Regression Procedure Research Articles

The standard errors of persistence

Many studies of historical persistence find that modern outcomes strongly reflect characteristics of the same places in the distant past. However they rely on data that often exhibit extreme spatial trends and autocorrelation, suggesting that their unusually large t-statistics may be due to inadequately controlling for spurious correlation. To analyze this we introduce a new regression procedure and two diagnostic tests of no treatment effect: (a) a placebo test where the treatment is replaced with spatial noise and (b) a synthetic outcomes test of the hypothesis that the outcome is generated by a trend plus a spatial noise process independent of the treatment. We then show how reliable regression results can be obtained by adding a low dimensional spatial basis to the regression of interest, and applying a large cluster standard error correction. Examining 30 persistence studies in leading journals we find that few approach significance at conventional levels. Our procedure applies to regressions with spatial observations more generally and is implemented in an open source package.

Brown vs green energy sources and resource productivity: The role of human capital and technology transfer in developing economies

This study determined the impacts of non-renewable and renewable energy consumption on natural resource productivity alongside human capital and technology transfer roles for 40 selected developing economies. The study relied on a dataset sourced between 1991 and 2021. The study applied the method of moments quantile regression (MMQREG) procedure for the analyses while ensuring inferential robustness through the fully modified ordinary least squares (FMOLS), dynamic OLS (DOLS), and Driscoll-Kraay (D-K) methods. Empirically, the study revealed that an increase in brown energy consumption exhausted resource productivity from the lower to the upper quantiles. In contrast, green energy utilisation enhanced resource productivity from the lower to the higher quantiles. Also, while human capital adversely affected resource productivity for both energy means, technology transfer positively impacted it from the lower to the upper quantiles. Likewise, inferences from the DOLS, FMOLS, and D-K techniques revealed similar findings. However, despite non-renewable energy being the dominant means of energy in these developing economies, the size of its adverse impact on resource productivity falls short of the increasing effect of renewable energy across all quantiles. Also, the magnitude of the negative impact of human capital on resource productivity is marginally more substantial with non-renewable energy. In contrast, the robustness of the enhancing impact of technology transfer is slightly more with renewable energy.

Self-rated health of the older adults in the northeastern region of India: Extent and determinants

AimTo analyse older adults’ self-rated health (SRH) in the northeastern region (NER) of India. MethodsThis study uses data from the 75th round survey on Household Social Consumption: Health conducted by the National Statistical Office (NSO), India, during July 2017–June 2018. The sample for the present consists of 3988 persons aged 60 years and above. Binary logistic regression procedure has been used to identify the determinants of SRH of the older adults. ResultsMore than three-fourth of the older adults in the region perceive their health as ‘good’ or ‘very good’. Older adults' SRH varies with their demographic and socioeconomic profiles. ConclusionIn the context of the NER, creating employment opportunities for the older adults may be of policy importance in the light of the fact that the majority of them report good or very good health but remain dependent on others financially – partially or fully. Achieving ‘healthy ageing’, as defined by WHO, nevertheless requires measures that goes beyond financial independence of the older adults to support their mental health and social wellbeing as well. Future studies may focus on older adults' objective health, health risks protection and their labor market participation in the region.

Navigating Burnout: Exploring Pharmacists’ Attitudes toward Patient Care

Abstract Background The study aimed to investigate the link between pharmacists’ burnout levels and their attitudes toward patient care, crucial for addressing burnout’s impact on service quality and fostering positive patient interactions. Methods The study utilized the Shirom-Melamed Burnout Questionnaire (SMBQ) to assess burnout levels among 442 community pharmacists. Additionally, the five-point Likert Scale of General Attitudes and Beliefs of Pharmacists about their Work with Patients (SOSUF), developed by the authors, was employed to measure pharmacists’ cognitive, affective, and behavioral attitudes toward patient care. Statistical analyses involved correlation and regression procedures. Results Moderate burnout levels among pharmacists observed (mean SMBQ score: 4.18 ± 0.96, range: 1.45 to 6.55), alongside generally positive attitudes toward patient care (mean SOSUF score: 3.44 ± 0.37). Regression analysis revealed a moderate positive correlation between burnout and attitudes toward patient care (R = 0.336, R Square = 0.113, Adjusted R Square = 0.111, p < .001). Burnout impacted pharmacists’ attitudes, notably in perceptions of patients not appreciating their efforts (r = -0.317, p < 0.001), finding patient interactions challenging (r = -0.409, p < 0.001), and disregarding their advice (r = -0.333, p < 0.001). Conclusions Despite generally positive attitudes toward patient care, burnout moderately correlates with negativity, notably impacting perceptions of patient appreciation, interaction challenges, and adherence to advice. Addressing burnout is crucial for maintaining positive patient care attitudes and ensuring quality service delivery. Key messages • Burnout impacts pharmacists’ patient care attitudes, emphasizing the need for intervention to enhance healthcare delivery. • Implementing strategies to reduce burnout among pharmacists can improve patient care outcomes.

