A practical introduction to methods for analyzing longitudinal data in the presence of missing data using a marijuana price survey

2015 ◽  
Vol 5 (2) ◽  
pp. 137-148 ◽  
Author(s):  
Jeremy N.V Miles ◽  
Priscillia Hunt
Keyword(s):  
Missing Data ◽  
Statistical Power ◽  
Criminal Psychology ◽  
Likelihood Estimation ◽  
Data Sets ◽  
Applied Psychology ◽  
Artificial Data ◽  
Data Set ◽  
Content Type ◽  
Biased Estimates

Purpose – In applied psychology research settings, such as criminal psychology, missing data are to be expected. Missing data can cause problems with both biased estimates and lack of statistical power. The paper aims to discuss these issues. Design/methodology/approach – Recently, sophisticated methods for appropriately dealing with missing data, so as to minimize bias and to maximize power have been developed. In this paper the authors use an artificial data set to demonstrate the problems that can arise with missing data, and make naïve attempts to handle data sets where some data are missing. Findings – With the artificial data set, and a data set comprising of the results of a survey investigating prices paid for recreational and medical marijuana, the authors demonstrate the use of multiple imputation and maximum likelihood estimation for obtaining appropriate estimates and standard errors when data are missing. Originality/value – Missing data are ubiquitous in applied research. This paper demonstrates that techniques for handling missing data are accessible and should be employed by researchers.

Missing Data - Better "Not to Have Them", but What If You Do? (Part 1)

Marketing ZFP ◽  
2019 ◽  
Vol 41 (4) ◽  
pp. 21-32
Author(s):  
Dirk Temme ◽  
Sarah Jensen
Keyword(s):  
Missing Data ◽  
Statistical Power ◽  
Missing Values ◽  
Graphical Representation ◽  
Marketing Research ◽  
Likelihood Estimation ◽  
Parameter Estimates ◽  
Full Information Maximum Likelihood ◽  
Definition Of ◽  
Traditional Approaches

Missing values are ubiquitous in empirical marketing research. If missing data are not dealt with properly, this can lead to a loss of statistical power and distorted parameter estimates. While traditional approaches for handling missing data (e.g., listwise deletion) are still widely used, researchers can nowadays choose among various advanced techniques such as multiple imputation analysis or full-information maximum likelihood estimation. Due to the available software, using these modern missing data methods does not pose a major obstacle. Still, their application requires a sound understanding of the prerequisites and limitations of these methods as well as a deeper understanding of the processes that have led to missing values in an empirical study. This article is Part 1 and first introduces Rubin’s classical definition of missing data mechanisms and an alternative, variable-based taxonomy, which provides a graphical representation. Secondly, a selection of visualization tools available in different R packages for the description and exploration of missing data structures is presented.

scholarly journals Maximum Likelihood Estimation of the VAR(1) Model Parameters with Missing Observations

2013 ◽  
Vol 2013 ◽  
pp. 1-13 ◽  
Author(s):  
Helena Mouriño ◽  
Maria Isabel Barão
Keyword(s):  
Stochastic Process ◽  
Missing Data ◽  
Maximum Likelihood ◽  
Moving Average ◽  
Practical Importance ◽  
Likelihood Estimation ◽  
Model Parameters ◽  
Missing Observations ◽  
Data Set ◽  
The Impact

Missing-data problems are extremely common in practice. To achieve reliable inferential results, we need to take into account this feature of the data. Suppose that the univariate data set under analysis has missing observations. This paper examines the impact of selecting an auxiliary complete data set—whose underlying stochastic process is to some extent interdependent with the former—to improve the efficiency of the estimators for the relevant parameters of the model. The Vector AutoRegressive (VAR) Model has revealed to be an extremely useful tool in capturing the dynamics of bivariate time series. We propose maximum likelihood estimators for the parameters of the VAR(1) Model based on monotone missing data pattern. Estimators’ precision is also derived. Afterwards, we compare the bivariate modelling scheme with its univariate counterpart. More precisely, the univariate data set with missing observations will be modelled by an AutoRegressive Moving Average (ARMA(2,1)) Model. We will also analyse the behaviour of the AutoRegressive Model of order one, AR(1), due to its practical importance. We focus on the mean value of the main stochastic process. By simulation studies, we conclude that the estimator based on the VAR(1) Model is preferable to those derived from the univariate context.

