Practical Research 2 PDF

CHAPTER 3 PRACTICAL RESEARCH 2 RESEARCH DESIGN PRACTICAL RESEARCH 2 TYPES OF QUANTITATIVE RESEARCH Quantitative Research EXPERIMENTAL RESEARCH NON-EXPERIMENTAL It allows the researcher to RESEARCH control the situation. Observes the phenomena...

CHAPTER 3 PRACTICAL RESEARCH 2 RESEARCH DESIGN PRACTICAL RESEARCH 2 TYPES OF QUANTITATIVE RESEARCH Quantitative Research EXPERIMENTAL RESEARCH NON-EXPERIMENTAL It allows the researcher to RESEARCH control the situation. Observes the phenomena It identify the cause and No manipulation or effect relationship. controlling of the variables Experimental Research A method wherein the conditions are controlled; so that 1 or more IV can be manipulated to test a hypothesis. It evaluates causal relationships among variables. Whether its is eliminated or controlled. TYPES OF QUANTITATIVE RESEARCH Experimental Research True Experimental Quasi-Experimental Pre-Experimental ❑Non-equivalent ❑One-shot case ❑Pretest design (Comparison) group ❑Posttest- study design ❑One group Pretest design ❑Pretest-Posttest pretest and ❑Solomon-Four Design posttest design Group Design ❑Interrupted Time Series Design ❑Combination Design TRUE-EXPERIMENTAL RESEARCH ❖Aims to determine causal relationships among variables ❖Involves random selection of participants ❖Used to test a hypothesis ❖Has control group and test group ❖May or may not have a pretest ❖Considered as the most accurate type of experimental research TYPES OF TRUE- EXPERIMENTAL RESEARCH TYPES OF TRUE-EXPERIMENTAL RESEARCH 1. POST TEST ONLY CONTROL GROUP ❖Subjects are randomly selected and assigned to groups ❖Treatments/Intervention is given to the experimental/test group, afterwards, both groups are tested and conclusion is drawn from comparison of results. TYPES OF TRUE-EXPERIMENTAL RESEARCH 2. PRETEST-POST TEST ONLY CONTROL GROUP ❖Subjects are randomly selected and assigned to groups ❖Both groups are tested prior to intervention/treatment. ❖Both groups are tested after the treatment to determine the degree of changes in each group. TYPES OF TRUE-EXPERIMENTAL RESEARCH 3. SOLOMON- FOUR GROUP DESIGN ❖Considered as a combination of the 2 true experimental research design. ❖Subjects are randomly selected and assigned to Four Groups. ❖Conducts to verify the effectiveness of a given treatment/intervention QUASI-EXPERIMENTAL RESEARCH ❖Quasi means partial or half ❖Aims to determine causal relationships among variables ❖Bears resemblance to the true experimental research, but not same. ⮚No random selection of participants ⮚Involves pretest and post test ⮚Control group is optional (dependent on the design) TYPES OF QUASI- EXPERIMENTAL RESEARCH TYPES OF QUASI-EXPERIMENTAL RESEARCH 1. NON-EQUIVALENCE (COMPARISON) GROUP DESIGN ❖Involves testing two groups ❖Considering as ‘non-equivalence’ since numbers of groups involved are not randomly assigned. TYPES OF QUASI-EXPERIMENTAL RESEARCH 2. PRETEST-POSTTEST DESIGN ❖Tests the dependent variable before the treatment/intervention is given and after the treatment has been given. TYPES OF QUASI-EXPERIMENTAL RESEARCH 3. INTERRUPTED TIME SERIES DESIGN ❖A variant of Pretest-Post test design. ❖Involves a series of testing/measuring at given intervals before and after an intervention has been given. TYPES OF QUASI-EXPERIMENTAL RESEARCH 4. COMBINATION DESIGN ❖Combined the elements of both non- equivalence design and pretest-post test design. ❖Involves having test group and a control group in conducting the research PRE-EXPERIMENTAL RESEARCH ❖Lack of Random Assignment: Participants are not randomly assigned to different conditions or groups. ❖No Control Group: Often, there is no comparison or control group against which to measure the effect of the intervention. ❖Limited Internal Validity: Due to the lack of random assignment and control groups, these designs have limited ability to establish causal relationships. TYPES OF PRE- EXPERIMENTAL RESEARCH One-Shot Case Study A single group is exposed to a treatment and then measured on the dependent variable. One-Shot Case Study For example: A school implements a new reading program for a group of students. After completing the program, the students take a reading comprehension test. The researcher measures their reading comprehension scores to evaluate the program's effectiveness, but there is no pretest or comparison group to assess changes relative to other factors. One-Group Pretest-Posttest Design A single group is measured on the dependent variable before and after the treatment. One-Group Pretest-Posttest Design For example: A company wants