COYNE AND MESSINA ARTICLES

Coyne and Messina Articles, Part 2 Statistical Assessment

Coyne and Messina Articles, Part 2 Statistical Assessment

Statistical Significance Of Outcomes

The questionnaire used to measure the satisfaction of hospitalization in this study was first developed in late 1980. In 1997, was amended to be valid in the monitoring of patient preferences and experiences. The instrument was developed after conducting customer and patient care groups, the literature review of current customer satisfaction, a review of survey instruments across the United States, using the latest tools and design techniques Survey of health organizations in the United States. In 2002, a validation study of patient satisfaction survey was conducted internally to ensure internal consistency and reliability (Press Ganey Associates 2002). The survey instrument was found to be psychometrically stable across a broad spectrum of evidence of validity and reliability. The overall score of Cronbach's alpha reliability is 0.94. (Messina, 2009)

The survey included questions related to the background, the admissions process, housing, meals, nurses, tests and treatments, visitors and family, physician, discharge, personal problems, and overall assessment. (Messina 2009) Patient satisfaction was measured using a Likert scale of five points labeled as follows: 1 = very poor, 2 = poor, 3 = Average, 4 = good and 5 = very good. The data were converted to a scale of 100, (entering the 01.05 and the average scores of them), to be the lower end of the very poor and 100 is high end very good.

Appropriateness Of The Statistics

Descriptive statistics as frequencies, means, medians and standard deviations were calculated and used to examine the specific characteristics of hospitals with respect to (1) and patient satisfaction mean scores (2) hospitalization data measured volume income. Statistical measures of skewness and kurtosis were also performed to allow examination of the shape and distribution of data from the survey response. (Messina, 2009)

Examination of the data revealed that, due to the size of the sample, if the data are normally distributed could not be determined conclusively, therefore, nonparametric statistical test was chosen to further analyze the data. The correlation coefficient of Spearman rank-order was used to analyze the relationships between the independent variable (patient satisfaction mean score) and the dependent variable (volume measured by income). The correlation analysis was performed in a group show of seven teaching and seven non-teaching hospitals. (Messina 2009) Next, an analysis of the differences between the subsample of teaching and non teaching subsample were performed with Mann-Whitney U-test. After this test, we conducted a separate analysis on the teaching of seven non-teaching hospitals. The two variables were used to discover if there was not a causal relationship, but to discern whether an association existed between satisfaction and the average score for admission.

Value Of Statistical Significance Vs. Pragmatic Usefulness

A comparative analysis of patient satisfaction that examines dissimilarities between educating and non-teaching clinics was presented utilizing a Mann-(Messina 2009)Whitney U-test. This check is a nonparametric analog of the unaligned group's t-test. It was utilized to work out if dissimilarities lived between the two unaligned groups--teaching ...