Journal articles: 'Variable selection bias'

1

Canan, Chelsea, Catherine Lesko, and Bryan Lau. "Instrumental Variable Analyses and Selection Bias." Epidemiology 28, no. 3 (May 2017): 396–98. http://dx.doi.org/10.1097/ede.0000000000000639.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Shin, Sung-Chul, Yeon-Joo Jeong, and Moon Sup Song. "Bias Reduction in Split Variable Selection in C4.5." Communications for Statistical Applications and Methods 10, no. 3 (December 1, 2003): 627–35. http://dx.doi.org/10.5351/ckss.2003.10.3.627.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Yeob Choi, Byeong, Jason P. Fine, and M. Alan Brookhart. "Bias testing, bias correction, and confounder selection using an instrumental variable model." Statistics in Medicine 39, no. 29 (August 27, 2020): 4386–404. http://dx.doi.org/10.1002/sim.8730.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Shih, Yu-Shan, and Hsin-Wen Tsai. "Variable selection bias in regression trees with constant fits." Computational Statistics & Data Analysis 45, no. 3 (April 2004): 595–607. http://dx.doi.org/10.1016/s0167-9473(03)00036-7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

García, O. "Estimating top height with variable plot sizes." Canadian Journal of Forest Research 28, no. 10 (October 1, 1998): 1509–17. http://dx.doi.org/10.1139/x98-128.

Full text

Abstract:

Conventional top height estimates are biased if the area of the sample plot differs from that on which the definition is based. Sources of bias include a sampling selection effect and spatial autocorrelation. The problem was studied in relation to the use of data sets with varying spatial detail for modelling Douglas-fir (Pseudotsuga menziesii (Mirb.) Franco) plantation growth. Improved top height estimators, developed taking into account the selection effect, eliminated the bias. Bias was reduced, but not eliminated completely, when the estimators were tested using more highly autocorrelated eucalypt data.

APA, Harvard, Vancouver, ISO, and other styles

6

Zhao, Pei Xin. "Penalized Estimation Based Variable Selection for Semiparametric Regression Models with Endogenous Covariates." Advanced Materials Research 1079-1080 (December 2014): 843–46. http://dx.doi.org/10.4028/www.scientific.net/amr.1079-1080.843.

Full text

Abstract:

In this paper, we study the variable selection problem for the parametric components of semiparametric regression models with endogenous variables. Based on the penalized empirical likelihood technology and the bias adjustment method, we propose a penalized empirical likelihood based variable selection procedure. Simulation studies show that the proposed variable selection procedure is workable, and the resulting estimator is consistent.

APA, Harvard, Vancouver, ISO, and other styles

7

Swanson, Sonja A. "A Practical Guide to Selection Bias in Instrumental Variable Analyses." Epidemiology 30, no. 3 (May 2019): 345–49. http://dx.doi.org/10.1097/ede.0000000000000973.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Marshall, Andrew, Leilei Tang, and Alistair Milne. "Variable reduction, sample selection bias and bank retail credit scoring." Journal of Empirical Finance 17, no. 3 (June 2010): 501–12. http://dx.doi.org/10.1016/j.jempfin.2009.12.003.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Qin, Xiao, and Junhee Han. "Variable Selection Issues in Tree-Based Regression Models." Transportation Research Record: Journal of the Transportation Research Board 2061, no. 1 (January 2008): 30–38. http://dx.doi.org/10.3141/2061-04.

Full text

Abstract:

Recently, there has been increasing interest in the use of classification and regression tree (CART) analysis. A tree-based regression model can be constructed by recursively partitioning the data with such criteria as to yield the maximum reduction in the variability of the response. Unfortunately, the exhaustive search may yield a bias in variable selection, and it tends to choose a categorical variable as a splitter that has many distinct values. In this study, an unbiased tree-based regression generalized unbiased interaction detection and estimation (GUIDE) model is introduced for its robustness against the variable selection bias. Not only are the underlying theoretical differences behind CART and GUIDE in variable selection presented, but also the outcomes of the two different tree-based regression models are compared and analyzed by utilizing intersection inventory and crash data. The results underscore GUIDE's strength in selecting variables equally. A simulation shed additional light on the resulting negative impact when an algorithm was inappropriately applied to the data. This paper concludes by addressing the strengths and weaknesses of—and, more important, the differences between—the two hierarchical tree-based regression models, CART and GUIDE, and advises on the appropriate application. It is anticipated that the GUIDE model will provide a new perspective for users of tree-based models and will offer an advantage over existing methods. Users in transportation should choose the appropriate method and utilize it to their advantage.

APA, Harvard, Vancouver, ISO, and other styles

10

Nishi, Hayato, Yasushi Asami, and Chihiro Shimizu. "Housing features and rent: estimating the microstructures of rental housing." International Journal of Housing Markets and Analysis 12, no. 2 (April 1, 2019): 210–25. http://dx.doi.org/10.1108/ijhma-09-2018-0067.

Full text

Abstract:

Purpose While consumers did not previously have information on detailed housing features via traditional media, such as magazines, nowadays, due to the progress in information technology, they can access detailed information on various housing features via housing information websites. Therefore, detailed housing features may affect current rents to some extent. This paper aims to identify the effects of detailed housing features on rent and on omitted variable bias in Tokyo, Japan. Design/methodology/approach This paper applies the hedonic approach. To identify the effects of features which are not observed previously, we use a unique data set that contains various housing features and over 200,000 housing units. This data set enables to simulate the situations when the researcher cannot get some variables, and this simulation shows which variables cause omitted variable bias. Findings The analysis shows that housing features significantly influence housing rent. If significant housing feature variables are not included in the hedonic model, the estimated coefficients show omitted variable bias. Additionally, unit-specific features such auto-locking door can cause omitted variable bias on location-specific features such accessibility to downtown. Originality/values This paper shows empirical evidence that detailed housing features can cause omitted variable bias on other features including variables which are often used in previous searches. The result from our unique data set can be a guide for variable selection to reduce omitted variable bias.

