In this class, course outline is given. We also studied different research design like Experimental, Quasi-Experimental and Pure Experimental.

Experiments are the top guns of research design, the most expensive and powerful techniques you can use. Before even considering an experimental design, you need to ask the following:

* Is it possible to precisely categorize the people, places, or things in your study?
* Is is possible to select random people, places, or things in your study?
* Is the process of random selection into experimental and control groups ethical and legal?

The word "quasi" means as if or almost , so a quasi-experiment means almost a true experiment. There are many varieties of quasi-experimental research designs, and there is generally little loss of status or prestige in doing a quasi-experiment instead of a true experiment, although you occasionally run into someone who is biased against quasi-experiments. Some common characteristics of quasi-experiments include the following:

* Matching instead of randomization is used
* Time series analysis is involved
* The unit of analysis is often something different than people.

We also went through some methods for research problem like Content based strategy, Statistics based strategy and External Criterion based strategy. Later in the class, we studing kind of scales available for use in the research survey, there effectiveness and shortcoming. Some measuring scales are Unipolar, Bipolar, Numerical scales, Semantic differential scales, Graphic rating scale, standard scale, BARS and forced choice scales.

Possible rating errors are also discussed in the class like halo effect, proximity error and ambiguity error. The whole point of this class is to know what kind of methods is useful in what condition. Pick the right Research Design for your research, then use the methods to solve research problem and keep the scaling of the question appropiate to the question. Later, we must also understand the possible rating errors done by those people who filled up our research survey form.

At the end of the class, Dr. Zubair Shiekh give us an assignment of filling the research proposal form which can be downloaded from the PTCL web site.

Course Outline:

Research Method - Course Outline (Document in doc format)

Teacher's Presentation Material:

Understanding Variables in Research (Presentation in ppt format)

Survey Methods (Presentation in ppt format)

Related Study:

http://www.okstate.edu/ag/agedcm4h/academic/aged5980a/5980/newpage2.htm
http://www.languages.ait.ac.th/el21meth.htm

First, we had a discussion on the assignment given in the previous class. Dr. Zubair Shiekh told us how to fill up the research proposal form by going through each section one by one. Later, Dr. Zubair Shiekh told us about his idea of creating a web portal whose utlimate goals will be to Improve the Quality of the IT Work Force in Pakistan. He also explain how the web portal should be, and who will be the audience of it.

The lecture start with the announcement of upcoming assignment of comparing two softwares/processes. Later, Dr. Zubair Shiekh discusses the importance of identifying the current variables in the research process. If identified currently, 50% of the research is completed.

By giving an example of possible research experimentation, Dr. Zubair Shiekh told us to write down our favourite search engine in a small paper and give that paper to him. When Dr. Zubair Shiekh opens that all the papers, everyone writes Google.com as there favourate search engine. The important point of this experiment is the perception that the result creates (i.e. every one uses Google for searching). Here, we take the sample of 15 people who are related to the field of Computer Science. This result doesn't mean that Google is the most popular web site on the internet. One can use other questions to validate the result created due to insufficient question. For example, later in the class, Dr. Zubair Shiekh asked the student about there email addresses. Only 10% students have email account on Gmail which clearly shows that Google is not the most popular side on the internet. Again, we can't make any conclusion on these two questions. So, the need for sophisticated questionnaire is required and the right kind of scale to measure it.

Related Study:

http://www2.latech.edu/~sajones/BIEN%20435%20Web%20Pages/Steps%20in%20Planning%20a%20Research%20Experiment.htm