Wednesday, April 29, 2015

Cara menulis laporan keputusan t-test satu sampel

I've read answers like the one below for one-sample t-test.
"The estimates (M=8.57, SD = 1.70) are significantly higher than the test value, t(28) = 15.2, p = .009."
You may be forgiven for wondering what exactly is the 'test value'. The answer did not provide enough 
information. A possible better answer is:

"A group of students were asked to freely draw a straight line without the aid of a ruler. They were instructed to draw a line which is 5cm long. The length of the lines (= 8.57, SD = 1.70) drawn by the students are significantly longer than 5cm (the line's intended length), t(28) = 15.2, p = .009, and the effect size is large, d = 2.1" 

Dalam SPSS, bagi one-sample t-test, 'test value' tu istilah umum - mungkin merujuk kepada nilai purata populasi, nilai ambang (threshold), nilai piawai, atau apa-apa yang ditetapkan oleh pengkaji. Silalah guna maklumat yang lebih khusus bagi setiap masalah yang dikaji. 'test value' istilah umumiah atau generaliziah; dalam jawapan kena beri yang khususiah atau specifikiah. Kalau tak, kuranglah markah kau Kiah. 

Kalau bakal suami kau lafazkan "aku terima nikah perempuan ini binti lelaki ini dengan mas kahwinnya X ringgit Malaysia tunai", agak-agak kau nak rasa hangin ke, atau rasa nak sedekah tazkirah 30 minit kat dia? Engkau bukan pemboleh ubah dalam sistem aljabar. Ada nama dan identiti sendiri. Dalam konteks nak menikah, kena lah guna nama sendiri, kan?

Kau nak nota dalam bahasa apa lagi Bedah? Hibrid Melayu-Telugu?

p/s What mistake can you detect in the t-test results?

Usability and Islam

A website or software with poor usability will frustrate users. Some may be angered to the point of spewing expletives and destroying near by objects. I wonder how many istighfar were required due to bad usability.

A poor usability has also been identified as a factor that led to poor take up or usage of a software. At work, the UI for continuous assessment marks has much to be desired. The difficulty to use the system had caused considerable delay and unnecessary stress for course instructors. Some were not able to customise the course assessments by the deadline given.

Usability is also important to reduce errors. I wonder how many marks were keyed in wrongly as a result of poor UI. In the list of students, there is a glaring infirmation missing: the list number! It should be a basic thing to include in a list. When it is not there, the task of entering the marks requires more time - to check the name without a number shortcut. I usually write the marks on a printed class list and then transfer the marks to the CAM system. When doing that,  reading "Nur Fitriyana Syuhada binti Mohammad Syukur Azlan" is longer than "6", right? And, when there is "Nur Fitrizana Shuhada binti Mohamad Shukur Azlan" in the list, it gets more confusing.  Numbers in a sequential list is easier to discriminate.

The task is especially difficult when I want to check a specific student i  the list. I have to scroll down the list by reading the names or (the longer) matric number instead of locating the respective listing number.

Can we say then that usability is an Islamic requirement for websites and software (especially those meant for the public)? In other words, designing usability into software/website is an Islamic duty, right?

Monday, April 27, 2015

Doa Perlindungan Yang Komprehensif

Cantiknya doa ini... kalimah-kalimah yang indah. Sebelum dimakbulkan pun boleh terasa lunak di hati.
“Ya Allah aku berlindung dari rundungan sedih dan kedukaan, dari lemah kemauan dan rasa malas, dari sifat pengecut dan bakhil, dari belenggu hutang dan tekanan manusia.”
Dalam sebaris doa, ada dirangkumkan perlindungan daripada elemen emosi, sikap, tingkah laku, kewangan, dan sosial.
nota kaki: emosi tak semuanya negatif. tapi emosi yang negatif memang boleh merosakkan diri. Mungkin sebab itu kita diajar untuk berdoa mengelak daripada dibelenggu emosi yang negatif.

Learning Statistics with One Direction

Friday, April 24, 2015

Kepalang Ajar

Masrhmallow test and sex

Self-control or 'delay of gratification' has been shown to be related to academic success and life success. The marshmallow test shown in the vid is very instructive in examining people's responses to a temptation. It reminded me of a verse in al-Quran. The kitab is indeed a miracle.
"Dan Janganlah kamu manghampiri zina, sesungguhnya zina itu adalah satu perbuatan yang keji dan satu jalan yang jahat."

Pantun statistics

Joe Flizzow and Malique
Good buddies making musics
Orthogonal and oblique 
Are variate dependence in statistics

Sunday, April 12, 2015

Orang tak pandai parking

Situasi di tempat parking: ada banyak petak kosong. Kalau ada orang yg sengaja park kereta di belakang kereta lain (sehingga menyusahkan kereta itu untuk keluar), sedangkan tempat itu bukan petak letak kereta, orang berkenaan mengalami sindrom

A. Kurang belaian kasih sayang
B. kurang sel-sel otak yang berhubung
C. Terlebih rasa dirinya penting
D. Kurang didoakan cepat masuk syurga

Bila menteri buat silap atau dilaporkan buat silap, banyak rakyat yang marah. Realiti dalam hidup sehari-hari, 'rakyat' jugalah yang menyusahkan hidup rakyat lain secara langsung.

Marahkan menteri, rakyat lain yang dibakar.

Peribahasa moden

Lebih troll dari jambatan = keghairahan mempersendakan orang lain berdasarkan maklumat dari orang lain tanpa mengesahkan kebenaran maklumat tersebut.

Pelajar Universiti Memasak?

