For more information
Call 1-800-351-0222
Call 1-800-351-0222
DATA COLLECTION & ANALYSIS.
Term Paper ID:20989
Essay Subject:
Basic concepts & techniques. Validity, reliability, test-retest, quantity vs. quality, naturalistic research, field work, interpretation, limitations.... More...
20 Pages / 4500 Words
10 sources, 39 Citations,
APA Format
$80.00
More Papers on This Topic
Paper Abstract:
Basic concepts & techniques. Validity, reliability, test-retest, quantity vs. quality, naturalistic research, field work, interpretation, limitations.
Paper Introduction:
Basic Concepts of Data Collection and Analysis
Anastasi (1988) and Welch, and Comer (1983) report that there are several levels of measurement relative to data collection and analysis. These levels include, but are not limited to, nominal, ordinal, interval and ratio; and carry with them important limitations due to the need for differing statistical techniques. The first level, nominal, refers to a means of classifying the data. For this type of data collection and/or analysis, there is no order, in that the units of analysis are merely classified into two or more categories. As an example of nominal data, consider that all white houses would be categorized together, while all red barns would be placed in another category. The primary limitation of nominal data is that there is no order to the given units of .analysis; just classification. Further,
Text of the Paper:
The entire text of the paper is shown below. However, the text is somewhat scrambled. We want to give you as much information as we possibly can about our papers and essays, but we cannot give them away for free. In the text below you will find that while disordered, many of the phrases are essentially intact. From this text you will be able to get a solid sense of the writing style, the concepts addressed, and the sources used in the research paper.
Further, field work is quite difficult toconduct. Since there are numerous behaviors that can be studiedusing systematic observation, the researcher must be careful to eitherlocate or develop a coding system that allows for the accurate analysis ofdata. As a result, he or she may not be able to afford the costs oftelephoning subjects, or mailing questionnaires. Last, the use of personal documentsallows the researcher to view the subject relative to the history of his orher time and how he or she has been influenced by the variety of social,religious, political, and economic currents. Experimental methodology (3rd ed.). For example, when a child isobserved during play in the school yard, he or she may be more prone toholler when the ball is unfairly taken by another child. Second, there is the probability that reactivity will occur,whereby the presence of the observer will influence the behaviors ofsubjects. Or, the researcher can ask subjects how much they like redapples on a scale of one through five, which is far more complete. Methods in behavioral research (4th Ed.). The data analysis is, thus, based on structure,although chronological order can be important. Welch, S., & Comer, J. An example of this would be when the researcher ismeasuring how many workers drink a cocktail during the lunch hour of aworking day. As one example or ordinal data, consider that attitudesabout the use of nuclear plants would be placed in order, ranging from"strongly favor," to "favor," "depends," "do not favor," and to "stronglydo not favor." With the use of ordinal data, there is both classificationand order. Bogdan, R., & Taylor, S. Christensen (1985) continues that, in addition to these, there is thedifficulty of the researchers controlling the myriad extraneous variableswhen field work, or field observation, is conducted. We learn about groups and experiences about which we may know nothing. Somewhat in contrast to Kidder and Judd (1986), Bogdan and Taylor(1975) report that qualitative research consists of participantobservation, which is systematic, and personal documents. This is animportant consideration, since the targeted subjects must be approachedwith the researcher's utilizing language, etc. Using thisapproach to gather qualitative data, the researcher has no direct stake inthe activities of the subjects and, resultantly, are not tied to thesetting. 36).Welch and Comer (1983) continue that ratio data, which is quite similar tointerval data, refers to the presence of absolute and fixed zero points,such as in percentage or proportion measures (e.g., percent urban versuspercent rural, percent female crime rate per 1, population, proportionof green apples to all apples grown in a given geographic region, etc.).The use of ratio data collection and/or analysis allows the researcher toclassify/categorize, order, assume fixed intervals, and state an absolutezero point. Christensen (1985) and Cozby (1989) report that the last criterion iscompleteness, which refers to the items being sufficiently written andplaced to elicit the desired information. The researcher thenutilizes several specific examples that occurred during the field work tosupport his or her interpretations. This is particularlyregarding the address of multiple variables real life behavior, and theshaping of behavior by numerous variables. They note the following aboutqualitative research, as one of the characteristics of naturalisticinquiry. Thus, unnatural treatment is acceptable in naturalisticresearch. The fourth criterionis cost, which refers to the amount of monies the researcher will have toexpend to conduct his or her study. This is not the case for the subjects, however, in that they areintensely involved in the naturalistic setting will tend to engage innatural behaviors, and will be more prone to react or respond to naturalevents within their milieu. For this type of data collection and/oranalysis, there is no order, in that the units of analysis are merelyclassified into two or more categories. quantitative" statistical summaries. 