RiskDiff

A web tool for the analysis of the difference due to risk and demographic factors for incidence or mortality data

Cite: Valls J, Cleries R, Galvez J, Moreno V, Gispert R, Borras JM et al. RiskDiff: a web tool for the analysis of the difference due to risk and demographic factors for incidence or mortality data. BMC Public Health 2009;9:473.

This tool can be useful to study the differences in the incidence or mortality observed in two given situations (such as time points, geographical areas, or males versus females). The method performed splits the observed differences into three components: (1) the risk itself, (2) difference attributed to changes in the population size and (3) difference attributed to changes in population structure. For its use, you may provide the number of cases (or deaths), for separate age-groups (e.g. 5 years) and the respective reference population for both groups.

Upload a Data Set into RiskDiff
A dataset can be uploaded into RiskDiff in two ways: (1) using a tab-separated text file with 4 columns, one for each vector or (2) directly typing the data into the web interface separately for each vector.
The dataset should have 2 columns with the number of incident/death cases (one column for the reference group and another for the comparison one) as well as 2 columns for the person-years at risk for each age group considered. Once the dataset has been uploaded, RiskDiff will ask for the group labels to identify each column. Finally, RiskDiff produces a web page with summary tables, graphical representations and a short paragraph of text to facilitate the interpretation of the results. The RiskDiff user can find in this web page two example datasets with the required format. The source of data from which these example datasets have been created can be also found in this web page.
* We reccomend to be at least 2 age groups to perform RiskDiff, otherwise there is no evolution of the age structure and changes can be only attributed to population size and risk.

Data files:

Example dataset 1:Mortality.cancer.Catalonia.men.1985.2004.txt
Example dataset 2:Mortality.cancer.Catalonia.women.1985.2004.txt

Source data of the example datasets (not to be run with RiskDiff): CancerMortalityCataloniaData.txt

Using data from Example dataset 1, let us assume that we want to compare the evolution of mortality in Catalonia comparing year 2004 with 1985. Assume that reference group could be year 1985 data whereas the comparison one is year 2004 data.
In this dataset, columns 1 and 2 are the Baseline and Comparison cases respectively, whereas columns 3 and 4 are the Baseline and Comparison populations at risk. You can copy this example and paste it into the box below in order to see how RiskDiff works.

Files to download to perform the analysis with R

Send us an e-mail to get functions source code

Source R file containing some examples using R functions: ExampleRiskDiff.R

WARNING: THIS PROCESS MAY TAKE SOME TIME

Enter the text file with your data

or enter data here

Read Labels from file header

Finally, select delimiter between columns: