Browsing by Author "Hirschauer, Norbert"

It has often been noted that the “null-hypothesis-significance-testing” (NHST) framework is an inconsistent hybrid of Neyman-Pearson’s “hypothesis testing” and Fisher’s “significance testing” that almost inevitably causes misinterpretations. To facilitate a realistic assessment of the potential and the limits of statistical inference, we briefly recall widespread inferential errors and outline the two original approaches of these famous statisticians. Based on the understanding of their irreconcilable perspectives, we propose “going back to the roots” and using the initial evidence in the data in terms of the size and the uncertainty of the estimate for the purpose of statistical inference. Finally, we make six propositions that hopefully contribute to improving the quality of inferences in future research.

Farm-level adaptation to changing economic environments is often slower than expected. Technological innovations, for instance, are frequently adopted at a later date than the net present value of investment suggests. This can be explained by a model of "investment under uncertainty," which consistently accounts for uncertainty, sunk costs, and the flexibility of investment timing. Its essential conclusion is that, due to temporal opportunity costs, critical incremental cash flows that trigger investments might be higher than those needed for simple cost recovery. This accounts for an ostensible reluctance to invest (economic hysteresis). In this article, we demonstrate how slow conversion to organic farming in general, and the different rates of conversion in Germany and Austria in particular, can be explained by the new investment theory.

This article shows that including inconsistent subjects in a Holt-and-Laury analysis will bias the mean, as well as the variance of the risk attitudes of the subject group of interest to an extent that cannot be determined a priori and that must not be neglected. One might be tempted to simply drop inconsistent subjects from the analysis to avoid such biases in a population-level analysis. Unfortunately, however, this is not a solution: first, the sample size may fall to an unacceptably low level. Second - and even more important - simply dropping inconsistent subjects from the analysis may introduce another unknown bias since systematic differences may exist in the risk preferences of those who answer consistently and those who do not. One must thus conclude that, if the group of interest contains a large proportion of inconsistent subjects, the whole set-up of the Holt-and-Laury lottery (HLL) experiment must be critically reconsidered and the experiment eventually repeated.

In the past decades, a great interest has emerged in understanding the nature of people's well-being beyond consumption opportunities. It is widely believed that happiness research based on self-reports on people's satisfaction with life has made a significant contribution to this understanding. The growing numbers of happiness studies provoke the question whether, and eventually how, public economists should include well-being considerations into policy analysis. Aiming to contribute in answering this question, this review paper provides a survey of the general happiness conception, the formative steps of happiness research, and its relationship to the economic concepts of ordinal and cardinal utility. We furthermore describe the pitfalls of conventional utility approaches and find that both the ordinal and the cardinal approaches have shortcomings which are not shared by happiness measurements. One advantage is that self-reports on well-being reflect the consequences of people's choices in terms of the well-being they eventually experience. Externalities, as well as the effects of bounded rationality, are inherently taken account of when using happiness measurements for the evaluation of public policies. While it is not entirely clear yet how evidence from happiness research is to be used towards enlightening policy makers, the answer will certainly depend on the policy field under consideration. In general, happiness research may make two major inroads: it may help to discover which conditions foster people's well-being, besides the goods and services provided by the market; it may also help to develop a realistic conception of man, thus facilitating an adequate modeling of multiple-goal and potentially bounded rational real-life actors in policy impact analysis.

Experiments are often used to study individual decision-making under controlled circumstances. Due to their low opportunity costs and high availability, university students are frequently recruited as the study population. Even though they are rather untypical with regard to many characteristics (e.g. age and income) compared to the representatives of the social group of interest, the experimental behaviours of students are sometimes prematurely generalised to other social groups or even to humans in general. Given the widespread challenges in the agricultural and environmental sector, it is particularly interesting to address farmers’ decision-making. We analyse whether agricultural students can be used to approximate the behaviour of farmers in simple economic experiments, which are often used to measure risk aversion, impatience, positive reciprocity, negative reciprocity, altruism and trust. Moreover, we consider the role of systematically varied monetary incentives. We find no differences between agricultural students and farmers in their risk aversion; farmers’ positive reciprocity and trust are positively associated with the incentive level, which cannot be observed with agricultural students. Findings regarding altruism in the two populations are mixed and challenge the finding of earlier studies of students being less pro-social. Agricultural students are a lower boundary of impatience and negative reciprocity. These heterogeneous results suggest that scientific inference from agricultural students to farmers should be made cautiously. However, we do not deal with a representative sample of our target population (e.g. gender). Replication studies are required to evaluate the generalisability of our findings.