Masa belajar untuk bachelor (Kanada), saya belajar memasak sendiri. Setiap semester ambil antara 12 ke 15 jam kredit.

Semasa belajar peringkat master di London, saya duduk di asrama dan selalu memasak di dapur guna sama.

Semasa belajar buat PhD di Loughborough, England, saya banyak memasak dan makan di rumah sendiri atau di rumah kawan-kawan.

Makan di luar (i.e. beli di kafe atau restoran) adalah satu bentuk kemewahan yang dikecap sekali sekala.

Bukan sesuatu yang pelik untuk mahasiswa/i memasak. Mungkin di Malaysia aje yang ketara peliknya.

Wednesday, April 08, 2015

5 Steps of consumer decision-making

Steps in consumer decision-making

1. Problem/need recognition

I had a health screening on 5th of March, a present of SOCSO for turning 40 this year. It was yesterday that I collected the results from the MSD. Alhamdulillah, my blood pressure, blood sugar level, and haematology analysis are all normal. The highlight of the report is the cholesterol level. The total cholesterol level is 6.5, way above the 5.2 upper range of healthy level. In fact, readings of more than 6.2 is considered as high risk.
"Oh noooo! I don't want to be at risk for heart diseases." [recognised there is a problem]

2. Information search 

Based on the last blood test that I've done, my cholesterol level was near the borderline range. So, I'm not surprised that it had went up. But I was surprised that it went up by that much. So, now I have to find out the ways to reduce cholesterol level [information search].  The letter from the clinic said that I should exercise 3 times a week (checked; I go to Celebrity Fitness every week), reduce intake of food with high cholesterol level (internal organ, seafood, and egg yolk), and start taking medication.

I am not keen on medication. I want to know which food would help me. I googled quickly while waiting to see the doctor at the IIUM clinic. People, including Dr Zubaidi, recommended oat, Omega 3 fish oil, [both of which are part of my evoked set; choices that are readily available from my memory] psyllium husk,  and plants that have phytosterols. Some people also testified the benefits of soy, date vinegar and apple cider [part of my inert set: choices that I have not considered due to lack of knowledge]. On top of the online search, seeing the doctor is also part of my strategy to get more information about the interventions available. 

3. Evaluation of alternatives to meet this need

Based on my reading and consultation with the doctor, these are my evaluation of the options available at the moment. 

a. A commonly prescribed drug to reduce cholesterol level is statin. It may produce effects such as physical weakness (e.g. aching muscles). It also tend to be a life time medication. You can control, but not necessarily lower the cholesterol [statin is in my inert set: choices that I have not ruled out].

b. Dieting is an effective method, though the time taken to see results may be more than you could be patient for. You also need to be highly disciplined. Avoiding bad food and eating healthy ones are difficult to implement if you have poor self-control. To make matter worse, the choices of food available to you (e.g. at the cafetaria) may seem to mock and tempt you into making a bad choice.

c. Functional food and supplements are heavily advertised. They may be effective, natural (compared to medication), and easier to take, albeit more pricey. I have started taking Shaklee's OmegaGuard (fish oil high in Omega 3) and Alfalfa. Both were cited as helpful in reducing cholesterol level. Last year, Shaklee introduced another supplement in the Malaysian market: Phytocol-St. A daily dosage of Phytocol-St will give you 2,000mg of phytosterols.  

In short, medication is my last resort. After all, the doctor said I do not have other risk factor like high BP and sugar level. So, I can try dieting for 2 months before a follow up appointment with her. 

4. Purchase decision

Yesterday I bough Phytocol-St from Shaklee Sri Rampai branch (RM208.82 retail price, with GST - but I bought at a much lower member price) and Oat Bran powder (beta glucan) from a pharmacy in Wangsa Walk. Hopefully both of these, in combination with OmegaGuard and Alfalfa would bring the desired results in two months time. If there is a downward trend, I will be very happy.

5. Post-purchase behavior

What happened after the purchase? 

I had started taking Phytocol-ST last night: two tablets. The daily dose is 4 tablets; two tablets each time at two meal times. I had also taken the Oat Bran. To ensure consistency, I brought one can of Oat Bran to the office and kept another two at home (bought 3 cans at a discounted price). Perhaps I should also buy another bottle of Phytocol-St to keep at the office. 

Will I continue consumption, change habit, or modify perception of the problem? That is subject to the will of Allah s.w.t.  We plan and make decisions; and He will give what He wills. I pray that He give me good health.

Monday, April 06, 2015

Words to describe strange statistics experience

I was bitten by a logophile bug after reading this post: Warning: logophile usually comes together with nerdititis. So, here are my own creative words based on my experience as a student and teacher of statistics.

1. Chronophasia - the inability to understand the concept of deadline.
e.g. I feel frustrated looking at the low quality of assignment submitted by students. It is as if they did it the very last night before it is due. Perhaps they were experiencing chronophasia since the beginning of the semester.

2. Annoyva - frustrating and irritating calculation to get an F statistic.
e.g. The pain was evident is the students' face as they tried to figure out the sum of squares and the mean squares. The exercise was clearly an Annoyva.

3. Statisnonstick - very slippery statistics lessons; ones that are difficult to stick in mind
e.g. He is repeating the course this semester. And he still feels that nothing makes sense. The whole course is statisnonstick.

4. Estimath - an answer to math question that is close enough to the actual answer
e.g. When all that she reviewed dissipated into thin air, she was only able to provide estimaths in the math test. 

5. Mathematips - helpful hints for math exam.
e.g. During the final examination, she continued to gaze deeply into the question paper, hoping to magically retrieve some mathematips from the margins of the paper.