On the examination of the reliability of statistical software for estimating regression models with discrete dependent variables

2017 ◽  
Vol 33 (2) ◽  
pp. 757-786 ◽  
Author(s):  
Jason S. Bergtold ◽  
Krishna P. Pokharel ◽  
Allen M. Featherstone ◽  
Lijia Mo
Keyword(s):  
Regression Models ◽  
Statistical Software ◽  
Dependent Variables ◽  
Discrete Dependent Variables

scholarly journals The Influence of Industrial Clusters and Place on Innovation and Entrepreneurial Behaviour

2007 ◽  
Vol 8 (3) ◽  
pp. 165-174 ◽  
Author(s):  
Pam McRae-Williams ◽  
Julian Lowe ◽  
Peter Taylor
Keyword(s):  
Regression Models ◽  
Personal Characteristics ◽  
Industrial Clusters ◽  
Factor Scores ◽  
Standard View ◽  
Behaviour Factor ◽  
Regional Clusters ◽  
Entrepreneurial Behaviour ◽  
Dependent Variables ◽  
Central Result

Responses from a questionnaire survey of wine and tourism businesses operating in regional clusters were analysed using factor analysis. These suggested three factor scores relating to entrepreneurial behaviour; four factor scores relating to cluster activities and attributes; and three factors relating to the respondents' personal characteristics. The three entrepreneurial behaviour factor scores were interpreted as: innovator, calculator and venturer. These were used as dependent variables in regression models. The independent variables were the cluster and personal characteristics factor scores, industry and place. The central result was that the cluster activity variables did not have a significant impact on the innovator behaviour variable, which contradicts the standard view. Cluster activities and attributes were found to attract entrepreneurs of the calculator kind, and to a lesser extent, of the venturer kind. Place did seem to offer an attraction to entrepreneurs beyond those offered by the intensities of the cluster activities and attributes.

Women in the Legislatures and Executives of the World: Knocking at the Highest Glass Ceiling

1999 ◽  
Vol 51 (4) ◽  
pp. 547-572 ◽  
Author(s):  
Andrew Reynolds
Keyword(s):  
Multivariate Regression ◽  
Regression Models ◽  
Socioeconomic Development ◽  
Party System ◽  
Political Representation ◽  
Parliamentary System ◽  
Dependent Variables ◽  
The World ◽  
Political Office ◽  
Women In Parliament

This article reports the results of a survey of women in legislatures and executives around the world as they were constituted in 1998 (N = 180). The chief hypotheses regarding the factors hindering or facilitating women's access to political representation were tested by multivariate regression models. The regression models juxtaposed a cocktail of institutional, political, cultural, and socioeconomic variables with the following dependent variables: (1) the percentage of MPs who are women and (2) the percentage of cabinet ministers who are women.A number, although not all, of the cited hypotheses were statistically confirmed and more finely quantified. The socioeconomic development of women in society has an effect on the number of women in parliament but not in the cabinet. A country's length of experience with multipartyism and women's enfranchisement correlates with both the legislative and the executive percentage. Certain electoral systems are more women friendly than others. The ideological nature of the party system affects the number of women elected and chosen for cabinet posts. And last, the state's dominant religion, taken as a proxy for culture, also statistically relates to the number of women who will make it to high political office. However, other long-held hypotheses were not proved. The degree of democracy is not a good indicator of the percentage of women who will make it into the legislature or the cabinet, nor is the dichotomy between a presidential or parliamentary system.

scholarly journals A Regionalised Neyman-Scott Model of Rainfall with Convective and Stratiform Cells

1997 ◽  
Vol 1 (1) ◽  
pp. 71-80 ◽  
Author(s):  
P. S. P. Cowpertwait ◽  
P. E. O'Connell
Keyword(s):  
Cluster Model ◽  
Regression Models ◽  
Parameter Estimates ◽  
Model Parameter ◽  
Lack Of Fit ◽  
Dependent Variables ◽  
The Uk ◽  
Poisson Cluster ◽  
Residual Errors ◽  
Urban Sites

Abstract. A single-site Neyman-Scott Poisson cluster model of rainfall, with convective and stratiform cells, is fitted to data for 112 sites scattered throughout the UK using harmonic variables to account for seasonality. The model is regionalised by regressing the estimates of the harmonic variables on site dependent variables (e.g. altitude) to enable rainfall to be simulated at any ungauged site in the UK. An assessment of the residual errors indicates that the regression models can be used with reasonable confidence for urban sites. Furthermore, the regional variations of the model parameter estimates are found to be in agreement with meteorological knowledge and observation. Simulated I h extreme rainfalls are found to compare favourably with observed historical values, although some lack-of-fit is evident for higher aggregation levels.

Markov Models for Repeated Ordinal Data

2006 ◽  
Vol 45 (04) ◽  
pp. 414-418
Author(s):  
J. Wellmann
Keyword(s):  
Ordinal Data ◽  
Regression Models ◽  
Markov Models ◽  
Correlated Data ◽  
Repeated Measurements ◽  
Statistical Software ◽  
First Order ◽  
Regression Methods ◽  
Estimation Equations ◽  
Continuation Ratio

Summary Objectives: To demonstrate the application of Markov models, especially for ordinal outcomes, within the context of regression models for correlated data. Methods: A brief review of regression methods for correlated data is given. A proportional odds model and a continuation ratio model is applied to repeated measurements of macular pigment density, obtained in an intervention study on the supplementation of macular carotenoids. The correlation between repeated assessments is assumed to follow a first-order Markov model. The models are implemented with standard statistical software. Results: Both models, though not directly comparable, provide a similar conclusion. The application of these models with standard statistical software is straightforward. Conclusions: Markov models can be valuable alternatives to random effects modes or procedures based on generalized estimation equations.

Relationships Between GIS Environmental Features and Adolescent Male Physical Activity: GIS Coding Differences

2006 ◽  
Vol 3 (2) ◽  
pp. 230-242 ◽  
Author(s):  
Russell Jago ◽  
Tom Baranowski ◽  
Michael Harris
Keyword(s):  
Physical Activity ◽  
Environmental Variables ◽  
Regression Models ◽  
Adolescent Male ◽  
Grocery Stores ◽  
Activity Levels ◽  
Independent Variables ◽  
Environmental Features ◽  
Gis Data ◽  
Dependent Variables

Background:It is not clear if relationships between GIS obtained environmental features and physical activity differ according to the method used to code GIS data.Methods:Physical activity levels of 210 Boy Scouts were measured by accelerometer. Numbers of parks, trails, gymnasia, bus stops, grocery stores, and restaurants within the commonly used 400 m and 1-mile (1609.3 m) buffers of subject residences and distance to the nearest feature were calculated. Residential density, connectivity, and crime rate were calculated. Regression models with minutes of sedentary, light, or moderate-to-vigorous activity as dependent variables and environmental and demographics as independent variables were run with backward deletion of environmental variables.Results:Park, crime, and gym variables were associated with physical activity, but relationships varied according to whether a 400 m, 1 mile, or nearest criteria was used.Conclusion:Environmental variables were associated with the physical activity of adolescent males, but the association was method dependent.

Sign in / Sign up

Export Citation Format

Share Document