49). Or, the findings and/or conclusions of the study may well beirreparably flawed. This is the same case for the use of field observations. This is not only important becauseof professional and ethical considerations, but also because there arenumerous behaviors that present and cannot be accurately analyzed givenhaphazard methodology. 18).The primary problem with the test-retest method is that the subjects maylearn from taking the first administration of the test, and/or between thetime of the first and second test administrations. In addition, during the data collection, theresearcher may also use key informants to provide "inside" information,interview subjects, and examine related documents regarding the subjects,natural event, and the natural setting. Experimental Psychology (2nd Ed.). NewYork, NY: Prentice Hall. Thus,the issue of completeness relates to the need of the researcher to askquestions revolving around specific dimensions of interest or of theconstruct relative to the research question or hypothesis. Therefore if you apply your measure of verbal ability, for example, to a group of children in March and then apply the same test in May, the results should be the same. Newbury Park,NJ: Sage. Keppel, G. For theconduct of field research, the researcher makes observations in the givennatural setting (i.e., the field) over an extended period of time, using avariety of techniques to collect information or data. This is because field research data collection cannot always beconducted within the desired time frame and in the desired location. It is apparent that for the assessment of personality variables today one cannot rely entirely on standardized tests. Anexample of systematic observation would be when the researcher observes agroup of school children for one hour to determine how many times they willstand on one leg. Because they are precise numerical measures, the most powerful statistical techniques are appropriate to use with them (p. 522). With this level of analysis, the units of analysis are placed in theindicated order. There are, however, several widely acceptedmethods for deriving evidence of validity of measures. Naturalistic inquiry. Many tests that have been reviewed give evidence of the variety of approaches that have been followed in the assessment of personality. Kidder, L., & Judd, C. Anastasi (1988), Bogdan and Taylor (1975) Cozby (1989) andKeppel (1973) all concur that, when the researcher confronts insurmountabledifficulties in the conduct of qualitative or quantitative research, it isacceptable to obtain the services of a professional. Selection of Research Methodology Approach Given that the integration of qualitative data collection and/oranalysis and quantitative data collection and/or analysis is appropriate tothe topic of choice, this will be the selected methodological approach.There are several benefits to be derived from this integration, foremost ofwhich is that the data collected and analyzed will be "richer" in terms ofevidencing multiple realities that do not conveniently fit intoreductionist terms. Yet the best that can be said about most of them is that they are promising experimental techniques suitable for research purposes, or useful instruments when interpreted by a skilled clinician in conjunction with other information about the person. (1988). Further, there is no weight to nominal data. As an example of content validity for areading achievement test, the inclusion of reading, spelling, and writingwould be expected; while the inclusion of typing would not. Cozby (1989) reports that the coding of the datamust fit the topic of the study, so that all behaviors that are relevant tothe construct, research question, and/or hypothesis are captured. Research methods in social relations(5th Ed.). Quantitative methods for publicadministration (2nd Ed.). Psychological testing (6th ed.). Of note is that, while Tunnell and others(Christensen, 1985) conceive of naturalistic research as consisting of thenatural setting, natural behaviors, and the natural event, and Bogdan andTaylor (1975) conceive of naturalistic research as consisting ofobservation and personal documents, still other workers denote severalother characteristics of this type of research. In support of thiscontention, Lincoln and Guba (1985) report that there are 14characteristics of natural inquiry that interact to define qualitativeresearch. It is important to recognize that, especially in the domain of personality, tests cannot do the whole assessment job. (1973) Design and analysis - A researcher's handbook. Second, theresearcher must interpret what has occurred relative to these elements,thereby essentially generating hypotheses that help to explain the data andmake them understandable. Chicago, ILL: Dorsey.