A systematic review of machine learning-based missing value imputation techniques

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Tressy Thomas ◽  
Enayat Rajabi
Keyword(s):  
Machine Learning ◽  
Selection Process ◽  
Evaluation Metrics ◽  
Correct Prediction ◽  
Data Sets ◽  
Data Set ◽  
Missing Value ◽  
Content Type ◽  
Missing Value Imputation ◽  
Literature Reviews

PurposeThe primary aim of this study is to review the studies from different dimensions including type of methods, experimentation setup and evaluation metrics used in the novel approaches proposed for data imputation, particularly in the machine learning (ML) area. This ultimately provides an understanding about how well the proposed framework is evaluated and what type and ratio of missingness are addressed in the proposals. The review questions in this study are (1) what are the ML-based imputation methods studied and proposed during 2010–2020? (2) How the experimentation setup, characteristics of data sets and missingness are employed in these studies? (3) What metrics were used for the evaluation of imputation method?Design/methodology/approachThe review process went through the standard identification, screening and selection process. The initial search on electronic databases for missing value imputation (MVI) based on ML algorithms returned a large number of papers totaling at 2,883. Most of the papers at this stage were not exactly an MVI technique relevant to this study. The literature reviews are first scanned in the title for relevancy, and 306 literature reviews were identified as appropriate. Upon reviewing the abstract text, 151 literature reviews that are not eligible for this study are dropped. This resulted in 155 research papers suitable for full-text review. From this, 117 papers are used in assessment of the review questions.FindingsThis study shows that clustering- and instance-based algorithms are the most proposed MVI methods. Percentage of correct prediction (PCP) and root mean square error (RMSE) are most used evaluation metrics in these studies. For experimentation, majority of the studies sourced the data sets from publicly available data set repositories. A common approach is that the complete data set is set as baseline to evaluate the effectiveness of imputation on the test data sets with artificially induced missingness. The data set size and missingness ratio varied across the experimentations, while missing datatype and mechanism are pertaining to the capability of imputation. Computational expense is a concern, and experimentation using large data sets appears to be a challenge.Originality/valueIt is understood from the review that there is no single universal solution to missing data problem. Variants of ML approaches work well with the missingness based on the characteristics of the data set. Most of the methods reviewed lack generalization with regard to applicability. Another concern related to applicability is the complexity of the formulation and implementation of the algorithm. Imputations based on k-nearest neighbors (kNN) and clustering algorithms which are simple and easy to implement make it popular across various domains.

Fast and accurate detection of surface defect based on improved YOLOv4

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Jiawei Lian ◽  
Junhong He ◽  
Yun Niu ◽  
Tianze Wang
Keyword(s):  
Feature Extraction ◽  
Real Time ◽  
Surface Defect ◽  
Steel Ingot ◽  
Industrial Applications ◽  
Data Sets ◽  
Data Set ◽  
Processing Technologies ◽  
Content Type ◽  
Public Data

Purpose The current popular image processing technologies based on convolutional neural network have the characteristics of large computation, high storage cost and low accuracy for tiny defect detection, which is contrary to the high real-time and accuracy, limited computing resources and storage required by industrial applications. Therefore, an improved YOLOv4 named as YOLOv4-Defect is proposed aim to solve the above problems. Design/methodology/approach On the one hand, this study performs multi-dimensional compression processing on the feature extraction network of YOLOv4 to simplify the model and improve the feature extraction ability of the model through knowledge distillation. On the other hand, a prediction scale with more detailed receptive field is added to optimize the model structure, which can improve the detection performance for tiny defects. Findings The effectiveness of the method is verified by public data sets NEU-CLS and DAGM 2007, and the steel ingot data set collected in the actual industrial field. The experimental results demonstrated that the proposed YOLOv4-Defect method can greatly improve the recognition efficiency and accuracy and reduce the size and computation consumption of the model. Originality/value This paper proposed an improved YOLOv4 named as YOLOv4-Defect for the detection of surface defect, which is conducive to application in various industrial scenarios with limited storage and computing resources, and meets the requirements of high real-time and precision.

An application of data envelopment analysis for Korean banks with negative data

2017 ◽  
Vol 24 (4) ◽  
pp. 1052-1064 ◽  
Author(s):  
Yong Joo Lee ◽  
Seong-Jong Joo ◽  
Hong Gyun Park
Keyword(s):  
Data Envelopment Analysis ◽  
Data Sets ◽  
Data Envelopment ◽  
Negative Data ◽  
Ownership Type ◽  
Data Set ◽  
Translation Invariant ◽  
Content Type ◽  
Dea Models ◽  
Regional Banks