An Equation Model on the Professional Knowledge and Confidence for Future Employment of Students in Programs Supported With Emerging Technologies

Students enrolled in interdisciplinary programs supported with modern information technologies may face more challenges in learning, because they must learn from at least two curricula, including courses of big data, new media technologies and intelligent platform use, etc. Taking students in these programs as an example, this study aims to investigate relationships among eight variables related to student career development. The research employed the quantitative method of Pearson bivariate analysis, ANOVA and Hayes (2017) regression procedure to test the direct and indirect relationship among variables. The researcher developed a moderated mediation model visualizing the relationship between professional knowledge and confidence for successful employment. Recommendations of early intervention targeting first-year students and different curriculum designing were proposed to facilitate planning in the acquisition of professional knowledge and the establishment of career goals, aiming to enhance the career development and success of tertiary vocational college students.

Impact of the macroeconomic factors on the level of energy poverty-case of the Czech Republic, Poland and Slovakia

Energy poverty is a socio-economic topic that is not only related to the sustainability problem of natural resource extraction but also human activities. It reflects a situation in which households are unable to fully meet their energy needs. It mainly affects countries with a lower level of development, as well as those whose energy mix is largely based on non-renewable sources (such as coal). These undoubtedly include the Czech Republic, Poland and Slovakia. Investigations are still being conducted to explain the causes of the problem of energy poverty. The paper’s main aim is to assess the impact of selected macroeconomic factors on the level of energy poverty. A backward stepwise regression procedure was used to achieve this aim. Models have been developed for each of the three countries: the Czech Republic, Poland, and Slovakia separately and for all of them together. These models are intended to identify the most prominent macroeconomic factors across all three countries. Results from all four models have highlighted two prominent variables which may impact the level of energy poverty in selected countries. They are following: electricity prices for household consumers with all taxes and net electricity imports. In three of the four developed models, they explained the level of energy poverty in a statistically significant manner. In conclusion, it can be suggested that the governments of these countries take action on these variables, which can help manage energy poverty. Their identification and subsequent impact may help to reduce this problem in the analysed post-coal economies.

Prediction of live weight from body measurements using stepwise regresion models in Karacabey Merino lambs

Objective: The aim of this study is to determine regression models that can be used to estimate live weight from body measurements in Karacabey Merino lambs of different ages(6th, 8th, and 12th months).. Material-Method: The animal material for the study consisted of 200 Karacabey merino lambs. Some body measurements were taken from all lambs and live weights were also weighed. For live weight prediction equations with multiple linear regression analysis using some measurements according to age groups, stepwise multiple regression procedure was used in SAS (1999). DUNCAN test, one of the tests for multiple comparisons, was used to show the differences between groups. Result: The least squares means for body length (BL), withers height (HW), back height (BH), rump height (RH), breast depth (CD), breast width (CW), rump width (RW), and live weight (LW) were 71.28 cm, 69.91 cm, 70.50 cm, 71.57 cm, 30.05 cm, 87.25 cm, 21.50 cm, 23.32 cm, and 51.05 kg, respectively. It is noteworthy that the live weight estimation models for three different age groups using stepwise regression analysis(second, third, and fourth models) can be recommended for the 6th (R2:0.82), 8th (R2:0.71), and 12th (R2:0.79) months of life. The variables that can be used in the equations to estimate body weight for this breed, at these ages are HW, CW, RW, CG, CD, and BL. Conclusion: Finally, it has been demonstrated that the live weights of Karacabey merino lambs can be estimated with high accuracy using the stepwise regression method based on body measurements.

