![redd statbook redd statbook](https://3.bp.blogspot.com/-pj_EoEYnrpI/Tfuo2beyVII/AAAAAAAAAFE/CWhPccuZK0E/s1600/Lady+Remedy.jpg)
That said, “when statistical inference is performed properly, the conclusions about the population are almost always correct.” - Statistics Notebook All we can say is that there is strong evidence to support or reject assumptions made about the data. In fact, to claim that anything we learn from statistics is definitively true would be incorrect.
![redd statbook redd statbook](https://i.redd.it/768xm0izsbn71.png)
It is important to note, however, that when we infer something about a population based on sample data we aren’t stating that our inference is established truth. Hopefully the significance of this sinks in - through inferential statistics we are able to learn about a population even if we don’t have data for that entire population. Inferential statistics represents a collection of methods that can be used to make inferences about a population. Whenever sample data is used to make a conjecture about a characteristic of a population, it is called making inference.
![redd statbook redd statbook](https://i.pinimg.com/736x/3c/28/fe/3c28febb832c6f935e5fe83e9d25e8eb.jpg)
This is where inferential statistics comes in. Descriptive statistics is limited though when we only have sample data because descriptive statistics can only describe data that we already have, and not the entire population. This works great if we have population data, because tables and graphics can provide powerful insight that may not be obvious from raw data. Most of what we’ve done so far in this course falls under the descriptive statistics category - using tables, graphs, etc. In a similar way, statistics can be separated into descriptive and inferential statistics. They are for making statements and establishing something about the data. Declarative visualizations, on the other hand, are usually more in-depth and detailed and are usually created to answering specific questions. Generally they’re for understanding what information is contained in the data, figuring out what further analysis can be conducted, and answering broad, surface level questions. He states that exploratory visualizations are designed, as the name suggests, to explore data. In chapter 3 of Good Charts, Scott Berinato discusses the differences between declarative and exploratory data visualizations. Much of the material in this chapter was taken from the MATH 221 textbook.īefore we move into this chapter, it’s important to make sure that the meaning of statistical inference is clear. 6.1.5 Access your calendar, notes, and tasks.5.4.4 Resources for Finding and Landing a Job.5.4 Marketing Yourself as a Data Scientist.4.4.1 Comparing Proportions Using Confidence Intervals.2 Introduction to the Normal Distribution and Z-Scores.1.5.2 Comparison of summarized data, frequency data, and raw data.