## 27 NovHow to perform an explanatory analysis

Several steps are necessary to perform an explanatory analysis: Elicit the research hypothesis Select the response (explained) variable Y Select the main explanatory variable X Identify the covariates Check that the conditions are met Check the robustness of the model Elicit the research hypothesis All research requires hypotheses. For example, it may...

## 17 JulCreate new “calculated” columns using Excel

It is necessary to have a basic knowledge of the use of Excel to be able to create new columns. Be careful, it is useless and not recommended to transform numerical variables (e. g. age) to create categories (<20; 20-55; >55 for instance) because this leads to a loss of information....

## 16 JulThe basics of Excel

Essential concepts Excel is organized as a table, containing rows, columns and their intersection: the cells. The rows are numbered, the columns are identified by a letter (for example the 3rd column is cell C). A cell is referred to by its column letter followed by its row number (E1 is...

## 16 JulHow to prepare a file for statistical analysis of a clinical study?

You have a study to carry out? Great! We have prepared a list of 10 rules to follow in order to make your data analyzable by a statistical software. Which data entry software to choose? First of all, you will need to define on which file format you will input the data....

## 03 JulTransformation of numerical variables

In statistical modeling, it is often necessary to group the values the numerical variables to create classes in order to meet the conditions of the model. If we have no a priori idea about the appropriate grouping, it is preferable to base ourselves on the splines representing the relationship...

## 03 JulHow to perform a multivariable analysis when you have too few observations

It is sometimes surprising not to be able to carry out a multivariable analysis because the number of subjects is too small while the file contains several hundred observations (patients, subjects). Linear regressions For linear regressions, i. e. multivariable analyses for which the outcome variable is numerical, it is necessary to have...