The utility and application of mixed-effects models in second language research

Second language acquisition researchers often face particular challenges when attempting to generalize study findings to the wider learner population. For example, language learners constitute a heterogeneous group, and it is not always clear how a study’s findings may generalize to other individuals who may differ in terms of language background and proficiency, among many other factors. In this paper, we provide an overview of how mixed-effects models can be used to help overcome these and other issues in the field of second language acquisition. We provide an overview of the benefits of mixed-effects models and a practical example of how mixed-effects analyses can be conducted. Mixed-effects models provide second language researchers with a powerful statistical tool in the analysis of a variety of different types of data.

An overview of mixed-effects statistical models for second language researchers

As in any field of scientific inquiry, advancements in the field of second language acquisition (SLA) rely in part on the interpretation and generalizability of study findings using quantitative data analysis and inferential statistics. While statistical techniques such as ANOVA and t-tests are widely used in second language research, this review article provides a review of a class of newer statistical models that have not yet been widely adopted in the field, but have garnered interest in other fields of language research. The class of statistical models called mixed-effects models are introduced, and the potential benefits of these models for the second language researcher are discussed. A simple example of mixed-effects data analysis using the statistical software package R (R Development Core Team, 2011) is provided as an introduction to the use of these statistical techniques, and to exemplify how such analyses can be reported in research articles. It is concluded that mixed-effects models provide the second language researcher with a powerful tool for the analysis of a variety of types of second language acquisition data.

Coupled simulations of the Indian monsoon intraseasonal oscillation using a fine-resolution mixed-layer ocean model

The intraseasonal variability (ISV) of the Indian summer monsoon is dominated by a 30–50 day oscillation between “active” and “break” events of enhanced and reduced rainfall over the subcontinent, respectively. These organized convective events form in the equatorial Indian Ocean and propagate north to India. Atmosphere–ocean coupled processes are thought to play a key role the intensity and propagation of these events. A high-resolution, coupled atmosphere–mixed-layer-oceanmodel is assembled: HadKPP. HadKPP comprises the Hadley Centre Atmospheric Model (HadAM3) and the K Profile Parameterization (KPP) mixed-layer ocean model. Following studies that upper-ocean vertical resolution and sub-diurnal coupling frequencies improve the simulation of ISV in SSTs, KPP is run at 1 m vertical resolution near the surface; the atmosphere and ocean are coupled every three hours. HadKPP accurately simulates the 30–50 day ISV in rainfall and SSTs over India and the Bay of Bengal, respectively, but suffers from low ISV on the equator. This is due to the HadAM3 convection scheme producing limited ISV in surface fluxes. HadKPP demonstrates little of the observed northward propagation of intraseasonal events, producing instead a standing oscillation. The lack of equatorial ISV in convection in HadAM3 constrains the ability of KPP to produce equatorial SST anomalies, which further weakens the ISV of convection. It is concluded that while atmosphere–ocean interactions are undoubtedly essential to an accurate simulation of ISV, they are not a panacea for model deficiencies. In regions where the atmospheric forcing is adequate, such as the Bay of Bengal, KPP produces SST anomalies that are comparable to the Tropical Rainfall Measuring Mission Microwave Imager (TMI) SST analyses in both their magnitude and their timing with respect to rainfall anomalies over India. HadKPP also displays a much-improved phase relationship between rainfall and SSTs over a HadAM3 ensemble forced by observed SSTs, when both are compared to observations. Coupling to mixed-layer models such as KPP has the potential to improve operational predictions of ISV, particularly when the persistence time of SST anomalies is shorter than the forecast lead time.

Mixed Logit Model Performance and Distributional Assumptions: Preferences and GM foods

Using mixed logit models to analyse choice data is common but requires ex ante specification of the functional forms of preference distributions. We make the case for greater use of bounded functional forms and propose the use of the Marginal Likelihood, calculated using Bayesian techniques, as a single measure of model performance across non nested mixed logit specifications. Using this measure leads to very different rankings of model specifications compared to alternative rule of thumb measures. The approach is illustrated using data from a choice experiment regarding GM food types which provides insights regarding the recent WTO dispute between the EU and the US, Canada and Argentina and whether labelling and trade regimes should be based on the production process or product composition.

