Composite-Level and Item-Level Comparative Results

2010 Preliminary Comparative Results: Medical Office Survey on Patient Safety Culture (continued)

You can obtain a summary view of how your medical office compares to other medical offices by examining the composite-level and item-level percent positive scores displayed in Charts 1 through 4.

Calculating Item Percent Positive Scores

To compare your medical office results to the comparative results from the Medical Office Survey on Patient Safety Culture, it is helpful to understand how the medical office percent positive scores are calculated.

For positively worded items, percent positive is the total percentage of respondents who answered positively. This total is the combined percentage of "Strongly agree" and "Agree" responses or "Always" and "Most of the time" responses, depending on the response categories used for the item.

For Section B (Information Exchange With Other Settings), percent positive is based on the combined percentage of "Problems once or twice in the past 12 months" and "No problems in the past 12 months."

For negatively worded items, percent positive is the total percentage of respondents who answered negatively. This total is the combined percentage of "Strongly disagree" and "Disagree" responses or "Never" and "Rarely" responses, since a negative answer on these items indicates a positive response.

For Section A (List of Patient Safety and Quality Issues), all items are negatively worded, so the combined percentage of "Once or twice in the past 12 months" and "Not in the past 12 months" represents positive responses. 

Return to Contents

Calculating Composite Percent Positive Scores 

A composite score summarizes how respondents answered groups of items that all measure the same thing. Composite scores on the 12 patient safety culture survey dimensions tell you the average percentage of respondents who answered positively when looking at the survey items that measure each safety culture dimension. Composite scores allow a summary comparison because you compare against only 12 safety culture dimensions rather than 52 separate survey items.

To calculate each medical office's composite score on a particular safety culture dimension, calculate the average percent positive response of the items included in the composite. Table 12 shows an example of computing a composite score for Office Processes and Standardization. The composite has four items. Two are positively worded (items C9 and C15) and two are negatively worded (items C8 and C12). Keep in mind that DISAGREEING with a negatively worded item indicates a POSITIVE response. 

In this example, there were four items, with percent positive response scores of 46, 52, 46, and 56. Averaging these item-level percent positive scores ([46 + 52 + 46 + 56]/4 = 50) results in a composite score of .50 or 50% on Office Processes and Standardization. That is, an average of 50% of the respondents responded positively to the survey items in this composite.

The charts on the following pages display the composite-level and item-level comparative results from the 470 medical offices. Chart 1 shows the average percent positive response for each of the survey's patient safety culture composites, in order from most positive to least positive. Chart 2 provides the average percent positive response for the survey items. Chart 3 shows the average distribution of responses for the Overall Ratings on Quality, and Chart 4 shows the average distribution of responses for the Overall Rating on Patient Safety.

Use a difference of 5 percentage points as a rule when comparing medical office results to the results shown. Medical office percentages should be at least 5 points higher than the comparative results to be considered "better" (e.g., 75% vs. 70%) and should be at least 5 points lower to be considered "lower" than the comparative results (e.g., 60% vs. 65%). A 5 percentage point difference is likely to be statistically significant for most medical offices given the number of responses per medical office and is also a meaningful difference to consider. 

This information provides only relative comparisons. Although your medical office's results may be better than the comparative results, you may still believe there is room for improvement in an absolute sense.

Return to Contents

Comparative Results Using Percentiles

In addition to comparing percent positive scores from your medical office with the average percent positive scores from other medical offices, you may find it useful to examine additional comparative statistics: minimum and maximum scores and percentiles. 

The minimum and maximum percent positive scores are presented for each composite. These scores provide information about the range of percent positive scores from the pilot test medical offices and are actual scores from the lowest and highest scoring offices. When comparing against the minimum and maximum scores, keep in mind that these scores may represent offices that are extreme outliers.

The 25th, 50th, and 75th percentile scores are displayed for the survey composites. Percentiles provide information about the distribution of the medical office scores. To calculate percentile scores, percent positive scores from the 470 medical offices were rank ordered from low to high. A specific percentile score shows the percentage of medical offices that scored at or below a particular score. For example, the 75th percentile is the percent positive score where 75 percent of the medical offices scored the same or lower, and 25 percent of the medical offices scored higher. Interpret the percentile scores as shown in Table 13.  

For example, for a survey composite in Table 14, the 25th percentile score is 49 percent positive, and the 50th percentile score is 62 percent positive. If your medical office's score on the composite is 55 percent positive, it falls above the 25th percentile but below the 50th percentile, meaning that your medical office scored higher than at least 25 percent of the other medical offices. If your medical office's score on the composite is 65 percent positive, it falls above the 50th percentile, meaning your medical office scored higher than at least 50 percent of the other medical offices.

For each patient safety culture composite, Table 15 shows the average percent positive scores, minimum score, 25th percentile, 50th percentile, 75th percentile, and maximum score for the 470 medical offices.  

Table 16 shows the average percent positive scores, minimum score, 25th percentile, 50th percentile, 75th percentile, and maximum score for the 470 medical offices on each survey item sorted by patient safety culture composite.

Tables 17 and 18 show the average percent positive scores, minimum score, 25th percentile, 50th percentile, 75th percentile, and maximum score for the overall ratings on quality and overall ratings on patient safety, respectively. 

Return to Contents

Composite-Level and Item-Level Results by Staff Position

Tables 19 through 22 show the average percent positive scores for the survey composites and items across medical offices, broken down by staff position. These tables allow comparison of the survey results of various staff positions in the medical office. In the following four tables, the precise number of medical offices and respondents corresponding to each data cell varies, due to omission of survey items by some medical offices, individual nonresponse, and missing data.

Table 19 shows composite-level results by staff position.

Table 20 shows item-level results by staff position.

Table 21 shows the overall ratings on quality results by staff position, and Table 22 shows overall ratings on patient safety results.

Return to Contents

Current as of November 2010
Internet Citation: Composite-Level and Item-Level Comparative Results: 2010 Preliminary Comparative Results: Medical Office Survey on Patient Safety Culture (continued). November 2010. Agency for Healthcare Research and Quality, Rockville, MD. http://www.ahrq.gov/professionals/quality-patient-safety/patientsafetyculture/medical-office/2010/moreslt10c.html