Understanding WISH Output

I. Example of WISH output

This query requested age-adjusted rates by region for hospitalizations with cause of injury from motor vehicle traffic crash-motorcyclist (discharge year 2014).

Age-adjusted rates by region for hospitalizations with cause of injury from motor vehicle traffic crash-motorcyclist (discharge year 2014)
Region of Residence Number of Injury Hospitalizations Population Age-Adjusted Rate for Injury Hospitalizations 95% Confidence Interval
Southern 142 1,120,093 11.8 9.8 – 13.9
Southeastern 193 2,116,740 9 7.7 – 10.2
Northwestern 134 1,238,649 10.8 9.0 – 12.6
Western 73 783,963 9.2 7.1 – 11.3
Northern 46 488,513 8.5 5.9 – 11.1

II. Understanding rows, columns, and labels

A table is composed of rows and columns. A row is a horizontal line of cells in a table, and a column is a vertical line of cells.

In the example table, the rows are labeled according to region of residence: "Southern," "Southeastern," etc. The columns are labeled "Number of Injury Hospitalizations," "Population," "Age-Adjusted Rate of Injury Hospitalizations," and "95% Confidence Interval."

As indicated by the column headings, the example table provides four kinds of information related to injury hospitalizations in Wisconsin.

Column 1. "Number of Injury Hospitalizations." This reports the number (frequency) of the event that is the subject of the query (injury hospitalizations).

Column 2. "Population." This reports the total population for each region.

Column 3. "Age-Adjusted Rate of Injury Hospitalizations." This provides the age-adjusted rate of injury hospitalizations. It was calculated by dividing Column 1 by Column 2, multiplying by 100,000 residents, and then age-adjusting to a standard population (the 2000 U.S. standard population) (See Technical Notes and Definitions for more information on rate options).

Column 4. "95% Confidence Interval." A confidence interval is provided for all rates and percentages shown in WISH. See Part IV (below) for more information on interpretation of a confidence interval.

III. Reading the numbers

Looking at the row labeled "Southern," we can see that among residents of the Southern region of Wisconsin:

There were 142 injury hospitalizations for the time period selected.

The population in the Southern region was 1,120,093 for the time period selected.

The age-adjusted rate was 11.8 for the region.

We can be quite confident that the "true" rate for the Southern region lies in the range of 9.8 to 13.9. (See Part IV for more explanation.)

IV. Interpreting results and the confidence interval

Note about cell suppression (X)

If you are requesting data for a geographic area (such as a single county) or for a rare event where the annual number of events is small, it is often useful to combine years of data. WISH suppresses small numbers (when cell size is less than 5) to comply with Wisconsin vital records data privacy guidelines. You will note an X in a data field if the number has been suppressed.

95% Confidence Intervals (CI)

Output tables provide confidence intervals for all rates. A confidence interval is a range around a rate within which there is a 95% probability of containing the "true" value. Confidence intervals can assist in making comparisons between geographic areas and between years, for example. The size of a confidence interval will be affected by the number of events.

Example: In the example above, we queried the Injury Hospitalization data for age-adjusted rates for motor vehicle traffic crashes-motorcyclist in 2014 by region. Our data table included number of hospitalizations, population counts, age-adjusted rates, and 95% confidence intervals for each region. The Northern region had a rate of 8.5 per 100,000 residents with a 95% confidence interval of 5.9 to 11.1. This means that there is a 95% probability that the 2014 rate for the Northern region lies in the range of 5.9 to 11.1 per 100,000 residents.

When comparing rates (for example, across different regions or different time periods), it is useful to look at the confidence intervals and determine if they overlap or not. When CIs do not overlap, we can say that the two rates differ from one another (i.e., they are statistically significantly different).

Alternatively, when CIs overlap, it does not necessarily mean that there is no statistically significant difference. To understand when rates with overlapping CIs may be statistically significantly different, we recommend that you consult the statistical literature or experts on interpreting confidence intervals, especially when you find small numbers of events in an output table.

V. Citation of data obtained from WISH

It is important to provide a citation for the data you query and report. This is useful when trying to verify previous work or repeat aspects of your data query. The best way to do this is to cite the WISH module you queried (for instance, the Injury-Related Emergency Department Visits Module) and also the date that you accessed the data. The date is especially important for instances when there are changes to the datasets or the query module. A suggested citation is provided on each query results page.

Example citation: Wisconsin Department of Health Services, Division of Public Health, Office of Health Informatics. Wisconsin Interactive Statistics on Health (WISH) data query system, https://www.dhs.wisconsin.gov/wish/index.htm, Injury-Related Emergency Department Visits Module, accessed 2/11/2019.

Glossary

 
Last revised July 5, 2020