A cross-sectional study of reproductive performance of smallholder dairy cows in coastal Tanzania

A retrospective cross-sectional study was conducted on 200 randomly selected smallholder farms from a mixed dairy farming system in Tanga, Tanzania, between January and April 1999. We estimated the frequency and determinants of long calving interval (LCI), retention of fetal membrane (RFM), dystocia, and abortion in smallholder crossbred cattle and explored birth trends. The mean calving interval was 500 days and birth rate was 65 per 100 cow-years. Dystocia was reported to affect 58% of calvings, and 17.2% of animals suffered RFM. Using mixed effect models, the variables associated with LCI, RFM and dystocia were breed, level of exotic blood and condition score. Zebu breeding was associated with LCI (odds ratio (OR) = 2.3, p = 0.041) and Friesian breeding with lower odds for RF (OR = 0.26, p = 0.020). Animals with higher levels of exotic blood had lower odds for evidence of dystocia (OR = 0.45, p = 0.021). Evidence of dystocia was significantly associated with poor condition score (beta = -1.10, p = 0.001). Our observations suggest that LCIs are common in smallholder dairy farms in this region and a likely source of economic loss. Dystocia, RFM, poor condition score and mineral deficiency were common problems and were possibly linked to LCI.

Physical activity attenuates the body mass index-increasing influence of genetic variation in the FTO gene 1-3.

BACKGROUND: Intronic variation in the FTO (fat mass and obesity-associated) gene has been unequivocally associated with increased body mass index (BMI; in kg/m(2)) and the risk of obesity in populations of different ethnicity. OBJECTIVE: We examined whether this robust genetic predisposition to obesity can be attenuated by being more physically active. DESIGN: The FTO variant rs1121980 was genotyped in 20,374 participants (39-79 y of age) from the European Prospective Investigation into Cancer and Nutrition-Norfolk Study, an ethnically homogeneous population-based cohort. Physical activity (PA) was assessed with a validated self-reported questionnaire. The interaction between rs1121980 and PA on BMI and waist circumference (WC) was examined by including the interaction term in mixed-effect models. RESULTS: We confirmed that the risk (T) allele of rs1121980 was significantly associated with BMI (0.31-unit increase per allele; P < 0.001) and WC (0.77-cm increase per allele; P < 0.001). The PA level attenuated the effect of rs1121980 on BMI and WC; ie, whereas in active individuals the risk allele increased BMI by 0.25 per allele, the increase in BMI was significantly (P for interaction = 0.004) more pronounced (76%) in inactive individuals (0.44 per risk allele). We observed similar effects for WC (P for interaction = 0.02): the risk allele increased WC by 1.04 cm per allele in inactive individuals but by only 0.64 cm in active individuals. CONCLUSIONS: Our results showed that PA attenuates the effect of the FTO rs1121980 genotype on BMI and WC. This observation has important public health implications because we showed that a genetic susceptibility to obesity induced by FTO variation can be overcome, at least in part, by adopting a physically active lifestyle.

Non-replication of the association between 5HTTLPR and response to psychological therapy for child anxiety disorders

Background We previously reported an association between 5HTTLPR genotype and outcome following cognitive–behavioural therapy (CBT) in child anxiety (Cohort 1). Children homozygous for the low-expression short-allele showed more positive outcomes. Other similar studies have produced mixed results, with most reporting no association between genotype and CBT outcome. Aims To replicate the association between 5HTTLPR and CBT outcome in child anxiety from the Genes for Treatment study (GxT Cohort 2, n = 829). Method Logistic and linear mixed effects models were used to examine the relationship between 5HTTLPR and CBT outcomes. Mega-analyses using both cohorts were performed. Results There was no significant effect of 5HTTLPR on CBT outcomes in Cohort 2. Mega-analyses identified a significant association between 5HTTLPR and remission from all anxiety disorders at follow-up (odds ratio 0.45, P = 0.014), but not primary anxiety disorder outcomes. Conclusions The association between 5HTTLPR genotype and CBT outcome did not replicate. Short-allele homozygotes showed more positive treatment outcomes, but with small, non-significant effects. Future studies would benefit from utilising whole genome approaches and large, homogenous samples.