APA, Harvard, Vancouver, ISO, and other styles

11

Elwert, Felix, and Christopher Winship. "Endogenous Selection Bias: The Problem of Conditioning on a Collider Variable." Annual Review of Sociology 40, no. 1 (July 30, 2014): 31–53. http://dx.doi.org/10.1146/annurev-soc-071913-043455.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Hutton, J. L., and Paula R. Williamson. "Bias in meta‐analysis due to outcome variable selection within studies." Journal of the Royal Statistical Society: Series C (Applied Statistics) 49, no. 3 (January 2000): 359–70. http://dx.doi.org/10.1111/1467-9876.00197.

Full text

APA, Harvard, Vancouver, ISO, and other styles

13

Schork, Joachim, Cesare A. F. Riillo, and Johann Neumayr. "Survey Mode Effects on Objective and Subjective Questions: Evidence from the Labour Force Survey." Journal of Official Statistics 37, no. 1 (March 1, 2021): 213–37. http://dx.doi.org/10.2478/jos-2021-0009.

Full text

Abstract:

Abstract Web questionnaires are increasingly used to complement traditional data collection in mixed mode surveys. However, the utilization of web data raises concerns whether web questionnaires lead to mode-specific measurement bias. We argue that the magnitude of measurement bias strongly depends on the content of a variable. Based on the Luxembourgish Labour Force Survey, we investigate differences between web and telephone data in terms of objective (i.e., Employment Status) and subjective (i.e., Wage Adequacy and Job Satisfaction) variables. To assess whether differences in outcome variables are caused by sample composition or mode-specific measurement bias, we apply a coarsened exact matching that approximates randomized experiments by reducing dissimilarities between web and telephone samples. We select matching variables with a combination of automatic variable selection via random forest and a literature-driven selection. The results show that objective variables are not affected by mode-specific measurement bias, but web participants report lower satisfaction-levels on subjective variables than telephone participants. Extensive supplementary analyses confirm our results. The present study supports the view that the impact of survey mode depends on the content of a survey and its variables.

APA, Harvard, Vancouver, ISO, and other styles

14

Breunig, Christoph, Michael Kummer, Joerg Ohnemus, and Steffen Viete. "Information technology outsourcing and firm productivity: eliminating bias from selective missingness in the dependent variable." Econometrics Journal 23, no. 1 (September 20, 2019): 88–114. http://dx.doi.org/10.1093/ectj/utz016.

Full text

Abstract:

Summary Missing values are a major problem in all econometric applications based on survey data. A standard approach assumes data are missing at random and uses imputation methods or even listwise deletion. This approach is justified if item nonresponse does not depend on the potentially missing variables’ realization. However, assuming missingness at random may introduce bias if nonresponse is, in fact, selective. Relevant applications range from financial or strategic firm-level data to individual-level data on income or privacy-sensitive behaviors. In this paper, we propose a novel approach to deal with selective item nonresponse in the model’s dependent variable. Our approach is based on instrumental variables that affect selection only through a partially observed outcome variable. In addition, we allow for endogenous regressors. We establish identification of the structural parameter and propose a simple two-step estimation procedure for it. Our estimator is consistent and robust against biases that would prevail when assuming missingness at random. We implement the estimation procedure using firm-level survey data and a binary instrumental variable to estimate the effect of outsourcing on productivity.

APA, Harvard, Vancouver, ISO, and other styles

15

Song, Hyo-Im, Eun-Tae Song, and Moon Sup Song. "A Study on the Bias Reduction in Split Variable Selection in CART." Communications for Statistical Applications and Methods 11, no. 3 (December 1, 2004): 553–62. http://dx.doi.org/10.5351/ckss.2004.11.3.553.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Fakhraei, Shobeir, Hamid Soltanian-Zadeh, and Farshad Fotouhi. "Bias and stability of single variable classifiers for feature ranking and selection." Expert Systems with Applications 41, no. 15 (November 2014): 6945–58. http://dx.doi.org/10.1016/j.eswa.2014.05.007.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Pearl, Judea, and Azaria Paz. "Confounding Equivalence in Causal Inference." Journal of Causal Inference 2, no. 1 (March 1, 2014): 75–93. http://dx.doi.org/10.1515/jci-2013-0020.

Full text

Abstract:

AbstractThe paper provides a simple test for deciding, from a given causal diagram, whether two sets of variables have the same bias-reducing potential under adjustment. The test requires that one of the following two conditions holds: either (1) both sets are admissible (i.e. satisfy the back-door criterion) or (2) the Markov boundaries surrounding the treatment variable are identical in both sets. We further extend the test to include treatment-dependent covariates by broadening the back-door criterion and establishing equivalence of adjustment under selection bias conditions. Applications to covariate selection and model testing are discussed.

APA, Harvard, Vancouver, ISO, and other styles

18

Lee, J. Y., R. G. Rozier, E. C. Norton, and W. F. Vann. "Addressing Selection Bias in Dental Health Services Research." Journal of Dental Research 84, no. 10 (October 2005): 942–46. http://dx.doi.org/10.1177/154405910508401013.

Full text

Abstract:

When randomization is not possible, researchers must control for non-random assignment to experimental groups. One technique for statistical adjustment for non-random assignment is through the use of a two-stage analytical technique. The purpose of this study was to demonstrate the use of this technique to control for selection bias in examining the effects of the The Supplemental Program for Women, Infants, and Children’s (WIC) on dental visits. From 5 data sources, an analysis file was constructed for 49,512 children ages 1–5 years. The two-stage technique was used to control for selection bias in WIC participation, the potentially endogenous variable. Specification tests showed that WIC participation was not random and that selection bias was present. The effects of the WIC on dental use differed by 36% after adjustment for selection bias by means of the two-stage technique. This technique can be used to control for potential selection bias in dental research when randomization is not possible.

