# see if this helps a little
plot(L,W, type="p", pch=16)
model <- nls(W~a*L^b, start=list(a=a.start.value, b=b.stat.value))
lv <- seq(min(L), max(L), length=30)
wv<-predict(model,list(L=lv))
lines(lv,wv)

谢谢你vrooadk，我叫潘晓哲，很高兴能跟你学到东西 2# vrooadk

l w
59 4
59 4
60 5
60 5
60 6
61 4
62 4
62 4
62 4
62 5
62 6
63 4
63 6
63 6
64 5
64 5
65 4
63 4
65 4
92 8
92 9
92 9
92 9
93 8
94 7
95 8
95 10
95 10
95 10
96 10
96 12
97 12
98 10
98 10
100 10
100 10
100 10
100 10
68 4
68 5
68 6
68 6
69 4
70 4
70 5
70 6
71 4
72 4
73 4
73 4
73 4
73 4
73 4
73 5
74 4
74 5
74 5
74 5
74 5
74 8
90 8
90 9
90 9
91 8
91 8
91 9
92 8
92 9
92 9
92 9
93 8
94 7
95 8
95 10
95 10
95 10
96 10
96 12
97 12
98 10
98 10
100 10
100 10
100 10
100 10
100 11
100 13
102 11
102 11
102 13
104 11
104 13
104 13
105 12
105 12
105 13
105 15
105 15
105 20
108 14
110 14
110 14
110 15
110 15
112 15
112 17
113 14
114 15
115 16
115 18
117 17
118 18
118 20
120 18
120 18
120 18
120 18
120 20
120 21
120 21
120 23
121 21
122 15
122 20
122 23
123 21
123 22
80 6
80 6
80 6
80 7
80 7
80 7
80 8
81 6
81 6
81 6
81 7
82 5
82 5
82 5
82 6
82 6
82 7
82 7
83 5
83 5
83 6
83 6
83 6
83 7
83 9
84 6
126 27
127 25
128 20
128 24
128 25
128 25
128 25
128 27
128 28
129 20
129 30
130 21
130 21
130 22
130 22
130 22
130 22
130 22
130 22
130 22
130 23
125 18
125 20
125 20
125 21
125 21
125 21
125 21
125 22
125 22
125 22
126 27
127 25
128 20
128 24
128 25
128 25
128 25
128 27
128 28
129 20
129 30
130 21
130 21
130 22
130 22
130 22
130 22
130 22
130 22
125 25
125 25
75 5
75 7
75 8
76 4
76 4
76 7
77 5
77 5
77 5
77 5
77 6
77 6
78 4
78 5
78 5
78 5
78 5
78 5
78 6
78 6
78 7
79 5
80 5
80 6
80 6
80 6
80 6
80 7
80 7
80 7
126 26
126 27
127 25
128 20
128 24
128 25
128 25
128 25
128 27
128 28
129 20
129 30
130 21
130 21
88 8
89 6
89 7
89 8
90 6
90 7
90 7
90 7
90 7
90 7
90 7
90 7
90 8
75 7
75 8
76 4
76 4
76 7
77 5
77 5
77 5
77 5
81 6
81 6
81 7
82 5
82 5
82 5
82 6
82 6
82 7
82 7
83 5
83 5
83 6
83 6
83 6
83 7
83 9
84 6
84 6
84 6
84 6
84 7
84 7
84 7
84 9
84 11
85 6
85 6
85 6
85 6
85 6
85 6
85 7
85 7
85 7
85 7
85 7
86 5
86 6
87 6
87 6
87 7
87 8
88 7
88 7
88 8
88 8
rd<-read.delim("hui.txt")
l<-rd$l
w<-rd$w
plot(l,w, type="p", pch=16)
model <- nls(w~a*l^b, start=list(a=a.start.value, b=b.start.value))
lv <- seq(min(l), max(l), length=30)
wv<-predict(model,list(L=lv))
lines(lv,wv)
我照着你说的做了，不过还是没添加上趋势线，我想再请教一下 2# vrooadk

sorry! just saw it today.
When I tried it, it worked. did you choose your starting values for a and b?
# I used this, the starting values are randomly choosen, at least this code give me some points and a #line.  
l=c(59,59,60,60,60,61,62)
w=c(4,4,5,5,6,4,4)
plot(l,w)
model<-nls(w~a*l^b,start=list(a=.5,b=1))
lv=seq(min(l),max(l),length=10)
wv<-predict(model,list(l=lv))
lines(lv,wv)

5# vrooadk
谢谢（实在对不起，这些日子一直在实验室里忙，刚看到回复）