One highlight of scientific research is the process of cleaning and sorting data to identify and resolve any potential issues. Therefore, researchers should invest a significant amount of time inspecting their data for potential errors or inconsistencies. This meticulous approach ensures that the data is reliable and accurate, and helps to avoid any false conclusions or incorrect interpretations. By carefully examining and cleaning the data, researchers can have confidence in their results and ensure that their findings contribute to advancing knowledge in their field.

In the previous stages, COVID-19 data provided by the Peruvian government were analysed to fit statistical and/or mathematical models in order to answer questions about the spread of COVID-19 in Peru. For example, the effectiveness of using vaccination to control COVID-19 and the relationships between COVID-19 deaths, positivity, free ICU beds, and vaccinated people were investigated. To demonstrate or refute the previously proposed questions, we use Generalized Additive Models (GAMs). GAMs are models similar to Generalized Linear Models that consider the response variables adjusted to the family of exponential functions, but in the case of GAMs, they are associated with a smoothed link function of the predictor variable. This generates great flexibility for model selection but creates the problem of selecting the most optimal model (Wood & Augustin, 2002). When working with multiple input variables, it is necessary to assign a form of reparameterization of the smoothed variables (Wood, 2017). This can be done in two ways: the first is the reparameterization necessary to absorb the identifiability constraints in the matrix of smoothed input variables, and the second is a reparameterization that helps understand the effective degrees of freedom of each smoothed variable (Wood, 2017). One advantage of GAMs is that they can handle non-linear relationships between the response and predictor variables, as well as interactions between predictors, in a flexible and computationally efficient way. GAMs are particularly useful in fields like ecology, epidemiology, and finance, where complex non-linear relationships are often encountered. GAMs have been implemented in a variety of software packages, including R (with the mgcv package) and Python (with the pygam package).

After cleaning and sorting the COVID-19 data, it is possible to merge and analyze it to reveal patterns and trends in the spread of COVID-19. the next step is to perform a multivariate analysis, which will help to generate hypotheses about the spread of COVID-19 in the future.

This project is trying of improving quality and order of COVID-19 of Peru. First, I managed to order and clean conflict and bug due to fail type and others issues.

It´s R-script to improve aesthetic plotting of princals function of Gifi package.

Radiocarbon (C-14) is a cosmogenic radionuclide produced in the upper atmosphere that is frequently used in paleoceanography to date sediment cores. However, dating marine sediment records has an important particularity: contemporaneous terrestrial and marine organisms have different $^{14}C$ ages because the ocean is a source of $^{14}C$ . Therefore, marine organisms appear to be older than contemporaneous terrestrial organisms. This effect is called the marine reservoir effect (MRE) and it varies in space and time as a function of changes in water mass origin and circulation.