Data Collection Process Essay
Data Collection Process
Identify and briefly explain the quantitative data collection.
Data collection is often costliest and the most time consuming portion of study.Quantitative research is an approach for testing objective theories by examining the relationship among variables.The data collection method in quantitative research is in structured manner which involves decent planning of data collection.
The planning of data collection process involves certain steps as follows:
Identification of data needs.
Selecting types of measures of the variables.
Selection and development of instrument.
Pretesting of data collection.
Development of data collection forms and procedures.
1. Identification of data needs .
This is first step of planning data collection that involves identifying the types of data needed for study.In quantitative researcher need data for : testing hypothesis describing sample characteristics controlling confounding variables.
Analysis potential biases understanding subgroup effect interpreting results assessing treatment fidelity obtaining administrative information
2.Selecting types of measures of the variables.
After identifying of data needs the selection of types of data collection method is the next step.Data collection method is selected based on not only conceptual or theoretical definition but also other different factors such as the need or goal of research,,quality of instrument validity & reliability,ethical consideration,cost constraints,availability of human resource to help in data collection.I t can be various e.g self report,observations,physiologic or records.The methods can be used in
combined form in single study as well.
3.Selection and development of instrument.
The third step after selection of potential instruments for data collection.The existing instruments should be assessed considerations various factors to assess capability of the selected instrument to yield high quality data corresponding conceptual stability.The other factors affecting selection of an instrument includes ; Resource constraints e.g instrument use and scoring,data collectors salary,subject compensation Availability and familiarity ; e.g researcher expertise , equipment etc Population appropriateness; reading level and writing ability,cultural,ethnic origin gender biased,language issues,need of translators. Norms and comparability;e.g.established norms for instrument – provide comparison group ,Replication – use same instruments Administration issues; e.g expertise required of data collector for administration of instrument ,constraints of where, when, and how instrument administrated . Reputation of instrument from people who used it .
4.Pretesting of data collection
The pretest of both the existing or new instruments is important to assess the effectiveness,length,clarity and overall adequacy to variability of data.Multiple available instruments pretested before actual data collection performed so that it can be evaluated and refined as needed by identifying possible areas problematic for subjects misinterpretation of questions by participants.
offensive or objectionable or sensible questions for participants.e.g offensive terminology the need for training for data collectors the need of assessment the potential biases among participants based on various group for instance,age,gender or economic status. pretesting stand-alone methodological study to determine how much time it takes to administer the entire instrument package whether participants find it burdensome. identifying parts of the instrument package that are difficult for pretest subjects to read or understand or that may have been misinterpreted by them Identifying any instruments or questions that participants find objectionable or offensive Determining whether the sequencing of instruments is sensible Determining needs for training data collection staff
Determining if the measures yield data with sufficient variability.
5. Development of data collection forms and procedures.
The final step of planning data collection is the development of required forms which will be used in study as needed such as screening forms to assess eligibility to participants,informed consents,record of attempted contacts with participants and logs for recording the receipt data etc. Data collection protocols:Data collection protocols spell out the procedures to be used in data collection Conditions that must be met for collecting the data Specific procedures for collecting the data, including requirements for sequencing instruments and recording information Standard information to provide participants who ask routine questions about the study. Procedures to follow in the event that a participant becomes distraught or disoriented, or for any other reason cannot complete the data collection.
Alternatives methods of data collection:
Alternatives methods of data collection Face to face Telephone Mail CATI computer assisted telephone interviewing . CAPI computer assisted personal interviewing TDE Touchstone data entry OCR/ICR Optical/intelligent character recognition FAX Disk by Mail E-mail Web Computerized Self Administered Questionnaires IVR Interactive voice response SAQ Self administered questionnaire
Walkman Text CASI Audio CASI Video CASI
6. Implement data collection plan
An interview is a data-collection technique that involves oral questioning of respondents, either individually or as a group. Answers to the questions posed during an interview can be recorded by writing them down (either during the interview itself or immediately after the interview) or by tape-recording the responses, or by a combination of both. Interviews can be conducted with varying degrees of flexibility.it is verbal communication between research and subject; includes questionnaires ,open-ended questions , closed-ended questions.
