Qualitative Response Regression Modeling

2015 ◽  
pp. 172-183
Author(s):  
Aliyu Olayemi Abdullateef
Keyword(s):  
Probability Model ◽  
Categorical Variables ◽  
Response Variable ◽  
Explanatory Variables ◽  
Qualitative Variables ◽  
Binary Response Variable ◽  
Multiple Category ◽  
Qualitative Models ◽  
Definition Of ◽  
Linear Probability

In most regression models, readers have implicitly assumed that the dependent variable (regressand) Y is quantitative. On the contrary, explanatory variables could take the form of qualitative (or dummy), quantitative, or a triangulation thereof. This chapter discusses the observed fundamental differences between quantitative and qualitative models through a clear definition of their individual objectives. This chapter also considers many models in which the regressand is a qualitative variable, popularly called categorical variables, indicator variables, dummy variables, or qualitative variables. This chapter shows why it is not compulsory to restrict our dependent variable to dichotomous (yes/no) categories by establishing inherent benefits in estimating and interpreting trichotomous or polychotomous multiple category response variable. Relevant examples for developing, analyzing, and interpreting a probability model for a binary response variable using three known approaches (i.e. linear probability model, logit, and probit models) is also discussed.

scholarly journals Binary Response Models: Logits, Probits and Semiparametrics

2001 ◽  
Vol 15 (4) ◽  
pp. 43-56 ◽  
Author(s):  
Joel L Horowitz ◽  
N.E Savin
Keyword(s):  
Probability Model ◽  
Binary Response ◽  
Linear Probability Model ◽  
Response Models ◽  
Explanatory Variables ◽  
Nonparametric Models ◽  
Binary Response Model ◽  
Unrealistic Assumption ◽  
Binary Response Models ◽  
Linear Probability

A binary-response model is a mean-regression model in which the dependent variable takes only the values zero and one. This paper describes and illustrates the estimation of logit and probit binary-response models. The linear probability model is also discussed. Reasons for not using this model in applied research are explained and illustrated with data. Semiparametric and nonparametric models are also described. In contrast to logit and probit models, semi- and nonparametric models avoid the restrictive and unrealistic assumption that the analyst knows the functional form of the relation between the dependent variable and the explanatory variables.

Sibling Models, Categorical Outcomes, and the Intra-Class Correlation

2021 ◽  
Author(s):  
Richard Breen ◽  
John Ermisch
Keyword(s):  
Random Effects ◽  
Probability Model ◽  
Intraclass Correlation ◽  
Linear Probability Model ◽  
Intra Class Correlation ◽  
Sibling Differences ◽  
Sibling Models ◽  
Alternative Measures ◽  
Linear Probability ◽  
Parametric Estimate

Abstract In sibling models with categorical outcomes the question arises of how best to calculate the intraclass correlation, ICC. We show that, for this purpose, the random effects linear probability model is preferable to a random effects non-linear probability model, such as a logit or probit. This is because, for a binary outcome, the ICC derived from a random effects linear probability model is a non-parametric estimate of the ICC, equivalent to a statistic called Cohen’s κ. Furthermore, because κ can be calculated when the outcome has more than two categories, we can use the random effects linear probability model to compute a single ICC in cases with more than two outcome categories. Lastly, ICCs are often compared between groups to show the degree to which sibling differences vary between groups: we show that when the outcome is categorical these comparisons are invalid. We suggest alternative measures for this purpose.

scholarly journals Impact of differential copayment on patient healthcare choice: evidence from South Korean National Cohort Study

BMJ Open ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. e044549
Author(s):  
Sangkyun Jo ◽  
Duk Bin Jun ◽  
Sungho Park
Keyword(s):  
South Korea ◽  
Low Income ◽  
Primary Healthcare ◽  
Probability Model ◽  
Individual Characteristics ◽  
Research Database ◽  
Difference In Difference ◽  
Mild Disease ◽  
Tertiary Healthcare ◽  
Linear Probability

