novel and result very efficient.

Rainfall trend analysis and weather forecast accuracy in selected parts of Khyber Pakhtunkhwa, Pakistan

Climate change is a multidimensional phenomenon, which has various effects on people's environmental and socioeconomic conditions. In the agricultural economy that is susceptible to natural changes, its impact is more profound. Therefore, climate change directly affects society in different ways, and society must pay a price. Climate change, especially the changes in annual temperature and rainfall, has attracted widespread attention worldwide. The variability of these factors or the magnitude of fluctuations varies according to location. Therefore, in the context of climate change, especially in countries dominated by rainfed agriculture, studying the trend of meteorological variables is essential to assess climate-induced variations and propose feasible adaptation approaches. Focusing on this fact is the main goal of this research study was to determine the rainfall trend and the accuracy of predicted temperature at three particular stations of Khyber Pakhtunkhwa (Kp) Province, Pakistan. For this purpose, rainfall and temperature data were provided by Pakistan Meteorological Department (PMD), Islamabad, for the period 1960–2020. Two types of nonparametric techniques, Sen’s slope estimate and the Mann–Kendall test, were applied to determine a trend in the average monthly and annual rainfall. The results of the annual rainfall trend analysis showed that Peshawar and Dera Ismail Khan stations showed a positive increasing trend, while the monthly rainfall trend showed a negative decreasing trend for all stations. The trend was statistically significant for Peshawar and Saidu Sharif stations. The accuracy of predicted and actual temperature and rainfall indicated that mostly over-forecast occurred at Saidu Sharif and Peshawar. Most of the precipitation and temperature records showed under forecast for Dera Ismail Khan, but some over-prediction has also occurred. Graphical abstract

The relation between gender and differences in emotional intelligence of female managers in modern rural tourism

The main goal of this research is to examine the relation between gender and differences in affective attachment, emotional intelligence and self-esteem among students population. The scales for self-assessment of emotional intelligence, affective attachment and self-esteem were used in the current research. The sample consisted of 231 respondents, students of tourism and hospitality management, 71 males and 160 females. Considering that our sample is not representative, because there is a large disproportion in the number of male and female respondents, and that distribution of scores on measured variables deviates from normal, we used nonparametric techniques: Mann-Whitney U test and Kruskal-Walis oneway analysis of variance. The results show that female students have more pronounced emotional intelligence in the domain of perceiving and understanding emotions, as well as a better ability to regulate and manage emotions compared to male respondents, while the measured scores at scale of affective attachment and self-esteem did not show statistically significant differences between gender. On further, female managers in our research see the development of rural tourism as their business opportunity.

Ex-post effects of circuit breakers in crisis and calm markets

PurposeDespite regulatory claims of straitening volatility and preventing crashes, evidences on circuit breakers' ability to achieve so are nonconclusive. While previous scholars studies general performances of circuit breakers, the authors examine whether Malaysian price limits aggravate volatility, impede price discovery, and interfere with trading activities in both tranquil and stressful periods.Design/methodology/approachThe study uses a combination of parametric and nonparametric techniques consistent with Kim and Rhee (1997) to examine the major ex-post hypotheses in circuit breaker research.FindingsFor calm markets, the authors find significant success of upper limits in tempering volatility with low trading interference. Lower limits show mixed results. Conversely, in crisis markets limits fare poorly in nearly all aspects, particularly for lower limits.Practical implicationsRamifications of the paper's findings are discussed through highlighting the asymmetric nature of price limits' ex-post effects. The paper also contributes to regulatory debate surrounding the quest for an optimal price limit.Originality/valueThe paper is the first of its kind in documenting long-horizon evidence of ex-post effects of a wide-band price limit. Moreover, the paper is unique in its approach in bifurcating circuit breaker performance along the line of market stability periods.

Human Resource Management and the Performance Appraisal: satisfaction analysis of the Guarda Nacional Republicana Administration Officers

In a culture of development and globalization, organizations need to value their human capital. It is here that Human Resources Management and each of its areas of expertise gain importance, among them the Performance Appraisal, as it has a direct impact on the results of organizations and the performance of employees. It is from here that the subject of this research arises, to analyze the Performance Appraisal satisfaction of the Officers of Administration of the Guarda Nacional Republicana. This investigation is pertinent due to the lack of studies in public sector organizations, of which the Guarda Nacional Republicana is part, as one military security force. The overall objective of this paper is to analyze the satisfaction resulting from the Performance Appraisal process in the Guarda Nacional Republicana. Following the hypotheticaldeductive method, a questionnaire survey allowed to collect enough data to test the hypotheses of investigation, using parametric and nonparametric techniques. Thus, it was possible to conclude that the Administration Officers of the Guarda Nacional Republicana feel a slight Performance Appraisal satisfaction. This result was strongly influenced by the unsatisfactory results related to the Performance Appraisal System and the Performance Appraisal Interview, notorious in the results of the analysis of the data collected.

The Impact of Social Media on Restaurant Corporations’ Financial Performance

Social media, in the form of online reviews (ORs), has become an essential element for consumers in the restaurant industry, providing reliable and unbiased information based on the dining experiences of other consumers. Social media is not only a crucial phenomenon for the strategy of restaurants, but also for their corporations. However, previous literature has focused on the analysis at the establishment level, rather than at the corporate level, especially when referring to financial performance. The present study tries to verify if social media also affects corporate financial performance. For this, the impact of ORs on advanced measures of financial performance was examined at the corporate level on a sample of 800 restaurants selected from the total population of active restaurants in Europe in 2018. The investigation applied both regression analysis and nonparametric techniques. They demonstrate a positive effect of ORs on financial performance, and a heterogeneous relationship between both variables across the European countries. Restaurants are becoming aware of the implications of this phenomenon since it could provide strategies for sustainable economic development.