APA, Harvard, Vancouver, ISO, and other styles

19

Hughes, Rachael A., Neil M. Davies, George Davey Smith, and Kate Tilling. "Selection Bias When Estimating Average Treatment Effects Using One-sample Instrumental Variable Analysis." Epidemiology 30, no. 3 (May 2019): 350–57. http://dx.doi.org/10.1097/ede.0000000000000972.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Richards, Joseph W., Dan L. Starr, Henrik Brink, Adam A. Miller, Joshua S. Bloom, Nathaniel R. Butler, J. Berian James, James P. Long, and John Rice. "ACTIVE LEARNING TO OVERCOME SAMPLE SELECTION BIAS: APPLICATION TO PHOTOMETRIC VARIABLE STAR CLASSIFICATION." Astrophysical Journal 744, no. 2 (December 22, 2011): 192. http://dx.doi.org/10.1088/0004-637x/744/2/192.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Steyerberg, Ewout W., Michael Schemper, and Frank E. Harrell. "Logistic regression modeling and the number of events per variable: selection bias dominates." Journal of Clinical Epidemiology 64, no. 12 (December 2011): 1464–65. http://dx.doi.org/10.1016/j.jclinepi.2011.06.016.

Full text

APA, Harvard, Vancouver, ISO, and other styles

22

Yu, Ya-Hui, Kristian B. Filion, Lisa M. Bodnar, Maria M. Brooks, Robert W. Platt, Katherine P. Himes, and Ashley I. Naimi. "Visualization tool of variable selection in bias–variance tradeoff for inverse probability weights." Annals of Epidemiology 41 (January 2020): 56–59. http://dx.doi.org/10.1016/j.annepidem.2019.12.006.

Full text

APA, Harvard, Vancouver, ISO, and other styles

23

Hamada, Tsuyoshi, Takeshi Tsujino, Hiroyuki Isayama, and Kazuhiko Koike. "Pseudorandomization using an instrumental variable: a strong tool to break through selection bias." Gastrointestinal Endoscopy 76, no. 5 (November 2012): 1079–80. http://dx.doi.org/10.1016/j.gie.2012.06.016.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

McShane, Michael J., Gerard L. Coté, and Clifford Spiegelman. "Variable Selection in Multivariate Calibration of a Spectroscopic Glucose Sensor." Applied Spectroscopy 51, no. 10 (October 1997): 1559–64. http://dx.doi.org/10.1366/0003702971939118.

Full text

Abstract:

A variable selection method that reduces prediction bias in partial least-squares regression models was developed and applied to near-infrared absorbance spectra of glucose in pH buffer and cell culture medium. Comparisons between calibration and prediction capability for full spectra and reduced sets were completed. Variable selection resulted in statistically equivalent errors while reducing the number of wavelengths needed to fit the calibration data and predict concentrations from new spectra. Fewer than 25 wavelengths were selected to produce errors statistically equivalent to those yielded by the full set containing over 500 wavelengths. The algorithm correctly chose the glucose absorption peak areas as the information-carrying spectral regions.

APA, Harvard, Vancouver, ISO, and other styles

25

Collier, David, and James Mahoney. "Insights and Pitfalls: Selection Bias in Qualitative Research." World Politics 49, no. 1 (October 1996): 56–91. http://dx.doi.org/10.1353/wp.1996.0023.

Full text

Abstract:

Qualitative analysts have received stern warnings that the validity of their studies may be undermined by selection bias. This article provides an overview of this problem for qualitative researchers in the field of international and comparative studies, focusing on selection bias that may result from the deliberate selection of cases by the investigator. Examples are drawn from studies of revolution, international deterrence, the politics of inflation, international terms of trade, economic growth, and industrial competitiveness. The article first explores how insights about selection bias developed in quantitative research can most productively be applied in qualitative studies. The discussion considers why qualitative researchers need to be concerned about selection bias, even if they do not care about the generality of their findings, and it considers distinctive implications of this form of bias for qualitative research, as in the problem of what is labeled “complexification based on extreme cases.” The article then considers pitfalls in recent discussions of selection bias in qualitative studies. These discussions at times get bogged down in disagreements and misunderstandings over how the dependent variable is conceptualized and what the appropriate frame of comparison should be, issues that are crucial to the assessment of bias within a given study. At certain points it becomes clear that the real issue is not just selection bias, but a larger set of trade-offs among alternative analytic goals.

APA, Harvard, Vancouver, ISO, and other styles

26

Chang, Chung-Chou H. "Applications of the propensity score weighting method in psychogeriatric research: correcting selection bias and adjusting for confounders." International Psychogeriatrics 29, no. 5 (January 18, 2017): 703–6. http://dx.doi.org/10.1017/s1041610216002490.

Full text

Abstract:

The propensity score (PS) weighting method is an analytic technique that has been applied in multiple fields for a number of purposes. Here, we discuss two common applications, which are (1) to correct for selection bias and (2) to adjust for confounding variables when estimating the effect of an exposure variable on the outcome of interest.

APA, Harvard, Vancouver, ISO, and other styles

27

carolyn, Rutter, Flack Virgina, and Lachenbruch Peter. "Bias in error rate estimates in discriminant analysis when stepwise variable selection is employed." Communications in Statistics - Simulation and Computation 20, no. 1 (January 1991): 1–22. http://dx.doi.org/10.1080/03610919108812935.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Vasquez, Monica M., Chengcheng Hu, Denise J. Roe, Marilyn Halonen, and Stefano Guerra. "Measurement error correction in the least absolute shrinkage and selection operator model when validation data are available." Statistical Methods in Medical Research 28, no. 3 (November 23, 2017): 670–80. http://dx.doi.org/10.1177/0962280217734241.