ObjectiveWe evaluate the effectiveness of mild disease differential copayment policy aimed at reducing unnecessary patient visits to secondary/tertiary healthcare institutions in South Korea.DesignRetrospective study using difference-in-difference design.SettingSample Research database provided by the Korean National Health Insurance Service, between 2010 and 2013.Participants206 947 patients who visited healthcare institutions to treat mild diseases during the sample period.MethodsA linear probability model with difference-in-difference approach was adopted to estimate the changes in patients’ healthcare choices associated with the differential copayment policy. The dependent variable was a binary variable denoting whether a patient visited primary healthcare or secondary/tertiary healthcare to treat her/his mild disease. Patients’ individual characteristics were controlled with a fixed effect.ResultsWe observed significant decrease in the proportion of patients choosing secondary/tertiary healthcare over primary healthcare by 2.99 per cent point. The decrease associated with the policy was smaller by 14% in the low-income group compared with richer population, greater by 19% among the residents of Seoul metropolitan area than among people living elsewhere, and greater among frequent healthcare visitors by 33% than among people who less frequently visit healthcare.ConclusionThe mild disease differential copayment policy of South Korea was successful in discouraging unnecessary visits to secondary/tertiary healthcare institutions to treat mild diseases that can be treated well in primary healthcare.

scholarly journals Analysis of the Downscaling Effect and Definition of the Process Fingerprints in Micro Injection of Spiral Geometries

Micromachines ◽  
2019 ◽  
Vol 10 (5) ◽  
pp. 335 ◽  
Author(s):  
Antonio Luca ◽  
Oltmann Riemer
Keyword(s):  
Correlation Analysis ◽  
Process Parameters ◽  
Cross Sections ◽  
Mass Production ◽  
Process Window ◽  
Response Variable ◽  
Process Indicators ◽  
Flow Length ◽  
Definition Of ◽  
Microinjection Moulding

Microinjection moulding has been developed to fulfil the needs of mass production of micro components in different fields. A challenge of this technology lies in the downscaling of micro components, which leads to faster solidification of the polymeric material and a narrower process window. Moreover, the small cavity dimensions represent a limit for process monitoring due to the inability to install in-cavity sensors. Therefore, new solutions must be found. In this study, the downscaling effect was investigated by means of three spiral geometries with different cross sections, considering the achievable flow length as a response variable. Process indicators, called “process fingerprints”, were defined to monitor the process in-line. In the first stage, a relationship between the achievable flow length and the process parameters, as well as between the process fingerprints and the process parameters, was established. Subsequently, a correlation analysis was carried out to find the process indicators that are mostly related to the achievable flow length.

What explains the large disparity in child stunting in the Philippines? A decomposition analysis

2021 ◽  
pp. 1-36
Author(s):  
Valerie Gilbert T. Ulep ◽  
Jhanna Uy ◽  
Lyle Daryll Casas
Keyword(s):  
Dietary Diversity ◽  
Probability Model ◽  
Critical Role ◽  
Decomposition Analysis ◽  
The Philippines ◽  
Nutrition Status ◽  
Nutrition Survey ◽  
Child Stunting ◽  
Filipino Children ◽  
Linear Probability

Abstract Objective: About a third of under-five Filipino children are stunted, with significant socio-economic inequality. This study aims to quantify factors that explain the large gap in stunting between poor and non-poor Filipino children. Design: Using the 2015 Philippine National Nutrition Survey (NNS), we conducted a linear probability model to examine the determinants of child stunting then an Oaxaca-Blinder decomposition to explain the factors contributing to the gap in stunting between poor and non-poor children. Setting: Philippines Participants: 1, 881 children aged 6-23 months Results: The overall stunting prevalence was 38.5% with significant gap between poor and non-poor (45.0% vs. 32.0%). Maternal height, education, and maternal nutrition status account for 26%, 18%, and 17% of stunting inequality, respectively. These are followed by quality of prenatal care (12%), dietary diversity (12%), and iron supplementation in children (5%). Conclusions: Maternal factors account for more than 50% of the gap in child stunting in the Philippines. This signifies the critical role of maternal biological and socio-economic circumstances in improving the linear growth of children.

scholarly journals Estimating the Effects of Individual Nurses on ICU Outcomes

2020 ◽  
Author(s):  
Stephen E. Brossette ◽  
Ning Zheng ◽  
Daisy Y. Wong ◽  
Patrick A. Hymel
Keyword(s):  
Fixed Effects ◽  
Unobserved Heterogeneity ◽  
Probability Model ◽  
Kidney Injury ◽  
Fine Grained ◽  
High Side ◽  
Work Shifts ◽  
Near Term ◽  
Linear Probability ◽  
Mimic Iii

