Source recommendation for statistical modeling: theoretical and practical aspects I have asked following question few days ago.
Fitting distribution: Covid-19 confirmed cases
It turned out that I have a deeper problem beyond the statistical issues that I am dealing with. I didn't ask the right question in a right way. Thanks to @whuber I corrected some of that issue. I figured that I have been working on theoretical probability and lost the touch with the more important one, the practical statistics which really solve the real problems.
I model dynamical growth of social interactions, like epidemic behaviors, using differential equations. I have a fairly enough background on theoretical aspect of statistical modeling, but zero on the practical aspect, and that just hit me hard after asking the above question.
I decided to hold everything for 3 months and try to learn the practical implementations of statistical modelings with R programming. So I ask anyone whom can give me some recommendation, books, lecture notes, website etc, that can help me with it. What I am trying to learn includes the followings
1.preparing real-world data for the later statistical inference.
2. Fitting distributions to real-world data and all the tests, like goodness of fit, related to this task.
3. Being able to recognize the best approach toward the data mining, like should I use time series or a stochastic process or a random variable.
4. Doing previous steps in R environment.
I searched through the website and found some great books on subjects related to these but non of them really had these task in particular. I really don't have time for reading a lot of books, So I am asking people who are experts in the subject or got in tough with the same issues, to introduce me to the right resources so I won't waste a lot of time with searching through all the books and websites that have something in common with the subjects.

Edit
In the way of modeling epidemic kind of behaviors, what is most importan(say 90 percent of data mining task of the modeling) is fitting distributions. So I should've emphasized that in my question.
I am also aware of  this book
https://www.amazon.com/Handbook-Fitting-Statistical-Distributions-R/dp/1584887117
that is contributed entirely to fitting distributions. However the method is GLD, I wanted to know if there is a book like this for this task with outer methods rather than GLD. For example, through Q_Q plots, Histograms, Moment estimations,Bootstrapping and methods like these as their chapters.
Thanks in advance.
 A: Of the top of my head:
Introduction to econometrics with R - covers basic econometrics with direct examples/applications in R (freely available online)
Elements of statistical learning - the go-to statistical learning book, covers almost all model types, coupled with the solutions manual (freely available online)
Introduction to Time Series - Brockwell & Davis - for an introduction to TS
Introduction to Multiple Time Series - Lütkepohl - sort of "part 2" for the above, covers multivariate time series
A: For somebody with a strong math background like you, not intimidated by matrix algebra, I'd recommend Julian Faraway's 2 books:
1. Linear Models with R and
2. Extending the Linear Model with R: Generalized Linear, Mixed Effects and Nonparametric Regression Models.
Alternatively, in place of Faraway's second book, you could use Agresti's Categorical Data Analysis book. These books take their time to explain the theory quite thoroughly and yet have their eye fixed on practical applications (with R).
For time series and stochastic processes, I'd recommend 3. Robert P. Dobrow's "Introduction to Stochastic Processes with R". The book is intended for an undergraduate audience but does not shy away from the math; a perfect introduction to a difficult topic that does assume a strong (non-measure theoretic) probability background.
These 3 books will give you everything you're looking for in a time-efficient/effort-efficient way.
