RoperExplorer is a feature that allows users to generate their own crosstabs to compare responses on two questions from a survey without having to use a statistical software program. For example, a user might look at attitudes about abortion by the respondents’ age or examine whether people who say climate change is a serious problem are more likely to support regulation on industry.

Users must be logged into their personalized account to use RoperExplorer.

First select as your row question the question you are looking to analyze. This question is also referred to as the dependent variable —a question that depends on other factors. For example, take the question:  Do you think abortion should be legal in all cases, legal in most cases, illegal in most cases or illegal in all cases? Responses to this question could depend upon several factors, such as age, sex, or religiosity.

Then select your column question, also called the independent variable. This type of question is typically not changed by other factors and is often a demographic, such as sex or age.  The independent variable is the question you hypothesize will influence the dependent variable.

In making your selections for row and column, try asking yourself:  does the column question (independent variable) cause the row question (dependent variable) to change.

Those are the raw numbers, the exact number of respondents answering in each way.

In order to get statistically meaningful results, RoperExplorer removes any column response category with fewer than 100 respondents. Small samples, including subgroups of less than 100 people, increase the margin of sampling error significantly.  Suppressing these small sample groups prevents the user from inadvertently drawing conclusions that overstate the findings.

Yes. RoperExplorer uses the same weighting variable to weight the results as the polling organization that created the dataset used when analyzing the data for public release.

We would love to make Roper Explorer available for every survey we have. Unfortunately, that’s not possible. We have over 22,000 datasets, some of which are still in older formats. In some cases, the only data we have is the topline data – that is, the results from the total sample, without a dataset to allow further analysis. Staff are continuing to process the most current studies in this form and working hard to make Roper Explorer available for as many questions as possible as fast as we can.

At the top of the page, just above the three steps, there is a source citation for the survey that you are running. At the end of the citation, the link View Codebook will open a copy of the questionnaire and the codes for the survey in a separate PDF file.