----------------------- 23 That is, subjects are more likelyto behave in "real life" ways when they are interacting in naturalsettings. The primary limitation ofnominal data is that there is no order to the given units of .analysis;just classification. (1987). Or, the isolation, delineation anddefinition of a given variable may change with one group of subjects, whilenot for another. This continuous collection of data can be eliminated in some cases,however, should the researcher choose to utilize systematic observation.With this approach, there are still methodological issues that present.First, the cost of systematic observation can be high, particularly whenobservers must be trained and there must be several of them to conduct thestudy. Kidder and Judd (1986) report that third is the element of a naturalevent. The natural event is more prone to usewhen the researcher is conducting a causal or correlational study.Anastasi (1988) adds that natural research can be used to conduct a causalor correlational study without the use of an unnatural event, but there maybe considerable time delays and monetary outlays to facilitate this form ofresearch. Anastasi (1988) and Cozby (1989) note that there are clearly severalbenefits to the use of qualitative data that are not available from the useof quantitative data collection and/or analysis. The methods by which we study people of necessity affects how we view them. Second, the researchermay lack the necessary monies to code and analyze the data without his orher obtaining the services of a professional consultant. 4 ). (1985). This is because ordinaldata do not facilitate intervals. Further, the researcher is afforded the opportunity to learn newknowledge about the subjects under study. Participantobservation refers to the researcher's observing social interaction betweenhim or her and the subjects in the milieu of the latter, and within thebounds of unobtrusiveness and systematic data collection. Naturalisticresearch, thus, possesses several elements that are absent for quantitativedata collection and/or analysis. New YorkNY: MacMillan. The event can bemanipulated, particularly if the researcher is to use an unnaturaltreatment to answer the hypothesis. This refers to an event that naturally occurs within the givennaturalistic setting. There are several specific tests that can be usedto test for reliability of a given measure. Last,researchers are trained in observation and analysis, which allows them tobe more keenly focused on the emergent design and collect and analyze datain light of inductive reasoning to develop grounded theory. As one example of this, considerthat the researcher might ask subjects how they like fruit, which is rathervague and may yield either unintended data or data that is little value tothe researcher in assessing findings and relevance to the research questionor hypothesis. The firstcriterion is validity, which refers to whether or not the measure ismeasuring the target. That is, forexample, when subjects are subjected to the same laboratory conditions fornoise, illumination, and temperature, they will differentially experiencethese variables. (1986). Direct observations of behavior play an essential part in personality appraisal, whether in the clinic, counseling center, classroom, personnel office, or any other context calling for individual evaluations.Thus, the use of qualitative data collection and/or analysis not onlyyields additional information about the subjects under study, but it canalso be used to supplement quantitative data collection and/or analysis. Kidder and Judd (1986) report that field work, or field observation,cannot be used to answer all types of research questions and/or hypotheses. For example, the same childas noted above may only sulk or walk away when another child unfairly takesthe ball away from him or her while in the laboratory setting. Boston,MASS: Allyn and Bacon. These characteristics are: (1) the natural setting (i.e., theresearch is conducted in a natural setting or context of the entity understudy, which means that realities are taken as wholes and are inseparableinto parts); (2) the instrument is human (i.e., the primary data gatheringinstrument is human and, therefore, precludes the use of non-humaninstruments, because the human instrument is capable of differentiatingbetween various interactions); the utilization of knowledge is tacit (i.e.,tacit knowledge is legitimated, and used in addition to propositionalknowledge due to the numerous realities present during human interactions;(4) qualitative methods are used (i.e., these methods are more sensitiveand adaptable to the presentation of numerous shaping realities in thenatural setting; (5) the use of purposive sampling (i.e., the researcheravoids random or representative sampling because the scope of datacollected can be expanded and multiple realities can be discovered); (6)data analysis is inductive (i.e., the researcher collects data and thendevelops the hypothesis/hypotheses); (7) theory is grounded (i.e., thetheory emerges from the data because no a priori theory could possiblyaddress the many realities of the naturalistic setting. As an example of nominal data,consider that all white houses would be categorized together, while all redbarns would be placed in another category. Monterey, CA:Brooks/Cole. Christensen (1985) and Cozby (1989) report that the third criterionis comprehensibility, which refers to whether or not the intended subjectswill be able to comprehend the measures used on the instrument. References Anastasi, A. qualitative methodologies refer to research procedures which produce descriptive data: people's own written or spoken words and observable behavior. Bogdan and Taylor (1975) report that personal documents refer tothose materials that subjects use to reveal using their words, thoughts,and feelings, aspects about their lives within the social setting. The following is noted byAnastasi (1988, p. The second level of analysis is ordinal, which refers to ordereddata. Kidder and Judd (1986) report that observation, which is oftenreferred to as naturalistic research, is generally thought of as beingexemplary of qualitative data collection and/or analysis. New York, NY: John Wiley & Sons. Cozby, (1989) reports that field observation and field work aresometimes referred to as naturalistic observation or research. As a result, thedata