Unstructured interview -one subject’s world view; open-ended questions with probes and prompting; qualitative; audiotapes. Semi-structured interview -one subject; one list of topics or questions for discussion with additional probes, aka topic guide; uses both open and close-ended questions; tape. Structured interview – one subject; specific questions asked in consistent order using the same words each time; no variation from questions and no explanation of unclear questions. Focus group interview – 5 to 15 subjects in a group; interviewer/moderator asks open-ended questions; efficient yet some individuals inhibited by others in the group. Questionnaires is printed self-report form designed to elicit information that can be obtained via a written response. And a primary survey device to obtain information about the subjects’ attributes, facts about events or situations, attitudes, beliefs, and opinions.It can be Can be mailed or distributed directly to a large number of subjects and picked up later.the degree of structure can vary from open-ended questions to closed-ended, fix-alternative questions.A questionnaire is a standardized set of questions administered to the respondents in a survey Respondents are required to interpret a pre established set of questions and to supply the information these questions seek.
Open-ended questions allow subject to respond in their own words in narrative fashion,whereas closed ended questions offer response options,from which respond must choose the one that most closely matches the appropriate answer and fix-alternative questions may range from a simple yes/no question to complex expression of opinion or behavior. Open-ended questions that call for numerical answers Now, thinking about your physical health, which includes physical illness and injury, for how many days during the past 30 was your physical health not good? Note that: Open-ended items yield more exact information than closed items. Closed-ended questions Closed questions with ordered response scales Would you say that in general your health is: Excellent Very good Good Fair Poor The interviewer is instructed to “please read” the answer categories, but not the number attached to them. Types of closed-ended questions
Dichotomous questions contains two opposing choices; yes/no or true/false or male/female,it is especially appropriate for gathering factual information. Multiple choice questions contains more than two choices from which subject selects one option that allows respondents to express range of views and researcher can get more information. Rank-order questions asks subject places options in rank or order of importance based on tool directions such as most to least important.It can be misunderstood so the examples or proper instruction may be needed.People value different things in life. Below is a list of things that many people value. Please indicate their order of importance to you by placing a “1” beside the most important, “2” beside the second-most important, and so on. ____ Career achievement/work ____ Family relationships ____ Friendships, social interactions ____ Health ____ Money ____ Religion.
Forced-choice questions involves two polar alternative statements; similar to dichotomous, but in the form of sentences rather than single words. Rating questions are typically on bipolar scale,with end points specifying opposite extremes on a continuum,the subjects are asked to evaluate something along an ordered dimension, Checklists is a two dimensional arrangement in which a series of question is listed along one dimension usually vertically and response alternatives are listed along the order.It is very easy to understand but difficult to read orally.Therefore,it is used in self administered questionnaires because of its efficiency. Other sources of data collections are life history -such as anthropological; chronological changes; sequence of events ,critical incident in which subject describes an event (incident) from his/her viewpoint r/t research topic and diary includes subject’s daily log describing own experiences r/t the research topic Cognitive and Neuropsychological tests measures degree to which individuals possess or are characterized by target attributes,e.g intelligence tests,MMSE, standford-Binet I.Q.test. Multiple item self-report tools
Most nursing studies use self-report techniques for data collection. Data obtained by directly questioning people about the phenomena of interest. This is strong with respect to their directness and versatility. Visual analogue scales are used to represent subjective experience; pain, dyspnea, depression; researcher measures line at intersection to determine numerical value of pain, depression, etc.subject draws line across scale of 100 mm in length. Likert scale consists of several declarative items that express a view point on a topic.It indicates the degree of agreement or disagreement with expressed by the statement.
