China
Africa
Explore chapters and articles related to this topic
Analyticity
Published in Vivek Kale, Digital Transformation of Enterprise Architecture, 2019
The term time series regression refers to regression analysis in which the organizing unit of analysis is time. We look at relationships among economic measures organized in time. Much economic analysis concerns time series regression. Special care must be taken to avoid what might be called spurious relationships, as many economic time series are correlated with one another because they depend upon underlying factors, such as population growth or seasonality. In time series regression, we use standard linear regression methods. We check the residuals from our regression to ensure that they are not correlated in time. If they are correlated in time (autocorrelated), then we use a method such as generalized least squares as an alternative to ordinary least squares. That is, we incorporate an error data model as part of our modeling process. Longitudinal data analysis or panel data analysis is an example of a mixed data method with a focus on data organized by cross-sectional units and time.
Analysis of the causes of unemployment in DKI Jakarta using panel data regression
Published in Yuli Rahmawati, Peter Charles Taylor, Empowering Science and Mathematics for Global Competitiveness, 2019
W. Rahayu, V. Maya Santi, D. Siregar
where i = 1, …, N; t = 1, …, T with i units across locations and t time series units. To estimate the parameters of a panel data regression model, the method to be used depends on assumptions about intercept, slope, and error constants. Judging from the various assumptions and their constituents, the panel data regression model consists of a pooled regression model, a fixed effect model, and a random effect model.
The propellants of the Logistics Performance Index: an empirical panel investigation of the European region
Published in International Journal of Logistics Research and Applications, 2023
Serdar Alnıpak, Erkan Isikli, Sudi Apak
Panel data is a type of longitudinal data; it involves repeated measurements on the same set of units (cross-sections) such as individuals, households, and firms (Dougherty 2015). Replications may be observed since measurements repeat over time or since different units within a given set exist (e.g. employees of a company). Panel data is basically classified into two groups: short panels and long panels. In the former, the number of individuals is large compared to the number of observations for a given individual. In the latter, however, the data is rich enough to fit time series models to each individual. Furthermore, if a panel data has missing observations distributed among the variables, it is called an unbalanced panel; if the data set is complete, it is called a balanced panel. Regarding parameter estimation, these two types of panels do not require different approaches though.
Traffic congestion and air pollution: Empirical evidence before/after COVID-19 in Seoul, Korea
Published in International Journal of Sustainable Transportation, 2023
Table 1 presents the descriptive statistics of the variables used in this study. The averages of PM10 and PM2.5 are 43.38 and 24.01 respectively. The maximum values of PM10 and PM2.5, 479 and 204 indicating that the highest levels of PM10 and PM2.5 are substantially serious and may negatively affect citizens’ personal health. The average RCI is 1.64 and the COVID19 dummy is 0.2. The average temperature, wind speed, and precipitation are 13.40 °C, 1.63 m/s, and 0.14 m/s, respectively. As we use hourly based samples between 2016 and 2020, our sample size is large, especially 501,906. Missing values often occur when collecting, cleaning, and processing data because of various reasons. In our samples, the PM10 data contain 1.5% (16,523) missing values and PM2.5 contain 2.3% (24,732) missing values, respectively. Balanced panel data is ideal, but most panel data contain some missing values. Hence, we use unbalanced panel models that has been widely used among researchers.
Measurement of inland port spatial relationship: a case study of Yangtze River inland ports
Published in Maritime Policy & Management, 2022
In panel data analysis, the Hausman test is used for model selection, and the null hypothesis of the test is that the preferred model is a random effect rather than a fixed effect (Greene 2008). Lee and Yu (2012) extended the Hausman test to the spatial panel model. Therefore, in this study, the form of the model is first determined using the Hausman test. In all model specifications (W1,W2,W3, and W4), the Hausman test results (Table 2) showed that p-values are at least<0.1. The Hausman test reflected the overly restrictive assumption that treats specific effects (μi) as random variables. Therefore, a fixed-effects model was selected instead of a random-effects model. Fixed effects, such as those associated with socio-economic conditions and geographical aspects, may account for time-invariant regional heterogeneity affecting inland port activities. The spatial section investigated in this study is representative of the entire sample range (which includes almost all inland ports along the Yangtze River), and the adjacent spatial units are located in an unbroken study area; thus, the fixed-effect model may be more appropriate (Elhorst 2014).