CariDotMy

 Forgot password?
 Register

ADVERTISEMENT

12Next
Return to list New
View: 6939|Reply: 33

You Can Call Me Now : Basic&Applied Stat

[Copy link]
Post time 14-11-2006 01:14 PM | Show all posts |Read mode
Hai kengkawan,

jika ada any idea, suggestion, opinion, question dan etc etc etc...mengenai basic@elementary@applied statistics...please,write down here....

kita sama-sama tolong, kita sama-sama jawab. Kalau tak pasti..i x jawab. hheheheh. ok ke? oklah kut...JOmm'Sss!!!

Minat ke? Ahakss..just offer diri...sebab i nampak topik kat bahagian STAM ni kurang aktif.


[ Last edited by  Sinaran at 14-11-2006 01:16 PM ]
Reply

Use magic Report


ADVERTISEMENT


 Author| Post time 19-11-2006 10:48 AM | Show all posts

Pensampelan/; Intro

Apa itu pensampelan?

proses mendapatkan sampel daripada populasi

Recall : populasi>> seluruh/semua 'individu' yg ingin dikaji
             sampel >> subset kepada populasi @ sebahagian daripada populasi

            Contoh : kajian mengenai halaju basikal buatan cap kapak di Felda XXX
                           populasi : semua basikal buatan cap kapak di Felda XXX
                           sampel : " sebahagian" basikal buatan cap kapak di Felda XXX

nota kaki :
1.  "individu" boleh merujuk kepada manusia,haiwan,tumbuh-tumbuhan, peralatan dan sebagainya yg diminati utk kajian.

2. " sebahagian" - bilangan sampel akan ditentukan menggunakan formula berdasarkan jenis pensampelan apa yg akan digunakan.

Jenis-jenis pensampelan:
1. pensampelan berkebarangkalian-strata,rawak mudah, kelompok dan sistematik
2. pensampelan tidak berkebarangkalian-kuota,bola salji, mudah dll yg kebanyakannya tidak berasas tetapi hanya menggunakan logik fikiran.

Jumpa lagi....
Reply

Use magic Report

Post time 19-11-2006 11:04 PM | Show all posts
ada satu soalan aku nak tanya.
pasal bilangan penonton yg menonton sesuatu rancangan.
macam mana dia buat? pakai statistik method ke?
apsal aku tak penah masuk populasi yg dibuat persampelan tu?
Reply

Use magic Report

Post time 19-11-2006 11:43 PM | Show all posts
camner plak kes yg ader pasal critical value ngan accepted value .. yg kener pakai outlier utk kiter tau sama ada nilai tu kiter accepted or rejected .. susah la ... ajar skit
Reply

Use magic Report

Post time 20-11-2006 05:38 PM | Show all posts
Originally posted by orang_awam at 19-11-2006 11:04 PM
ada satu soalan aku nak tanya.
pasal bilangan penonton yg menonton sesuatu rancangan.
macam mana dia buat? pakai statistik method ke?
apsal aku tak penah masuk populasi yg dibuat persampelan tu?


rasanya statistik yang dibuat adalah berdasarkan pensampelan (mungkin strata ataupun sistematik - kurang pasti)... sampel yang dibuat nie secara statistiknya mengambarkan populasi rakyat Malaysia
Reply

Use magic Report

Post time 20-11-2006 05:43 PM | Show all posts
Originally posted by DDT_pacak85 at 19-11-2006 11:43 PM
camner plak kes yg ader pasal critical value ngan accepted value .. yg kener pakai outlier utk kiter tau sama ada nilai tu kiter accepted or rejected .. susah la ... ajar skit


biasanya apa yang dikatakan outlier tu adalah data-data yang didapati terasing daripada satu set data... kalau tak silap ... data-data tu terletak pada lebih daripada 2-sigma (bergantung kepada test yang dibuat)
Reply

Use magic Report

Follow Us
Post time 22-11-2006 08:23 AM | Show all posts
Originally posted by orang_awam at 19-11-2006 11:04 PM
ada satu soalan aku nak tanya.
pasal bilangan penonton yg menonton sesuatu rancangan.
macam mana dia buat? pakai statistik method ke?
apsal aku tak penah masuk populasi yg dibuat persampelan tu?


selalunya,utk statistik ni..dia akan amik sample dari satu populasi yg besar..