Full text

Abstract:

Measurement of serum biomarkers by multiplex assays may be more variable as compared to single biomarker assays. Measurement error in these data may bias parameter estimates in regression analysis, which could mask true associations of serum biomarkers with an outcome. The Least Absolute Shrinkage and Selection Operator (LASSO) can be used for variable selection in these high-dimensional data. Furthermore, when the distribution of measurement error is assumed to be known or estimated with replication data, a simple measurement error correction method can be applied to the LASSO method. However, in practice the distribution of the measurement error is unknown and is expensive to estimate through replication both in monetary cost and need for greater amount of sample which is often limited in quantity. We adapt an existing bias correction approach by estimating the measurement error using validation data in which a subset of serum biomarkers are re-measured on a random subset of the study sample. We evaluate this method using simulated data and data from the Tucson Epidemiological Study of Airway Obstructive Disease (TESAOD). We show that the bias in parameter estimation is reduced and variable selection is improved.

APA, Harvard, Vancouver, ISO, and other styles

29

Ye, Zhaoxin, Yeying Zhu, and Donna L. Coffman. "Variable selection for causal mediation analysis using LASSO-based methods." Statistical Methods in Medical Research 30, no. 6 (March 23, 2021): 1413–27. http://dx.doi.org/10.1177/0962280221997505.

Full text

Abstract:

Causal mediation effect estimates can be obtained from marginal structural models using inverse probability weighting with appropriate weights. In order to compute weights, treatment and mediator propensity score models need to be fitted first. If the covariates are high-dimensional, parsimonious propensity score models can be developed by regularization methods including LASSO and its variants. Furthermore, in a mediation setup, more efficient direct or indirect effect estimators can be obtained by using outcome-adaptive LASSO to select variables for propensity score models by incorporating the outcome information. A simulation study is conducted to assess how different regularization methods can affect the performance of estimated natural direct and indirect effect odds ratios. Our simulation results show that regularizing propensity score models by outcome-adaptive LASSO can improve the efficiency of the natural effect estimators and by optimizing balance in the covariates, bias can be reduced in most cases. The regularization methods are then applied to MIMIC-III database, an ICU database developed by MIT.

APA, Harvard, Vancouver, ISO, and other styles

30

Harrison, Paul M. "Variable absorption of mutational trends by prion-forming domains during Saccharomycetes evolution." PeerJ 8 (August 6, 2020): e9669. http://dx.doi.org/10.7717/peerj.9669.

Full text

Abstract:

Prions are self-propagating alternative states of protein domains. They are linked to both diseases and functional protein roles in eukaryotes. Prion-forming domains in Saccharomyces cerevisiae are typically domains with high intrinsic protein disorder (i.e., that remain unfolded in the cell during at least some part of their functioning), that are converted to self-replicating amyloid forms. S. cerevisiae is a member of the fungal class Saccharomycetes, during the evolution of which a large population of prion-like domains has appeared. It is still unclear what principles might govern the molecular evolution of prion-forming domains, and intrinsically disordered domains generally. Here, it is discovered that in a set of such prion-forming domains some evolve in the fungal class Saccharomycetes in such a way as to absorb general mutation biases across millions of years, whereas others do not, indicating a spectrum of selection pressures on composition and sequence. Thus, if the bias-absorbing prion formers are conserving a prion-forming capability, then this capability is not interfered with by the absorption of bias changes over the duration of evolutionary epochs. Evidence is discovered for selective constraint against the occurrence of lysine residues (which likely disrupt prion formation) in S. cerevisiae prion-forming domains as they evolve across Saccharomycetes. These results provide a case study of the absorption of mutational trends by compositionally biased domains, and suggest methodology for assessing selection pressures on the composition of intrinsically disordered regions.

APA, Harvard, Vancouver, ISO, and other styles

31

Liu, Zhenqiu, and Gang Li. "Efficient Regularized Regression withL0Penalty for Variable Selection and Network Construction." Computational and Mathematical Methods in Medicine 2016 (2016): 1–11. http://dx.doi.org/10.1155/2016/3456153.

Full text

Abstract:

Variable selections for regression with high-dimensional big data have found many applications in bioinformatics and computational biology. One appealing approach is theL0regularized regression which penalizes the number of nonzero features in the model directly. However, it is well known thatL0optimization is NP-hard and computationally challenging. In this paper, we propose efficient EM (L0EM) and dualL0EM (DL0EM) algorithms that directly approximate theL0optimization problem. WhileL0EM is efficient with large sample size, DL0EM is efficient with high-dimensional (n≪m) data. They also provide a natural solution to allLp p∈[0,2]problems, including lasso withp=1and elastic net withp∈[1,2]. The regularized parameterλcan be determined through cross validation or AIC and BIC. We demonstrate our methods through simulation and high-dimensional genomic data. The results indicate thatL0has better performance than lasso, SCAD, and MC+, andL0with AIC or BIC has similar performance as computationally intensive cross validation. The proposed algorithms are efficient in identifying the nonzero variables with less bias and constructing biologically important networks with high-dimensional big data.

APA, Harvard, Vancouver, ISO, and other styles

32

Jiang, Zhichao, Yasutaka Chiba, and Tyler J. VanderWeele. "Monotone Confounding, Monotone Treatment Selection and Monotone Treatment Response." Journal of Causal Inference 2, no. 1 (March 1, 2014): 1–12. http://dx.doi.org/10.1515/jci-2012-0006.

Full text

Abstract:

AbstractManski (Monotone treatment response. Econometrica 1997;65:1311–34) and Manski and Pepper (Monotone instrumental variables: with an application to the returns to schooling. Econometrica 2000;68:997–1010) gave sharp bounds on causal effects under the assumptions of monotone treatment response (MTR) and monotone treatment selection (MTS). VanderWeele (The sign of the bias of unmeasured confounding. Biometrics 2008;64:702–6) provided bounds for binary treatment under an assumption of monotone confounding (MC). We discuss the relation between MC and MTS and provide bounds under various combinations of these assumptions. We show that MC and MTS coincide for a binary treatment, but MC does not imply MTS for a treatment variable with more than two levels.

