Saturday, July 18, 2009

Causality in Parent-Child Dynamics

by Alan

I recently finished reading a new book by Johns Hopkins University sociologist Andrew Cherlin entitled The Marriage-Go-Round: The State of Marriage and the Family in America Today. As the title implies, the U.S. has a lot of couple and family turnover. Though Americans' high rates of marriage and divorce are well-known, there's a third element, of which I wasn't really familiar. Namely, Americans also have a high rate of re-partnering after the break-up of marital and non-marital couples. An illustrative statistic Cherlin cites is the percentage of women in different countries who have "three or more live-in partners (married or cohabiting) by age thirty-five" (p. 19). In the U.S., it's 10%, whereas in other English-speaking nations (those in Europe, as well as Canada, Australia, and New Zealand), none was higher than 4.5%.

Cherlin notes further that, "Children who experiences a series of transitions appear to have more difficulties than children raised in stable two-parent families and perhaps even more than children raised in stable lone-parent families" (p. 20). He acknowledges, however, that, "we cannot be sure that experiencing parents and partners moving in and out of the house actually causes the difficulties researchers have found in children. Some aspects of the parents' personalities or abilities could affect both the stability of their partnerships and their children's behavior" (pp. 20-21). The possibility that a genetic-based factor, present in the parent and passed to the children, could cause both the parent's relationship difficulties and the children's behavior problems is also acknowledged.

Cherlin discusses two research approaches that attempt to get around these interpretational difficulties. Regarding the genetic issue:

A way to test this possibility is to compare the adjustment of biological children, who share their parents' genes, with adopted children, who do not. If having genes in common is the root cause of the difficulties we see in families of divorce, we would expect that biological children of divorced parents would show more problems after a parental divorce than would adopted children. But that's not what researchers find... (p. 21).

In the endnotes (pp. 216-217), Cherlin adds the following:

Paula Fomby and I looked at this question another way. If what's happening is merely that parents are passing along traits that lead to difficulties, then, we reasoned, children who are acting out or delinquent should be more likely to have parents who acted out or were delinquent when they were children... We examined the records of a twenty-year national study that followed women beginning when they were teenagers. Most of the women became mothers during the study. We found that even after we took into account whether the mothers had, when they were teenagers, used drugs, shoplifted, stolen something, or had early sexual intercourse, their children still had more behavior problems and admitted to more delinquency if their mothers had had more partners. Our study suggests that experiencing a series of partnerships may be, at least in part, a true cause of children's difficulties.

These findings were said to hold for white families, but not for black families. With non-experimental research, alternative explanations for findings are virtually always present. The research described by Cherlin is noteworthy, in my mind, for the creative research designs used in an attempt to rule out some of the leading alternative interpretations.

Thursday, July 9, 2009

SEMNET Message from Judea Pearl

The following is a message from Judea Pearl to the SEMNET (Structural Equation Modeling) discussion list (conveyed by Dr. Pearl's colleague Stephen Sivo). Given Dr. Pearl's apparent intent to have these announcements publicized to a wide audience, I (Alan) have reprinted it below (lightly edited for apparent typos and ease of accessing links)...

Dear Colleagues in Causality,

Below, a few items that I thought would be of interest to researchers active in causal reasoning.

1. A new article, authored by Ilya Shpitser and myself is now posted on the UCLA Causality-Blog (see also here). It offers a solution to the problem of evaluating "Effects of Treatment on the Treated (ETT)." The problem is of theoretical interest because ETT, despite its blatant counterfactual character (e.g., "I just took an aspirin, perhaps I shouldn't have?"), can be evaluated from experimental studies in many, though not all, cases. Characterizing those cases illuminates therefore the empirical content of counterfactuals.

2. Many of you have commented on my article "Myth, Confusion and Science in Causal Analysis" (inspired by Don Rubin), a revised version of which is now posted on our website here . I would like to encourage a blog-discussion on the main points raised there. For example:

2.1. Whether graphical methods are in some way "less principled" than other methods of analysis.
2.2. Whether confounding bias can only decrease by conditioning on a new covariate.
2.3 Whether the M-bias, when it occurs, is merely a mathematical curiosity, unworthy of researchers' attention.
2.4. Whether Bayesianism instructs us to condition on all available measurements.

If you feel strongly about defending any of these claims (which seem to be
still simmering in certain circles, see video), the Causality-Blog can be an effective arena for airing them in an open discussion. Requests for anonymity will be honored.

3. Forbes magazine ran an issue on artificial intelligence last week, to which I contributed a popular article on progress in causal analysis (from my humble perspective, of course). Comments are welcome.

4. I have volunteered to give a tutorial at the JSM meeting (Washington, DC, August 5, 2009, 2-4 pm) on "Causal Analysis in Statistics: A Gentle Introduction." If any of your colleagues or students could benefit from such tutorial, I promise to be truly gentle.

5. Just before the tutorial, at 12 noon, there will be a book-signing gathering at the Cambridge University Press booth, where I will be signing copies of the 2nd Edition of Causality (and will engage in gossip and debates about where causality is heading).

Best wishes, and May clarity shine over causality land,
Judea Pearl

Note that all of Dr. Pearl's requests for blog discussion pertain to his blog at UCLA. I have thus turned off the comments option here.