HPA axis related genes and response to psychological therapies: genetics and epigenetics

Background Hypothalamic–pituitary–adrenal (HPA) axis functioning has been implicated in the development of stress-related psychiatric diagnoses and response to adverse life experiences. This study aimed to investigate the association between genetic and epigenetics in HPA axis and response to cognitive behavior therapy (CBT). Methods Children with anxiety disorders were recruited into the Genes for Treatment project (GxT, N = 1,152). Polymorphisms of FKBP5 and GR were analyzed for association with response to CBT. Percentage DNA methylation at the FKBP5 and GR promoter regions was measured before and after CBT in a subset (n = 98). Linear mixed effect models were used to investigate the relationship between genotype, DNA methylation, and change in primary anxiety disorder severity (treatment response). Results Treatment response was not associated with FKBP5 and GR polymorphisms, or pretreatment percentage DNA methylation. However, change in FKBP5 DNA methylation was nominally significantly associated with treatment response. Participants who demonstrated the greatest reduction in severity decreased in percentage DNA methylation during treatment, whereas those with little/no reduction in severity increased in percentage DNA methylation. This effect was driven by those with one or more FKBP5 risk alleles, with no association seen in those with no FKBP5 risk alleles. No significant association was found between GR methylation and response. Conclusions Allele-specific change in FKBP5 methylation was associated with treatment response. This is the largest study to date investigating the role of HPA axis related genes in response to a psychological therapy. Furthermore, this is the first study to demonstrate that DNA methylation changes may be associated with response to psychological therapies in a genotype-dependent manner.

EDITOR'S CHOICE: REVIEW: Trait matching of flower visitors and crops predicts fruit set better than trait diversity

Understanding the relationships between trait diversity, species diversity and ecosystem functioning is essential for sustainable management. For functions comprising two trophic levels, trait matching between interacting partners should also drive functioning. However, the predictive ability of trait diversity and matching is unclear for most functions, particularly for crop pollination, where interacting partners did not necessarily co-evolve. World-wide, we collected data on traits of flower visitors and crops, visitation rates to crop flowers per insect species and fruit set in 469 fields of 33 crop systems. Through hierarchical mixed-effects models, we tested whether flower visitor trait diversity and/or trait matching between flower visitors and crops improve the prediction of crop fruit set (functioning) beyond flower visitor species diversity and abundance. Flower visitor trait diversity was positively related to fruit set, but surprisingly did not explain more variation than flower visitor species diversity. The best prediction of fruit set was obtained by matching traits of flower visitors (body size and mouthpart length) and crops (nectar accessibility of flowers) in addition to flower visitor abundance, species richness and species evenness. Fruit set increased with species richness, and more so in assemblages with high evenness, indicating that additional species of flower visitors contribute more to crop pollination when species abundances are similar. Synthesis and applications. Despite contrasting floral traits for crops world-wide, only the abundance of a few pollinator species is commonly managed for greater yield. Our results suggest that the identification and enhancement of pollinator species with traits matching those of the focal crop, as well as the enhancement of pollinator richness and evenness, will increase crop yield beyond current practices. Furthermore, we show that field practitioners can predict and manage agroecosystems for pollination services based on knowledge of just a few traits that are known for a wide range of flower visitor species.

Assessing species’ habitat associations from occurrence records, standardised monitoring data and expert opinion: a test with British butterflies

Accurate knowledge of species’ habitat associations is important for conservation planning and policy. Assessing habitat associations is a vital precursor to selecting appropriate indicator species for prioritising sites for conservation or assessing trends in habitat quality. However, much existing knowledge is based on qualitative expert opinion or local scale studies, and may not remain accurate across different spatial scales or geographic locations. Data from biological recording schemes have the potential to provide objective measures of habitat association, with the ability to account for spatial variation. We used data on 50 British butterfly species as a test case to investigate the correspondence of data-derived measures of habitat association with expert opinion, from two different butterfly recording schemes. One scheme collected large quantities of occurrence data (c. 3 million records) and the other, lower quantities of standardised monitoring data (c. 1400 sites). We used general linear mixed effects models to derive scores of association with broad-leaf woodland for both datasets and compared them with scores canvassed from experts. Scores derived from occurrence and abundance data both showed strongly positive correlations with expert opinion. However, only for occurrence data did these fell within the range of correlations between experts. Data-derived scores showed regional spatial variation in the strength of butterfly associations with broad-leaf woodland, with a significant latitudinal trend in 26% of species. Sub-sampling of the data suggested a mean sample size of 5000 occurrence records per species to gain an accurate estimation of habitat association, although habitat specialists are likely to be readily detected using several hundred records. Occurrence data from recording schemes can thus provide easily obtained, objective, quantitative measures of habitat association.