APA, Harvard, Vancouver, ISO, and other styles

33

Park, Younghee, and Kyunga Na. "The Effect of Lease Accounting on Credit Rating and Cost of Debt: Evidence from Firms in Korea." Social Sciences 7, no. 9 (September 7, 2018): 154. http://dx.doi.org/10.3390/socsci7090154.

Full text

Abstract:

This study examines the effect of capital lease and operating lease options in accounting on credit ratings and the cost of debt using data for 13 years (2001 to 2013) on 6133 listed and unlisted domestic firms in Korea that recognize leases on financial statements. We use the Heckman two-stage model to control for sample selection bias from lease selection. The first stage is the probit regression in which the dependent variable is a dummy variable on the lease selection and the explanatory variables are factors known to affect lease selection. The second stage consists of the ordered probit regression model and the ordinary least square regression model where the dependent variables are credit rating and cost of debt, respectively. The results show that lease selection does not significantly affect corporate credit ratings—however, in terms of the cost of debt, enterprises that adopt operating leases spend considerably less than firms that engage in capital leases. Further analysis suggests that the results for credit ratings do not differ by listing status. However, the cost of debt for listed companies does not seem to differ by lease selection, while unlisted firms see a sharp decline in their cost of debt when they choose operating leases over capital leases.

APA, Harvard, Vancouver, ISO, and other styles

34

Geddes, Barbara. "How the Cases You Choose Affect the Answers You Get: Selection Bias in Comparative Politics." Political Analysis 2 (1990): 131–50. http://dx.doi.org/10.1093/pan/2.1.131.

Full text

Abstract:

This article demonstrates how the selection of cases for study on the basis of outcomes on the dependent variable biases conclusions. It first lays out the logic of explanation and shows how it is violated when only cases that have achieved the outcome of interest are studied. It then examines three well-known and highly regarded studies in the field of comparative politics, comparing the conclusions reached in the original work with a test of the arguments on cases selected without regard for their position on the dependent variable. In each instance, conclusions based on the uncorrelated sample differ from the original conclusions.

APA, Harvard, Vancouver, ISO, and other styles

35

Rabinovitch, Hagai, Yoella Bereby-Meyer, and David V. Budescu. "Achieving More With Less: Intuitive Correction in Selection." Psychological Science 31, no. 4 (March 23, 2020): 437–48. http://dx.doi.org/10.1177/0956797620903717.

Full text

Abstract:

Choosing between candidates for a position can be tricky, especially when the selection test is affected by irrelevant characteristics (e.g., reading speed). One can correct for this irrelevant attribute by penalizing individuals who have unjustifiably benefited from it. Statistical models do so by including the irrelevant attribute as a suppressor variable, but can people do the same without the help of a model? In three experiments (total N = 357), participants had to choose between two candidates, one of whom had higher levels of an irrelevant attribute and thus enjoyed an unfair advantage. Participants showed a substantial preference for the candidate with high levels of the irrelevant attribute, thus choosing the less suitable candidate. This bias was attenuated when the irrelevant attribute was a situational factor, probably by making the correction process more intuitive. Understanding the intuitive judgment of suppressor variables can help candidates from underprivileged groups boost their chances to succeed.

APA, Harvard, Vancouver, ISO, and other styles

36

Bowles, Tyler J., and Jason Jones. "An Analysis of the Effectiveness of Supplemental Instruction: The Problem of Selection Bias and Limited Dependent Variables." Journal of College Student Retention: Research, Theory & Practice 5, no. 2 (August 2003): 235–43. http://dx.doi.org/10.2190/486t-mhvc-cg0c-rm3b.

Full text

Abstract:

Single equation regression models have been used rather extensively to test the effectiveness of Supplemental Instruction (SI). This approach, however, fails to account for the possibility that SI attendance and the outcome of SI attendance are jointly determined endogenous variables. Moreover, the standard approach fails to account for the fact that these two endogenous variables are categorical. This article presents and applies a simultaneous equation, limited dependent variable model of SI effectiveness. Our analysis suggests that results from applying this type of model may differ markedly from the traditional statistical models applied in SI research. Specifically, our results suggest that students with below average academic ability are more likely to attend SI and that common measures of student ability included in single equation models fail to adequately control for this characteristic. Therefore, single equation OLS models may underestimate SI effectiveness.

APA, Harvard, Vancouver, ISO, and other styles

37

Alawadi, Zeinab, Uma Phatak, Chung-Yuan Hu, Christina Edwards Bailey, Lillian Kao, Y. Nancy You, and George J. Chang. "Comparative effectiveness of primary tumor resection in metastatic colon cancer: An instrumental variable analysis." Journal of Clinical Oncology 33, no. 3_suppl (January 20, 2015): 674. http://dx.doi.org/10.1200/jco.2015.33.3_suppl.674.

Full text

Abstract:

674 Background: Although the safety of chemotherapy without primary tumor resection (PTR) has been established, questions remain regarding potential survival benefit with PTR. The purpose of this study was to compare mortality with and without PTR among patients with unresectable metastatic colon cancer using nationwide hospital based cancer registry data. Methods: An observational study was conducted of patients with stage 4 colon cancer identified from the National Cancer Data Base (2003-2005). Patients who underwent metastectomy were excluded. Patient, treatment, and hospital data were analyzed. Multivariate Cox regression stratified by receipt of chemotherapy was performed to compare survival with and without PTR. To account for treatment selection bias, Propensity Score Weighting (PSW) and Instrumental Variable (IV) analyses, using hospital-level PTR rate as the instrument, were performed. In order to account for the potential bias associated with early comorbidity or disease burden associated deaths (survivor treatment bias), 1 year landmark analysis was performed. Results: A total of 14,399 patients met inclusion criteria and 6,735 patients were eligible for landmark analysis. PTR was performed in 38.2% of the total cohort and 73.8% of those at landmark. Using multivariate Cox regression analysis, PTR was associated with a significant reduction in mortality (HR 0.39; 95% CI, 0.38-0.41). This effect persisted with PSW (HR 0.4; 95% CI, 0.38-0.43). However, IV analysis showed a much smaller effect, (RR 0.88; 95% CI, 0.83-0.93). While a smaller benefit was seen on landmark analysis using multivariate Cox regression (HR 0.6; 95% CI, 0.55-0.64) and PSW (HR 0.59; 95% CI, 0.54-0.64), IV analysis showed no improvement in survival with PTR (RR 0.97; 95% CI, 0.87-1.06). Stratification by chemotherapy did not alter the results. Conclusions: Among patients with stage IV colon cancer, PTR offered no survival benefit over systemic chemotherapy alone when the IV method was applied at the 1 year landmark. Subject to selection and survivor treatment bias, standard regression analysis may overestimate the benefit of PTR. Future study should focus on identifying patients most likely to benefit from PTR.