to improve employee productivity by introducing a new software tool. Employees' productivity levels are measured before the software is introduced (pretest). After using the software for a month, their productivity levels are measured again (posttest). The difference in productivity scores is used to evaluate the software's impact. Static-Group Comparison Involves a treatment group and a non-equivalent comparison group, but no pretest. Static-Group Comparison For example: A health clinic wants to test a new diet program. They select one group of patients to follow the new diet (treatment group) and another group to continue their usual diet (comparison group). After a month, both groups are measured for changes in weight. The difference in weight loss between the two groups is used to evaluate the diet program. NON-EXPERIMENTAL RESEARCH ❖research that lacks the manipulation of an independent variable, random assignment of participants to conditions or orders of conditions, or both. ❖is based on the observation of phenomena in their natural environment. TYPES OF QUANTITATIVE RESEARCH Non-Experimental Research SURVEY CORRELATIONAL EX-POST FACTO STUDIES SURVEY RESEARCH ❖It intends to provide a quantitative or numeric descriptions of trends, attitudes or opinions of a population by studying a sample of that population (Creswell, 2003). Example: Public Opinion on Climate Change and Environmental Policies: A Nationwide Survey CORRELATIONAL RESEARCH ❖Considered non-experimental because it focuses on the statistical relationship between two variables but does not include the manipulation of an independent variable. Example: Technology Use and Sleep Patterns: A Correlational Study in Adolescents EX-POST FACTO RESEARCH ❖aka Causal-Comparative Research ❖Used to investigate causal relationships. ❖It examine one or more conditions could possibly caused subsequent differences in groups of subjects. ❖It identifies differences between groups have results in an observed difference in the I.V. EX-POST FACTO RESEARCH Example: Maternal Smoking During Pregnancy and Its Effects on Child Development: An Ex-Post Facto Examination Experimental vs. Non-Experimental Manipulation of the Control Random Research Independent Variable/s (Group) Assignment (TRUE) EXPERIMENTAL √ √ √ QUASI-EXPERIMENTAL √ √ X PRE-EXPERIMENTAL √ X X NON-EXPERIMENTAL X X X SAMPLING PROCEDURE PRACTICAL RESEARCH 2- LESSON 2-2ND QRT LEARNING OBJECTIVES: At the end of this lesson, the learners should be able to: 1. explain the meaning of sampling; 2. compare and contrast sampling techniques; and 3. adopt the most appropriate sampling technique for a chosen research topic. SAMPLE SIZE DETERMINATION A sample (n) is a selection of respondents for a research study to represent the total population (N). You can use: 1. Slovin’s Formula 2. Raosoft 3. Power Analysis SAMPLE SIZE DETERMINATION Slovin’s Formula where: n- sample size N- total population e- margin of error SAMPLE SIZE DETERMINATION Slovin’s Formula Example: A researcher wants to conduct a survey. If the population of a big university is 35, 000, find the sample size if the margin of error is 5%. SAMPLE SIZE DETERMINATION Slovin’s Formula Example: A researcher wants to conduct a survey. If the population of a big university is 35, 000, find the sample size if the margin of error is 5%. https://www.statology.org/ slovins-formula-calculator/ SAMPLE SIZE DETERMINATION Raosoft is a software tool commonly used for determining sample size in survey research and for calculating various statistics related to sample size and survey design. SAMPLE SIZE DETERMINATION Power Analysis If your analysis plan comprises detecting a significant association between variables of interest, a power analysis can help you estimate a target sample size. Many free online and commercially available power analysis calculators are available (e.g., G*Power; Faul et al., 2007; Faul et al., 2009). SAMPLE SIZE DETERMINATION Power Analysis (Parameters) 1. Effect Size (d): Estimate the magnitude of the effect you expect to find. This can be based on prior research, pilot studies, or a theoretical framework. Common benchmarks are small (0.2), medium (0.5), and large (0.8) effect sizes. 2. Significance Level (1-α): The probability of rejecting the null hypothesis when it is true (Type I error). This is typically set at 0.05. 3. Power (1-β): The probability of correctly rejecting the null hypothesis when it is false. Commonly set at 0.80 or 80%, meaning you have an 80% chance of detecting an effect if it exists. 