From One Heath to One Sustainability: The Role of Contagious Mastitis Pathogens in Decreasing the Dairy Herd Sustainability.

Economic, social, and environmental sustainability are the results of efforts aiming to improve all aspects of milk production, respecting animal welfare and improving herd health. An epidemiological study was designed to assess the role of contagious pathogens (S. aureus and S. agalactiae) in a cohort of 120 dairy herds located in the southern regions of Italy. Milk quality was assessed using certified methods, and the prevalence of mastitis pathogens in bulk tank milk was determined using quantitative polymerase chain reaction. Welfare scores were assessed using a scoring card that has more than 100 items, including animal-based measurements. Statistical analyses were performed using general lineal model and logistic regression procedures. The results showed that S. aureus had a significant negative effect on the amount of milk nutrients delivered to the dairy plant, and on the level of welfare, whereas the presence of S. agalactiae did not show any significant association. The major risk factors associated with the presence of S. aureus were also identified to help prioritize control programs. These results support the "One Sustainability" approach, implying that an increase in animal productivity is related to the improvement of animal health and welfare and potentially leading to the mitigation of greenhouse gas emissions.

On robust inference in time-series regression

Summary Least squares regression with heteroskedasticity consistent standard errors (‘OLS-HC regression’) has proved very useful in cross-section environments. However, several major difficulties, which are generally overlooked, must be confronted when transferring the HC technology to time-series environments via heteroskedasticity and autocorrelation consistent standard errors (‘OLS-HAC regression’). First, in plausible time-series environments, OLS parameter estimates can be inconsistent, so that OLS-HAC inference fails even asymptotically. Second, most economic time series have autocorrelation, which renders OLS parameter estimates inefficient. Third, autocorrelation similarly renders conditional predictions based on OLS parameter estimates inefficient. Finally, the structure of popular HAC covariance matrix estimators is ill-suited for capturing the autoregressive autocorrelation typically present in economic time series, which produces large size distortions and reduced power in HAC-based hypothesis testing, in all but the largest samples. We show that all four problems are largely avoided by the use of a simple and easily implemented dynamic regression procedure, which we call DURBIN. We demonstrate the advantages of DURBIN with detailed simulations covering a range of practical issues.

Confidence intervals estimator of the kinetic parameters: do its reliability depend on the assembling method of the oxygen uptakes?

Gas exchange data acquired repeatedly under the same exercise conditions are assembled together to improve the kinetic parameters of breath-by-breath oxygen uptake. The latter are provided by the non-linear regression procedure, together with the corresponding estimators of the width of the Confidence Intervals (i.e., the Asymptotic Standard Errors; ASEs). We tested, for two different assembling procedures, whether the range of values identified by the ASE actually correspond to the 95% Confidence Interval. Ten O2 uptake responses were acquired on 10 healthy volunteers performing a square-wave moderate-intensity exercise. Kinetic parameters were estimated running the non-linear regression with a mono-exponential model on an increasingly greater number of responses (Nr, from 1 to 10), assembled together using the "stacking" and the "1-s-bins" procedures. Kinetic values obtained assembling together the 10 repetitions were assumed as "true" values. The time constant was not affected by Nr or by the assembling procedure (ANOVA; p>0.54 and p>0.16, respectively). The corresponding ASE decreased according to Nr (ANOVA; p=0.000), being significantly smaller for the "1-s-bins" procedure compared to the "stacking" one (ANOVA; p<0.001). Excluding 20s at the start of the fitting window, the range of values identified with the ASE provided by the "1-s-bins" and the "stacking" procedures included the "true" value in 85% and in 95% of cases, respectively. The "stacking" procedure should be preferred since it yielded ASEs for the time constant that provided a range of values satisfying the statistical meaning of the width of the Confidence Intervals, at the given degree of probability.

