Stata Technical Bulletin
35
Y-variable : Iogwt
Grouped by: foreign (Car type)
Group numbers:
|
Car type ∣ |
Freq. |
Percent |
Cum. |
|
Domestic ∣ |
52 |
70.27 |
— 70.27 |
|
Foreign I |
22 |
29.73 |
100.00 |
|
Total I |
74 |
100.00 |
— |
Transformation: Fisherzs z
95% confidence interval(s) for percentile ratio(s)
between values of exp(logwt) in first and second groups:
Percent Pctl-Rat Minimum Maximum
rl 25 1.1935375 1.0341465 1.3533567
r2 50 1.4806389 1.3101849 1.6280196
r3 75 1.744916 1.6079542 1.8772724
We note that, typically, American cars are 148% heavier than foreign cars, with confidence limits ranging from 131% to
163% as heavy. The 25th percentile ratio (103% to 135%) shows that the two car types do not overlap a great deal.
Saved results
cendif saves in r():
Scalars
|
r(N) |
number of observations |
r(N-dust) |
number of clusters |
|
r(N_l) |
sample size Arι |
r(N_2) |
sample size N2 |
|
r(df-r) |
residual degrees of freedom (if tdist present) | ||
|
Macros | |||
|
r(depvar) |
name of dependent variable |
r(by) |
name of by variable defining groups |
|
r(clustvar) |
name of cluster variable |
r(tdist) |
tdist if specified |
|
r(wtype) |
weight type |
r(wexp) |
weight expression |
|
r(centiles) |
list of percents for percentiles |
r(Dslist) |
list of D - -values for percentiles |
|
r(transf) |
transformation specified by transf |
r(tranlab) |
transformation label in output |
|
r(level) |
confidence level |
r(eform) |
eform if specified |
|
Matrices | |||
|
r(cimat) |
confidence intervals for differences or ratios |
r(Dsmat) |
upper and lower limits for D*(0) |
Acknowledgments
I would like to thank Nick Cox of Durham University, UK, and Bill Gould of Stata Corporation for some very helpful
advice on the coding of infinite confidence limits, such as those occasionally resulting from Equation (9).
References
Campbell, M. J. and M. J. Gardner. 1988. Calculating confidence intervals for some non-parametric analyses. British Medical Journal 296: 1454-1456.
Conover, W. J. 1980. Practical Nonparametric Statistics. 2d ed. New York: John Wiley & Sons.
Gardner, M. J. and D. G. Altman. 1989. Statistics with Confidence. London: British Medical Journal.
Newson, R. 2000. snp15.2: Update to somersd. Stata Technical Bulletin 58: 30.
Royston, P. 1998. CID: Stata module to calculate confidence intervals for means or differences. On the Ideas list at
http://ideas.uqam.ca/ideas/data/Softwares/bocbocodeS338001.html.
Somers, R. H. 1962. A New asymmetric measure of association for ordinal variables. American Sociological Review 27: 799-811.
sts15.1 Tests for stationarity of a time series: update
Christopher F. Baum, Boston College, [email protected]
Richard Sperling, The Ohio State University, [email protected]
Abstract: Enhances the Elliott-Rothenberg-Stock DF-GLS test and the Kwiatkowski-Phillips-Schmidt-Shin KPSS tests for sta-
tionarity of a time series introduced in Baum (2000) and corrects an error in both routines.
Keywords: stationarity, unit root, time series.