APA, Harvard, Vancouver, ISO, and other styles

38

Singha, Chandan. "Impact of the adoption of vegetative soil conservation measures on farm profit, revenue and variable cost in Darjeeling district, India." Environment and Development Economics 24, no. 5 (August 14, 2019): 529–53. http://dx.doi.org/10.1017/s1355770x19000226.

Full text

Abstract:

AbstractThis study evaluates the effects of vegetative soil conservation practices (afforestation and/or bamboo planting) on farm profit and its components, revenue and variable cost. Since farmers self-select themselves as adopters of conservation measures, there could be a problem of selection bias in evaluating their soil conservation practices. We address the selection bias by using propensity score matching. We also check if there exists spatial spillover in adoption of vegetative conservation measures and how it affects matching. We use primary survey data from the Darjeeling district of the Eastern Himalayan region for the year 2013. Our results suggest strong spatial correlation. We find that the propensity score estimated from the spatial model provides better matches than the non-spatial model. While the results show that vegetative soil conservation can lead to significant gains in revenue, it also increases costs so that no significant gains in profit accrue to farmers.

APA, Harvard, Vancouver, ISO, and other styles

39

Malik, Muhammad Nauman, and Masood Sarwar Awan. "Analysing Econometric Bias and Non-linearity in Returns to Education of Pakistan." Pakistan Development Review 55, no. 4I-II (December 1, 2016): 837–51. http://dx.doi.org/10.30541/v55i4i-iipp.837-851.

Full text

Abstract:

This study estimates the returns to education while controlling endogeneity and sample selection biases in Pakistan, over a time period using Ordinary Least Square (OLS), simultaneous approach using both Heckman Sample Selection and Instrumental Variable, and Fixed Effect techniques. Household Integrated Economic Survey (HIES) data for 2004-05 and 2011-12 time periods have been used in this study. The returns to education have been found downward biased in OLS estimates for both time periods. The unbiased real returns to education have increased on average for wage workers over time period. Landholding and Non-earned income have been used as exclusion restrictions to control for sample selection bias in the Heckman Sample Selection technique. The endogeneity bias has been controlled for with the help of parental education as instrument in Instrumental Variable technique. Both techniques have also been used collectively or simultaneously to get more efficient estimate in simultaneous approach. Household Fixed Effect technique has also been used with the assumption that ability and family characteristics largely remain same within family or household. The increase in the unbiased and real returns to education shows that profitability still exists in investing in education whereas experience via skill enhancement reinforces this rise in wage. Sadly, the historic gender and regional discriminations persist or aggravate in wage market. Married persons are getting more in returns relative to the unmarried individuals. Having negative implications for income inequality, Convexity in education-earning relationship in Pakistan has been confirmed by Indicator Function technique for both time periods. Low education prompt low-earning workers who would be unable to bear the schooling cost of their children. This seriously inhibits earning potential making income inequality worse. JEL Classification: I26, I24, J24 Keywords: Returns to Education, Human Capital

APA, Harvard, Vancouver, ISO, and other styles

40

Arjasakusuma, Sanjiwana, Sandiaga Swahyu Kusuma, and Stuart Phinn. "Evaluating Variable Selection and Machine Learning Algorithms for Estimating Forest Heights by Combining Lidar and Hyperspectral Data." ISPRS International Journal of Geo-Information 9, no. 9 (August 24, 2020): 507. http://dx.doi.org/10.3390/ijgi9090507.

Full text

Abstract:

Machine learning has been employed for various mapping and modeling tasks using input variables from different sources of remote sensing data. For feature selection involving high- spatial and spectral dimensionality data, various methods have been developed and incorporated into the machine learning framework to ensure an efficient and optimal computational process. This research aims to assess the accuracy of various feature selection and machine learning methods for estimating forest height using AISA (airborne imaging spectrometer for applications) hyperspectral bands (479 bands) and airborne light detection and ranging (lidar) height metrics (36 metrics), alone and combined. Feature selection and dimensionality reduction using Boruta (BO), principal component analysis (PCA), simulated annealing (SA), and genetic algorithm (GA) in combination with machine learning algorithms such as multivariate adaptive regression spline (MARS), extra trees (ET), support vector regression (SVR) with radial basis function, and extreme gradient boosting (XGB) with trees (XGbtree and XGBdart) and linear (XGBlin) classifiers were evaluated. The results demonstrated that the combinations of BO-XGBdart and BO-SVR delivered the best model performance for estimating tropical forest height by combining lidar and hyperspectral data, with R2 = 0.53 and RMSE = 1.7 m (18.4% of nRMSE and 0.046 m of bias) for BO-XGBdart and R2 = 0.51 and RMSE = 1.8 m (15.8% of nRMSE and −0.244 m of bias) for BO-SVR. Our study also demonstrated the effectiveness of BO for variables selection; it could reduce 95% of the data to select the 29 most important variables from the initial 516 variables from lidar metrics and hyperspectral data.