contohnya dlm hal ini populasi = semua rakyat malaysia

sample = 1000 org rakyat malaysia

tp dlm nak amik sample ni,kita tak boleh bias..kena pastikan sample yg diambil mewakili seluruh populasi..jd dlm hal ni,kena pastikan yg sampel tu diambil dari rakyat diseluruh malaysia..setiap negeri contohnya..bukan org di KL je ke etc..
Reply

Use magic Report

Post time 22-11-2006 08:25 AM | Show all posts
Originally posted by DDT_pacak85 at 19-11-2006 11:43 PM
camner plak kes yg ader pasal critical value ngan accepted value .. yg kener pakai outlier utk kiter tau sama ada nilai tu kiter accepted or rejected .. susah la ... ajar skit


outlier ni adalah data2 terpencil..maksudnya,data ni jauh dari sekumpulan data yg lain..dlm statistik,kita akan ketepikan outlier ni..kiraannya samada 2sigma ke,bergantung kepada test yg kita buat..dan keperluan kita terhdp hasil statistik tu..

tp jika terlalu byk outlier dlm set data,dlm industry process application,kita akan conclude yg process tu sbg tak stabil..
Reply

Use magic Report


ADVERTISEMENT


Post time 22-11-2006 06:20 PM | Show all posts
Originally posted by orang_awam at 19-11-2006 11:04 PM
ada satu soalan aku nak tanya.
pasal bilangan penonton yg menonton sesuatu rancangan.
macam mana dia buat? pakai statistik method ke?
apsal aku tak penah masuk populasi yg dibuat persampelan tu?



Macam bilangan penonton ni dorang dapat statistik ni dari 2 agensi yang bertauliah kat m`sia ni... Nelson Media (NMR) lagi satu Audit Bureau of Circulation (ABC)
caranya dengan melantik secara "random" penduduk kat m'sia ni lebih kurang 1000 orang atau lebih.. sesiapa yang terpilih tu dekat rumah dorang akan dipasang alat kat tv.. daripada situ NMR atau ABC akan tahu rancangan mane paling banyak di tonton oleh orang yang dipilih tadi... dan dibuat kesimpulan dari situ sebagai mewakili penduduk kat m'sia ni.
Reply

Use magic Report

 Author| Post time 26-11-2006 10:48 AM | Show all posts
Originally posted by orang_awam at 19-11-2006 11:04 PM
ada satu soalan aku nak tanya.
pasal bilangan penonton yg menonton sesuatu rancangan.
macam mana dia buat? pakai statistik method ke?
apsal aku tak penah masuk populasi yg dibuat persampelan tu?



Kalau nak baca kaedah yang betul, sila rujuk pada buku Marketing Research yg di tulis oleh Prem S.Malhotra dan buku-buku lain yg seumpamanya. while, mengenai bilangan pengiraan penonton tu, bagaimana dikira? ada macam-macam cara they all guna, salah satunya (sepengetahuan saya) selain diletakkan alat pada tv,they all cuma call saja, tapi....itu cuma anggaran dan dengan andaian bahawa responden tidak tukar channel. maka ia belum terbukti benar.

anyway..sehebat mana statistik, sehebat mana alat @teknologi yg digunakan, semuanya depends on sampling.jika tidak rawak, maka hancuslah statistiknya.

Nota : rawak @ random = peluang individu yg bakal menjadi sampel adalah tidak diketahui. kadang-kadang orang salah faham pada istilah ini.
Reply

Use magic Report

 Author| Post time 26-11-2006 10:57 AM | Show all posts
Originally posted by DDT_pacak85 at 19-11-2006 11:43 PM
camner plak kes yg ader pasal critical value ngan accepted value .. yg kener pakai outlier utk kiter tau sama ada nilai tu kiter accepted or rejected .. susah la ... ajar skit


saya cuba jawab, tapi...saya tak berapa jelas dengan soalan yg dikemukakan.
dalam melaksanakan pengujian hipotesis, akan melibatkan 5 langkah utama
1. hypotheses statement : hipotesis null and alternative
2. test statistic : need to calculate by using formula
3. critical value : find out from statistical table
4. decision : reject H null if test stat > critical value
5. conclusion

memandangkan banyak sofware stat yg melambak di pasaran gelap.hehhehe. sperti SAS, SPSS, S-plus etc. maka step 2  menjadi : penentuan nilai p (p-value) dan step 3 menjadi: penentuan aras keertian(sgnificant level) lain-lain step tidak berubah.

