![[BACK]](/cvsweb/icons/back.gif){kind=icon}
Return to sample10 CVS log ![[TXT]](/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvsweb/icons/dir.gif){kind=icon}
Up to [Research Unix] / researchv10no / cmd / tbl / tmp|
Return to sample10 CVS log | Up to [Research Unix] / researchv10no / cmd / tbl / tmp |
1.1 root 1: .EQ
2: delim $$
3: .EN
4: .SH
5: 7K. A 2-section example
6: .PP
7: Let us turn back to suspended deposits as given in exhibit 8.
8: We need something like logs to make the sizes of residuals
9: about the same. Exhibit
10: .B
11: 32
12: .R
13: lists the 3R smooth of the logs, and its rough,
14: and gives the stem-and-leaf and modified letter
15: values -- both for residuals and for their SIZES --
16: doing this first for all years
17: and then for two groups of years. Clearly,
18: the residuals are bigger for the second group of years,
19: the comparison being
20: .KS
21: .in 1i
22: .TS
23: box;
24: c c s c s
25: c c c c c
26: n n n n n .
27: Spreads Sizes
28: *Hspr *Espr *M *H
29: 1921-44 19h 50 8 23h
30: 1948-67 53 97 34 80
31: .TE
32: .in 0
33: .KE
34: The apparent ratio of sizes varies from 2:1 to 4:1.
35: .PP
36: Exhibit
37: .B
38: 33
39: .R
40: shows the corresponding plot, with the rough
41: supporting the smooth. Here we have used two lengths of
42: bars, one for each group of years. The result is quite effective.
43: .ce
44: * review questions for 7K *
45: .PP
46: What did we take as an example? How many sections
47: seemed needed? How did the sizes behave?
48: .ls 1
49: .ce 4
50: exhibit 32 of chapter 7+ -- suspended depostis
51: .br
52: The 3R smooth of the logs of suspended deposits and
53: .br
54: the corresponding residuals
55: .br
56: (deposits in 100 log of millions of dollars)
57: .LP
58: A) The SMOOTH and the ROUGH
59: .KS
60: .TS
61: allbox;
62: c c c c c c c
63: c c c c c c c
64: n r l n n n n .
65: Susp.
66: Date deposits 3R Rough Size F G
67:
68: 1951 49 15 34 34
69: 2 15 49,46 -31 31
70: 3 165 46,49 116 116 F G
71: 4 46 81 -35 35
72: 55 81 81 z
73: 6 108 108 z
74: 7 111 108 3 3
75: 8 80 80 z
76: 9 30 80 -50 50 F
77: 60 90 88 2 2
78: 1 88 88 z
79: 2 88 88 -80 80 F
80: 3 136 134 2 2
81: 4 134 136,134 z
82: 65 165 134 31 31
83: 6 -15 107 -122 122 F
84: 7 107 107 z
85: .TE
86: .KE
87: .nf
88: L = "lower still" entered as the log of zero
89: G = "F" for analysis of panel E
90: .fi
91: .LP
92: B) STEM-and-LEAF for ALL residuals
93: .KS
94: .TS
95: n l .
96: _
97: 3 H|(71,H,116)((?))
98: _
99: 4 5|6
100: _
101: 5 4|2
102: _
103: 8 3|041
104: 2|
105: _
106: 10 1|47
107: _
108: 14 0|9322
109: _
110: 19 Z|0000000000000000000
111: _
112: 12 -0|4584
113: _
114: 8 -1|5
115: -2|
116: _
117: 7 -3|415
118: -4|
119: _
120: 4 -5|0
121: _
122: 3 L|(L,3,-80,-122)((?))
123: _
124: .TE
125: .KE
126: .LP
127: C) *LETTER VALUES WITHOUT and WITH ?'s for ALL residuals
128: .KS
129: .TS
130: box;
131: c c s s c c s s
132: n n n n n n n n .
133: *#35h (zeroes/2,no?) #37h (zeroes/2,yes?)
134: =
135: *M18 0 M19 (18) 0
136: *H 9h 15h -11h H10 (9) 17 -8
137: *E 5 42 -35 E 5h(4h) 49 -42
138: .TE
139: .KE
140: .KS
141: .TS
142: c c s s c c s s
143: l l l l l l l l .
144: 27 gives 40h 25 gives 37h
145: F 56 -52 F 54h -45h
146: FF 96h -92h FF 92 -83
147: .TE
148: .KE
149: .KS
150: .TS
151: allbox;
152: c c c c
153: r r r r .
