Dr. Engr. Sami ur Rahman Assistant Professor Department of Computer Science University of Malakand Research Methods in Computer Science Lecture: Research Strategies

Research Strategies  Experiments  Case Studies  Surveys  Statistical Measurements of Research Work Digital University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 2

Experimental Research University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 3

Experimental Research Experimental research is an attempt by the researcher to maintain control over all factors that may affect the result of an experiment. In doing this, the researcher attempts to determine or predict what may occur. University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 4

Experimental Study Steps  Identify and define the problem.  Formulate hypothesis and deduce its consequence.  Construct an experiment that represents all the elements, conditions, and relations to the consequence.  Conduct the experiment.  Compile raw data and reduce to usable form.  Apply an appropriate test of significance. University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 5

Experimental Research Tries to Establish Cause and Effect  Selection of a good theoretical framework  Application of appropriate experimental design  Use of correct statistical model and analysis  Proper selection and control of independent variables  Appropriate selection and measurement of dependent variables  Correct interpretation of results University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 6

Case Studies University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 7

Case Studies Through careful examination and discussion of various cases, “[researchers] learn to identify actual problems, to recognize key players and their agendas, and to become aware of those aspects of the situation that contribute to the problem..." (Merseth, 1991 in m ) m Case Study: an in-depth description and analysis of a bounded system The collection and presentation of detailed information about a particular participant or small group, frequently including the accounts of subjects themselves University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 8

Case Studies Example How older people learn to use a computer? Case study: How one older person learns to use a computer - one particular program - one classroom of learners University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 9

Case Studies  Steps 1.Determine topic 2.Determine type of case study method used and mode of data collection - Documents - Interviews - Direct observation - Participant observation 3.Select participants 4.Collect data 5.Data Analysis 6.Write up report University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 10

Case Studies: Strengths & Weaknesses  Strengths 1.Anchored in real-life situations 2.Holistic account of the phenomenon 3.Advances a field’s knowledge base 4.Contextualization of the phenomenon University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 11

Case Studies: Strengths & Weaknesses  Weaknesses 1.Difficult to generalize 2.Too subjective 3.May be costly 4. Time consuming University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 12

Surveys University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 13

What is a Survey?  Researchers are often interested in the opinions of a large group of people about a particular topic or issue.  There are three major characteristics that most surveys possess: 1) Information is collected from a group of people in order to describe some aspect of the population 2) Information is collected by asking questions of the members of the selected group 3) Information is collected from a sample rather than from every member of the population University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 14

Why Are Surveys Conducted?  The purpose of surveys is to describe the characteristics of a population.  Researchers find out how the members of a population distribute themselves on one or more variables.  A selected sample is surveyed and the description of the population is inferred from what is found out about the sample.. University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 15

Types of Surveys  There are two types of surveys: 1) Cross-sectional survey  Collects information from a sample that has been drawn from a predetermined population  Information is collected at just one point in time, even though it could take days to gather all the data 2) Longitudinal survey  Information is collected at different points in time in order to study changes over time University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 16

Steps in Survey Research  The following steps are used in conjunction with performing proper surveys in research:  Defining the problem  Identifying the target population  Choosing the mode of data collection  Mail surveys  Telephone surveys  Personal interviews University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 17

Steps in Survey Research (cont.)  The following steps are used in conjunction with performing proper surveys in research:  Selecting the sample  Preparing the instrument (questionnaire)  Closed-ended questions  Open-ended questions  Pre-testing the questionnaire  Training interviewers University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 18

Non-response  In almost all surveys, some members of the sample will not respond.  Item non-response is due to unclear or questionable forms of wording.  Non-response is a serious problem in many surveys.  A variety of techniques are employed to reduce this problem (e.g., rewards or incentive for completing the surveys). University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 19

Data Analysis in Survey Research  After researchers receive the completed questionnaires, the task of summarizing the results remains.  The total size of the sample and total percentage of returns should be reported.  The percentage of the total sample responding for each item should be reported.  The percentage of respondents who chose each alternative for each question should be given. University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 20

Survey Research Demo University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 21

Statistical measurement of Research Work University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 22

Introductory Statistics  Why Use Statistics  Types of Statistical Analysis  Common Types of Descriptive Statistics  Basic Concepts  Central Tendency University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 23

Why Use Statistics?  Statistics are powerful tools that help people understand interesting phenomena.  “Whether you are a student, a researcher, or just a citizen interested in understanding the world around you, statistics can offer methods for helping you make sense of your environment” (Urdan, 2001). University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 24

Types of Statistical Analysis  Descriptive  Used to describe and summarize data  Inferential  Used to make inferences or predictions about the similarity of a sample to the population from which the sample is drawn. University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 25

Common Types of Descriptive Statistics  Percentage  The number per 100 individuals who achieved a certain score.  Mean  The arithmetic average of a distribution of scores  Standard Deviation  The average deviation between the individual scores in the distribution and the mean for the distribution University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 26

Basic Concepts  Population: the whole set of a “universe”  Sample: a sub-set of a population  Parameter: an unknown “fixed” value of population characteristic University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 27

Basic Concepts (contd.)  Randomness: Many things occur by pure chances…. rainfall, disease, birth, death,..  Variability: Stochastic processes bring in them various different dimensions, characteristics, properties, features, etc., in the population  Statistical analysis: Methods have been developed to deal with these very nature of real world. University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 28

Central Tendency Central tendency: The way in which quantitative data tend to cluster around some value. A measure of central tendency is any of a number of ways of specifying this "central value" MedianMode Central Tendency Average (Mean) University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 29

Mean Mean (arithmetic mean) of data values University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 30

Mean  The most common measure of central tendency  Affected by extreme values (outliers) Mean = 5Mean = 6 University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 31

Median Median: The “middle” number Not affected by extreme values Median = Median = 5 University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 32

Mode Mode: Value that occurs most often  Not affected by extreme values  There may be no mode  There may be several modes Mode = No Mode University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 33

Which measure of Central Tendency should be used? Measures of Central Tendency The measure you choose should give you a good indication of the typical score in the sample or population. University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 34

Measures of Central Tendency Mean … the most frequently used but is sensitive to extreme scores e.g Mean = 5.5 (median = 5.5) e.g Mean = 6.5 (median = 5.5) e.g Mean = 14.5 (median = 5.5) University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 35

Measures of Central Tendency Median … is not sensitive to extreme scores … use it when you are unable to use the mean because of extreme scores University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 36

Measures of Central Tendency Mode … does not involve any calculation or ordering of data … use it when you have categories (e.g. occupation) University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 37

Assignment No. 3 Find at least one research paper on each of the following Research Strategies.  Surveys  Experiments  Case studies University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 38

Thanks for your attention University Of Malakand | Department of Computer Science | Visual Computing Research Group | Dr. Engr.Sami ur Rahman | 39