4.decision : reject H null if p-value< significant level

nota : significant level :can be any value,depends on researcher, but, usually less than 10%.

sorry jika huraian saya sukar difahami.
Reply

Use magic Report

 Author| Post time 26-11-2006 10:58 AM | Show all posts
Originally posted by DDT_pacak85 at 19-11-2006 11:43 PM
camner plak kes yg ader pasal critical value ngan accepted value .. yg kener pakai outlier utk kiter tau sama ada nilai tu kiter accepted or rejected .. susah la ... ajar skit


saya cuba jawab, tapi...saya tak berapa jelas dengan soalan yg dikemukakan.
dalam melaksanakan pengujian hipotesis, akan melibatkan 5 langkah utama
1. hypotheses statement : hipotesis null and alternative
2. test statistic : need to calculate by using formula
3. critical value : find out from statistical table
4. decision : reject H null if test stat > critical value
5. conclusion

memandangkan banyak sofware stat yg melambak di pasaran gelap.hehhehe. sperti SAS, SPSS, S-plus etc. maka step 2  menjadi : penentuan nilai p (p-value) dan step 3 menjadi: penentuan aras keertian(sgnificant level) lain-lain step tidak berubah.

4.decision : reject H null if p-value< significant level

nota : significant level :can be any value,depends on researcher, but, usually less than 10%.

sorry jika huraian saya sukar difahami.
Reply

Use magic Report

 Author| Post time 26-11-2006 11:34 AM | Show all posts

What is Statistics?

What is Statistics?
"I like to think of statistics as the science of learning from data...It presents exciting opportunities for those who work as professional statisticians. Statistics is essential for the proper running of government, central to decision making in industry, and a core component of modern educational curricula at all levels."

Jon Kettenring
ASA President, 1997


American Heritage Dictionary&reg; defines statistics as: "The mathematics of the collection, organization, and interpretation of numerical data, especially the analysis of population characteristics by inference from sampling."


The Merriam-Webster抯 Collegiate Dictionary&reg; definition is: "A branch of mathematics dealing with the collection, analysis, interpretation, and presentation of masses of numerical data."

Rate

1

View Rating Log

Reply

Use magic Report

 Author| Post time 26-11-2006 11:44 AM | Show all posts

What do Statisticians do?

Statisticians help determine the sampling and data collection methods, monitor the execution of the study and the processing of data, and advise on the strengths and limitations of the results. They must understand the nature of uncertainties and be able to draw conclusions in the context of particular statistical applications.

*       Surveys: Survey statisticians collect information from a carefully specified sample and extend the results to an entire population.

*       Government Operations: Government statisticians conduct experiments to aid in the development of public policy and social programs.

*       Scientific Research: Statistical sciences are used to enhance the validity of inferences in all scientific research.

*       Business And Industry: Statisticians quantify unknowns in order to optimize resources.
Reply

Use magic Report

Post time 30-11-2006 03:59 PM | Show all posts

salam..

cuba bagi tau i basic terms ni

univariate - ( in english sebab dalam malay i pening)
bivariate

anything with inferential stats!

tq
Reply

Use magic Report

Post time 30-11-2006 04:03 PM | Show all posts

aah lagi satu...

i ada dalam lecture biostats ni - tapi yg menarik kan semua org confuse pasal p - value - nak tergelak kiter .. so why do not you ambil peluaang ni citer apa tu P- value - null hypothesis rejection
etc kot kot sapa yg nak buat thesis this sem nak tanya.

sometimes just a simple concept could baffle people for weeks

apa yg i tahu ialah p - value tu is the probability of ur research to get the value so extreme in order to prove the null hypothesis is right , so in the usual context we just take the cut off points to be 0.05 ( alpha lah kan)


cuba ternagkan statistic inferential pasti menarik.

