Maximum Likelihood Estimation of Asymmetric Double Type II Pareto Distributions

Abstract

This paper considers a flexible class of asymmetric double Pareto distributions (ADP) that allows for skewness and asymmetric heavy tails. The inference problem is examined for maximum likelihood. Consistency is proven for the general case when all parameters are unknown. After deriving the Fisher information matrix, asymptotic normality and efficiency are established for a restricted model with the location parameter known. The asymptotic properties of the estimators are then examined using Monte Carlo simulations. To assess its goodness of fit, the ADP is applied to companies’ growth rates, for which it is favored over competing models.

Amundsen versus Scott: are growth paths related to firm performance?

Article (with peer review)Publication

Coad, A., Daunfeldt, SO. & Halvarsson, D.

Publication year

2022

Published in

Small Business Economics 59, 593–610 (2022).

Abstract

In the race to the South Pole, Roald Amundsen’s expedition covered an equal distance each day, irrespective of weather conditions, while Scott’s pace was erratic. Amundsen won the race and returned without loss of life, while Scott and his men died. In the context of firm growth, the Amundsen hypothesis suggests that smoother growth paths are associated with better performance in subsequent periods. We develop a new method to investigate how firms’ sales growth deviates from their long-run average growth path. Our baseline results suggest that growth path volatility is associated with higher growth of sales and profits, but also with higher exit rates. However, this result is driven by firms with negative growth rates. For positive-growth firms, volatility is negatively associated with both sales growth and survival, providing nuanced support for the Amundsen hypothesis.

The article can be accessed here.

Ratio Working Paper No. 358: Native Population Turnover & Emerging Segregation: The Role of Amenities, Crime and Housing

Working paperPublication

Korpi, M., Halvarsson, D., Öner, Ö., A.V. Clark, W., Mihaescu, O., Östh, J. & Bäckman, O.

Download

Publication year

2022

Published in

Ratio Working Paper.

Abstract

Using geo-coded full-population grid-level data for the three largest metropolitan areas in Sweden, 1993-2016, this paper i) estimates the level and pace of ethnic segregation, ii) examines possible tipping points in this development, and iii) gauges the importance of several mitigating or exacerbating factors (such as the mix of housing area tenure type, different types of amenities, and crime). We use OLS and 2SLS to estimate outcomes at two different geographic levels; 250 x 250 square meter grids and SAMS areas (roughly equivalent to US census tracts), respectively. On average, we find that for every 1 percentage point increase in immigration, native growth is reduced by around -0.3 percentage points. Crime levels exacerbate developments and factors such as housing area tenure-type mix and access to various amenities slows it down, but only marginally so. Using repeated and single random sampling for cross-validation, and the twin common methodological approaches as suggested in the literature, we estimate possible tipping points in these segregation developments. In contrast to most other studies in the literature, none of our potential tipping points are however statistically significant when probing their relevance in explaining factual population developments, suggesting a rather more continuous – albeit steeply so – segregation process rather than a structural brake. In terms of tipping point methodology, our main findings are that fixed-point estimation is less robust than R-square maximization for small geographical units, and that the former consistently selects for lower tipping-point candidates than the latter.

Ratio Working Paper No. 360: Do gender norms travel within corporations? The impact of foreign subsidiaries on the home country gender wage gap

Working paperPublication

Halvarsson, D., Lark, O., Tingvall, P., Vatherd, P. & Videnord, J.

Download

Publication year

2022

Published in

Ratio Working Paper series.

Abstract

In this note, we provide evidence that gender norms can be transferred within firms and across borders by means of foreign direct investment. Using microdata from both Sweden and Estonia, two countries with vastly different levels of gender inequality, we find that firms in Sweden with strong intra-firm linkages to Estonia display a relatively large gender wage gap at home.

Abstract

Similar content