4. Type of Test: Decide whether you will use a one-tailed or two- tailed test. SAMPLE SIZE DETERMINATION Example: You want to compare the means of two independent groups using a t-test. You expect a medium effect size (Cohen's d = 0.5), and you want a power of 0.80 with a significance level of 0.05. Find the critical value (1-α/2) & (1-β) SAMPLE PROCEDURE Sampling is a formal process of choosing the correct subgroup called a sample from a population to participate in a research study. FACTORS AFFECTING SAMPLE SELECTION 1. Sample Size 2. Sampling Technique a. Probability Sampling b. Non-Probability Sampling 3. Heterogeneity of Population 4. Statistical Technique 5. Time and Cost (Tuckman & Engel, 2012; Babbie, 2013; Edward, 2013) SAMPLE METHODS 1. Probability Sampling- is a sampling method where you base your selection of respondents on pure chance (randomly). a. Simple Random Sampling b. Systematic Sampling c. Stratified Sampling d. Cluster Sampling (Tuckman & Engel, 2012; Babbie, 2013; Edward, 2013) PROBABILITY SAMPLING a. Simple Random Sampling- choosing of respondents based on pure chance. b. Systematic Sampling - picking out from the list every nth member sampling frame until the completion of the desired total number of respondents. (Tuckman & Engel, 2012; Babbie, 2013; Edward, 2013) PROBABILITY SAMPLING c. Stratified Sampling – choosing a sample that will later on subdivided into strata, subgroups, or sampling frame until the completion of desired total number of respondents. d. Cluster Sampling – selecting respondents in clusters, rather than in separate individuals such as choosing 5 classes of 40 students each from a whole population of 5,000 students. (Tuckman & Engel, 2012; Babbie, 2013; Edward, 2013) SAMPLE METHODS 1. Non-Probability Sampling- is a sampling method where your samples are not chosen randomly, but purposefully. a. Quota Sampling b. Voluntary Sampling c. Purposive Sampling d. Availability Sampling e. Snowball Sampling (Tuckman & Engel, 2012; Babbie, 2013; Edward, 2013) NON-PROBABILITY SAMPLING a. Quota Sampling –choosing specific samples that you know correspond to the population in terms of one, two, or more characteristics. b. Voluntary Sampling – selecting people who are very much willing to participate as respondents in the research projects. (Tuckman & Engel, 2012; Babbie, 2013; Edward, 2013) NON-PROBABILITY SAMPLING c. Purposive Sampling –choosing respondents whom you have judged as people with good background knowledge about the research. d. Availability Sampling (Convenience/Haphazard Sampling) – picking out people who are easy to find or locate and willing to establish contact with you. (Tuckman & Engel, 2012; Babbie, 2013; Edward, 2013) NON-PROBABILITY SAMPLING e. Snowball Sampling –researcher identifies key informant about the research of interest and then refers another respondents who can participate in the study. RANDOM SAMPLING vis-à-vis STATISTICAL METHODS The most preferred sampling technique in qualitative or quantitative research is random sampling. Simple Random, Stratified, and Systematic Samplings are depended greatly on statistics for sample accuracy. STEPS IN CONDUCTING STRATIFIED SAMPLING: 1. Decide on the size of the sample. 2. Divide the sample into sub-sets or sub-samples, with the sub-samples having the same aggregate number as that of the sample they came from. 3. Select the appropriate sub-sample randomly from each sub-group or stratum. 4. Put together the sub-sample results to get the total number of the overall sample. ADVANTAGES AND DISADVANTAGES OF BASIC SAMPLING TECHNIQUES ADVANTAGES AND DISADVANTAGES OF BASIC SAMPLING TECHNIQUES References Creswell, J. W. (2014). Research Design: Qualitative, Quantitative, and Mixed Methods Approaches (4th ed.). Sage Publications. Clemente, Richard, Julaton, Aaron, & Orleans, Antriman. (2016). Research in Daily Life 1. SIBS Publishing, Inc., Quezon City, Philippines. Creswell, J. (2015). Educational research: Planning, conducting, and evaluating quantitative and qualitative research (5th ed.). Pearson Education, Inc. Cristobal, Amadeo, & Cristobal, Maura. (2017). Practical Research 1 for Senior High School. C&E Publishing, Inc. Quezon City, Philippines. Minichiello, Victor. (1990). In-depth Interviewin: Researching People. Longman Cheshire. Australia Prieto, Nelia, Naval, Victoria, & Carey, Teresita. (2017). Practical Research 2. Lorimar Publishing, Inc. Quezon City, Philippines Sihag, Prashant. (2019). “Scientific Method for Data Analysis”. Medium. Retrieved from: https://medium.com/analytics-vidhya/scientific-method-for-data- analysis- 41798626371a