EpiData Analysis

From EpiDataWiki

A short overview of analysis of data with EpiData Analysis

EpiData Analysis is a program for data analysis and data management.

Use EpiData analysis when you want to do basic descriptive statistical analyses, modifications or tabulation of data. Extended analysis such as statistical modelling can be done with other software such as Stata, R etc.

EpiData Analysis is based on the same principles as EpiData Entry. If you properly define, document and verify data with EpiData Entry, the definitions are also available in EpiData Analysis. E.g. specified legal values with attached text labels(1 = No 2= Yes) or definitions of missing values. When reading data EpiData Analysis will do some control based on variable definitions, e.g. all dates are verified.

EpiData Analysis is suitable for small as well as rather large datasets. simple datasets like one questionnaire as well as datasets with many or branching dataforms.

The principle of EpiData is rooted in the simplicity of the dos program Epi Info v6, which has many users around the world. EpiData Analysis is used for: Basic descriptive Analysis of quantitive data, Defining and modifying data, Editing / correcting data already entered, Graphing Data, Asserting that the data are consistent across variables and printing or listing data for documentation of error-checking and error-tracking.

• Limits and specification

No limit on number of observations. (tested with >100.000). Specification of the data file structure must fit within 999 lines of text. EpiData comes as a few files and only a few extra files are added to accomplish saving of graph files. Options are saved in an ini file. EpiData Analysis is freeware.

Works on Windows 95/98/NT/Professional/2000/XP and Machintosh with RealPc emulator. Tested on more than ten Linux variants based on WINE.

• Downloading and installing

Download from www.epidata.dk and follow the instructions when you run the installation file. EpiData Analysis will not interfere with the setup of your computer. EpiData consists of one program file and a number of help files in html or pdf format. The program as such cannot be sold for money or service value. It is absolutely free. All translated versions must ALSO be supplied as free. There can be NO charge taken by a web site for downloading of EpiData.

• Flowsheet of working with EpiData Analysis

A simplified flowsheet of how EpiData Analysis is working. Blue parts are optional, black parts are in memory and red parts save permanently to disk. Note that the programme always works with a copy of data. Your data on the disk are not changed unless you as a user instruct the programme to do so. Note also that the commands issued are saved when you exit.

• Output formatting

EpiData Analysis output is based on the html (hyper text meta language) format. HTML is a structured formatting principle used on all internet pages. EpiData Analysis will comply with the W3C standards. W3C is an international organisation informing about developments and standards on Http://www.w3c.org. For most users knowledge of this is not necessary, but you should know that experienced users can adapt the output as they desire in a style sheet (CSS) containing definitions for size, colour, margins etc. A full documentation of the output principles is available The documentation is installed with the analysis programme.

1. First run and Setup screen of EpiData:

Current version is always shown at the top.

The EpiData Analysis screen has a “standard” windows layout with one menu line, a toolbar, an output window, a command prompt where you write commands, an output window, a statusbar and depending on user action also a data browser, an editor and smaller windows showing available commands, variables in current file and a history of previous commands.

A. Start EpiData from either the programme group where you installed the programme or an icon.

B. First time you run EpiData Analysis the opening screen will be a setup screen where you decide overall size of programme, size for fonts you prefer etc. Just follow the numbers:

C. After clicking start, the screen changes.

2. First trial with programme:

To give you an idea of how the programme works we will now try the “Process Toolbar”:

Press the “Read Data” button to the left on your screen and point your disk selector to where you installed the EpiData Analysis programme in the subfolder “testdata”.

Select “bromar.rec” (possibly shown only as “bromar”)by double clicking and notice the information in the output window, How many records and fields ? A copy of data is red into memory for a Marathon race.

Browse data

Every time you open a data file it is good practice to view the data.

So on the process tool bar press the ”Browse” button, and you get this dialog box:

Select any number of variables or all by the ->> and choose ”Run”.

A data browser window is shown. Look at the data. Resize the window to cover right half of the screen and close it again.

Showing a graph

Now we will try to see some results. Press the ”Graph” button and you see the small menu, where you choose ”Bar”

A dialog is shown to specify the graph further:

At this point only worry about the ”Choose X Variable”. Select Decgrp and press ”Run” The graph is shown on a special form with some buttons.

Just press ”exit”

The graph will be added to the output window.

Try with kmgrp or decgrp variables and notice how the labels are shown at the buttom of the graph..

Showing a table of frequencies

On the ”process toolbar” try now analysis-->Frequency:

Select sex and agegrp variables in the dialog which is shown and press ”run”, after which you will see these tables:

Showing means of age by sex

Now choose "Means" instead of Frequency under the Analysis Button. Choose Age and Sex and click on the > button to select both variables, then click on ”run”:

Are males or females on average the youngest ?

3. Which elements are on the screen ?

You have now acquainted yourself with the programme and working with the process toolbar. On this page you see a complete picture.

To see a picture like this: Start EpiData Analysis, read a datafile into memory and press function keys F2 (commands), F3 (variables) and F7 (history).

To get acquainted with the windows try the following:

1. Switch the extra windows on the right on and off a few times: Press keys: F2, F3 or F7

2. Resize the program by dragging in sides or the separator between output window (viewer) and right side parts.

3. Save current position in window menu. ”Save Window Position”

4. Try to change folder by clicking on the lower left side of the statusbar.

5. Try the editor. From within you can run commands or save pgm files for future use.

6. Try the help menu. If you are connected to internet you can activate ”Check Version” part which will compare your version with the most updated on on www.epidata.dk

• Further introduction

Try the programme as it is and experience how you can soon get into more commands or features. If you press F1 an overview of help files is shown and if you press find (Ctrl+F) you can soon see how to get further explanations.