Tuesday, February 26, 2008

Hypothesis and its testing

Hypothesis(from Greek):
It consists either of a suggested explanation for a fact or of a reasoned proposal suggesting a possible correlation between multiple facts. Scientists generally base such assumption or hypotheses on prior readings or on outcome of scientific theories. Even though the words "hypothesis" and "theory" are often used synonymously, a scientific hypothesis is not the same as a scientific theory. A hypothesis requires either a confirmation or disproval by researchers. In due course, a confirmed hypothesis may become part of a theory or can grow to become a theory itself. Now-a-days, scientific hypotheses have the form of a mathematical model.

  1. If and then in case of dependent variables.
  2. Statistical
    Null Hypothesis- H0: coin-tossing operates "fairly" (equally likely to fall "Heads" or "Tails")
    Alternate Hypothesis- H1: coin-tossing operates in a biased manner to give a 90% probability of falling "Heads"

The purpose of hypothesis testing is to test the viability of the null hypothesis in the light of experimental data. Depending on the data, the null hypothesis either will or will not be rejected as a viable possibility. The null hypothesis is often the reverse of what the experimenter actually believes; it is put forward to allow the data to contradict it.

However, various statistical approaches (such as Bayesian statistics and classical statistics (i.e. t-tests)) can quantify the strong intuition that H1 appears much less likely than H0 let us suppose that if, in 1,000 tosses, 495 came out "Heads" — and much more likely if 895 came out "Heads". Researchers generally evaluate experiments statistically.

  1. After specifying the H0, the next step is to select a significance level(it is the criterion used for rejecting the null hypothesis). The level of significance is chosen as 0.05 level(also referred as 5%) or 0.01 level(also referred as 1%).

  2. Then the difference between the results of the experiment and the null hypothesis is determined.

  3. Next, assuming the null hypothesis is true, the probability of a difference that large or larger is computed .

  4. Finally, this probability is compared to the significance level. If the probability is less than or equal to the significance level, then the null hypothesis is rejected and the outcome is said to be statistically significant.

For further understanding pls. pay a visit to http://statpages.org/

Sunday, February 24, 2008

From Researching to Publication

How to perform scientific experiment

You notice something, and wonder why it happens. You see something and ponder what causes it. You want to know how or why something works. You ask questions about what you have seen.The first step is to write down what you have noticed.

Find out about what you want to investigate. Read books, magazines, search internet or ask professionals who might know in order to learn about the effect or area of study. Keep track of where you got your information.

Choose a title that describes the effect or thing you are investigating.

What do you want to find out? Write a statement that describes what you want to do. Use your observations and questions to write the statement.

Make a list of answers to the questions you have.Hypothesis must be stated in a way that can be tested by an experiment.

Design an experiment to test each hypothesis.

Make a list of the things you need to do the experiments, and prepare them.

Do the experiment and record all numerical measurements made. Data can be amounts of chemicals used, how long something is, the time something took, etc. If you are not making any measurements, you probably are not doing an experimental science project.

Observations can be written descriptions of what you noticed during an experiment, or problems encountered. Keep careful notes of everything you do, and everything that happens. Observations are valuable when drawing conclusions, and useful for locating experimental errors .

Perform any math needed to turn raw data recorded during experiments into numbers you will need to make tables, graphs or draw conclusions.

Summarize what happened. This could be in the form of a table of numerical data or graphs. It could also be a written statement of what occurred during the experiments.

Using the trends in your experimental data and your experimental observations, try to answer your original questions. Is your hypothesis correct? Now is the time to pull together what happened, and assess the experiments you did.
Other Things You Can Mention in the Conclusion are:
If your hypothesis is not correct, what could be the answer to your question?
Summarize any difficulties or problems you had doing the experiment.
Do you need to change the procedure and repeat your experiment?
What would you do different next time?
List other things you learned.

COURTESY: http://www.isd77.k12.mn.us/resources/cf/SciProjIntro.html

Monday, February 18, 2008

My Profile

I'm a technical writer with Masters in Software Development(Coventry University, UK) and Genetics(Karachi University, Pakistan).
My hobbies are writing, reading, travelling, photography and recycling anything recyclable!