Hey guys in the last part (PART 1) we have seen about sample yada yada! Here we are gonna see about How actually we are gonna select sample from Population. Let's dive into it!
But First, let's see what is contained in Data? Data can be of two types:
- Qualitative
- Quantitative
What are those Q's mean? Qualitative Data - deals with categorical values. For example: Hair Color,Eye Color,Blood Group blah blah stufff
Quantitative Data - deals with numbers. Messing up with counting/ measuring results in some numerical values are the data that are quantitative. For example : Temperature,pulse rate,weight etc..
Quantitative data maybe Discrete / Continuous data. wtf is discrete here? data that can be counted - quantitative Discrete Data. For example : how many time that i had attended school this week? 4 or 5 like that!
Continuous Data - includes fractions, decimal,irrational numbers in the data. Maybe like "Length of the phone calls in minute that you had in the week. like 2.4 , 101.4" like that!
Try out the exercise in the OpenStax IntroductoryStatistics! That's interesting i promiseee!
we can collect data as numbers and make it look like categorically one. For example grade points 90-100 as O like that ..for every Grade!
Sampling:
we talked about taking sample,how do we do that (selecting random from population...)🤔.
Random Sampling is the probabilistic method to choose sampling! Problem is that we have to select the sample in way that it represents the whole population. So there are many ways to select the random from the population that's called Random Sampling!.
First up, Simple Random Sample!
- The name suggest that it's one of the easy method to find the random sample!
- For example : selecting random group of students in the class for some activity.
Here okay it's easy to see but how the heck we can represent in our math (here statistics). Assume that people wearing dali masks are represented using a number! 0 to total number of people) then we can find the random number easily. Like in Money Heist 💰, number one come forward like that(here number not name tho😬).
We have seen about Simple one, now to the next method!
Stratified Sample
- The Sample data is selected from population by dividing into groups called strata.
- from various strata , select random data (here we can use simple random sampling!!)and make a sample.
Cluster Sample
- Divide the population into clusters(groups) and select randomly from the clusters or some clusters.
For example : if we divide the group of athletes, we can cluster them according to their sport and select one from each group.
Hmm, Cluster and Stratified Sampling lookin like same ain't it?🤔 Actually, they are easily get confused with each other.
So what makes those sampling techniques differ? -> Stratified Sampling - makes characteristic select from the population in order to make sample (strata). In that example of Stratified, 2 girls and 2 boys are selected -> Whereas Cluster Sampling - makes the random group without depending on any characteristic. In that example of cluster sample, the clusters are formed randomly and girls & boys are selected randomly.
Systematic Sample
Here in this Sampling Method, the samples are taken in form of an interval (for every odd,even,prime like that rule). That is, Selecting number for every odd index,even index etc. Let's see the example,
Here, we have selected Dogs which is indexed at odd positions. (ie) For every Odd number of dog,select it.
if dog is in odd position(index), select it.
We Saw about randomized sampling method, but now we are going to see about "Convenience Sampling" which is not selecting from random instead use the population at hand/near to hand rather than randomized result of probablistic sampling techniques.
That's all for now! we will learn about FREQUENCY AND STUFF in the next part of the series. Thanks for reading and comment down what you think!
Icons by Icons8