Collection for FIU, 1-129.
De Ridder, A., & Djehiche, B. (2007). Extreme Day Returns on Stocks: Evidence from Sweden.
Switzer, L. N., Wang, J. & Lee, S. (2017). Extreme Risk and Small Investor Behavior in Developed Markets. Journal of Asset Management, 1-19. https://doi.org/10.1057/s41260-017-0047-6
Veld, C., & Veld-Merkoulova, Y. V. (2008). The Risk Perceptions of Individual Investors. Journal of Economic Psychology, 29(2), 226-252.
Wander, B. H. & Vari R. D. (2003). The Limitations of StandardDeviation
Yusuke Ozaki, Takeshi Ueda, Tomohiro Fukuda, Tatsuya Inai, Eri Kido and Daiki Narisako
, changes of speed, and stride patterns during racing ( Iskra and Coh, 2011 ). However, there are no studies that have focused on the stride adjustment technique.
There are studies which quantified the stride adjustment technique during the takeoff in jumping events, such as the long jump and pole vault. Lee et al. (1982) showed that standarddeviation of the ground contact position of the plurality of trials during the approach of the long jump athlete gradually increased from the start, reached a maximum value at a point in the latter half of the approach, and then
Determining the Total Dispersion Zone for Micrometer SM Measuring Equipment
The aim of the total dispersion zone for measuring equipment SM is to define if three workers A, B, C can achieve the same values of measurement using the same measuring equipment. Before estimating the total dispersion zone for measuring equipment SM. the calibration of the micrometer was carried out. The values were obtained by measuring the width of clip anchor. It is necessary to calculate the average values XA, XB, X C and to calculate standard deviations SΔA, SΔB, SΔC for three workers. Finally, the total dispersion zone SM will be calculated and the results will be interpreted.
training with pixel-distorted scaled-turned-shifted images,” Information processing systems , iss. 7 (132), pp. 98–107, 2015.
 V. V. Romanuke, “Optimal Pixel-to-Shift StandardDeviation Ratio for Training 2-Layer Perceptron on Shifted 60 × 80 Images with Pixel Distortion in Classifying Shifting-Distorted Objects,” Applied Computer Systems , vol. 19, no. 1, Jan. 2016. https://doi.org/10.1515/acss-2016-0008
 V. V. Romanuke, “Boosting ensembles of heavy two-layer perceptrons for increasing classification accuracy in recognizing shifted
Studies investigating the relation between risk and return occupy an important place in the discussion about the effectiveness of investing in real estate. A review of the available studies shows that real estate investments are less profitable than stocks, but in terms of risk and return, are usually the best option. This worldwide regularity may not necessarily be presented in Poland, as the Polish market is not fully fledged yet. The analysis presented in this article was performed with a view to reducing a research gap resulting from the lack of comprehensive Polish studies in this field. In the article, data spanning the years from 2006 to 2016 are examined by means of descriptive statistics, measures of risk, and the analysis of variance (ANOVA) to determine which of the following investment vehicles - bonds, real estate or stocks - offer the best risk-return ratio. The article has two parts. The analytical part is a review of studies on risk measurement methods and of earlier studies investigating risk and return by a class of assets (particularly real estate). In the empirical part, assets are compared with the use of statistical methods. The results of the risk-return analysis point to the money market as the best option for investors. Stocks and real estate ranked second and third, respectively.
An optimization problem of classifying shifting-distorted objects is studied. The classifier is 2-layer perceptron, and the object model is monochrome 60 × 80 image. Based on the fact that previously the perceptron has successfully been attempted to classify shifted objects with a pixel-to-shift standard deviation ratio for training, the ratio is optimized. The optimization criterion is minimization of classification error percentage. A classifier trained under the found optimal ratio is optimized additionally. Then it effectively classifies shifting-distorted images, erring only in one case from eight takings at the maximal shift distortion. On average, classification error percentage appears less than 2.5 %. Thus, the optimized 2-layer perceptron outruns much slower neocognitron. And the found optimal ratio shall be nearly the same for other object classification problems, when the number of object features varies about 4800, and the number of classes is between two and three tens.
The main goal of this publication is to determine the impact of the alignment condition to the repeatability of measured values. In the experimental work were performed four series of measurements, each contains 25 individual measurements on a single component. The component was measured according to the rules for making the comparison of measured values for repeatability. This comparison of measurement results was made by using statistical methods. A given goal was completely fulfilled. Experimental work has shown a dominant impact of the alignment condition on the measured values.
We have developed a simple and fast quantitative method for depth and shape determination from residual gravity anomalies due to simple geometrical bodies (semi-infinite vertical cylinder, horizontal cylinder, and sphere). The method is based on defining the anomaly value at two characteristic points and their corresponding distances on the anomaly profile. Using all possible combinations of the two characteristic points and their corresponding distances, a statistical procedure is developed for automated determination of the best shape and depth parameters of the buried structure from gravity data. A least-squares procedure is also formulated to estimate the amplitude coefficient which is related to the radius and density contrast of the buried structure. The method is applied to synthetic data with and without random errors and tested on two field examples from the USA and Germany. In all cases examined, the estimated depths and shapes are found to be in good agreement with actual values. The present method has the capability of minimizing the effect of random noise in data points to enhance the interpretation of results.
The production of milk, the quantity of fat respectively constitute the main criterion of assessment of dairy cows in the mountain area and downhill. The average performance in the succession of eight lactations per total lactation is 3420.67 kg, and per normal lactation is 3209.20 kg milk. The limits vary between 1506 kg of milk and 8835 kg milk recorded for lactation and 1506 kg of milk and 7322 kg milk for normal lactation. The study of statistical parameters of index of the total duration of lactation allows us to affirm that the cows from the herd studied have the genetic potential to increase lactation beyond the limits of normal lactation of 305 per days. Milk production per day is higher with + 0.45 kg per total lactation than normal lactation. Extension of lactation and breast resting shortening represents loss of milk production in both current lactation and the next lactation. To estimate the effect of localities was used the analysis of variance within samples. Raw data tables have been processed to create tables of variances between herds of the 6 localities and within the herd in each locality. The influence of the locality on the milk production is null.
The output production of milk cows has as enablers: daily output and duration of lactation on her. The raise of the productive cows milk level in the mountain area and hence income breeders is achievable through the integration and expansion of biotechnology.
Part 2: distributions, summary statistics and outliers
Andrea Harnos, Tibor Csörgő and Péter Fehérvári
This paper is the second part of our bird ringing data analyses series (Harnos et al. 2015a) in which we continue to focus on exploring data using the R software. We give a short description of data distributions and the measures of data spread and explain how to obtain basic descriptive statistics. We show how to detect and select one and two dimensional outliers and explain how to treat these in case of avian ringing data.