Distribution-agnostic landslide hazard modelling via Graph Transformers

In statistical applications, choosing a suitable data distribution or likelihood that matches the nature of the response variable is required. To spatially predict the planimetric area of a landslide population, the most tested likelihood corresponds to the Log-Gaussian case. This causes a limitation that hinders the ability to accurately model both very small and very large landslides, with the latter potentially leading to a dangerous underestimation of the hazard. Here, we test a distribution-agnostic solution via a Graph Transformer Neural Network (GTNN) and implement a loss function capable of forcing the model to capture both the bulk and the right tail of the landslide area distribution. An additional problem with this type of data-driven hazard assessment is that one often excludes slopes with landslide areas equal to zero from the regression procedure, as this may bias the prediction towards small values. Due to the nature of GTNNs, we present a solution where all the landslide area information is passed to the model, as one would expect for architectures built for image analysis. The results are promising, with the landslide area distribution generated by the Wenchuan earthquake being suitably estimated, including both zeros, the bulk and the extremely large cases. We consider this a step forward in the landslide hazard modelling literature, with implications for what the scientific community could achieve in light of a future space–time and/or risk assessment extension of the current protocol.

Robust Regression as a Sensible Alternative to the Weighted Ordinary Least Squares Regression in case of Heteroskedasticity. A Tutorial

Background: The robust regression is rarely used in the statistical analyses in comparison with the Ordinary Least Squares regression and the Weighted Regression. In addition, in the frequent case of the heteroskedasticity of the residuals, a weighted regression carried out once is the main suggestion of the statistical books and the resulting reduced heteroscedasticity is usually considered sufficiently satisfactory. Methods: We showed the OLS regression analysis on data simulated with a well evident heteroskedasticity and an ad hoc outlier, followed by a weighted regression iteratively carried out by using iteratively reweighted least squares, an estimation method used also in several procedures of the robust regression analysis. Therefore, the link between the iteratively performed weighted regression and the robust regression becomes immediate. Furthermore, the same data have been analysed using some robust regression procedures.Results: It has been shown that in a simulated sample of heteroscedastic data with and without an obvious artificially created outlier the weighted regression performs worse with more biased parameter estimates than robust regression procedures (such as the robust MO procedure) as the presence of the outlier is not adequately neutralized. Discussion: In presence of a heteroskedastic pattern of the residuals, the suggestion to use robust regression procedures which can also deal with the almost sure presence of outliers seems more sensible. Among the robust regression procedures carried out, the performance of the robust MO procedure appears particularly appealing since it allows biostatisticians a more reasoned management of the outliers shown in a very illustrative “ad hoc” plot. Robust regression procedures represent a sensible alternative to OLS regression taking into account that its assumptions are practically not always fulfilled and that outliers, which are almost certainly present, are not only difficult to handle in classical OLS regression but can also provide highly biased estimates.

Informal Credits in India’s Agriculture Sector: Debt Incidence, Size and Distribution across Major Farm-size Groups

Until recently, studies on agricultural finance in India mostly focus on farmers’ access to formal credits, thereby largely sidelining their informal borrowings. This study makes an effort to present an analysis of farmers’ informal debts and their distribution across the major farm-size groups in India. The study uses unit-level data from the 77th round ‘Situation Assessment Survey (SAS)’ of agricultural households conducted by the National Statistical Office (NSO), Ministry of Statistics and Programme Implementation (MOSPI), Government of India (GOI), during January–December, 2019. Data were collected for the reference period of July 2018–June 2019. We use descriptive statistics and multivariate regression procedures for analysis. Results show that about one-half of the borrowers continue to depend on informal credit sources—partially or fully. Informal sources also account for about one-third of the total debt of the agricultural households. Informal debt incidence (IDI) and informal debt share (IDS) are found to be higher among the smallholders. Our findings are imperative of policy measures to improve the current state of the antecedents of formal credit access to benefit the otherwise high default risk and credit-rationed smallholders. Future studies may focus on formal credit rationing, informal credit terms and repayment burden of the agricultural households in India.

Aggressive Behaviour Risk Assessment Tool for Hospitalised Patients in Non-Psychiatric Inpatient Units.