According to demographic forecasts, the German labour force supply will decrease dramatically over the next decades. In its attempt to attract sufficiently large numbers of young professionals the farming sector may thus face fierce competition from other industries. With this in mind, we have carried out a survey among various social groups: students of agriculture, employees from both within and from outside the agricultural field, and farmers. Regarding the perception of jobs in the agricultural industry this survey produced some interesting results: First, outsiders have an overwhelmingly negative assessment of the industry's working conditions. They overestimate, for example, the required overtime hours. Second, given the great number of non-economic advantages the sense of professional fulfilment and job satisfaction are considerably higher within the farming industry than outside. Third, there are effective and less effective ways to increase job satisfaction by providing a little "top-up". A pay rise leads to farm workers proportionally accepting an increased number of annual working hours by working more hours each weak. The opposite is true if the overall work load is increased by reducing employees' annual leave entitlement. Since many people outside the agricultural world often have but poor information about the industry and its jobs, conveying objective information about the excellent and diverse working opportunities is crucial if the sector is to compete successfully for qualified young professionals.

Abstract Statistical inference allows researchers to learn things about a population using only a sample of data from that population. But if it isn't a random sample, inference becomes tricky or outright impossible, as Norbert Hirschauer, Sven Grüner, Oliver Mußhoff, Claudia Becker and Antje Jantsch explain

The p-value is often considered as the gold standard in inferential statistics. The standard approach for evaluating empirical evidence is to equate low p-values with a high degree of credibility and to refer to findings with p-values below certain thresholds (e.g., 0.05) as statistically significant. The p-value is also referred to as error probability. Both terms are problematic as they invite serious misconceptions. In addition, researchers' fixation on obtaining statistically significant results may introduce biases and increase the rate of false discoveries. Misinterpretations of the p-value as well as the introduction of bias through arbitrary analytical choices (p-hacking) have been critically discussed in the literature for decades. Nonetheless, they seem to persist in empirical research and criticisms of inappropriate approaches have increased in the recent past-mainly due to the non-replicability of many studies. Unfortunately, the critical concerns that have been raised in the literature are not only scattered over many academic disciplines but often also linguistically confusing and differing in their main reasons for criticisms. Against this background, our methodological comment systematizes the most serious flaws and discusses suggestions of how best to prevent future misuses.

Investment decisions are not only characterised by irreversibility and uncertainty but also by flexibility with regard to the timing of the investment. This paper describes how stochastic simulation can be successfully integrated into a backward recursive programming approach in the context of flexible investment planning. We apply this hybrid approach to a marketing question from primary production which can be viewed as an investment problem: should grain farmers purchase sales contracts which guarantee fixed product prices over the next 10 years? The model results support the conclusion from dynamic investment theory that it is essential to take simultaneously account of uncertainty and flexibility.

Weather-index insurances are innovative risk management instruments that - compared to conventional insurances - cause low administration and regulation costs and are not accompanied by moral hazard or adverse selection problems. Despite these advantages, farmers make little use of weather-index insurances as yet. With this in mind, the present study focuses on the question if bounded rationality provides an explanation for the missing willingness to adopt this type of insurance. For lack of a natural experiment, an "extra-laboratory experiment" is carried out in the form of a multi-period, single-person business simulation game with students of agricultural sciences. Two major questions are to be answered: first, does the demand for weather-index insurances change if the subjects are not only informed about the total insurance premium but also about the loading? Second, does demand change in a framing where subjects are told that the (unchanged loading) is the result of a subsidized insurance offer? In the experiment, the explicit communication of the loading did not have a significant effect. However, demand increased in the subsidization framing. This indicates that government funding is per se considered as a quality signal and that subsidized actions are preferred without an individual analysis of their relative competitiveness.

