DEVELOPING A RESEARCH INSTRUMENT
Pure experimental/Quasi-experimental –to find out the increase in performance after the
experiment. The researcher will develop a “pretest-posttest” with a table of specifications.
The research will use Revised Bloom’s Taxonomy to construct TOS in this case.
Interviews/Focus Groups – design an interview schedule or topic guide. The interview
guide is a list of questions/topic areas that all the interviewers will use for all the
participants/respondents.
Survey – design a questionnaire. It may be answered face-to-face/online.
Steps Required to Design and Administer a Questionnaire
1. Define the objectives/purposes of the study.
2. Identify the target respondents and methods to reach them.
3. Develop the questionnaire.
4. Pilot-testing to establish reliability.
5. Administer the questionnaire.
6. Interpret the results.
DEVELOPING A QUESTIONNAIRE
Each question should contribute to testing one or more hypotheses/ research questions established
in the research design. Questions could be:
1. Open format questions that are without a predetermined set of responses.
2. Closed format questions that take the form of multiple-choice questions.
Points to be considered when writing and interpreting questionnaires:
1. Clarity (question has the same meaning for all respondents)
2. Phrasing (short and simple sentences, only one piece of information at a time, ask precise
questions, in line with respondent’s level of knowledge)
3. Hypothetical questions should be avoided if possible.
DATA COLLECTION AND ANALYSIS PROCEDURES
Quantitative analysis is the technique utilized for analyzing the data gathered.
Quantitative data can be analyzed in a variety of different ways.
What is Quantitative Data?
usually gathered by surveys
deals with percentages, averages, and other mathematical operations
typically gathered from large numbers of respondents
analyzed by statistical methods
answer the what, when, and who questions
How do you get it?
a. Quantitative Secondary Data
Census Data
Knowledge, attitude, and behavior
Agency progress reports
Clinic Data
Evaluation data
b. Quantitative Primary Data
Surveys (can be self-administered, administered face to face or online)
Key Principles of Data Collection
1. Confidentiality (Data Privacy Act of 2012)
The following steps should be taken to protect the confidentiality of key informants:
1. Names, addresses, or other identifying information should not be collected unless for
collecting follow-up information at a later date.
2. If identifying information is collected, no one should have access to it except for key staff
persons in charge of data collection activities.
3. After data have been collected, identifying information should be destroyed as soon as
possible.
2. Informed Consent
3. Cultural Sensitivity
4. Reliability refers to the extent to which collected data is free of unpredictable kinds of error.
5. Validity refers to the ability of your instrument to help produce an accurate, relevant,
representative, and complete description of your community or program.
Things to Remember in Data Collection
1. Gather together information from all sources and observations.
2. Make a backup of all the recordings (audio or video) and other collected materials.
3. Encode all narratives and numerical information into the computer.
4. Perform any statistical treatment.
5. Transcribe (make an exact, word-for-word text version) of the content of audio/video recordings.
6. Organize the data collected.
Quantitative Analysis in Evaluation
Before the research begins the analysis, identify the level of measurement associated with the
quantitative data. The level of measurement can influence the type of analysis the researchers can
use. The descending order of precision, the four different levels of measurement: Nominal, Ordinal,
Interval, and Ratio.
Levels of Measurement
1. Nominal data use numbers for the purpose of identifying names or members of a group or
category.
2. Ordinal data connote ranking or inequalities.
3. Interval scales indicate an actual amount and there is an equal unit of measurement separating
each score, specifically equal intervals.
4. Ratio data are the strongest level of measurement; have all the properties of the other three but
have a meaningful zero that represents the absence of the measured quantity.