To refine and validate an electronic version of the Aggressive Behaviour Risk Assessment Tool (ABRAT) and determine the sensitivity and specificity for identifying potentially violent patients in non-psychiatric inpatient units. A prospective cohort study design was used. All patients admitted or transferred to three inpatient units of an acute care hospital in Nebraska, USA, from 7 February to 9 April 2023, were included. The 10-item ABRAT assessments were performed daily for the first 3 days of admission. The violent events were collected until discharge in three categories: Physical aggression towards others, physical aggression towards property and verbal intimidation/threat towards others. Kendall's tau tests and a multivariate logistic regression procedure were performed to select a parsimonious set of items that best predict violent events. Of 1179 patients, 69 had ≥1 violent event (5.9%). The revised six-item tool with item weighting was named ABRAT for Hospitalised Patients (ABRAT-H). The area under the curve from the Receiver Operating Characteristics analysis was 0.82. The sensitivity and specificity at a cutoff score of two were 68.1% and 85.2%, respectively. As ABRAT-H scores increased, the percentage of violent patients also increased and for patients with scores ≥5, 55.2% became violent. ABRAT-H appears to be useful for identifying potentially violent patients in non-psychiatric inpatient units with satisfactory sensitivity and specificity. The availability of ABRAT-H may help provide focused preventive measures that target patients at high risk for violence and reduce violent events. A majority of the nursing workforce is employed in acute care hospital setting, and the availability of ABRAT-H can further enhance the culture of a safe work environment and have positive impacts not only on the nurses' physical and mental health but also on the quality of patient care. We have adhered to relevant STROBE guidelines for reporting observational studies. No Patient or Public Contribution.

Nonparametric Test for Logistic Regression with Application to Italian Enterprises’ Propensity for Innovation

In this work, a nonparametric method is proposed to jointly test the significance of the regression coefficient estimates in a logistic regression model and identify which explanatory variables are effective in predicting the binary response. The motivating example is related to the factors affecting the propensity of Italian Small Medium Enterprises (SMEs) to innovate. The explanatory variables of the model represent firms’ characteristics, such as size and age, and the possible effect of the sector of economic activity is taken into account by including a set of binary variables as control factors. The dependent variable indicates whether a company, in the period under study, introduced at least one product or process innovation. Therefore, it is also dichotomous, and the logistic regression model is appropriate for representing the relationship between explanatory variables and dependent variables. Specifically, the logit transformation of the firm’s propensity to innovate, i.e., the probability that a company randomly chosen from the population of Italian SMEs has introduced an innovation or, equivalently, the proportion of innovative companies among the Italian SMEs, is expressed as a linear function of the predictors (explanatory and control variables). The proposed test is based on the permutation approach and satisfies important statistical properties, proved in a simulation study. The test is more flexible and robust than the classic parametric approach, and is preferable to typical stepwise regression procedures for the selection of a parsimonious and effective model.

Predictive utility of self-efficacy in early stroke rehabilitation

ABSTRACT Introduction A biopsychosocial approach entailing person-centered factors provides valuable insight to post-stroke rehabilitation potential. The consideration of an individual’s belief in their capabilities, known as self-efficacy, may prove especially informative in the inpatient rehabilitation setting where motor learning often occurs. Objective To assess the predictive utility of self-efficacy in functional independence status change during inpatient rehabilitation. Methods Individuals with stroke admitted to an inpatient rehabilitation facility (IRF) completed an assessment battery near IRF admission and discharge involving motor assessments, participant-reported self-efficacy (Stroke Self-Efficacy Questionnaire), and functional independence status evaluation (sum of self-care and mobility Quality Indicators (QI) from the IRF-Patient Assessment Instrument). Linear regression was performed to determine the predictive performance of self-efficacy on QI change during IRF stay while accounting for age, time post-stroke, and IRF length of stay. Regression procedures were repeated for separate subgroups based on initial motor impairment level. Results Thirty individuals with stroke (14 females, age = 67.0 ± 9.80 years, 10.4 ± 3.46 days post-stroke) were enrolled. Self-efficacy at IRF admission explained a significant percentage of variance in QI Change for the cohort (R2 = 30.7%, p = .001) and for the moderate to severe motor impairment subgroup (n = 12; R2 = 49.9%, p = .010). After accounting for confounders, self-efficacy remained a significant predictor for the cohort (n = 30) model. Discussion Findings generated from this work support the predictive utility of self-efficacy in early post-stroke motor recovery. The inclusion of self-efficacy in a multi-faceted evaluation framework may therefore optimize rehabilitation outcomes by providing therapists with additional knowledge to better tailor an individual’s care.

