310 likes | 498 Views
Academic Research. Dr Kishor Bhanushali kishorkisu@gmail.com M-9898422620. Gujarat University – PhD course work 25 th December 2013. Research. Search and Research Scientific Investigation Systematic Investigation New knowledge Academic activity. Objective of Research.
E N D
Academic Research Dr Kishor Bhanushali kishorkisu@gmail.com M-9898422620 Gujarat University – PhD course work 25th December 2013
Research • Search and Research • Scientific Investigation • Systematic Investigation • New knowledge • Academic activity
Objective of Research • To discover answer to questions through the application of scientific procedure • To find out undiscovered truth • Gaining familiarity with the phenomenon – exploratory research • Study the characteristics of variable – descriptive research • Study the relationship/association – causal research • Test the causal relationship between variable – hypothesis testing
Research Problem…… defined • General statement of the problem • Understanding the nature of problem • Survey of relevant literature • Developing ideas through discussions • Rephrasing research problem • Specific Statement of problem • Scope of problem • Assumptions
Types of Research • Descriptive & Analytical Research • Applied & Fundamental Research • Quantitative & Qualitative Research • Conceptual & Empirical Research • One Time & Longitudinal Research • Field setting & Simulation Research & Laboratory Research
Research Process • Define Research Problem • Review of Literature : Review Concepts and Theories , Review Previous Research Findings • Formulate Hypothesis • Prepare research design • Designing Research : including sampling • Data Collection • Data Analysis: Hypothesis Testing • Interpret and report
Good Research • Clearly defined purpose • Well defined research process • Planned research procedure • Frank reporting • Adequate and relevant analysis • Conclusions based on research findings • Ethical standards
Sampling • Probability and Non Probability Sampling • Purposive sampling • Simple random sampling • Systematic sampling • Stratified sampling • Quota sampling • Cluster sampling • Multi stage sampling • Snowball sampling
Good Sample • Representativeness • Small sampling error • Consistent with financial availability • Controlling systematic biases • Generalization of results
Sampling • Need for sampling • Statistics and parameters • Sampling error • Confidence and significant level • Sampling distribution • Central Limit Theorem • Concept of Standard Error • Estimation
Sample Size Determination • Nature of universe • Number of classes proposed • Nature of study • Type of sampling • Standard of accuracy and acceptable confidence level • Availability of Financial Resources • Availability of human resource
Data Collection • By observation • Through personal interview • Through telephonic interview • By mailing questionnaire • In depth interview • Case study • Focus Group Discussion
Secondary Data • Reliability of data • Suitability of data • Adequacy of data
Data Processing • Editing • Coding • Classification • Tabulation • Percentages
Analysis • Univariate analysis: Measures of central tendency and measure of dispersion • Bivariate analysis : Measure of association and causality • Multivariate analysis : Simultaneous analysis of more than two variables • Index number • Time series
Hypothesis • Research hypothesis is predictive statement , capable of being tested by scientific methods, that relates an independent variables to some dependent variable • Specific • Precise • Testable • Consistent with known facts • Explain the facts
Hypothesis Testing • Null and Alternate Hypothesis • The level of significance • Decision rule or test of hypothesis • Type I and Type II error • Tow tailed and one tailed tests
Procedure for Hypothesis Testing • Making formal Statement • Selecting a significant level • Deciding the distribution to be used • Selecting a random sample and computing appropriate value • Calculating the probability • Comparing probability
Test of Hypothesis • Hypothesis testing helps to decide on the basis of sample data, whether the hypothesis about population is likely to be true of false • Test of hypothesis: (a) Parametric tests or standard test of hypothesis and (b) Non parametric tests or distribution free test of hypothesis
Parametric Test • Parametric test usually assume certain properties of the parent population from which we draw sample • Assumption like observations come from normal population, sample size is large, assumptions about population parameters like mean, variance etc. must hold good before parametric test can be used
Non-parametric tests • In certain situation when the researcher cannot of does not want to make such assumptions. In such situation we use statistical methods for testing hypothesis which are called non-parametric tests because such test do not depends on any assumptions about the parameter of the parent population • Most non-parametric tests assumes only nominal or ordinal data, where as parametric test require measurements equivalent to at least interval scale
Z-test • Z-test is based on the normal probability distribution and used for judging the significance of several statistical measures ,particularly the mean • Z-test is generally used for comparing the mean of sample to some hypothesized mean of population in case of large sample or when the population variance is known • Z-test is also used for judging the significance of difference between means of two independent samples in case of large samples or when population variances are known • Z-test is also used for comparing the sample proportion to a theoretical value of population proportion or judging the difference in proportion of tow independent sample when ‘n’ happens to be very large • Z-test is also used for judging the significance of median, mode, coefficient of correlation and several other measures
t-test • T-test is considered an appropriate for judging the significance of the sample mean or for judging the significance of difference between the means of two samples in case of small samples when population variance is not known • In the case two samples are related, we use paired t-test for judging the significance if the means of differences between the two related samples • It can also be used for judging the significance of the coefficient of simple and partial correlations • T-test is applied only in the case of small samples when population variance is not known
Chi-Square test • Chi-square test is based on chi-square distribution and as a parametric test is used for comparing a sample variance to a theoretical population variance
F-test • F-test is based on F distribution • Used to compare the variance of the two – independent samples • Also used in the context of ANOVA for judging the significance of more than two sample means at one and the same time • Also used for judging the significance of multiple correlation coefficients
Nonparametric Tests • Test of a hypothesis concerning some single value for the given data : One Sample Sign Test • Test of hypothesis concerning no difference among two or more set of data: Two Sample Sing Test, Fisher-Irwin test, Rank Sum Test • Test of hypothesis of a relationship between variables: Rank Correlation Kendall’s Coefficient of Concordance etc.
Cont… • Test of a hypothesis concerning variations in the given data: Kruskal-Wallis Test • Test of randomness of a sample based in the theory of runs: One Sample Run Test • Test of hypothesis to determine if categorical data shows dependence or if two classifications are independent: Chi square Test