Total score is computed by summing item scores, each of which is scored for the intensity and direction of favor-ability. Semantic differential scales asks respondents to rate concepts on series of bipolar adjectives such as good or bad,effective or ineffective, important or unimportant semantic differential scales are flexible and easy to construct.It indicates reaction toward a phenomenon by measuring evaluative,activity and potency of the statement. Q Sort This instrument includes one hundred cards, each displaying a descriptive personality statement that observers arrange according to how well they describe a person. It measures personality assessment of adults and other ratings of personality. Vignettes is a brief descriptions of event the respondent are asked to react to events in order to assess respondents perceptions, hypothetical behaviors and decisions.These are an economical means of eliciting information about hoe people might behave in situation that would be difficult to observe in daily life.I t would corporate into questionnaires,and are, therefore,an inexpensive data collection strategy. Questionnaires Versus Interview.
While developing data collection plan,researcher need to decide whether to collect data through interviews or questionnaires. Both has benefits and drawbacks. Questionnaires | Interviews |
Questionnaires are less costly and time-consuming Less costly Less time-consuming Anonymity No risk of interviewer bias Group administration: Most economical Mail: low response rate Web-based survey | Higher response rate Wider variety of people Richer data Data quality: Interpersonal skills Ease and build rapport Probing |
Designing structured self report instrument.
Developing Structured Self-Report Instruments includes
Related constructs should be clustered into separate modules or areas of questioning Sequencing modules Introductory comments about the nature and purpose of the study. Discuss critically with experts people who are knowledgeable about questionnaire construction reviewed by someone capable of detecting technical problems, such as spelling mistakes, grammatical errors, and so forth Revised version of the instrument can be pretested.
Tips for Wording Questions
Clarity Ability of respondents to give information
Bias Sensitive information
State questions in the affirmative
Avoid long sentences or phrases, and avoid technical terms Avoid “double-barreled” questions that contain two distinct ideas. Do not assume that respondents will be aware of, or informed about, issues or questions in which you are interested Avoid leading questions that suggest a particular kind of answer State a range of alternatives within the question itself when possible For questions that deal with controversial opinions or socially unacceptable behavior (e.g., excessive drinking habits, noncompliance with medical instructions), closed-ended questions may be preferred. Impersonal wording of a question is some times useful in minimizing embarrassment and encouraging honesty. Researchers concerned about possible respondent confusion or misinterpretation sometimes conduct cognitive questioning during the pretest.
Preparing Response Alternatives:
Responses options should cover all significant alternatives. Alternatives should be mutually exclusive There should be an underlying rationale for ordering alternatives Response alternatives should not be too lengthy.
Formatting an Instrument:
The researcher should consider following ;
Not try to compress too many questions into too small a space Set off the response options from the question or stem itself . Give special care to formatting filter questions
Avoid forcing all respondents to go through inapplicable questions in an SAQ.
Administering structured self report instrument.
Self-administered questionnaire is a data collection tool in which written questions are presented that are to be answered by the respondents in written form. Sending questionnaires by mail with clear instructions on how to answer the questions and asking for mailed responses; Gathering all or part of the respondents in one place at one time, giving oral or written instructions, and letting the respondents fill out the questionnaires; Hand-delivering questionnaires to respondents and collecting them later. Collecting questionnaires data via internet is an economical means of distributing questionnaire web-based surveys. Collecting Interview Data and follow up reminders are effective in achieving rates for mailed and internet questionnaires.
Evaluating structures self report.
Even though self reports are a powerful data collection method,they are susceptible to the risk of various response biases.the common response set biases are Social desirability refers to tendency of some individuals to misrepresent themselves giving answers that are congruent with prevailing social values. Extreme response are a bias reflecting consistent selection of extreme alternatives. Acquiescence falls under “yea-sayer” who have been found to agree with statement regardless of content.”nay-sayaer” to disagree with statement independently of question content.
Structured Participant observation
It is used to document specific behaviors,actions and events.It involves using formal instrument and protocols that indicate what to observe,how long to observe and how to record information.Observational methods can vary in degree of structure Observational research is particularly well suited to nursing ethical difficulties distorted behavior observer biases Emotions, prejudices, attitudes, and values of observers Personal interest and commitment Anticipation of what is to be observed Hasty decisions before adequate information.
Methods of Recording Structures observation.