analysis may be incomplete or insufficient for the purposes of thestudy. . Forexample, a bathroom weight scale that accurately measures the weight of aperson is valid. Thus, the researcher may well need to replicate thestudy in a more methodologically sound fashion, in order to achieveaccurate findings or conclusions. Of qualitativedata, Cozby reports the following. In addition, the researchercan view the subject within the context of his or her entire life, so thata fuller understanding is developed. This is because there are severaland complex ways in which the researcher as a human instrument can biaseach and every aspect of the study, including the analysis of data,interpretation of data, and the drawing of conclusions. Last, given the massive amount of data that canbe collected using this approach, Kidder and Judd (1986) note that "Theresearcher must sort through the data again and again, develop hypothesesto explain them, and make sure all the data are consistent with thehypothesis (p. The second benefit of using such acoding system is that there is usually training material already published,which will assist and guide the researcher in analyzing and interpretingthe data. Anastasi (1988) and Welch and Comer (1983) report that interval datacollection and/or analysis involves allowing the researcher to make exactdeterminations of the distances between two points on a scale. Myers (1987) reports that, forqualitative research, the issue of the researcher can be even moreimportant than in quantitative research. In contrast tonaturalistic settings, when subjects are, in laboratory settings, they maywell exhibit behaviors that are not akin to "real life" and, resultantly,provide the researcher with flawed findings. , the researcher can say that it is twice as expensive as an itemcosting $25. These kinds of measures give us the most information because they allow us to classify, to order, and to array along a clearly delineated scale. There exists some disagreement relative to the dimensions ofnaturalistic research. This isbecause interval data collection and/or analysis is based upon points on ascale having fixed and equal intervals. First is the element of naturalbehaviors, and second is the element of natural setting; both of which areinseparable when discussing observation. Tunnell (Christensen, 1985) notes, however,that considerable bias can be controlled for when the field work, or fieldobservation, format is used to conduct a study. While the researcher's testing for validity is integralin data collection and/or analysis, there are few hard and fast rules thatfacilitate this activity. As one example ofthis dilemma, again consider the researcher who is measuring how manyworkers drink a cocktail during the lunch hour of a working day. When we reduce people to statistical aggregates, we lose sight of the subjective nature of human behavior. Thus, ordinal data allows the researcher to state thatone item is more than, or less than, another. Qualitative Data Collection and/or Analysis Anastasi (1988), Bogdan and Taylor (1975), Cozby (1989), Kidder andJudd (1986), and Lincoln and Guba (1985) report that, while there arenumerous advantages to the use of quantitative data collection and/oranalysis, there are as well several limitations, as have been noted above.There is one way in which the researcher can balance the conduct ofresearch relying upon quantitative data collection and/or analysis; thatis, he or she can integrate quantitative data collection and/or analysiswith qualitative data collection and/or analysis. Bogdan and Taylor (1975)provide the following definition of, and insight to, qualitative research. Keppel (1973) and Myers (1987) note that, in the experimental design,there is bound to be treatment variability among subjects. Forexample, a bathroom weight scale that showed a person weighing ten poundsmore than he or she actually does each and every time, even when the personis not overweight, would be reliable to the extent that the same resultsare yielded over time. In a test-retest method, March scores are correlated with those in May (p. This type ofnonreactive research generally consists of three dimensions, which arenatural behavior, natural setting, and the natural event. Criteria for Data Collection and/or Measurement Welch and Comer (1987) report that there are several criteria for themeasurement of data whether it is collected or analyzed. (1985). . Further, the researcher must be sureto utilize several confirmations of interpretations. (1983). Cozby (1989) andMyers (1987) note that this is particularly the case regarding the analysisand interpretation of data.Limitations to Naturalistic Research Christensen (1985) reports that there are several limitations tofield work, or field observation. For example, when an item costs$5 . Introduction to qualitativeresearch methods. Kidder and Judd (1986) report that systematic observation, which is aderivative of field observation, is more focused. These tests include, but arenot limited to the test-retest method and the split-half technique. Lincoln and Guba (1985) add that there are several other benefits tobe derived from the use of qualitative research. That is, this type ofobservation uses the targeting of one or more specific behaviors among orby the subjects. However, there is no reason why quantitative data cannot be gathered in a field observation study. This is particularly the case when complex social settings are not atissue for the given study. The useof a previously investigated coding system is preferred, given that it hasbeen validated and found to be reliable. The first level, nominal, refers to ameans of classifying the data. This is because,given