[R] summary(lm(x~y)) difference between R-2.2.1 and R-2.3.0

[Robin Hankin]

Hi

[macOSX 10.4.6; R-2.3.0]

I have encountered a difference in behaviour between R-2.2.1 and  
R-2.3.0 when
performing a linear model.  Transcript follows for R-2.3.0 (R-2.2.1  
worked as
expected).   How to make R-2.3.0 perform as R-2.2.1 did?



 > dput(x)
c(29.13, 29.88, 30.09, 29.99, 29.74, 29.64, 29.65, 29.7, 30.04,
29.89, 29.96, 29.65, 28.76, 28.41, 28.38, 29.55, 29.76, 29.75,
29.84, 29.85, 29.75, 29.99, 29.32, 29.38, 28.97, 28.48, 29.06,
28.74, 29.23, 29.16, 29.19, 29.23, 29.17, 29.25, 29.24, 29.22,
29.15, 29.15, 28.78, 29.28, 29.31, 29.44, 29.28, 29.47, 29.28,
29.32, 29.39, 29.27, 28.68, 28.73, 28.09, 28.19, 29.1, 29.1,
29.14, 29.48, 29.48, 29.39, 29.39, 29.22, 28.95, 29.11, 27.94,
28.32, 27.98, 28.22, 28.89, 29.4, 29.28, 29.66, 30.05, 30.12,
30.09, 29.85, 29.99, 29.92, 28.44, 28.92, 28.92, 28.94, 28.97,
28.95, 29.39, 29.26, 29.7, 29.48, 29.72, 29.71, 29.84, 29.59,
29.17, 29.39, 29.27, 29.39, 28.53, 29.32, 29.32, 28.44, 29.39,
28.55, 29.39, 29.46, 29.73, 30.01, 30.11, 30.25, 30.37, 30.22,
30.33, 30.35, 30.38, 30.25, 29.27, 27.34)
 > dput(y)
c(36, 72.43, 37.57, 72.78, 55.88, 38.41, 79.79, 32, 56.92, 69.72,
63.53, 50.94, 82.82, 50.77, 41.05, 75.62, 64, 63.04, 35.83, 91.71,
93.29, 42.16, 65.57, 60.05, 27.38, 83.64, 67.6, 39, 53.21, 54.24,
49.58, 34.29, 81.5, 48.94, 64.84, 32.86, 66.71, 41.67, 42.27,
45.22, 51.23, 64.03, 58, 48.15, 59.8, 72.94, 40.33, 56.82, 32,
75.32, 49.25, 44.38, 27.5, 37, 40.22, 33.63, 43, 49.92, 36, 63.78,
41.74, 58.07, 37.5, 41.27, 54.28, 51.39, 49.92, 93, 33.75, 30.81,
102.31, 67.95, 64.48, 47, 33.56, 42.44, 44.25, 63.93, 38.92,
74.47, 58.46, 35.25, 94.45, 40.71, 38.35, 78.26, 65.1, 89.54,
43.34, 34.71, 37.83, 62.45, 31.43, 38.14, 50, 75.77, 88.14, 60.14,
42.02, 36.79, 34.9, 46.33, 47.55, 35.67, 75.41, 28.6, 61.29,
62.43, 59.08, 46.3, 84.56, 43.96, 91.68, 41.67)
 > summary(lm(x~y))

Call:
lm(formula = x ~ y)

Residuals:

*** caught bus error ***
address 0x18, cause 'invalid alignment'

Traceback:
1: sort(x, partial = unique(c(lo, hi)))
2: quantile.default(resid)
3: quantile(resid)
4: structure(quantile(resid), names = nam)
5: print.summary.lm(list(call = lm(formula = x ~ y), terms = x ~      
y, residuals = c(-0.0990169973225879, 0.442597843688031,  
0.852002363105233, 0.550595790280227, 0.397266369114154,  
0.397197434926506, 0.170497520598225, 0.493863613052272,  
0.691317410416682, 0.468099457217023, 0.573507201772172,  
0.335523922927148, -0.736834541760754, -0.903503651131917,  
-0.877903767920926, 0.0943505569140546, 0.370818730053123,  
0.366310076543096, 0.6119
[snip]




--
Robin Hankin
Uncertainty Analyst
National Oceanography Centre, Southampton
European Way, Southampton SO14 3ZH, UK
  tel  023-8059-7743