#3

Assalamualaikum, hello and salam sejahtera everyone.
So seperti mana yang dijanjikan last week (ngeh pemalasnya iolls :p) I'll be updating an entry about some important terminology used in statistics. Sampai bila-bila pun yang paling penting hat ni lah ha. Kalau tak faham, dia akan jadi susah untuk the next-next level, okeng? Don't worry, be happy, buku sentiasa ada as a references ngehngeh so untuk kali ni, saya refer buku Applied Nonparametric Statistics, written by Wayne W. Daniel :))


------------------------------


Last entry kan ada cakap pasal collecting data and stuffs, so bila related dengan data, mestilah ada dua jenis. Satu jenis data yang kita ambik dari population, dan ada juga data yang kita simplify kan, just consider the sample. Apakah perbezaan antara population dengan sample? Bila masa nak guna population and bila masa pulak nak guna sample? Haaaaa. Daripada tulisan Wayne W. Daniel, beliau kata....


Population :

• Collection of persons, places or things, depends on the investigator's or researcher's sphere of interest. It may be defined as the largest collection of persons, places or things in which we have interest. 
• It also may be finite (possible to count the element of which it is composed // boleh dikira) & infinite (composed of limitless number of elements // susah untuk dikira)
• May be either real or hypothetical (impractical to create it)

Sample :

• Part of population 
• Usually researcher akan guna sample bila population terlampau besar dan it is impossible to examine every element in it. So daripada sample yang kita ambil daripada population, conclusions about a population are usually based on the information contained in a sample that has been drawn from that population.
• There are two types of sample :- 

1. Random Sample : 

• Statistical inference consists of reaching conclusions about a population on the basis of information contained in a sample.
• Basically, kita tak boleh lah just select any type of sample, it is not necessarily appropriate kan. So validity of results based on statistical inference rests on the assumption that a special type of sample, called a random sample has been employed in the process. 
• Yang paling common adalah Simple Random Sampling ||  the sample of size n is selected in such a way that every one in the population has the same probability of being selected as a sample. Usually samples are selected through the use of a table of random numbers (dalam buku stats) or with the help of computer which generate the random numbers. The advantage of using SRS is it eliminate biased sebab semua ada equal chances to be selected.
• Btw, random sample bukan hanya ada SRS, ada banyaaakkk lagi, so kita akan go through random sampling dengan lebih mendalam in the next entry, okay? :)

    2.  Non Random Sample / Samples of Convenience

• Selalunya kalau people yang fresh from a statistics course akan macam terkejut mak aih susahnya nak buat random sampling, so instead of random samples drawn with the help of random number tables / random number generated from computer, so they (dari dalam buku Wayne ni ha, page 4) find that sample yang senang adalah sample yang available and convenient. 
• Logically, selalunya kalau samples of convenience ni kita tak boleh depends 100% dan tahap ke-rasional-an nya adalah diragui ramai pihak sebab it may be high biased. Sebolehnya kita mestilah nak conclude population kita takde bias apa-apa, ye dak? Ha centu. 

------------------------------

Next adalah perbezaan antara parameter and statistic. Benda ni simple dan perlu ingat sampai bila-bila ye kawan-kawan. Jangan tertukar. Hiks :3

Parameter :

• A constant that determines the specific form of a density function, from population.
• Example: population mean (μ ), population variance (σ² ), population correlation coefficient (ρ )

Statistic (without s) : 

• A function of one or more random variables, computed from sample. 
• Example: sample mean (x̄), sample variance (s² ), sample correlation coefficient (r)

------------------------------

And next adalah, type of variable. Okay daripada buku Wayne ni, beliau menyatakan ada 3 types of variable which are:

1. Random Variable
2. Continuous Variable
3. Discrete Variable

Random Variable : 

• Usually assume that the numerical data on which we perform statistical analyses are the outcomes of a random sampling procedure or a random experiment. 
• A set of outcomes is called a random variable.
• Observe one or more values of the random variable in the process of sampling or experimenting.

Continuous Variable :

• A random variable is continuous if the values that it can assume consist of all real numbers in some interval; that is; a continuous variable can assume any of the uncountable and infinite number of values within a relevant interval.
• Example: Time interval, time of reaction to some stimulus.

Discrete Variable :

• The number of values that may be either finite or infinite but countable. 
• Might be able to assume values that are fractions or combinations of fractions and whole numbers.

Last but not least yang saya nak share dengan you guys adalah perbezaan antara parametric and non parametric (sebab selalu sangat lupa padahal dah nak grad oi kakaka ), daripada website:-

 (http://changingminds.org/explanations/research/analysis/parametric_non-parametric.htm)

So untuk next entry hmmm we'll see later okay apa yang akan saya update? Stay tuned!

See you soon!
Byeeeeeee :]