DEVELOPING RESEARCH PROPOSAL METHODOLOGY LEARNING OBJECTIVE ■ To understand the research design ■ To identify the sampling techniques ■ To identify technique for sample size determination ■ To identify appropriate research instrumentation ■ To identify appropriate data collection procedures ■ To determine appropriate data analysis TABLE OF CONTENT ■ Research design of the study ■ Sampling procedures ■ Sample size determination ■ Instrumentation ■ Data collection procedures ■ Data analysis INTRODUCTION ■ In Methodology, subtopics that need to add in are 1. Introduction 2. Research Design 3. Sampling 4. Instrumentation 5. Data collection procedures 6. Data analysis RESEARCH DESIGN ■ RESEARCH DESIGN refers to the plan, structure, and strategy of research--the blueprint/framework that will guide the research process (data collection, measurement, analysis). ■ To choose the research design, answer: 1 - What is going on (Descriptive research)? 2 - Why is it going on (Experimental research)? ■ Deliver the evidence necessary to answer the research problem as accurately, clearly as possible. RESEARCH DESIGN • THE TEST FOR THE QUALITY OF A STUDY’S RESEARCH DESIGN IS THE STUDY’S CONCLUSION VALIDITY. RESEARCH DESIGN ➢ CONCLUSION VALIDITY refers to the extent of researcher’s ability to draw accurate conclusions from the research. that is, the degree of a study’s: a) INTERNAL VALIDITY— correctness of conclusions regarding the relationships among variables examined • whether the research findings accurately reflect how the research variables are really connected to each other. b) EXTERNAL VALIDITY – generalizability of the findings to the intended/appropriate population/setting • whether appropriate subjects were selected for conducting the study DESCRIPTIVE RESEARCH (SURVEY) ■ Determining the views or practices ■ describe the attitudes, opinions, behaviors, or characteristics ■ Interviews or by administering a questionnaire ■ Limitation: – Do not reveal factors that cause or influence – Information obtained maybe inaccurate or misinterpreted DESCRIPTIVE RESEARCH (SURVEY) ■ Method: – Phone interview ■ Not often used. Mostly used in marketing research – Personal interview ■ Meets with each member of the sample needed – Distributed questionnaire ■ Sample have geographically spread or cannot be brought together as group. ■ By mailing, distributed by hand or having another person to distribute DESCRIPTIVE RESEARCH (CROSS SECTIONAL) ■ Method for testing/observational study that analyzes data from a population, or a representative subset, at a specific point in time—that is, cross-sectional data. – Eg: fitness level for different age Different group from age 6 – 18 had been taken and assess their fitness. – Limitation: cannot always answer longitudinal study DESCRIPTIVE RESEARCH (LONGITUDINAL) ■ The collection of data at more than one point in time over an extended period. ■ Eg: twice a year respondent from age 6 – 18 will be observed their fitness level. ■ May takes many years to complete ■ Difficult to keep track the participant over the many years ■ The result more valuable compare to cross sectional study DESCRIPTIVE RESEARCH (CASE STUDY) ■ Measurement and/or observation of a small group of individual or a person or event in great detail ■ Highly organized and very systematic in collecting the information needed to write the report DESCRIPTIVE RESEARCH (CORRELATIONAL) ■ To determine if a relationship exist between variables ■ Could not establish cause and effect DESCRIPTIVE RESEARCH (OBSERVATION) ■ Observations of people or program ■ Eg: – 5 days a week for 18 weeks a researcher observed a community program and wrote down everything he observed – End of 18 weeks, the researcher wrote a report based on those recorded observations WHAT CAN BE OBSERVED Human behavior or physical action Shoppers movement pattern in a store Verbal behavior Statements made by airline travelers who wait in line Expressive behavior Facial expressions, tone of voice, and other form of body language DESCRIPTIVE RESEARCH (CAUSAL COMPARATIVE) ■ Also call ex post facto ■ Seeks to investigate cause and effect relationships that explain differences that already exist in groups or individuals ■ Eg: investigate the effect of eyesight on motor skill ■ It cannot be manipulated where it is unethical ■ Just look at the different between groups but not a causality EXPERIMENTAL RESEARCH ■ Independent variable is manipulated to observe the effect on a dependent variable ■ The purpose is to determine a cause and effect relationship ■ IV consist of control