On Lord's Paradox. Program Statistics Research [electronic resource] / Paul W. Holland and Donald B. Rubin.
Lord's Paradox is analyzed in terms of a simple mathematical model for causal inference. The resolution of Lord's Paradox from this perspective has two aspects. First, the descriptive, non-causal conclusions of the two hypothetical statisticians are both correct. They appear contradictory...
Saved in:
| Online Access: |
Full Text (via ERIC) |
|---|---|
| Main Author: | |
| Corporate Author: | |
| Other Authors: | |
| Format: | Electronic eBook |
| Language: | English |
| Published: |
[S.l.] :
Distributed by ERIC Clearinghouse,
1982.
|
| Subjects: |
MARC
| LEADER | 00000cam a22000002u 4500 | ||
|---|---|---|---|
| 001 | b6312889 | ||
| 003 | CoU | ||
| 005 | 20080221101449.9 | ||
| 006 | m d f | ||
| 007 | cr un | ||
| 008 | 820521s1982 xx |||| ot ||| | eng d | ||
| 035 | |a (ERIC)ed237515 | ||
| 040 | |a ericd |c ericd |d MvI | ||
| 088 | |a ETS-PSRP-TR-82-34 | ||
| 088 | |a ETS-RR-82-36 | ||
| 099 | |f ERIC DOC # |a ED237515 | ||
| 099 | |f ERIC DOC # |a ED237515 | ||
| 100 | 1 | |a Holland, Paul W. | |
| 245 | 1 | 0 | |a On Lord's Paradox. Program Statistics Research |h [electronic resource] / |c Paul W. Holland and Donald B. Rubin. |
| 260 | |a [S.l.] : |b Distributed by ERIC Clearinghouse, |c 1982. | ||
| 300 | |a 47 p. | ||
| 500 | |a ERIC Document Number: ED237515. | ||
| 500 | |a ERIC Note: Prepared for the Festschrift in honor of Frederic M. Lord, May 22-23, 1982. |5 ericd. | ||
| 520 | |a Lord's Paradox is analyzed in terms of a simple mathematical model for causal inference. The resolution of Lord's Paradox from this perspective has two aspects. First, the descriptive, non-causal conclusions of the two hypothetical statisticians are both correct. They appear contradictory only because they describe quite different aspects of the data. Second, the causal inferences of the statisticians are neither correct nor incorrect since they are based on different assumptions that our mathematical model makes explicit, but neither assumption can be tested using the data set that is described in the example. We identify these differing assumptions and show how each may be used to justify the differing causal conclusions of the two statisticians. In addition to analyzing the classic "diet" example which Lord used to introduce his paradox, we also examine three other examples that appear in the three papers where Lord discusses the paradox and related matters. (Author) | ||
| 521 | 8 | |a Researchers. |b ericd. | |
| 650 | 0 | 7 | |a Estimation (Mathematics) |2 ericd. |
| 650 | 1 | 7 | |a Influences. |2 ericd. |
| 650 | 1 | 7 | |a Mathematical Models. |2 ericd. |
| 650 | 1 | 7 | |a Research Methodology. |2 ericd. |
| 650 | 1 | 7 | |a Statistical Analysis. |2 ericd. |
| 650 | 0 | 7 | |a Statistics. |2 ericd. |
| 700 | 1 | |a Rubin, Donald B. | |
| 710 | 2 | |a Educational Testing Service. |b Program Statistics Research Project. | |
| 856 | 4 | 0 | |u http://files.eric.ed.gov/fulltext/ED237515.pdf |z Full Text (via ERIC) |
| 907 | |a .b63128895 |b 07-06-22 |c 10-13-10 | ||
| 998 | |a web |b 10-23-12 |c f |d m |e - |f eng |g xx |h 0 |i 1 | ||
| 956 | |a ERIC | ||
| 999 | f | f | |i 40d51b21-8282-5581-bd1e-1957863fe99f |s 4473865e-21d7-5284-bdb2-c62572a6e74a |
| 952 | f | f | |p Can circulate |a University of Colorado Boulder |b Online |c Online |d Online |e ED237515 |h Other scheme |i web |n 1 |