Ecological traits affect the sensitivity of bees to land-use pressures in European agricultural landscapes

1. Bees are a functionally important and economically valuable group, but are threatened byland-use conversion and intensification. Such pressures are not expected to affect all species identically; rather, they are likely to be mediated by the species’ ecological traits. 2. Understanding which types of species are most vulnerable under which land uses is an important step towards effective conservation planning.3. We collated occurrence and abundance data for 257 bee species at 1584 European sites from surveys reported in 30 published papers (70 056 records) and combined them with species-level ecological trait data. We used mixed-effects models to assess the importance of land use (land-use class, agricultural use-intensity and a remotely-sensed measure of vegetation),traits and trait 9 land-use interactions, in explaining species occurrence and abundance.4. Species’ sensitivity to land use was most strongly influenced by flight season duration and foraging range, but also by niche breadth, reproductive strategy and phenology, with effects that differed among cropland, pastoral and urban habitats.5. Synthesis and applications. Rather than targeting particular species or settings, conservation action s may be more effective if focused on mitigating situations where species’ traits strongly and negatively interact with land-use pressures. We find evidence that low-intensity agriculture can maintain relatively diverse bee communities; in more intensive settings, added floral resources may be beneficial, but will require careful placement with respect to foraging ranges of smaller bee species. Protection of semi-natural habitats is essential, however; in particular, conversion to urban environments could have severe effects on bee diversity and pollination services. Our results highlight the importance of exploring how ecological traits mediate species responses to human impacts, but further research is needed to enhance the predictive ability of such analyses.

A comparison of three canopy interception models for a leafless mixed deciduous forest stand in the eastern United States

Canopy interception of incident precipitation is a critical component of the forest water balance during each of the four seasons. Models have been developed to predict precipitation interception from standard meteorological variables because of acknowledged difficulty in extrapolating direct measurements of interception loss from forest to forest. No known study has compared and validated canopy interception models for a leafless deciduous forest stand in the eastern United States. Interception measurements from an experimental plot in a leafless deciduous forest in northeastern Maryland (39°42'N, 75°5'W) for 11 rainstorms in winter and early spring 2004/05 were compared to predictions from three models. The Mulder model maintains a moist canopy between storms. The Gash model requires few input variables and is formulated for a sparse canopy. The WiMo model optimizes the canopy storage capacity for the maximum wind speed during each storm. All models showed marked underestimates and overestimates for individual storms when the measured ratio of interception to gross precipitation was far more or less, respectively, than the specified fraction of canopy cover. The models predicted the percentage of total gross precipitation (PG) intercepted to within the probable standard error (8.1%) of the measured value: the Mulder model overestimated the measured value by 0.1% of PG; the WiMo model underestimated by 0.6% of PG; and the Gash model underestimated by 1.1% of PG. The WiMo model’s advantage over the Gash model indicates that the canopy storage capacity increases logarithmically with the maximum wind speed. This study has demonstrated that dormant-season precipitation interception in a leafless deciduous forest may be satisfactorily predicted by existing canopy interception models.

Mixed-phase cloud physics and Southern Ocean cloud feedback in climate models

Increasing optical depth poleward of 45° is a robust response to warming in global climate models. Much of this cloud optical depth increase has been hypothesized to be due to transitions from ice-dominated to liquid-dominated mixed-phase cloud. In this study, the importance of liquid-ice partitioning for the optical depth feedback is quantified for 19 Coupled Model Intercomparison Project Phase 5 models. All models show a monotonic partitioning of ice and liquid as a function of temperature, but the temperature at which ice and liquid are equally mixed (the glaciation temperature) varies by as much as 40 K across models. Models that have a higher glaciation temperature are found to have a smaller climatological liquid water path (LWP) and condensed water path and experience a larger increase in LWP as the climate warms. The ice-liquid partitioning curve of each model may be used to calculate the response of LWP to warming. It is found that the repartitioning between ice and liquid in a warming climate contributes at least 20% to 80% of the increase in LWP as the climate warms, depending on model. Intermodel differences in the climatological partitioning between ice and liquid are estimated to contribute at least 20% to the intermodel spread in the high-latitude LWP response in the mixed-phase region poleward of 45°S. It is hypothesized that a more thorough evaluation and constraint of global climate model mixed-phase cloud parameterizations and validation of the total condensate and ice-liquid apportionment against observations will yield a substantial reduction in model uncertainty in the high-latitude cloud response to warming.