AbstractA better understanding of the effects of nursing on clinical outcomes could be used to improve the safety, efficacy, and efficiency of inpatient care. However, measuring the performance of individual nurses is complicated by the non-random assignment of nurses to patients, a process that is confounded by unobserved patient, management, workforce, and institutional factors. Using the MIMIC-III ICU database, we estimate the effects of individual registered nurses (RNs) on the probability of acute kidney injury (AKI) in the ICU. We control for significant unobserved heterogeneity by exploiting panel data with 12-hour fixed effects, and use a linear probability model to estimate the near-term marginal effects of individual RN assignments. Among 270 ICU RNs, we find 15 excess high-side outliers, and 4 excess low-side outliers. We estimate that in one twelve-hour work shift, each high-side RN outlier increases the probability of AKI by about 4 percentage points, and in 25 work shifts, causes about one additional AKI. Conversely, each low-side outlier prevents about one AKI in 50 work shifts. Given the fine-grained nature of the fixed effects employed, we believe that the estimated individual nursing effects are approximately causal. We discuss our contribution to the literature and identify potential use cases for clinical deployment.

Analysis of variance (ANOVA).

2021 ◽  
pp. 155-165
Author(s):  
Donald Quicke ◽  
Buntika A. Butcher ◽  
Rachel Kruft Welton
Keyword(s):  
Linear Model ◽  
Analysis Of Variance ◽  
Explanatory Variable ◽  
T Test ◽  
Specific Function ◽  
Real Numbers ◽  
Response Variable ◽  
Explanatory Variables ◽  
Student’S T ◽  
One Way Anova

Abstract Analysis of variance is used to analyze the differences between group means in a sample, when the response variable is numeric (real numbers) and the explanatory variable(s) are all categorical. Each explanatory variable may have two or more factor levels, but if there is only one explanatory variable and it has only two factor levels, one should use Student's t-test and the result will be identical. Basically an ANOVA fits an intercept and slopes for one or more of the categorical explanatory variables. ANOVA is usually performed using the linear model function lm, or the more specific function aov, but there is a special function oneway.test when there is only a single explanatory variable. For a one-way ANOVA the non-parametric equivalent (if variance assumptions are not met) is the kruskal.test.

More generalized linear modelling.

2021 ◽  
pp. 171-186
Author(s):  
Donald Quicke ◽  
Buntika A. Butcher ◽  
Rachel Kruft Welton
Keyword(s):  
Generalized Linear Models ◽  
Count Data ◽  
Binary Data ◽  
Linear Models ◽  
Explanatory Variable ◽  
Response Variable ◽  
Explanatory Variables ◽  
Continuous Response ◽  
Generalized Linear Modelling ◽  
Linear Modelling

Abstract This chapter employs generalized linear modelling using the function glm when we know that variances are not constant with one or more explanatory variables and/or we know that the errors cannot be normally distributed, for example, they may be binary data, or count data where negative values are impossible, or proportions which are constrained between 0 and 1. A glm seeks to determine how much of the variation in the response variable can be explained by each explanatory variable, and whether such relationships are statistically significant. The data for generalized linear models take the form of a continuous response variable and a combination of continuous and discrete explanatory variables.

scholarly journals Binary logistic regression to estimate household income efficiency. (south Darfur rural areas-Sudan)

2016 ◽  
Vol 4 (1) ◽  
pp. 31
Author(s):  
Sofian A. A. Saad ◽  
Amin Adam ◽  
Afra H. Abdelateef
Keyword(s):  
Logistic Regression ◽  
Rural Areas ◽  
Household Income ◽  
Household Head ◽  
Binary Logistic Regression ◽  
Statistical Technique ◽  
Household Expenditure ◽  
Response Variable ◽  
Explanatory Variables ◽  
Main Factors

<p>The main objective behind this study is to find out the main factors that affects the efficiency of household income in Darfur rejoin. The statistical technique of the binary logistic regression has been used to test if there is a significant effect of fife binary explanatory variables against the response variable (income efficiency); sample of size 136 household head is gathered from the relevant population. The outcomes of the study showed that; there is a significant effect of the level of household expenditure on the efficiency of income, beside the size of household also has significant effect on the response variable, the remaining explanatory variables showed no significant effects, those are (household head education level, size of household head own agricultural and numbers of students at school).</p>

Sign in / Sign up

Export Citation Format

Share Document