154:
155: outside: 71,116,H outside: 56,71,116,H,?
156: and: -80,-122,L and: -50,-80,-122,L,?
157: far-out: 116,H,-122,L far-out: 116,H,?,-122,L,?
158: .TE
159: .KE
160: .sp
161: Note that counts in (B) omit ?'s, hence the change
162: when ?'s are no longer omitted.
163: .LP
164: D) STEM-and-LEAF and *-LETTER VALUE for SIZES of ALL RESIDUALS
165: .KS
166: .TS
167: allbox;
168: c c
169: n l .
170: Left Right
171: =
172: 8 H|(71,116,H,80,122,L,?,?)
173: 10 5|06
174: 11 4|2
175: 17 3|011445
176: 20 1|457
177: 28 0|22344589
178: 19 z|0000000000000000000
179: .TE
180: .KE
181: .sp
182: *median = 16 (at depth 18h, since * = 36h)
183: .LP
184: E) STEM-and-LEAF and LETTER-VALUE for 1921-45 and 1948-67
185: .KS
186: .ce 1000
187: .TS
188: c s c s
189: n l n l .
190: 1921-45 1948-67
191: 1 H|(71) 2 H|(H,116)
192: 2 5|6 5|
193: 3 4|2 4|
194: 4 3|0 4 3|41
195: 2| 2|
196: 6 1|47 1|...
197: 7 0|9 7 0|322
198: 12 z|000000000000 6 z|000000
199: 6 -0|4584 -0|
200: 2 -1|5 -1|
201: -2| -2|
202: 1 -3|4 7 -3|15
203: -4| -4|
204: -5| 5 -5|0
205: L| 4 L|(L,-63,-80,-122)
206: .TE
207: .ce 0
208: .KE
209: .KS
210: .TS
211: allbox center;
212: c c s s c c s s
213: n n n n n n n n .
214: *#=19=13+$12 over 2$ (zeroes/2) \*=17=14+$6 over 2)$ (zeroes/2)
215: *M10 0 *M9 0
216: *H 5h 15h -4 19h *H5 3 -50 53
217: *E 3 42 -8 50 *E3 34 -63 97
218: .TE
219: .KE
220: .KS
221: .TS
222: box, center;
223: c c s s c c s s
224: l l l l l l l l .
225: 19h gives 29h 53 gives 79h
226: =
227: *F 45 -33h *F 82h -139h
228: *FF 74h -63 *FF 162 -219
229: .TE
230: .KE
231: This is a long line of text whose only purpose is to tell me where the right margin
232: is on this page so the centering of the tables can be checked.
233: .KS
234: .TS
235: box;
236: c c c c
237: r l r l .
238:
239: outside: 56,71,-34 outside: 116,H,L
240: far out: _ far out: H,L
241: _ 42 and -15) _ 34 and -122)
242: .TE
243: .KE
244: .LP
245: .KS
246: F) STEM-and-LEAF and *-LETTER VALUES for SIZES of residuals in 1921-44 and 1948-67
247: .TS
248: box;
249: c s c s
250: n l n l .
251: 1921-45 1948-67
252: =
253: 1 H|(71) 6 H|(H,116,63,80,122,L)
254: _
255: 2 5|6 7 5|0
256: _
257: 3 4|2 4|
258: _
259: 3|04 11 3|1145
260: 5 _ _ _
261: 2| 2|
262: _
263: 8 1|457 1|
264: _
265: 13 0|44589 14 0|223
266: _
267: 12 z|000000000000 6 z|000000
268: -0|
269: -1|
270: -2|
271: -3|
272: -4|
273: -5
274:
275: .TE
276: .KE
277: .nf
278: .ta 30
279: *median = 8 (at depth 10) *median = 34 (at depth 9)
280: *H = 23h (at depth 5h) *E = 80 (at depth 5)
281: .fi
282: .LP
283: P) PROBLEMS
284: .PP
285: 32a. Make stem-and-leaf displays, and find *M and *H for the SIZES
286: of residuals for periods 1921-33 and 1934-45.
287: How do they compare with each other and with 1948-67? How many groups
288: seem to be needed? What are they?
289: .PP
290: 32b. (Triple value) Repeat Panels (A), (B) and (F) for
291: started logs, using 100 log (1+suspended deposits in millions).
292: .PP
293: 32c. (After b) Do 32a for this new analysis.
This archive runs on limited infrastructure. Preserving old code on modern bandwidth. Automated agents are requested to crawl responsibly.