APA, Harvard, Vancouver, ISO, and other styles

41

Eniade, Olanrewaju Davies, Joshua Odunayo Akinyemi, Oyindamola Bidemi Yusuf, Rotimi Felix Afolabi, and Olufunmilayo I. Fawole. "Effect of Education on Attitude Towards Domestic Violence in Nigeria: An Exploration Using Propensity Score Methodology." International Journal of Statistics and Probability 10, no. 3 (April 30, 2021): 154. http://dx.doi.org/10.5539/ijsp.v10n3p154.

Full text

Abstract:

Propensity Score Methodology (PSM) was used to investigate the effect of education on attitude towards domestic violence (ATDV) among men and women in Nigeria. A total of 14,495 and 33,419 records were extracted for men and women respectively from the 2016-2017 Multiple Indicator Cluster Survey (MICS) in Nigeria. The outcome variable was ATDV. The study framework described the role of education on ATDV in the light of demographic characteristics, socioeconomic profile, and lifestyle. Selection bias was checked among the levels of education using the multinomial logit regression. Propensity scores (PS) and PS weights were generated for the treatment variable and average treatment effects (ATE) of ATDV were estimated using logistic regression that combined regression adjustment and inverse-probability weight. Descriptive statistics, odds ratios and 95%CI were presented. The mean age of men and women were 30.8±10.2 years and 29±9.4 years respectively. About 22% men and 35% women justified domestic violence (DV) respectively. Selection bias was found between the covariates and level of education (p<0.05). PSM effectively corrected the selection bias (SD diff ≈ 0, Variance ratio ≈ 1). Men (AOR = 0.84, 95% CI: 0.78, 0.92) and women (AOR=0.94, 95%CI: 0.80, 2.22) who have attained tertiary level of education were less likely to justify DV in comparison to their uneducated counterparts. Tertiary education was protective for ATDV among men and women. The use of PSM effectively controlled for selection bias in estimating the effect of education on ATDV. PSM will enable researchers make causal inference from non-experimental/cross-sectional studies in situations where randomized control trials are not feasible.

APA, Harvard, Vancouver, ISO, and other styles

42

Choi, Jungsoon, and Andrew B. Lawson. "A Bayesian two-stage spatially dependent variable selection model for space–time health data." Statistical Methods in Medical Research 28, no. 9 (April 11, 2018): 2570–82. http://dx.doi.org/10.1177/0962280218767980.

Full text

Abstract:

In space–time epidemiological modeling, most studies have considered the overall variations in relative risk to better estimate the effects of risk factors on health outcomes. However, the associations between risk factors and health outcomes may vary across space and time. Especially, the temporal patterns of the covariate effects may depend on space. Thus, we propose a Bayesian two-stage spatially dependent variable selection approach for space–time health data to determine the spatially varying subsets of regression coefficients with common temporal dependence. The two-stage structure allows reduction of the spatial confounding bias in the estimates of the regression coefficients. A simulation study is conducted to examine the performance of the proposed two-stage model. We apply the proposed model to the number of inpatients with lung cancer in 159 counties of Georgia, USA.

APA, Harvard, Vancouver, ISO, and other styles

43

Ertefaie, Ashkan, Dylan Small, James Flory, and Sean Hennessy. "Selection Bias When Using Instrumental Variable Methods to Compare Two Treatments But More Than Two Treatments Are Available." International Journal of Biostatistics 12, no. 1 (May 1, 2016): 219–32. http://dx.doi.org/10.1515/ijb-2015-0006.

Full text

Abstract:

Abstract Instrumental variable (IV) methods are widely used to adjust for the bias in estimating treatment effects caused by unmeasured confounders in observational studies. It is common that a comparison between two treatments is focused on and that only subjects receiving one of these two treatments are considered in the analysis even though more than two treatments are available. In this paper, we provide empirical and theoretical evidence that the IV methods may result in biased treatment effects if applied on a data set in which subjects are preselected based on their received treatments. We frame this as a selection bias problem and propose a procedure that identifies the treatment effect of interest as a function of a vector of sensitivity parameters. We also list assumptions under which analyzing the preselected data does not lead to a biased treatment effect estimate. The performance of the proposed method is examined using simulation studies. We applied our method on The Health Improvement Network (THIN) database to estimate the comparative effect of metformin and sulfonylureas on weight gain among diabetic patients.

APA, Harvard, Vancouver, ISO, and other styles

44

Lai, Peng, Qihua Wang, and Heng Lian. "Bias-corrected GEE estimation and smooth-threshold GEE variable selection for single-index models with clustered data." Journal of Multivariate Analysis 105, no. 1 (February 2012): 422–32. http://dx.doi.org/10.1016/j.jmva.2011.08.009.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Arezzo, Maria Felice, and Giuseppina Guagnano. "Misclassification in Binary Choice Models with Sample Selection." Econometrics 7, no. 3 (July 24, 2019): 32. http://dx.doi.org/10.3390/econometrics7030032.

Full text

Abstract:

Most empirical work in the social sciences is based on observational data that are often both incomplete, and therefore unrepresentative of the population of interest, and affected by measurement errors. These problems are very well known in the literature and ad hoc procedures for parametric modeling have been proposed and developed for some time, in order to correct estimate’s bias and obtain consistent estimators. However, to our best knowledge, the aforementioned problems have not yet been jointly considered. We try to overcome this by proposing a parametric approach for the estimation of the probabilities of misclassification of a binary response variable by incorporating them in the likelihood of a binary choice model with sample selection.

APA, Harvard, Vancouver, ISO, and other styles

46

Mauro, Francisco, Zane Haxtema, and Hailemariam Temesgen. "Comparison of sampling methods for estimation of nearest-neighbor index values." Canadian Journal of Forest Research 47, no. 6 (June 2017): 703–15. http://dx.doi.org/10.1139/cjfr-2016-0239.