and treatment group can be manipulated to get the outcome (DV) EXPERIMENTAL RESEARCH (PRE-EXPERIMENTAL) EXPERIMENTAL RESEARCH (TRUE EXPERIMENTAL) ■ The most recommended ■ Good control group ■ Random sampling ■ All threats to internal validity control ■ Example: pre post test and control group – Pre post test: received treatment between pre and post – Control group: receives no treatment – Random sampling perform to divide sample between each groups EXPERIMENTAL RESEARCH (QUASI- EXPERIMENTAL) ■ Much better than pre experimental design ■ Either lack random sampling of participants or random assignment of participants to groups ■ Example: Pre post-test and control group BUT not assigned to groups by using random sampling SUMMARY EXAMPLE EXPERIMENTAL RESEARCH ■ Explain data collection protocol ■ Example >>> PILOT STUDY ■ Use a tool with established reliability ■ Pilot study: – to establish reliability prior to actual data collection – Test reliability and validity of the measurement – Reliability: consistency of the measurement – Validity: test measuring what it is intended to measure PILOT STUDY Cont.. ■ Eg: evaluate reliability of raters – Rater’s responses are less reliable during data collection than during specific testing ■ Questionnaire, report Cronbach’s alpha (more than .80 acceptable) SAMPLING To identify technique for sample population determination SAMPLING PROCEDURE ■ Participants must be appropriate to the methods, techniques, and instrumentation ■ Availability of participant throughout study duration? ■ Number must be large enough to – Ensure reliability of the research results – Permit a reasonable number of participants Three basic questions to consider: 1. Participants appropriate for the research question? 2. participants representative of the population? 3. How many research participants should be used? TECHNICAL SAMPLING TERMS ■ Population - refers to an entire group or aggregate of people having common characteristics ■ Sample – a small subgroup of a population thought to be representative of a population ■ Sampling – the process of selecting a subgroup or sample of the population ■ Sampling Frame – the accessible population or collection of elements from which the sample is actually drawn SAMPLING PROCEDURE ■ Sampling process: – Identify the target population – Identify the accessible population – Determine the desired sample size – Select the specific sampling technique – Implement the sampling plan RANDOM PROCESSES IN RESEARCH ■ Random Selection • Enable generalization of the results to a larger population. ■ Random Assignment • Enable assumption that groups are “equivalent” at the beginning of the study. • This adds control to a study; it has nothing to do with the selection of the sample. RANDOM PROCESSES IN RESEARCH Randomization: – To ensure representativeness of the sample to the population – Unbiased – Equalize characteristics SAMPLE SELECTION METHODS Probability Sampling – Sampling techniques in which probability of selecting known – Utilizes random processes, guarantee the population the each participant is but does not sample is representative of – Every element within the population has a known probability of being selected for the sample – Estimates of sampling error (chance variation may occur) are possible SAMPLE SELECTION METHODS Non Probability Sampling – Samples are not selected at random – Difficult to claim sample is representative of population – Intact groups, volunteers SAMPLE SELECTION METHODS ■ Probability Sampling – Simple random sampling – Stratified random sampling – Systematic sampling – Cluster sampling ■ Non Probability Sampling – Purposive sampling – Convenience sampling SIMPLE RANDOM SAMPLING ■ Equal probability of being selected for the sample. ■ The selection of one member of the population does not affect the chances of any other ■ Bias free: no factor can affect selection ■ Sampling with replacement vs. without replacement ■ Usual procedure: – Fishbowl technique – Table of random numbers – Computer generated sampling STRATIFIED RANDOM SAMPLING ▪ One obtained by separating the population elements into non-overlapping subgroups (strata) and then selecting a simple random sample from each strata. ▪ No sampling unit can appear in more than one strata. ▪ The number of sampling units drawn from each strata depends upon the size of the sampling frame as well as each strata SYSTEMATIC SAMPLING An alternative to simple random sampling in which the sampling units are selected in a series according to some predetermined sequence. CLUSTER SAMPLING ■ A simple