naturalistic constraints, the variables may not be easily isolated,delineated and/or defined, particularly given that they may represent anoverlap of several variables. Children who score low in March should continue to score low in May if the test is reliable. Examples ofconfirmations would be an event occurring several times, similarinformation being reported by different subjects, and several differentevents that may occur and can support the same conclusion. This is an important consideration forseveral reasons. That is, with the use of qualitative data collectionand analysis, the data will evidence a variety of information that is notreadily available when only quantitative data collection and analysis areused. As another example, mortality rates, the number ofpatients treated, age, crime rates, years of education and income are allconsidered interval level measures. N elects qualitative methods over quantitative (although not exclusively) because they are more adaptable to dealing with multiple (and less aggregatable) realities; because such methods expose more directly the nature of the transaction between investigator and respondent (or object) and hence make easier an assessment of the extent to which the phenomenon is described in terms of (is biased by) the investigator's own posture; and because qualitative methods are more sensitive to and adaptable to the many mutually shaping influences and value patterns that may be encountered (p. As aresult, the researcher could not present data in relation to weight, orvalue; just classification. The natural event may or may not be linked to thenatural setting and natural behavior of the subject. Theextraneous variables could be: workers having had arguments with theirsupervisors; workers having had arguments with their co-workers; workersfearing an impending poor performance evaluation; or workers having todecide whether or not to remain with the company, in light of impendinglayoffs in their department. Validity refers to the measure (e.g., item,question, behavior, etc.) measuring what it is supposed to measure. The definition of drink could mean one cocktail for somesubjects, several cocktails for other subjects, one wine cocktail for somesubjects, one hard liquor cocktail for other subjects, etc. The primary problem withordinal data, however, is that the researcher is not allowed to assignweights that allow comparison based on intervals. Lincoln and Guba (1985) continue: (8) the design of the research isemergent (i.e., the research design emerges, rather than being preordinate,since enough could not possibly be known in advance about the multiplerealities); (9) the outcomes are negotiated (i.e., the meanings andinterpretations of the observed behaviors are negotiated because they arechiefly drawn from the construction of reality as demonstrated); (1 ) thereporting mode is case study (i.e., the scientific or technical reportcannot allow the researcher to address the description of multiplerealities as are present in naturalistic research); (11) the interpretationis idiographic (i.e., the data is interpreted in light of the particularsof the given naturalistic setting, behaviors and event, rather thannomothetically); (12) the application of the findings is tentative (i.e.the findings are not generalized to a broad group or numerous situations,since realities are multiple and differ in these cases); (13) theboundaries are focus-determined (i.e., the boundaries of the naturalisticinquiry are focused on the emergent variable, such as research problems,evaluands for evaluation, etc.); and (14) there are special criteria fortrustworthiness (i.e., the researcher will most probably find that thestandards of internal and external validity, reliability and objectivitydiffer for the conduct of naturalistic research and will, as a result,construct new standards).Interpreting Qualitative Data Cozby (1989) reports that there are several considerations relativeto the interpretation of field work, or field observation. 51). To these,Anastasi (1988) adds content validity, which refers to the systematicexamination of the test or tool content, so that the researcher candetermine whether or not it covers a representative sample of the behaviordomain that is to be measured. The use ofpersonal documents allow the researcher to study the subjects in ways thatare not directly observable. The lack of random subject selection can also yield findings thatmay not be generalizable to the population from which the sample was drawn;and may of necessity involve considerable standardized error in subjectresponses. Such data can be reported and interpreted along with qualitative data gathered from interviews and direct observations (p. An example of fieldwork is the study of urban villagers, in which the researcher studied theimpact of the subjects residing in a Boston West End slum. Other sources of information are needed to follow up or supplement the leads provided by test scores, to assess traits for which no adequate tests are available, and to obtain criterion data for developing instruments. Myers (1987) and Cozby (1989) report that the coding of qualitativedata must be systematically conducted. We experience what they experience in their daily struggles with their society. Theselevels include, but are not limited to, nominal, ordinal, interval andratio; and carry with them important limitations due to the need fordiffering statistical techniques. By so using the appropriatelanguage, the subjects can better answer the items. When this is not fully possible,the researcher may use a previously investigated coding system and modifyit to the specific topic of study. Statistical techniques are less