Graphical Data Representation in Bankruptcy Analysis



15


Graphical Data Representation in Bankruptcy Analysis

Variable No.

Fig. 11. Median improvement in AR. SVM vs. DA (the upper line) and SVM
vs. logit regression (the lower line). Box-plots are estimated basing on 100 random
subsamples for the case of DA. Each model includes variables K5, K29, K7, K33,
K18, K21, K24 and one of the remaining


Red colour is often used in finance to highlight negative information, while
green and blue are used to convey positive information. Therefore, we would
like to code PDs with colours ranging from red for the highest PD to blue-
green for the most solvent company. For this end we normalise PDs so, that
the lowest PD corresponds to the hue equal 180 (green-blue) or 120 (green)
while the highest PD corresponds to the hue equal 0 (red). The resulting graph
that shows the data and PDs in the dimensions of variables K33 and K29 is
shown in Figures 15-17. The three figures correspond consequently to three
SVMs with high, average and high complexity. The saturation was fixed at
0.85 to make colours look more noble and the luminance was fixed at 0.46, the
maximum possible value for the chosen saturation. The HLS colours obtained
in this way were transformed into RGB ones and plotted by the XploRe ([8],
[7]) as a contour plot. The outliers that lie beyond the 5% and 95% quantiles
are plotted at the rand.

To produce the plot a grid was generated with 101 steps both in horizontal
and vertical directions. For each point of the grid a PD was estimated and
represented in the HLS colour encoding. Then the HLS colour was converted



More intriguing information

1. THE DIGITAL DIVIDE: COMPUTER USE, BASIC SKILLS AND EMPLOYMENT
2. HOW WILL PRODUCTION, MARKETING, AND CONSUMPTION BE COORDINATED? FROM A FARM ORGANIZATION VIEWPOINT
3. The name is absent
4. Real Exchange Rate Misalignment: Prelude to Crisis?
5. Olfactory Neuroblastoma: Diagnostic Difficulty
6. Moi individuel et moi cosmique Dans la pensee de Romain Rolland
7. The geography of collaborative knowledge production: entropy techniques and results for the European Union
8. Managing Human Resources in Higher Education: The Implications of a Diversifying Workforce
9. Anti Microbial Resistance Profile of E. coli isolates From Tropical Free Range Chickens
10. An Efficient Circulant MIMO Equalizer for CDMA Downlink: Algorithm and VLSI Architecture
11. Implementation of a 3GPP LTE Turbo Decoder Accelerator on GPU
12. Secondary stress in Brazilian Portuguese: the interplay between production and perception studies
13. Performance - Complexity Comparison of Receivers for a LTE MIMO–OFDM System
14. Creating a 2000 IES-LFS Database in Stata
15. Experience, Innovation and Productivity - Empirical Evidence from Italy's Slowdown
16. The name is absent
17. Prevalence of exclusive breastfeeding and its determinants in first 6 months of life: A prospective study
18. The economic doctrines in the wine trade and wine production sectors: the case of Bastiat and the Port wine sector: 1850-1908
19. fMRI Investigation of Cortical and Subcortical Networks in the Learning of Abstract and Effector-Specific Representations of Motor Sequences
20. Fiscal Rules, Fiscal Institutions, and Fiscal Performance