random sample in which each sampling unit is a collection (group) or cluster, of elements ■ The sampling unit is the “cluster.” ■ • • • Cluster sampling is an effective when: A good frame listing population elements is not available Removal of elements from cluster unit is not possible Impractical to conduct simple random sampling NONPROBABILITY SAMPLING ■ The probability that an element will be chosen is not known, with the result being that a claim for representativeness of the population cannot be made ■ The researcher’s ability to generalize findings beyond the actual sample is greatly limited ■ But ... it is less expensive and less complicated ■ Convenience sampling and purposive sampling are common examples PURPOSIVE SAMPLING ■ When members of the sample are purposively selected because they possess certain traits that are critical to the study ■ Limited generalizability ■ Example: Selecting elite athletes for a biomechanics study CONVENIENCE SAMPLING ■ Refers to selecting research participants on the basis of being accessible and convenient to the researcher ■ Often involves use of volunteers ■ Limited generalizability ■ Example: Using fellow graduate students as research participants SAMPLE SIZE To identify appropriate sample size SAMPLE SIZE ■ Sample size must representative of the population ■ A well selected and controlled small sample is better than a poorly selected and poorly controlled large sample. ■ Points to consider regarding sample size: – Nature of the study – Statistical considerations – Number of treatment groups – Practical factors IDENTIFY THE SAMPLE SIZE Table by Krejcie and Morgan (1970) 2. Power and effect size (ES) (G power software) – Power: ■ Probability of making a correct rejection of the null hypothesis when it is false ■ Acceptable level of power is more than 80 (Cohen, 1992) – Effect size: ■ The larger different between 2 pop means, the greater ES ■ The smaller variance within 2 population, the greater ES ■ There are the scale for each type of effect size EFFECT SIZE D • 0.2 BE CONSIDERED A 'SMALL' EFFECT SIZE, • 0.5 REPRESENTS A 'MEDIUM' EFFECT SIZE • 0.8 A 'LARGE' EFFECT SIZE EFFECT SIZE S : pooled standard deviation INSTRUMENTATION Instrumentation is the course of action (the process of developing, testing, and using the device). INSTRUMENTATION ■ The published instruments (device) – cite manufacturer’s specification or – State the validity and reliability of the instrument ■ Main concern: – Establish the instrumentation used in the study was appropriate for the particular research problem – The process of using the device ■ If the instrument is already established, the proposal should include its name and reported reliability and validity ■ List out every variable that will be measured and instrument that will be used to measured the variable DATA COLLECTION PROCEDURE EXAMPLE: Ethic approval Ask permission to do research Give briefing to the sample about the study and questionnaire Distribute questionnaire to the sample Collect the questionnaire DATA ANALYSIS • Describes the methods of handling and presenting data and outlines the statistical procedures to be used. • Data presented as mean ± SD (SE) • 2 types: • Descriptive statistics • Inferential statistics DATA ANALYSIS • Set the significant level (0.5, 0.05, 0.01) DATA ANALYSIS ■ 2 types: – Descriptive statistics – Inferential statistics Hypothesis There is no significant difference on body weight between endurance and strength training among FSR students Inferential statistics IV : strength training endurance training DV: body weight ▪ Set the significant level (0.5, 0.05, 0.01) Paired sample t-tests METHODOLOGY 3.1 3.2 Introduction Research design - Name of the design - This proposed study will use the randomized pretest posttest control group design to test the hypothesis. Justification - This design was chosen because ..... IV & DV Research notation/ paradigm R 01 X 03 R 02 04 - Figure 1: ...... 3.3 Population/ sample/participants/ sampling techniques 3.3.1 Population 3.3.2 Sample/participants, - Inclusion criteria - Exclusion criteria - Sampling technique 3.3.4 Sample size - calculation Krejchie & Morgan table - G-power calculation (show the table/graph) 3.4 Treatment (for experimental/quasi-experimental design only) 3.5 Instrumentation 3.5.1 Questionnaire (identify the questionnaire used) (cite)/domain/score 3.5.2 What do you use to measure IV and DV 3.5.2.1 Describe the model of the machine used/how to conduct 3.6 Data collection procedure - Include also flowchart 3.7 Data analysis THANKS! ALinoby_19