- #FORMAT DATA FOR STATISTICAL ANALYSIS IN EXCEL SOFTWARE#
- #FORMAT DATA FOR STATISTICAL ANALYSIS IN EXCEL CODE#
When in doubt, ask the statistician, data analyst, or programmer. This can be a separate worksheet or document file. The data dictionary should include all of the variable names, data type that corresponds to the variable, a label or longer name that describes the variable including the units it is measured in, the codes for any categorical variables, and any notes for the variable. It is a good idea to document what your variables are and what they mean. Documenting your database will help the statistician, programmer, data manager, and yourself, the researcher, understand your data and database. Document your database with a data dictionary and/or codebook. These features can be used on other separate "subset" or "analysis" spreadsheets that are for the investigator, but not the statistician or programmer. hidden columns, graphs on the data sheet that is your primary database, colors, italics, bold). Avoid using "special" Excel features (i.e. For example, treated versus non-treated patients can be handled by column variable that has a code for Treated (yes/no). Do not "stack" data on the same sheets. If you decide to use multiple sheets for you data, follow the variable naming conventions for the tabs that name the sheets (keep the names simple and unique). The sex variable is still a character variable, but statistical software will read this variable as having six different levels instead of two. In the Bad Example the date variable is in different formats without a 4 digit year for all the observations. Notice in the Good Example above that the date variable has the same format (mm/dd/yyyy) and the sex variable is consistent throughout in both case and type (character variable).
When entering data keep the same format throughout. Be sure, if you use a missing value code, that it cannot be confused with a "real" data value. To enter a missing data value either enter a blank or an "impossible" numeric code (for numbers) or an easily recognizable single digit character code for character (trying to avoid mixing numeric and character data). Missing data can cause a multitude of problems. The best format for dates is mm/dd/yyyy, where mm is a 2 digit month, dd is a 2 digit day and yyyy is a 4 digit year. Two digit years can cause problems for statistical software when reading data from Excel files. When entering dates (especially for years prior to 1930) include a 4 digit year. Include a separate column for each answer. Don't enter data as "A,C,D" or "BDF" if there are three possible answers to a question. Enter systolic blood pressure as one variable and diastolic blood pressure as another variable. Don’t enter data such as "120/80" for blood pressure. Use a separate column for each piece of information. Choose readily recognizable names for variables - but not too long (<= 16 characters best). Do not include special characters (#, !, ?, %, etc.) or spaces in your variable names. Variable names must start with a letter. Be sure that each variable name is unique (no duplicate variable names). Include a unique identifying number for each case. Put variables in columns and observation in rows. Here is a good example of data entry into an Excel file followed by guidelines for data entry. 
In order to have your data easily imported into a statistical software package we have developed these guidelines for data entry into Excel. However, most research projects require more extensive statistical techniques that can be most easily performed using additional statistical software packages such as SAS or SPSS software.
Researchers can use Excel's simple statistical and plotting functions to help gain insight into their data. Microsoft Excel can be a useful platform to enter and maintain research study data. We have prepared some helpful hints for entering data into an Excel Workbook for ease in statistical analysis. Accurate data entry is critical for the success of the study. Some researchers collect and enter their own data for analysis. We encourage researchers to include CCORDA in all phases of the study from design to analysis and dissemination of results. The members of CCORDA have expertise in design and planning of studies, including preparation of data collection forms and database creation.
Best Practices: Caring for an Ebola Patient. Central States Center for Agricultural Safety and Health. Center for Health Policy Analysis and Rural Health Research. Center for Global Health and Development. Center for Collaboration on Research Design and Analysis. Biosecurity, Biopreparedness, & Emerging Infectious Diseases. Health Services Research & Administration. 
Environmental, Agricultural & Occupational Health. Prospective Students | Current Students | Faculty & Staff | Public Health Alumni
0 kommentar(er)