Evaluation of a large-eddy model simulation of a mixed-phase altocumulus cloud using microwave radiometer, lidar and Doppler radar data

Using the Met Office large-eddy model (LEM) we simulate a mixed-phase altocumulus cloud that was observed from Chilbolton in southern England by a 94 GHz Doppler radar, a 905 nm lidar, a dual-wavelength microwave radiometer and also by four radiosondes. It is important to test and evaluate such simulations with observations, since there are significant differences between results from different cloud-resolving models for ice clouds. Simulating the Doppler radar and lidar data within the LEM allows us to compare observed and modelled quantities directly, and allows us to explore the relationships between observed and unobserved variables. For general-circulation models, which currently tend to give poor representations of mixed-phase clouds, the case shows the importance of using: (i) separate prognostic ice and liquid water, (ii) a vertical resolution that captures the thin layers of liquid water, and (iii) an accurate representation the subgrid vertical velocities that allow liquid water to form. It is shown that large-scale ascents and descents are significant for this case, and so the horizontally averaged LEM profiles are relaxed towards observed profiles to account for these. The LEM simulation then gives a reasonable. cloud, with an ice-water path approximately two thirds of that observed, with liquid water at the cloud top, as observed. However, the liquid-water cells that form in the updraughts at cloud top in the LEM have liquid-water paths (LWPs) up to half those observed, and there are too few cells, giving a mean LWP five to ten times smaller than observed. In reality, ice nucleation and fallout may deplete ice-nuclei concentrations at the cloud top, allowing more liquid water to form there, but this process is not represented in the model. Decreasing the heterogeneous nucleation rate in the LEM increased the LWP, which supports this hypothesis. The LEM captures the increase in the standard deviation in Doppler velocities (and so vertical winds) with height, but values are 1.5 to 4 times smaller than observed (although values are larger in an unforced model run, this only increases the modelled LWP by a factor of approximately two). The LEM data show that, for values larger than approximately 12 cm s(-1), the standard deviation in Doppler velocities provides an almost unbiased estimate of the standard deviation in vertical winds, but provides an overestimate for smaller values. Time-smoothing the observed Doppler velocities and modelled mass-squared-weighted fallspeeds shows that observed fallspeeds are approximately two-thirds of the modelled values. Decreasing the modelled fallspeeds to those observed increases the modelled IWC, giving an IWP 1.6 times that observed.

Factors influencing anthropogenic carbon dioxide uptake in the North Atlantic in models of the ocean carbon cycle

The uptake and storage of anthropogenic carbon in the North Atlantic is investigated using different configurations of ocean general circulation/carbon cycle models. We investigate how different representations of the ocean physics in the models, which represent the range of models currently in use, affect the evolution of CO2 uptake in the North Atlantic. The buffer effect of the ocean carbon system would be expected to reduce ocean CO2 uptake as the ocean absorbs increasing amounts of CO2. We find that the strength of the buffer effect is very dependent on the model ocean state, as it affects both the magnitude and timing of the changes in uptake. The timescale over which uptake of CO2 in the North Atlantic drops to below preindustrial levels is particularly sensitive to the ocean state which sets the degree of buffering; it is less sensitive to the choice of atmospheric CO2 forcing scenario. Neglecting physical climate change effects, North Atlantic CO2 uptake drops below preindustrial levels between 50 and 300 years after stabilisation of atmospheric CO2 in different model configurations. Storage of anthropogenic carbon in the North Atlantic varies much less among the different model configurations, as differences in ocean transport of dissolved inorganic carbon and uptake of CO2 compensate each other. This supports the idea that measured inventories of anthropogenic carbon in the real ocean cannot be used to constrain the surface uptake. Including physical climate change effects reduces anthropogenic CO2 uptake and storage in the North Atlantic further, due to the combined effects of surface warming, increased freshwater input, and a slowdown of the meridional overturning circulation. The timescale over which North Atlantic CO2 uptake drops to below preindustrial levels is reduced by about one-third, leading to an estimate of this timescale for the real world of about 50 years after the stabilisation of atmospheric CO2. In the climate change experiment, a shallowing of the mixed layer depths in the North Atlantic results in a significant reduction in primary production, reducing the potential role for biology in drawing down anthropogenic CO2.