Transcriptome-Wide Root Causal Inference.

Root causal genes correspond to the first gene expression levels perturbed during pathogenesis by genetic or non-genetic factors. Targeting root causal genes has the potential to alleviate disease entirely by eliminating pathology near its onset. No existing algorithm discovers root causal genes from observational data alone. We therefore propose the Transcriptome-Wide Root Causal Inference (TWRCI) algorithm that identifies root causal genes and their causal graph using a combination of genetic variant and unperturbed bulk RNA sequencing data. TWRCI uses a novel competitive regression procedure to annotate cis and trans-genetic variants to the gene expression levels they directly cause. The algorithm simultaneously recovers a causal ordering of the expression levels to pinpoint the underlying causal graph and estimate root causal effects. TWRCI outperforms alternative approaches across a diverse group of metrics by directly targeting root causal genes while accounting for distal relations, linkage disequilibrium, patient heterogeneity and widespread pleiotropy. We demonstrate the algorithm by uncovering the root causal mechanisms of two complex diseases, which we confirm by replication using independent genome-wide summary statistics.

The Influence of Promotion via Social Media Instagram and Facebook on Purchase Interest among Generation Y at the FP Bali Hotel, Kuta

This study examines the impact of promotions through Instagram and Facebook on the purchase intention of generation Y at the FP Bali Hotel, Kuta. The quantitative method was used by distributing questionnaires to 100 Instagram and Facebook followers of the hotel who are generation Y. The data analysis process used multiple linear regression procedures on SPSS version 27.0. The findings show that the purchase intention of generation Y is significantly and positively influenced by product promotions on Instagram and Facebook, both individually and simultaneously. The management of FP Bali Hotel is expected to be able to utilize these findings as input to increase purchase intention through the implementation of appropriate promotion strategies.

Mixed‐Effects Modeling with a Multinomial Dependent Variable

AbstractIn this Methods Showcase Article, we illustrate mixed‐effects modeling with a multinomial dependent variable as a means of explaining complexities in language. We model data on future‐time reference in second language Spanish, which consists of a nominal dependent variable that has three levels, measured over 73 participants. We offer step‐by‐step procedures for multinomial logistic regression with fixed and random effects, and we discuss the interpretation of the model and its advantages and limitations.

Predicting Walking Capacity Outcomes After Moderate to High Intensity Locomotor Training in Chronic Stroke.

Moderate-to-high intensity locomotor training (M-HIT) is strongly recommended in stroke rehabilitation but outcomes are variable. This study aimed to identify baseline clinical characteristics that predict change in walking capacity following M-HIT in chronic stroke. This analysis used data from the HIT-Stroke Trial (N=55), which involved up to 36 sessions of either moderate or high intensity locomotor training. A prespecified model assessed how well baseline motor impairment (Fugl-Meyer lower limb motor scale [FM-LL]), comfortable gait speed (CGS), and balance confidence (Activities Balance Confidence scale [ABC]), independently explain changes in 6-minute walk distance (Δ6MWD), while controlling for treatment group. Exploratory analysis tested additional baseline covariates using the all-possible regressions procedure. The prognostic value of each potential covariate was assessed by its average contribution to the explained variance in Δ6MWD (Δ pseudo-R 2 ). With the prespecified model, 8-week Δ6MWD was significantly associated with baseline FM-LL (β=5.0 [95% CI: 1.4, 8.6]) and ABC (β=0.7 [0.0, 1.4]), but not CGS (β=-44.6 [-104.7, 15.6]). The exploratory analysis revealed the top 7 covariates with the highest mean Δ pseudo-R 2 were: FM-LL, pain-limited walking duration, ABC, the use of an assistive device, fatigue, depression, and recent walking exercise history >2 days per week. On average, participants with less motor impairment and higher balance confidence have greater walking capacity improvements after M-HIT in chronic stroke. Additional negative prognostic factors may include pain-limited walking duration, use of an assistive device, fatigue, depression, and recent walking exercise but these exploratory findings need to be confirmed in future studies.