R_LMM_dummy_variables.sagews

Фиктивные переменные

f = open('apartment.tsv', 'r')
s = f.read().replace(',', '.')
f.close()
fnew = open('ap.tsv', 'w')
fnew.write(s)
fnew.close()

%r
ap <- read.table('ap.tsv', header=TRUE, sep='\t')
str(ap)

'data.frame': 100 obs. of 10 variables: $ X : int 1 2 3 4 5 6 7 8 9 10 ... $ Y : num 15.9 27 21.1 24.5 13.5 22.5 15.5 75.9 15.1 26 ... $ X1: int 1 3 2 4 1 2 3 4 1 2 ... $ X2: Factor w/ 4 levels "К","М","П","С": 4 1 4 4 1 1 4 3 1 1 ... $ X3: num 39 68.4 54.7 90 34.8 48 68.1 132 39 55.5 ... $ X4: num 20 40.5 28 64 16 29 44.4 89.6 20 35 ... $ X5: num 8.2 10.7 10.7 15 10.7 8 7.2 11 8.5 8 ... $ X6: int 0 0 0 0 0 1 0 1 0 0 ... $ X7: int 1 1 1 0 0 1 0 1 1 1 ... $ X8: Factor w/ 2 levels "В","Н": 2 2 2 1 2 1 1 2 2 1 ...

%r
X8.f <- factor(ap$X8)
dummy8 <- model.matrix(~X8.f)
dummy8

	(Intercept)	X8.fН
1	1	1
2	1	1
3	1	1
4	1	0
5	1	1
6	1	0
7	1	0
8	1	1
9	1	1
10	1	0
11	1	0
12	1	0
13	1	1
14	1	0
15	1	1
16	1	1
17	1	0
18	1	1
19	1	1
20	1	1
21	1	0
22	1	0
23	1	1
24	1	1
25	1	1
26	1	0
27	1	0
28	1	0
29	1	1
30	1	1
⋮	⋮	⋮
71	1	1
72	1	0
73	1	0
74	1	0
75	1	1
76	1	1
77	1	1
78	1	0
79	1	0
80	1	1
81	1	0
82	1	0
83	1	0
84	1	1
85	1	1
86	1	1
87	1	0
88	1	0
89	1	0
90	1	1
91	1	1
92	1	1
93	1	0
94	1	0
95	1	0
96	1	1
97	1	1
98	1	1
99	1	1
100	1	0

%r
X2.f <- factor(ap$X2)
dummy2 <- model.matrix(~X2.f)
dummy2

	(Intercept)	X2.fМ	X2.fП	X2.fС
1	1	0	0	1
2	1	0	0	0
3	1	0	0	1
4	1	0	0	1
5	1	0	0	0
6	1	0	0	0
7	1	0	0	1
8	1	0	1	0
9	1	0	0	0
10	1	0	0	0
11	1	0	1	0
12	1	0	0	0
13	1	0	0	0
14	1	1	0	0
15	1	1	0	0
16	1	0	0	1
17	1	1	0	0
18	1	0	0	0
19	1	0	1	0
20	1	1	0	0
21	1	0	0	1
22	1	0	0	0
23	1	0	1	0
24	1	0	1	0
25	1	0	1	0
26	1	1	0	0
27	1	0	1	0
28	1	0	0	0
29	1	0	0	1
30	1	0	1	0
⋮	⋮	⋮	⋮	⋮
71	1	0	0	1
72	1	1	0	0
73	1	1	0	0
74	1	0	1	0
75	1	1	0	0
76	1	0	1	0
77	1	0	1	0
78	1	0	0	1
79	1	0	0	1
80	1	0	0	0
81	1	0	1	0
82	1	0	0	1
83	1	0	0	1
84	1	1	0	0
85	1	1	0	0
86	1	0	1	0
87	1	1	0	0
88	1	0	0	1
89	1	0	0	1
90	1	0	1	0
91	1	1	0	0
92	1	0	1	0
93	1	0	0	0
94	1	0	0	1
95	1	0	0	1
96	1	1	0	0
97	1	0	1	0
98	1	1	0	0
99	1	1	0	0
100	1	1	0	0

%r
ap.lm <- lm(ap$Y ~ ap$X1 + ap$X3 + ap$X4 + ap$X5 + dummy8[,2])
summary(ap.lm)

Call: lm(formula = ap$Y ~ ap$X1 + ap$X3 + ap$X4 + ap$X5 + dummy8[, 2]) Residuals: Min 1Q Median 3Q Max -12.1940 -4.0914 0.2285 3.0462 15.8874 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) -2.8049 1.8582 -1.509 0.1345 ap$X1 -1.9545 1.0562 -1.850 0.0674 . ap$X3 0.6377 0.1201 5.308 7.38e-07 *** ap$X4 -0.1911 0.1493 -1.280 0.2038 ap$X5 -0.3848 0.1973 -1.951 0.0541 . dummy8[, 2] 8.2635 1.2797 6.457 4.65e-09 *** --- Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 Residual standard error: 5.633 on 94 degrees of freedom Multiple R-squared: 0.8406, Adjusted R-squared: 0.8321 F-statistic: 99.13 on 5 and 94 DF, p-value: < 2.2e-16