Purpose The purpose of this paper is to measure the comparative efficiency of 18 Korean commercial banks under the presence of negative observations and examine performance differences among them by grouping them according to their market conditions. Design/methodology/approach The authors employ two data envelopment analysis (DEA) models such as a Banker, Charnes, and Cooper (BCC) model and a modified slacks-based measure of efficiency (MSBM) model, which can handle negative data. The BCC model is proven to be translation invariant for inputs or outputs depending on output or input orientation. Meanwhile, the MSBM model is unit invariant in addition to translation invariant. The authors compare results from both models and choose one for interpreting results. Findings Most Korean banks recovered from the worst performance in 2011 and showed similar performance in recent years. Among three groups such as national banks, regional banks, and special banks, the most special banks demonstrated superb performance across models and years. Especially, the performance difference between the special banks and the regional banks was statistically significant. The authors concluded that the high performance of the special banks was due to their nationwide market access and ownership type. Practical implications This study demonstrates how to analyze and measure the efficiency of entities when variables contain negative observations using a data set for Korean banks. The authors have tried two major DEA models that are able to handle negative data and proposed a practical direction for future studies. Originality/value Although there are research papers for measuring the performance of banks in Korea, all of the papers in the topic have studied efficiency or productivity using positive data sets. However, variables such as net incomes and growth rates frequently include negative observations in bank data sets. This is the first paper to investigate the efficiency of bank operations in the presence of negative data in Korea.

A scalable eigenspace-based fuzzy c-means for topic detection

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hendri Murfi
Keyword(s):  
Representation Learning ◽  
Detection Methods ◽  
Data Sets ◽  
Topic Detection ◽  
Data Set ◽  
Content Type ◽  
Running Time ◽  
Fuzzy C Means ◽  
Coherence Score ◽  
Value Decomposition

PurposeThe aim of this research is to develop an eigenspace-based fuzzy c-means method for scalable topic detection.Design/methodology/approachThe eigenspace-based fuzzy c-means (EFCM) combines representation learning and clustering. The textual data are transformed into a lower-dimensional eigenspace using truncated singular value decomposition. Fuzzy c-means is performed on the eigenspace to identify the centroids of each cluster. The topics are provided by transforming back the centroids into the nonnegative subspace of the original space. In this paper, we extend the EFCM method for scalability by using the two approaches, i.e. single-pass and online. We call the developed topic detection methods as oEFCM and spEFCM.FindingsOur simulation shows that both oEFCM and spEFCM methods provide faster running times than EFCM for data sets that do not fit in memory. However, there is a decrease in the average coherence score. For both data sets that fit and do not fit into memory, the oEFCM method provides a tradeoff between running time and coherence score, which is better than spEFCM.Originality/valueThis research produces a scalable topic detection method. Besides this scalability capability, the developed method also provides a faster running time for the data set that fits in memory.

A systematical approach to classification problems with feature space heterogeneity

Kybernetes ◽  
2019 ◽  
Vol 48 (9) ◽  
pp. 2006-2029
Author(s):  
Hongshan Xiao ◽  
Yu Wang
Keyword(s):  
Factor Analysis ◽  
Meta Analysis ◽  
Feature Space ◽  
Classification Performance ◽  
Classification Algorithm ◽  
Significant Feature ◽  
Data Sets ◽  
Data Set ◽  
Classification Techniques ◽  
Content Type

Purpose Feature space heterogeneity exists widely in various application fields of classification techniques, such as customs inspection decision, credit scoring and medical diagnosis. This paper aims to study the relationship between feature space heterogeneity and classification performance. Design/methodology/approach A measurement is first developed for measuring and identifying any significant heterogeneity that exists in the feature space of a data set. The main idea of this measurement is derived from a meta-analysis. For the data set with significant feature space heterogeneity, a classification algorithm based on factor analysis and clustering is proposed to learn the data patterns, which, in turn, are used for data classification. Findings The proposed approach has two main advantages over the previous methods. The first advantage lies in feature transform using orthogonal factor analysis, which results in new features without redundancy and irrelevance. The second advantage rests on samples partitioning to capture the feature space heterogeneity reflected by differences of factor scores. The validity and effectiveness of the proposed approach is verified on a number of benchmarking data sets. Research limitations/implications Measurement should be used to guide the heterogeneity elimination process, which is an interesting topic in future research. In addition, to develop a classification algorithm that enables scalable and incremental learning for large data sets with significant feature space heterogeneity is also an important issue. Practical implications Measuring and eliminating the feature space heterogeneity possibly existing in the data are important for accurate classification. This study provides a systematical approach to feature space heterogeneity measurement and elimination for better classification performance, which is favorable for applications of classification techniques in real-word problems. Originality/value A measurement based on meta-analysis for measuring and identifying any significant feature space heterogeneity in a classification problem is developed, and an ensemble classification framework is proposed to deal with the feature space heterogeneity and improve the classification accuracy.

scholarly journals Waiting longer before claiming, and activating youth: no point?

