TY  - JOUR
A1  - Kohler, Ulrich
A1  - Kreuter, Frauke
A1  - Stuart, Elizabeth A.
T1  - Nonprobability Sampling and Causal Analysis
JF  - Annual review of statistics and its application
N2  - The long-standing approach of using probability samples in social science research has come under pressure through eroding survey response rates, advanced methodology, and easier access to large amounts of data. These factors, along with an increased awareness of the pitfalls of the nonequivalent comparison group design for the estimation of causal effects, have moved the attention of applied researchers away from issues of sampling and toward issues of identification. This article discusses the usability of samples with unknown selection probabilities for various research questions. In doing so, we review assumptions necessary for descriptive and causal inference and discuss research strategies developed to overcome sampling limitations.
KW  - causal inference
KW  - generalizability
KW  - self-selection
KW  - nonprobability sampling
KW  - validity
KW  - measurement error
KW  - heterogeneous treatment effects
KW  - big data
Y1  - 2018
U6  - https://doi.org/10.1146/annurev-statistics-030718-104951
SN  - 2326-8298
SN  - 2326-831X
VL  - 6
SP  - 149
EP  - 172
PB  - Annual Reviews
CY  - Palo Alto
ER  - 
TY  - JOUR
A1  - Asendorpf, Jens B.
A1  - Conner, Mark
A1  - De Fruyt, Filip
A1  - De Houwer, Jan
A1  - Denissen, Jaap J. A.
A1  - Fiedler, Klaus
A1  - Fiedler, Susann
A1  - Funder, David C.
A1  - Kliegl, Reinhold
A1  - Nosek, Brian A.
A1  - Perugini, Marco
A1  - Roberts, Brent W.
A1  - Schmitt, Manfred
A1  - vanAken, Marcel A. G.
A1  - Weber, Hannelore
A1  - Wicherts, Jelte M.
T1  - Recommendations for increasing replicability in psychology
JF  - European journal of personality
N2  - Replicability of findings is at the heart of any empirical science. The aim of this article is to move the current replicability debate in psychology towards concrete recommendations for improvement. We focus on research practices but also offer guidelines for reviewers, editors, journal management, teachers, granting institutions, and university promotion committees, highlighting some of the emerging and existing practical solutions that can facilitate implementation of these recommendations. The challenges for improving replicability in psychological science are systemic. Improvement can occur only if changes are made at many levels of practice, evaluation, and reward.
KW  - replicability
KW  - confirmation bias
KW  - publication bias
KW  - generalizability
KW  - research transparency
Y1  - 2013
U6  - https://doi.org/10.1002/per.1919
SN  - 0890-2070
VL  - 27
IS  - 2
SP  - 108
EP  - 119
PB  - Wiley-Blackwell
CY  - Hoboken
ER  - 
TY  - JOUR
A1  - Klaus, Valentin H.
A1  - Hölzel, Norbert
A1  - Boch, Steffen
A1  - Müller, Jorg
A1  - Socher, Stephanie A.
A1  - Prati, Daniel
A1  - Fischer, Markus
A1  - Kleinebecker, Till
T1  - Direct and indirect associations between plant species richness and productivity in grasslands regional differences preclude simple generalization of productivity-biodiversity relationships
JF  - Preslia : the journal of the Czech Botanical Society
N2  - Plant species richness of permanent grasslands has often been found to be significantly associated with productivity. Concentrations of nutrients in biomass can give further insight into these productivity-plant species richness relationships, e.g. by reflecting land use or soil characteristics. However, the consistency of such relationships across different regions has rarely been taken into account, which might significantly compromise our potential for generalization. We recorded plant species richness and measured above-ground biomass and concentrations of nutrients in biomass in 295 grasslands in three regions in Germany that differ in soil and climatic conditions. Structural equation modelling revealed that nutrient concentrations were mostly indirectly associated with plant species richness via biomass production. However, negative associations between the concentrations of different nutrients and biomass and plant species richness differed considerably among regions. While in two regions, more than 40% of the variation in plant species richness could be attributed to variation in biomass, K, P. and to some degree also N concentrations, in the third region only 15% of the variation could be explained in this way. Generally, highest plant species richness was recorded in grasslands where N and P were co-limiting plant growth, in contrast to N or K (co-) limitation. But again, this pattern was not recorded in the third region. While for two regions land-use intensity and especially the application of fertilizers are suggested to be the main drivers causing the observed negative associations with productivity, in the third region the little variance accounted for, low species richness and weak relationships implied that former intensive grassland management, ongoing mineralization of peat and fluctuating water levels in fen grasslands have overruled effects of current land-use intensity and productivity. Finally, we conclude that regional replication is of major importance for studies seeking general insights into productivity-diversity relationships.
KW  - anthropogenic effect
KW  - Biodiversity Exploratories project
KW  - fen grasslands
KW  - generalizability
KW  - land-use history
KW  - nitrogen
KW  - phosphorus
KW  - potassium
KW  - plant species richness
KW  - structural equation modeling
Y1  - 2013
SN  - 0032-7786
VL  - 85
IS  - 2
SP  - 97
EP  - 112
PB  - Czech Botanical Soc.
CY  - Praha
ER  -