China
Africa
Explore chapters and articles related to this topic
Correlation Analysis and Regression Analysis
Published in M. Venkataswamy Reddy, Statistical Methods in Psychiatry Research and SPSS, 2019
The phi-correlation coefficient is computed for the data in which both the variables being correlated are genuine dichotomous, and the classes are separated by a real gap between them. In order to compute phi-coefficient, the 2 × 2 contingency table has to be prepared. The phi-coefficient is given by (with usual notations),
Missing Data Handling in Clinical Trials
Published in Mark Chang, John Balser, Jim Roach, Robin Bliss, Innovative Strategies, Statistical Solutions and Simulations for Modern Clinical Trials, 2019
Mark Chang, John Balser, Jim Roach, Robin Bliss
The phi coefficient (mean square contingency coefficient), which is computationally equivalent to the Pearson correlation coefficient in the 2 × 2 case (i.e., ), is
Descriptive statistics
Published in Louis Cohen, Lawrence Manion, Keith Morrison, Research Methods in Education, 2017
Louis Cohen, Lawrence Manion, Keith Morrison
The variables involved in connection with the phi coefficient measure of association in Table 40.13 are described as ‘true dichotomies’ and at the nominal scale of measurement. Truly dichotomous variables (such as sex or driving test result) can take only two values (male or female; pass or fail).
Alcohol Use Severity among Hispanic Emerging Adults: Examining Intragroup Marginalization, Bicultural Self-Efficacy, and the Role of Gender within a Stress and Coping Framework
Published in Behavioral Medicine, 2023
Miguel Ángel Cano, Mario De La Rosa, Seth J. Schwartz, Christopher P. Salas-Wright, Brian T. H. Keum, Christina S. Lee, Miguel Pinedo, Cory L. Cobb, Craig A. Field, Mariana Sanchez, Linda G. Castillo, Priscilla Martinez, Elma I. Lorenzo-Blanco, Brandy Piña-Watson, Marcel A. de Dios
Descriptive statistics, including means and standard deviations, were computed for continuous variables, and frequencies and proportions were generated for categorical variables. Correlations between continuous variables (i.e., age) and ordinal variables (i.e., financial strain, role repertoire, social groundedness, intragroup marginalization, alcohol use severity) were estimated with a Pearson correlation coefficient, correlations between dichotomous variables (i.e., gender, study site, partner status, nativity, Hispanic heritage, student status, employment status) and ordinal/continuous variables were estimated with a point-biserial correlation coefficient. Correlations between two dichotomous variables were estimated with a Phi coefficient. Multicollinearity was assessed using two diagnostic indicators, tolerance and the variance inflation factor (VIF). It is recommended that the tolerance value be higher than .10 and the VIF value be lower than 10.42At the item-level, missing data for multi-item measures were below 2% and the expectation-maximization algorithm was used to handle missing values prior to computing each respective scale score. The variables from the demographic questionnaire had no missing data.
Motives between the Sheets: Understanding Obligation for Sex at Midlife and Associations with Sexual and Relationship Satisfaction
Published in The Journal of Sex Research, 2023
Monika Georgieva, Robin R. Milhausen, Christopher Quinn-Nilas
We analyzed the associations between obligation and doing something nice as motives for last sex. The Phi coefficient showed that there was not a statistically significant association (φ =.009, p = .813) and an analysis of the cross tabulated frequencies showed that only 4 participants indicated both obligation and to do something nice as reasons. Additionally, we considered the extent to which participants endorsed our motives of interest (obligation and to do something nice for a partner) in conjunction with other love and pleasure motives. An analysis of the cross-tabulated frequencies indicated that of the 45 people who reported having sex because they felt obligated to, 7 also indicated they were motivated by a desire to express their love for their partner, 5 indicated they did so because they “were turned on sexually,” 4 indicated that they wanted to experience sexual pleasure, and 4 indicated that they were attracted to the other person. Of the 59 people who reported that they engaged in sex to do something nice for their partner, 45 also reported they wanted to express love for their partner, 29 reported pleasure as a concurrent motive, 22 reported arousal, and 20 indicated they were attracted to the other person.
Online monitoring of high-dimensional binary data streams with application to extreme weather surveillance
Published in Journal of Applied Statistics, 2022
Zhiwen Fang, Wendong Li, Xin Liu, Xiaolong Pu, Dongdong Xiang
The estimation of 3]). In fact, when estimated for two binary variables, the phi coefficient is equivalent to the Pearson correlation coefficient. Hence, we estimate ith data stream. Based on 3. Then, B times, and the B run-length values are averaged to get the actual calculated IC ARL value. Then 18]).