2019 ◽  
Vol 40 (4) ◽  
pp. 658-687 ◽  
Author(s):  
Bart Cockx ◽  
Eva Van Belle
Keyword(s):  
Low Income ◽  
Statistical Power ◽  
Local Treatment ◽  
Unemployment Duration ◽  
Data Set ◽  
Waiting Period ◽  
Content Type ◽  
Highly Educated ◽  
Job Finding ◽  
The Impact

Purpose The purpose of this paper is to estimate the impact of two policies (an extension of the waiting period before entitlement to unemployment insurance (UI) and an intensification of counselling) targeted at unemployed school-leavers in Belgium on unemployment duration and on the quality of work. Design/methodology/approach The length of both policies is sharply determined by two distinct age thresholds. These thresholds are exploited to estimate the impact within a regression discontinuity design using a large administrative data set of all recent labour market entrants. Findings The longer waiting period does not significantly impact job finding while the Youth Work Plan does increase the job-finding rate eight months after the onset of the programme. The accepted wage is unaffected, but both policies lower the number of working days resulting in lower earnings. This effect is especially prevalent for youth from low-income households. Research limitations/implications For both policies, participation was delineated by an age cut-off which was only four months apart. This sizeably reduced the width of the age window to detect a corresponding discontinuity in behaviour and hereby also the statistical power of the estimator. Additionally, due to confounding policies the estimated effects are local treatment effects for highly educated youth around the age cut-offs. Social implications The findings suggest that threatening with a sanction is not the right instrument to activate highly educated unemployed school-leavers. While supportive measures appear to be more effective, this may be partly a consequence of acceptance of lower quality jobs due to liquidity constraints and of caseworkers giving misleading advice that temporary jobs are stepping stones to long-term employment. Originality/value To the best of the authors’ knowledge, this is the first paper to estimate the impact of changing the waiting period in UI. The paper adds to the existing literature on the effects of counselling and UI design on employment and job quality.

US academic libraries' staffing and expenditure trends (1996–2016)

2020 ◽  
Vol 41 (4/5) ◽  
pp. 247-268 ◽  
Author(s):  
Starr Hoffman ◽  
Samantha Godbey
Keyword(s):  
Academic Libraries ◽  
The United States ◽  
Data Sets ◽  
Size Category ◽  
Data Set ◽  
Content Type ◽  
Education Statistics ◽  
Trends Over Time ◽  
Doctoral Institutions ◽  
Over Time

PurposeThis paper explores trends over time in library staffing and staffing expenditures among two- and four-year colleges and universities in the United States.Design/methodology/approachResearchers merged and analyzed data from 1996 to 2016 from the National Center for Education Statistics for over 3,500 libraries at postsecondary institutions. This study is primarily descriptive in nature and addresses the research questions: How do staffing trends in academic libraries over this period of time relate to Carnegie classification and institution size? How do trends in library staffing expenditures over this period of time correspond to these same variables?FindingsAcross all institutions, on average, total library staff decreased from 1998 to 2012. Numbers of librarians declined at master’s and doctoral institutions between 1998 and 2016. Numbers of students per librarian increased over time in each Carnegie and size category. Average inflation-adjusted staffing expenditures have remained steady for master's, baccalaureate and associate's institutions. Salaries as a percent of library budget decreased only among doctoral institutions and institutions with 20,000 or more students.Originality/valueThis is a valuable study of trends over time, which has been difficult without downloading and merging separate data sets from multiple government sources. As a result, few studies have taken such an approach to this data. Consequently, institutions and libraries are making decisions about resource allocation based on only a fraction of the available data. Academic libraries can use this study and the resulting data set to benchmark key staffing characteristics.

A classification approach based on variable precision rough sets and cluster validity index function

2014 ◽  
Vol 31 (8) ◽  
pp. 1778-1789
Author(s):  
Hongkang Lin
Keyword(s):  
Optimal Number ◽  
Data Sets ◽  
Cluster Validity ◽  
Cluster Validity Index ◽  
Index Method ◽  
Data Set ◽  
Content Type ◽  
The Individual ◽  
Variable Precision Rough Sets ◽  
Optimal Number Of Clusters

Purpose – The clustering/classification method proposed in this study, designated as the PFV-index method, provides the means to solve the following problems for a data set characterized by imprecision and uncertainty: first, discretizing the continuous values of all the individual attributes within a data set; second, evaluating the optimality of the discretization results; third, determining the optimal number of clusters per attribute; and fourth, improving the classification accuracy (CA) of data sets characterized by uncertainty. The paper aims to discuss these issues. Design/methodology/approach – The proposed method for the solution of the clustering/classifying problem, designated as PFV-index method, combines a particle swarm optimization algorithm, fuzzy C-means method, variable precision rough sets theory, and a new cluster validity index function. Findings – This method could cluster the values of the individual attributes within the data set and achieves both the optimal number of clusters and the optimal CA. Originality/value – The validity of the proposed approach is investigated by comparing the classification results obtained for UCI data sets with those obtained by supervised classification BPNN, decision-tree methods.

Sign in / Sign up

Export Citation Format

Share Document