Full text

Abstract:

Neighborhood-based indices such as mingling index and diameter differentiation are a set of diversity measures that are based on the relationship between a reference tree and a certain number of nearest neighbors (i.e., trees to which it has the lowest horizontal distance). Using stem-mapped data from eight headwater sites, we compared the relative bias and relative root mean square error (relative to the true mean of each site) of several different methods of choosing reference trees for calculation of diameter differentiation ([Formula: see text]) and species mingling ([Formula: see text]) index. Indices were defined using two, three, and four neighbors and methods for selection of the reference tree were random selection of a tree in a fixed-radius plot (FI), random selection of a tree in a variable-radius plot (VA), azimuth selection method (AZ), and nearest tree selection (NT). In general, the relative bias was lower than ±2.5% for [Formula: see text] and lower than ±10% for [Formula: see text] regardless of the method. The FI method consistently had the lowest relative bias and relative root mean squared error. The NT and AZ methods were second in terms of relative root mean squared error for [Formula: see text] and [Formula: see text], respectively. Simplicity of these two methods might outweigh their slightly worse performance.

APA, Harvard, Vancouver, ISO, and other styles

47

Caniglia, Ellen C., Rebecca Zash, Sonja A. Swanson, Kathleen E. Wirth, Modiegi Diseko, Gloria Mayondi, Shahin Lockman, et al. "Methodological Challenges When Studying Distance to Care as an Exposure in Health Research." American Journal of Epidemiology 188, no. 9 (May 20, 2019): 1674–81. http://dx.doi.org/10.1093/aje/kwz121.

Full text

Abstract:

Abstract Distance to care is a common exposure and proposed instrumental variable in health research, but it is vulnerable to violations of fundamental identifiability conditions for causal inference. We used data collected from the Botswana Birth Outcomes Surveillance study between 2014 and 2016 to outline 4 challenges and potential biases when using distance to care as an exposure and as a proposed instrument: selection bias, unmeasured confounding, lack of sufficiently well-defined interventions, and measurement error. We describe how these issues can arise, and we propose sensitivity analyses for estimating the degree of bias.

APA, Harvard, Vancouver, ISO, and other styles

48

Cheung, Peter, Isaac Schweitzer, Olga Yastrubetskaya, Kathleen Crowley, and Virginia Tuckwell. "Studies of Aggressive Behaviour in Schizophrenia: Is There a Response Bias?" Medicine, Science and the Law 37, no. 4 (October 1997): 345–48. http://dx.doi.org/10.1177/002580249703700411.

Full text

Abstract:

Of 73 patients who met selection criteria to enter into a study on aggressive behaviour in schizophrenia, 11 patients (15.1%) did not participate. The participants and non-participants were similar in age, gender ratio and proportion who had aggressive behaviour. The participants, however, had a longer duration of illness, a longer duration of current admission, were more likely to suffer from residual schizophrenia, but less likely to suffer from disorganized schizophrenia and were less severely ill than the non-participants. These results indicate the need, in studies of aggressive behaviour in schizophrenia, to consider non-response bias as a confounding variable.

APA, Harvard, Vancouver, ISO, and other styles

49

Pérez-Galarce, F., K. Pichara, P. Huijse, M. Catelan, and D. Mery. "Informative Bayesian model selection for RR Lyrae star classifiers." Monthly Notices of the Royal Astronomical Society 503, no. 1 (February 5, 2021): 484–97. http://dx.doi.org/10.1093/mnras/stab320.

Full text

Abstract:

ABSTRACT Machine learning has achieved an important role in the automatic classification of variable stars, and several classifiers have been proposed over the last decade. These classifiers have achieved impressive performance in several astronomical catalogues. However, some scientific articles have also shown that the training data therein contain multiple sources of bias. Hence, the performance of those classifiers on objects not belonging to the training data is uncertain, potentially resulting in the selection of incorrect models. Besides, it gives rise to the deployment of misleading classifiers. An example of the latter is the creation of open-source labelled catalogues with biased predictions. In this paper, we develop a method based on an informative marginal likelihood to evaluate variable star classifiers. We collect deterministic rules that are based on physical descriptors of RR Lyrae stars, and then, to mitigate the biases, we introduce those rules into the marginal likelihood estimation. We perform experiments with a set of Bayesian logistic regressions, which are trained to classify RR Lyraes, and we found that our method outperforms traditional non-informative cross-validation strategies, even when penalized models are assessed. Our methodology provides a more rigorous alternative to assess machine learning models using astronomical knowledge. From this approach, applications to other classes of variable stars and algorithmic improvements can be developed.

APA, Harvard, Vancouver, ISO, and other styles

50

Loayza Acosta, Gustavo Ilich, Naisha Alyssa Bernardo Reyes, and Margarita Elluz Calle Arancibia. "Returns to Investment in University Education - Economics Career at Continental University." Research in World Economy 12, no. 1 (January 6, 2021): 166. http://dx.doi.org/10.5430/rwe.v12n1p166.

Full text

Abstract:

The present work analyzes the returns to the years of superior schooling of graduates of Economics Career at Continental University within the labor market of the region Junín of the period 2019. For this purpose, the returns to education are investigated under the normal assumptions of Mincer's equation, and later the incorporation of the instrumental variable: school of origin is proposed, in order to correct the problem of endogeneity. Finally, to correct the problem of selection bias, Heckman's technique is used: two-stage regression. This consists of first analyzing the probability of accessing the labor market in the Junín region in terms of variables such as: geographic location, school of origin, age, direct costs. Subsequently, analyzing the return to years of schooling. Likewise, it is important to specify that in the modeling of the probability a second regression is estimated incorporating the variable Academic Grade in order to be able to study the Sheepskin Effect. The results obtained showed that the return to years of schooling is 0.8%, which is not significant and is not corrected for Heckman's selection bias. We also have that the R2 is 10.11% which is very low for this type of cross-sectional data. This result is explained by the degree of rootedness of the graduates in staying in the Huancayo province and the low migration to other labor markets. In addition, this means that they do not have better working conditions that can be transformed into higher income.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Variable selection bias'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles