flexpaneldid: A Stata Command for Causal Analysis with Varying Treatment Time and Duration
IWH Discussion Papers,
The paper presents a modification of the matching and difference-in-differences approach of Heckman et al. (1998) and its Stata implementation, the command flexpaneldid. The approach is particularly useful for causal analysis of treatments with varying start dates and varying treatment durations (like investment grants or other subsidy schemes). Introducing more flexibility enables the user to consider individual treatment and outcome periods for the treated observations. The flexpaneldid command for panel data implements the developed flexible difference-in-differences approach and commonly used alternatives like CEM Matching and difference-in-differences models. The novelty of this tool is an extensive data preprocessing to include time information into the matching approach and the treatment effect estimation. The core of the paper gives two comprehensive examples to explain the use of flexpaneldid and its options on the basis of a publicly accessible data set.
SMEs and Access to Bank Credit: Evidence on the Regional Propagation of the Financial Crisis in the UK
Journal of Financial Stability,
We study the sensitivity of banks’ credit supply to small and medium size enterprises (SMEs) in the UK with respect to the banks’ financial condition before and during the financial crisis. Employing unique data on the geographical location of all bank branches in the UK, we connect firms’ access to bank credit to the financial condition (i.e., bank health and the use of core deposits) of all bank branches in the vicinity of the firm for the period 2004–2011. Before the crisis, banks’ local financial conditions did not influence credit availability irrespective of the functional distance (i.e., the distance between bank branch and bank headquarters). However, during the crisis, we find that SMEs with banks within their vicinity that have stronger financial conditions faced greater credit availability when the functional distance is close. Our results point to a “flight to headquarters” effect during the financial crisis.
IWH-FDI-Mikrodatenbank Die IWH-FDI-Mikrodatenbank (FDI = Foreign Direct Investment)...
Is the 'Central German Metropolitan Region' Spatially Integrated? An Empirical Assessment of Commuting Relations
The 'Central German Metropolitan Region' is a network of cities and their surroundings, located in the three East-German states of Saxony, Saxony-Anhalt and Thuringia. It was founded to bring the bundled strengths of these cities into an inter-municipal cooperation, for making use of the possible advantages of a polycentric region. As theory claims, a precondition for gains from polycentricity is spatial integration of the region. In particular, markets for high skilled labour should be integrated. To assess how this precondition is fulfilled in Central Germany, in the framework of a doubly constrained gravity model the commuting relations between the functional regions of the (until 2013) 11 core cities of the network are analysed. In particular for higher educated employees, the results display that commuting relations are determined not only by distance, but also by the state borders that cross the area.
Subsidized Vocational Training: Stepping Stone or Trap? – Assessing Empirical Effects using Matching Techniques
Swiss Journal of Economics and Statistics,
Using replacement matching on the basis of a statistical distance function we try to answer the question of whether subsidized vocational training is related to a negative image effect for the graduates. The results show that young people with equal qualifications acquired during subsidized vocational training are disadvantaged solely due to the kind of education they have received. The probability of finding adequate employment is lower than in the control group. Besides the 'general effect' of support we also find less favorable job opportunities for those who attended 'external' as compared to 'workplace-related' training.
Distance Functions for Matching in Small Samples
Computational Statistics & Data Analysis,
The development of ‘standards’ for the application of matching algorithms in empirical evaluation studies is still an outstanding goal. The first step of the matching procedure is the choice of an appropriate distance function. In empirical evaluation situations often the sample sizes are small. Moreover, they consist of variables with different scale levels which have to be considered explicitly in the matching process. A simulation is performed which is directed towards these empirical challenges and supplements former studies in this respect. The choice of the analysed distance functions is determined by the results of former theoretical studies and recommendations in the empirical literature. Thus, two balancing scores (the propensity score and the index score) and the Mahalanobis distance are considered. Additionally, aggregated statistical distance functions not yet used for empirical evaluation are included. The matching outcomes are compared using non-parametric scale-specific tests for identical distributions of the characteristics in the treatment and the control groups. The simulation results show that, in small samples, aggregated statistical distance functions are the better choice for summarising similarities in differently scaled variables compared to the commonly used measures.
Subsidized Vocational Training: Stepping Stone or Trap? An Evaluation Study for East Germany
IWH Discussion Papers,
The aim of this paper is to analyze whether the formally equal qualifications acquired during a subsidized vocational education induce equal employment opportunities compared to regular vocational training. Using replacement matching on the basis of a statistical distance function, we are able to control for selection effects resulting from different personal and profession-related characteristics, and thus, to identify an unbiased effect of the public support. Besides the ‘total effect’ of support, it is of special interest if the effect is stronger for subsidized youths in external training compared to persons in workplace-related training. The analysis is based on unique and very detailed data, the Youth Panel of the Halle Centre for Social Research (zsh).
The results show that young people who successfully completed a subsidized vocational education are disadvantaged regarding their employment opportunities even when controlling for personal and profession-related influences on the employment prospects. Besides a quantitative effect, the analysis shows that the graduates of subsidized training work in slightly worse (underqualified) and worse paid jobs than the adolescents in the reference group. The comparison of both types of subsidized vocational training, however, does not confirm the expected stronger effect for youths in external vocational education compared to workplace-related training.
Cross-Border Bank Contagion in Europe
International Journal of Central Banking,
We analyze cross-border contagion among European banks in the period from January 1994 to January 2003. We use a multinomial logit model to estimate, in a given country, the number of banks that experience a large shock on the same day (“coexceedances”) as a function of common shocks and lagged coexceedances in other countries. Large shocks are measured by the bottom 95th percentile of the distribution of the daily percentage change in distance to default of banks.We find evidence of significant cross-border contagion among large European banks, which is consistent with a tiered cross-border interbank structure. The results also suggest that contagion increased after the introduction of the euro.
Cross-border Bank Contagion in Europe
ECB Working Paper, No. 662,
This paper analyses cross-border contagion in a sample of European banks from January 1994 to January 2003. We use a multinomial logit model to estimate the number of banks in a given country that experience a large shock on the same day (“coexceedances“) as a function of variables measuring common shocks and lagged coexceedances in other countries. Large shocks are measured by the bottom 95th percentile of the distribution of the daily percentage change in the distance to default of the bank. We find evidence in favour of significant cross-border contagion. We also find some evidence that since the introduction of the euro cross-border contagion may have increased. The results seem to be very robust to changes in the specification.