Data envelopment analysis (DEA) is widely used to compare the empirical performance of public institutions such as law enforcement agencies, judicial authorities or national health care systems. Many DEA analysts, however, ignore the fact that DEA efficiency values are non-metric. They consequently do not hesitate to compute (arithmetic) means. They do not hesitate either to treat DEA values as metric data in econometric analyses. Instead of providing useful insights into the performance of public bodies, the confusion of non-metric data with metric data constitutes a lack of internal validity that may cause serious fallacies. Against this background, we believe that a clear warning against an uncritical processing and interpretation of DEA values is pertinent and should be routinely considered by efficiency analysts as well as referees of efficiency papers.

Mathematical programming has for a long time been recognized as a powerful tool. Despite its capacity for solving constrained optimization problems under uncertainty, some methodological obstacles have persisted over the years. The main problem is that the eventually complex results of an unbiased statistical analysis (multiple correlated stochastic variables with different distributions and nonadditive links between) cannot be adequately accounted for within minimization of total absolute deviation (MOTAD) or expected value-variance (EV) models that rely on the algorithmic determination of the variability measure. In this paper, we develop a methodological hybrid consisting of Monte Carlo simulation and genetic algorithms: the Monte Carlo simulation facilitates the easy representation of diverse stochastic processes and correlation, and the genetic algorithm ensures that the optimization procedure remains applicable even in the case of complex stochastic information. This hybrid approach is applied to the production-planning problem of a German crop farm. Variant calculations are used to account for the unknown risk attitude of the farmer. Model results demonstrate that optimized production programs and expected total gross margins are not only highly sensitive to the risk attitude, but also to the stochastic processes that are estimated (or assumed) for various activities. We furthermore find evidence that the hybrid approach is able to generate considerable improvement in farm-program decisions and outperforms planning models that assume static distributions.

Since the mid-1990s, agricultural economists have discussed the relevance of index-based insurances, also called “weather derivatives”, as hedging instruments for volumetric risks in agriculture. Motivated by the question of how weather derivatives should be priced for agricultural firms, this paper describes an extended risk-programming model which can be used to determine farmers’ willingness to pay (demand function) for weather derivative’s farm-specific risk reduction capacity and the individual farmer’s risk acceptance. Applying it to the exemplary case of a Brandenburg farm reveals that even a highly standardized contract which is based on the accumulated rainfall at the capital’s meteorological station in Berlin-Tempelhof generates a relevant willingness to pay. Our findings suggest that a potential underwriter could even add a loading on the actuarially fair price which exceeds the level of traditional insurances. Since translation costs are low compared to insurance contracts, this finding indicates there may be a relevant trading potential.

Regulatory policies often aim to steer the behaviour of economic agents by changing their framework conditions. Assessing the impact of such policies requires forecasts of how humans adapt to changes in their economic environment. A prerequisite for a meaningful policy impact analysis is a profound knowledge why and to what extent economic agents behave in a bounded rational way. We propose that business management games be used to contribute to a better understanding since they provide an inexpensive opportunity to reach beyond the existing anecdotic evidence of "behavioural anomalies". Modifying an existing business management game, in which investment, financing and production decisions have to be made, we demonstrate how bounded rationality can be quantified and separated into its two components: incomplete information and limited cognitive abilities. The resulting data indicate that the decisions made by the participants of the game have been strongly influenced by bounded rationality. They also show that both incomplete information and limited cognitive abilities are relevant components of the bounded rationality that has been displayed by the players. Regulatory impact analysts who base their forecasts a priori on the standard rational choice assumption cause the risk of measures being designed for economic agents that do not exist in reality.