It can be either a checklist of a rating scale.It often involves constructing a category system to classify observed phenomena.A category system represents an attempt to designate in a system fashion the qualitative behaviors and events transpiring i the observational setting.It used to construct checklist which is the instrument observers use to record observed phenomena.With exhaustive checklists,the observers’ task is to place all behaviors in only one category for each element.Element refers either to a unit of behavior,such as a sentence in a conversion or to a time interval. The 8 categories are eight categories: (1) seeks information, (2)gives information, (3) describes problem, (4) offers suggestion, (5) opposes suggestion, (6) supports suggestion, (7) summarizes, and (8) miscellaneous.
Rating Scales observers to rate a phenomenon along a descriptive continuum that is typically bipolar. The ratings are quantified for subsequent statistical analysis.
Sampling for Structured Observations:
Observational sampling concerns the selection of behavior to be observed,not the selection of participant. Time sampling involves the selection of the time period during which observations will occur.The time interval may be selected systematically or at random. Event sampling uses integral behaviors sets or events for observation.Event sampling requires that the investigator either have knowledge about the occurrence of events or be in a position to
wait for their occurrence.
Wide variety of technical aids in observation is available for recording behaviors and events for analysis and categorizing at later time possible.such as auditory recording,videotaping,video recording etc.
Structured observations by Non research observations includes asking people not connected with the research to provide structured data,based on observations of characteristics or behavior of others.
Evaluation of structured observation,
Although it is an important data collection method for recording aspects of people’s behaviors when they are not capable to describing them reliably in self report,it can be biased from those being observed due to their awareness of observation. The most common observer biases found are
Enhancement of contrast effect; observer distort observations in the direction of dividing content into clear cut entities. Central tendency occurs when events are distorted toward a middle ground. Assimilatory biases,observer distort observations in the direction of identity with previous inputs. Halo effect it the tendency of observers to be influenced by one characteristic in judging other ,unrelated characteristics. Error of leniency is the tendency for observers to rate everything positively,whereas Error of severity is the contrasting tendency to rate too harshly.
Biophysiologic Measures are used in clinical studies both for creating independent variables and for measurement of outcomes.The purpose of collecting biophysic data are ; Physiologic and physical variables strength objectivity. Relative precision and Sensitivity
Weakness Technical failures.
Basic physiologic processes
Physiologic outcomes of nursing care Evaluations of nursing interventions Product assessments
Measurement and diagnosis improvement S studies of physiologic correlates,
Types of Bio physiologic Measures
In vivo measurements are performed directly in or on living organism.e.g measurement of oxygen saturation,blood pressure and body temperature. An in vitro measure is performed outside the organism’s body,as in case of measuring serum potassium level in blood. Some considerations for physiologic measurements to keep in mind while selecting biophysiologic measures. Will measure yield good information?
Does it fit research questions/hypothesis and variables of study? What other methods of measurement could be used? Invasive & noninvasive requirement of permission to use equipment.
Equipment and supply costs; reliability of equipment and complexity of operation . Training of personnel is required or not?
The advantage is biophysic measures are accurate and precise.it is objective and provide valid measurements of targeted variables.whereas,the disadvantages are it may be expensive or low or nonexistent.The measuring tool may affect the variables it is attempting to measure.It high risk of damaging cells by the use of high energy concentration.
Implementing a data collection plan
The quality of data is affected by not only by plan of data collection but also by the way the implementation of a plan of data collection .In order to ensure collection of quality data by other than researcher such as in larger studies. The selection of researcher should be done very carefully and they must be trained.The researcher should have following Experience
Background similar to subject
Unremarkable appearance – dress, make-up, jewelry
Personality – pleasant, sociable, non-judgmental, non-threatening Available to collect data for the entire study period
Training data collectors
Includes general principles of data collection & specifics for study . Data collection training manual .
Review manual, forms, and procedures
Demonstrate data collection and return demonstration with videotape . Periodic observation of data collection to verify procedures are followed . Critiquing structured methods of data collection.
In order to achieve the expected quality of data,every decision taken by researcher should be critiqued in evaluating the study’s evidence to the extent possible using specific guidelines.