" we do not reject, we just said not accepted"....
Reply

Use magic Report


ADVERTISEMENT


Post time 30-11-2006 10:47 PM | Show all posts
Originally posted by orang_awam at 19-11-2006 11:04 PM
ada satu soalan aku nak tanya.
pasal bilangan penonton yg menonton sesuatu rancangan.
macam mana dia buat? pakai statistik method ke?
apsal aku tak penah masuk populasi yg dibuat persampelan tu?



aku nak cuba jawab ni.....
nak bagi penjelasan yg lebih terperinci....

sebenarnya percentage rating TV ni dikira macamni.

Contohnya: Kat Malaysia ni ada 10 juta famili yg ada TV. Daripada jumlah tersebut, kita bole tahu anggaran kasar berapa ramai yg menonton TV. Bagi stesen TV, lagi ramai yg menonton, program TV tulah yg paling popular.

Sebenarnya, the percentage of homes in a given area that have one or more TV set turned on at any particular time is expressed as households using TV (H.U.T). Jadi, kalau ada 1000 TV dalam satu kawasan yg sedang di kaji selidik dan 500 TV sedang ditonton, figure is 50%.

Kalau anda semua perasan, ada sesetengah program TV ni sekejap je tunjuk kat TV. Sebenarnya program TV ni mempunyai rating TV yg amat rendah.Bila ratingnya amat rendah, pengiklan&sup2; mmg tak berminat nak sponsor program TV tersebut.Tapi, macammana nak kira rating????

sebenarnya macamni....

Rating= Number tuned into specific station/ TVHH

TVHH=the number of household that own TV set. kalau satu kawasan je, kita kira utk kawasan tu jek....

nilah cara sebenar rating TV dikira....
sesiapa yg tak percaya ada rancangan TV tu boleh mencapai rating 4 juta tu....terpulanglah.....
statistik pun takdela 100% betul tapi kita konfiden tulah anggaran yg hampir tepat....
harap fahamla...
nilah yg aku belajar dulu....

[ Last edited by  purpler at 30-11-2006 11:53 PM ]
Reply

Use magic Report

Post time 30-11-2006 11:08 PM | Show all posts
Originally posted by mbhcsf at 30-11-2006 04:03 PM
" we do not reject, we just said not accepted"....



The final conclusion once the test has been carried out is always given in terms of the null hypothesis. We either "do not accept H0 in favour of H1" or "Accept H0"; we never conclude "do not accept H1", or even "Accept H1".

If we conclude "Accept H0", this does not necessarily mean that the null hypothesis is true, it only suggests that there is not sufficient evidence against H0 in favour of H1. Rejecting the null hypothesis then, suggests that the alternative hypothesis may be true.

my lecturer pernah jugak cakap mmg tak digalakkan kata reject sebab kemungkinan dalam banyak&sup2; variables yg reject, mungkin ada satu variable yg kita accept. kalau kata reject, macam semua sekali kita reject.


[ Last edited by  purpler at 1-12-2006 12:53 PM ]
Reply

Use magic Report

Post time 1-12-2006 12:13 AM | Show all posts
Originally posted by mbhcsf at 30-11-2006 03:59 PM
cuba bagi tau i basic terms ni

univariate - ( in english sebab dalam malay i pening)
bivariate

anything with inferential stats!

tq



dulu aku ada explain pasal univariate dalam satu thread dalam board ni....
tapi cari&sup2; tak jumpa pulak thread tu (dah kena delete kot)....
siap ada contoh SAS lagi....
nanti aku cuba terangkan soalan ko...
skrg nak tido...ngantuk...:nerd:
Reply

Use magic Report

Post time 1-12-2006 11:33 AM | Show all posts
Originally posted by mbhcsf at 30-11-2006 03:59 PM
cuba bagi tau i basic terms ni

univariate - ( in english sebab dalam malay i pening)
bivariate


tq


univariate= one variable
bivariate= 2 variables


[ Last edited by  purpler at 2-12-2006 03:45 PM ]
Reply

Use magic Report

12Next
Return to list New
You have to log in before you can reply Login | Register

Points Rules

 

ADVERTISEMENT



 

ADVERTISEMENT


 


ADVERTISEMENT
Follow Us

ADVERTISEMENT


Mobile|Archiver|Mobile*default|About Us|CariDotMy

29-1-2025 03:17 AM GMT+8 , Processed in 0.053368 second(s), 33 queries , Gzip On, Redis On.

Powered by Discuz! X3.4

Copyright © 2001-2021, Tencent Cloud.

Quick Reply To Top Return to the list