Publication Type: Conference Paper/Unpublished Manuscript
Review Method: Peer Reviewed
Abstract: The study compares the results of two surveys based on the module 'Family and Changing Gender Roles' of the International Social Survey Programme (ISSP). The first survey was administered as a paper-and-pencil questionnaire to a representative sample of the German population. The second one was administered as a WebTV survey to a pre-recruited panel of the full population in Germany. Panel members were recruited with the aid of an RDD CATI procedure. Comparisons of the demographic variables (age, sex, education) yield only small differences. With regard to the substantive variables (family and gender roles), no relevant mode effects for half of all items were observed both for measures of the central tendency as well as for distributional characteristics. For the other half of all items, it can be demonstrated that the respondents in the WebTV survey chose more extreme categories. Due to space limitations on the screen, most of the these were presented screen-by-screen in WebTV mode, and as a matrix in the paper-and-pencil version, indicating a slight visual design effect.

Publication Type: Conference Paper/Unpublished Manuscript
Review Method: Peer Reviewed
Abstract: Non-response or non-participation can introduce selection bias in the analytic results by confounding the behavioral parameters of interest with parameters that determine response. By incorporating a model of selection into the data likelihood function, it is possible to correct potential selection bias. Correctly specified full information maximum likelihood (FIML) methods should be able to correct for selection bias even in discrete choice models with truncated data when no data is available for non-respondents or non-participants. Unfortunately, attempts to implement such methods have not been very successful. This paper carefully examines the FIML approach for estimating discrete choice models with truncated data in order to better understand the difficulties with implementing this estimation technique. Simulation results are used to demonstrate the difficulty implementing FIML estimates. Given the failure of FIML methods, alternative estimation techniques are proposed.

Publication Type: Conference Paper/Unpublished Manuscript
Review Method: Peer Reviewed
Abstract: Recent analysis of the Scottish Parliament suggests that it has not produced the innovations in political culture, policy-making processes or policy outputs that many of its proponents anticipated. This paper challenges this view by exploring the potential of the Parliament to develop innovative policy in the area of economic development. I evaluate the potential for the land reform bill currently being considered by the Scottish Parliament to contribute to economic development. I argue that the Land Reform (Scotland) Bill has the potential to have a positive impact on the economic fortunes of depressed rural areas. In fact, the bill may have a more radical impact than initially anticipated, by leading to a significant redistribution of wealth in the areas that it affects. Preliminary evidence from recent history in rural Scotland suggests that those aspects of the bill providing certain rural communities with the right to buy their land can contribute to the social and economic rejuvenation of these areas. Nonetheless, the radical potential of the bill must be understood as a _potential_, contingent upon the willingness of communities to act.

Publication Type: Conference Paper/Unpublished Manuscript
Review Method: Peer Reviewed
Abstract: Statistical analysis requires a probability model: commonly, a model
for the dependence of outcomes $Y$ on confounders $X$ and a
potentially causal variable $Z$. When the goal of the analysis is to
infer $Z$'s effects on $Y$, this requirement introduces an element
of circularity: in order to decide how $Z$ affects $Y$, the analyst
first determines, speculatively, the manner of $Y$'s dependence on
$Z$ and other variables. This paper takes a statistical perspective
that avoids such circles, permitting analysis of $Z$'s effects on
$Y$ even as the statistician remains entirely agnostic about the
conditional distribution of $Y$ given $X$ and $Z$, or perhaps even
denies that such a distribution exists. Our assumptions instead
pertain to the conditional distribution $Z \vert X$, and the role of
speculation in settling them is reduced by the existence of random
assignment of $Z$ in a field experiment as well as by
poststratification, testing for overt bias before accepting a
poststratification, and optimal full matching. Such beginnings pave
the way for ``randomization inference'', an approach which, despite
a long history in the analysis of designed experiments, is
relatively new to political science and to other fields in which
experimental data are rarely available.

The approach applies to both experiments and observational studies.
We illustrate this by applying it to analyze A. Gerber and
D. Green's New Haven Vote 98 campaign. Conceived as both a
get-out-the-vote campaign and a field experiment in political
participation, the study assigned households to treatment and
desired to estimate the effect of treatment on the individuals
nested within the households. We estimate the number of voters who
would not have voted had the campaign not prompted them to --- that
is, the total number of votes attributable to the interventions of
the campaigners --- while taking into account the non-independence
of observations within households, non-random compliance, and
missing responses. Both our statistical inferences about these
attributable effects and the stratification and matching that
precede them rely on quite recent developments from statistics; our
matching, in particular, has novel features of potentially wide
applicability. Our broad findings resemble those of the original
analysis by \citet{gerbergreen00}.

Publication Type: Conference Paper/Unpublished Manuscript
Review Method: Peer Reviewed
Abstract: The dramatic decline in welfare caseloads over the past six years of welfare reform has led to a plethora of research on the employability of recipients. In general, these studies have found that welfare recipients’ individual level obstacles, either singly or in combination, interfere with getting jobs, keeping jobs and increasing wages. However, such studies have typically overlooked or underestimated the role of structural factors, such as neighborhood level poverty conditions, and transportation and child care problems, in mothers’ employment. In addition, these studies tend to exclude non-TANF “working-poor” mothers from their analyses, even though these families face similar challenges to employment as TANF families. Further, given the transient nature of welfare participation, in which poor mothers move on and off the rolls, it is important that scholars investigate the presence of these work obstacles for TANF mothers as well as non-TANF mothers. Using new quantitative data from the Philadelphia Survey of Child Care and Work including poor urban mothers receiving public assistance and not, we explore the obstacles and more severe barriers that constrain poor mothers’ employment. By contextualizing paid work within a particular urban setting and local labor market, Philadelphia, and by using new data with improved information about child care, we can account for the ways in which individual and macro level factors shape mothers’ employment chances, and potentially shed light into how these work problems are similarly or differently felt for mothers on public assistance and those not.