Hypothesis Testing

Agak lama betul tidak singgah dan menulis di blog ni. Bulan Jun nampaknya bulan yang agak sibuk; balik kampung la, siapkan apa-apa yang patutla untuk seminar di Jakarta nanti (in July), sibuk dengan artikel jurnal, sibuk dengan pre-test tesis, sibuk jadi cikgu Iqra’ dan ABC anak la dan macam-macam hal lagi. Moga Allah memberi kekuatan untuk menghadapi segala cabaran dunia ini. Semoga kesibukan dunia tidak menghalang diri untuk mengingati Allah dan ukhrawi.

Rasanya untuk entri kali ini nak berkongsi sedikit mengenai pengujian hipotesis (hypothesis testing) yang telah diajar oleh assoc. prof. Dr. Bahaman Abu Samah dari UPM. Tapi kalau nak berbicara tentang idol dalam bidang statistik ini, mesti takkan dilupakan  jasa yang teramat besar iaitu Dr Jusang (UPM) yang menjadikan dunia statistik ini sangat menghiburkan dan menyenangkan. Really thank you Dr Jusang…Jasa mu dikenang. Indeed…it has been a very interesting insightful discussion about our class of statistics.

Back to our discussion, according to Dr Bahaman, the reason why we need to do a hypothesis testing; to test is it true or not true – assumptions to be tested. For sure, to develop the hypothesis we need to review any related literature of our study. And of course the hypothesis will be analyzed through statistical inferences.

There are two types of hypothesis; Ho (null hypothesis) and Ha (research hypothesis/alternative). The question is why we need to have another hypothesis – which is null hypothesis if you as researcher need to use Ha?

Then, here you are – we go by the logic. THE LOGIC  is its so difficult to prove something to be true. BUT its easier to prove something to be not true. That means we create the opposite of hypothesis.

For example: Ha – There is a difference between male and female of academic performance. So the result is whether we reject or fail to reject Ho. We as researcher should be happy if we can reject Ho because we can show the truth of our hypothesis. But if we fail to reject all the hypotheses…watch out! There is must be something wrong with our research and people can question our framework of study. Prepare yourself  and do a lot of justification.

One more thing  – its about one tailed and two tailed. Dont be confused about this two types of critical value. It is just to show us about directional (one tailed – positive or negative) and non directional (two tailed). In other words, this is about the power in your statistics – higher tendency to reject. And two tailed is more powerful. We always set the confidence level 0.05 (95% – higher tendency) and also 0.01 (99%) to check the probability of rejecting null hypothesis.

Have a blast ya!

2 thoughts on “Hypothesis Testing

  1. parfum says:

    You could definitely see your expertise in the paintings you write. The sector hopes for more passionate writers like you who are not afraid to mention how they believe. Always follow your heart.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s