Abstract
Freedman, Navidi and Peters (1988) had shown that when a two-stage variable selection procedure is used to screen linear regression equations, the type I error rate of the t-test for a forced-in-first estimator is inflated if the ratio of the number of parameters to number of data points is large. In this paper, we investigate the asymptotic distribution of the “force-in-last” estimator, and show that this estimator is bias toward zero asymptotically and its asymptotic standard error is close to the nominal standard error under certain conditions. To remedy the bias and reduce the inflation of the type I error rate, two estimators involved with propensity score (Rubin and Rosenbaum, 1983) were introduced.
| Original language | English |
|---|---|
| Pages (from-to) | 131-151 |
| Number of pages | 21 |
| Journal | Communications in Statistics - Theory and Methods |
| Volume | 24 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 1995 Jan 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Statistics and Probability
Cite this
}
Asymptotics of forced-in variables from screening processes. / Lian, Ie Bin.
In: Communications in Statistics - Theory and Methods, Vol. 24, No. 1, 01.01.1995, p. 131-151.Research output: Contribution to journal › Article
TY - JOUR
T1 - Asymptotics of forced-in variables from screening processes
AU - Lian, Ie Bin
PY - 1995/1/1
Y1 - 1995/1/1
N2 - Freedman, Navidi and Peters (1988) had shown that when a two-stage variable selection procedure is used to screen linear regression equations, the type I error rate of the t-test for a forced-in-first estimator is inflated if the ratio of the number of parameters to number of data points is large. In this paper, we investigate the asymptotic distribution of the “force-in-last” estimator, and show that this estimator is bias toward zero asymptotically and its asymptotic standard error is close to the nominal standard error under certain conditions. To remedy the bias and reduce the inflation of the type I error rate, two estimators involved with propensity score (Rubin and Rosenbaum, 1983) were introduced.
AB - Freedman, Navidi and Peters (1988) had shown that when a two-stage variable selection procedure is used to screen linear regression equations, the type I error rate of the t-test for a forced-in-first estimator is inflated if the ratio of the number of parameters to number of data points is large. In this paper, we investigate the asymptotic distribution of the “force-in-last” estimator, and show that this estimator is bias toward zero asymptotically and its asymptotic standard error is close to the nominal standard error under certain conditions. To remedy the bias and reduce the inflation of the type I error rate, two estimators involved with propensity score (Rubin and Rosenbaum, 1983) were introduced.
UR - http://www.scopus.com/inward/record.url?scp=0038230302&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0038230302&partnerID=8YFLogxK
U2 - 10.1080/03610929508831479
DO - 10.1080/03610929508831479
M3 - Article
AN - SCOPUS:0038230302
VL - 24
SP - 131
EP - 151
JO - Communications in Statistics - Theory and Methods
JF - Communications in Statistics - Theory and Methods
SN - 0361-0926
IS - 1
ER -