NV Chart (TW/CN/HK patent obtained)
In the field of statistics, whether certain method or model can be adopted depends on the distribution of the sample subject. And many commonly used methods or models today are only applicable when the sample is normal (or Gaussian) distribution, resulting that it is necessary and crucial to understand the distribution of the sample before adopting any model.
NV chart was therefore invented to provide a solution that can not only show whether a sample is normal (or Gaussian) distribution but also can present several samples in one chart for comparison.
Real life application example of Graphician NV Chart:
| 1stdataset |
| No. |
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
10 |
| Descending |
68 |
55 |
48 |
34 |
29 |
29 |
27 |
26 |
26 |
23 |
| No. |
11 |
12 |
13 |
14 |
15 |
16 |
17 |
18 |
19 |
20 |
| Descending |
21 |
22 |
20 |
20 |
19 |
19 |
18 |
17 |
16 |
16 |
| No. |
21 |
22 |
23 |
24 |
25 |
26 |
27 |
28 |
29 |
30 |
| Descending |
15 |
15 |
14 |
14 |
13 |
13 |
10 |
10 |
10 |
8 |
| 2nddataset |
| No. |
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
10 |
| Descending |
91 |
68 |
55 |
48 |
45 |
41 |
40 |
37 |
36 |
34 |
| No. |
11 |
12 |
13 |
14 |
15 |
16 |
17 |
18 |
19 |
20 |
| Descending |
31 |
30 |
29 |
29 |
27 |
26 |
26 |
26 |
26 |
25 |
| No. |
21 |
22 |
23 |
24 |
25 |
26 |
27 |
28 |
29 |
30 |
| Descending |
24 |
23 |
23 |
23 |
22 |
22 |
21 |
21 |
21 |
20 |
| No. |
31 |
32 |
33 |
34 |
35 |
36 |
37 |
38 |
39 |
40 |
| Descending |
20 |
20 |
19 |
19 |
19 |
19 |
19 |
18 |
18 |
18 |
| No. |
41 |
42 |
43 |
44 |
45 |
46 |
47 |
48 |
49 |
50 |
| Descending |
18 |
17 |
16 |
16 |
16 |
15 |
15 |
15 |
15 |
15 |
| No. |
51 |
52 |
53 |
54 |
55 |
56 |
57 |
58 |
59 |
60 |
| Descending |
14 |
14 |
14 |
13 |
13 |
13 |
13 |
13 |
13 |
13 |
| No. |
61 |
62 |
63 |
64 |
65 |
66 |
67 |
68 |
|
|
| Descending |
12 |
10 |
10 |
10 |
10 |
8 |
8 |
7 |
|
|
| 1stdataset |
| n16(M,3σ) |
68.00 |
v16(μ,3σ) |
63.20 |
| n14(M,2σ) |
68.00 |
v14(μ,2σ) |
49.60 |
| n12(M,1σ) |
29.00 |
v12(μ,1σ) |
36.10 |
| n10(M,0σ) |
19.00 |
v10(μ,0σ) |
22.50 |
| n11(M,3σ) |
13.00 |
v11(μ,3σ) |
8.90 |
| n13(M,3σ) |
8.00 |
v13(μ,3σ) |
-4.60 |
| n15(M,3σ) |
8.00 |
v15(μ,3σ) |
-18.20 |
| 2nddataset |
| n26(M,3σ) |
91.00 |
v26(μ,3σ) |
64.96 |
| n24(M,2σ) |
68.00 |
v24(μ,2σ) |
50.88 |
| n22(M,1σ) |
31.00 |
v22(μ,1σ) |
36.80 |
| n20(M,0σ) |
19.00 |
v20(μ,0σ) |
22.72 |
| n21(M,3σ) |
13.00 |
v21(μ,3σ) |
8.64 |
| n23(M,3σ) |
8.00 |
v23(μ,3σ) |
-5.44 |
| n25(M,3σ) |
7.00 |
v25(μ,3σ) |
-19.52 |
-
With the respective normal distribution “ruler” listed aside, Graphician NV chart can clearly show that the distributions of the 1st dataset and the 2nd dataset are similar: both are not normal distribution but with longer right tail, a.k.a positive skew or skewed to the right, while there is an outlier (91) in the 2nd dataset.