sophisticatedhere. Thismeans that the researcher may well have to expend considerable time in thedata gathering process, which can be quite expensive and protracted. Lincoln, Y., & Guba, E. First, the researcher may select, for example, too largea sample. . Chicago, ILL: Dorsey. Moreover, they will differentially experience theexperimenter, who may deviate ever so slightly in interacting with onegroup of subjects versus another, or one subject as opposed to another.Keppel (1973) notes: "This is because the experimenter will not beperfectly consistent in the conduct of the experiment, and environmentalfactors such as noise level, illumination, and temperature will not beidentical for each subject" (p. (1989). Given the lack of direct stake on the part ofthe researcher, he or she can devote all of his or her time to observingthe subjects in the setting, As a result, the researcher will be far moresystematic and objective than will the subjects under observation. Welch and Comer (1987)continue that the second method, split-half technique, refers to theresearcher's dividing the items on a test in half on a random basis andcorrelating the responses on both halves. (1987). Myers, A. There arenumerous extraneous variables that could influence how many cocktails, ifany, workers consume during the lunch hour of a working day. Thepersonal document can include such materials as diaries, letters,autobiographies, and transcripts of open-ended interviews. Of interval measures, Welch and Comer(1985) note the following. Welch, S., & Comer, J. First, the goalof the researcher is to describe the naturalistic setting, the naturalevents, and the natural behavior(s) of the subjects. Inaddition, if the researcher makes observations that are not consistent, heor she may have to continuing making them until such time as the dataanalysis is facilitated. The second criterion is reliability, which refers to whether or notthe instrument will yield the same, or similar, results over time. Finally, qualitative methods enable us to explore concepts whose essence is lost in other research approaches (pp. New York, NY: Holt, Rinehart and Winston. (1975). Cozby, P. Basic Concepts of Data Collection and Analysis Anastasi (1988) and Welch, and Comer (1983) report that there are severallevels of measurement relative to data collection and analysis. Quantitative methods for publicadministration. The data in field observation studies are primarily "qualitative" in nature; that is, the data are the descriptions of the observations themselves rather than . 643) regarding observation-based qualitative datacollection and/or analysis. This type of research demands that the researcherimmerse him or herself in the situation, observe every possible thing(e.g., the setting, the patterns of personal relationships, the reactionsof the subjects to events that occur, etc.), and then provide a completeand accurate depiction of these elements to formulate a hypothesis at theend of the research. Christensen, L. This approach, as we see it, directs itself at settings and the individuals within those settings holistically; that is, the subject of the study, be it an organization or an individual, is not reduced to an isolated variable or to an hypothesis, but is viewed instead as part of a whole. Given that this type of observation is less global, theobservations are often quantifiable and are usually collected in light of apreviously-developed hypothesis about the behaviors of the subjects. Foremost is that there is lacking randomselection of subjects, which can negatively influence representation of thesample. Third, there is the issue of reliability, in that inter-observerreliability may differ significantly as to what observers perceived ofthemselves observing (Kidder, & Judd, 1986). Welchand Comer (1987) note that the test-retest method refers to the following. ... 4-5).While there are several types of qualitative data collection and/ oranalysis, for the purposes of this paper, naturalistic observation, orfield observation, will be at focus. If circumstances allow it, data can be gathered on income, family size, education levels, and other easily quantifiable variables. Beyond these, there is the problem of the researcher's notbeing able to sufficiently operationalize the variables. Thus, themajor elements of the behavior to be studied must be defined in advance andadequately and proportionately included in the instrument. MountainView, CA: Mayfield. As a result, they may be less likely to prohibit their behavior,as they would in an artificial setting. The fact that there is order allows for the weighting ofsubject responses. Further, not only can the researcher discoverintimate views of the given social setting (e.g., home, organization,school, etc.) held by the subject, but he or she can also examineassumptions about the reality of the subject. Here, thenatural setting would be the slum, the natural behavior would be the waysin which the subjects resided in the slum, and the natural event would bethe events that occur on a daily basis during the course of the research.The purpose of field research is to allow the researcher to describe andunderstand how subjects in social settings live, work, and experience thenaturalistic setting. This, in turn, allows theresearcher to utilize inductive reasoning, develop a research questionand/or hypothesis at the end of the study, and develop or enhance agrounded theory. that they can understand andthat will not make them feel intimidated. A reliable measure gives the same findings when applied at different times assuming no change in the underlying dimension. Qualitative methods allow us to know people personally and to see them as they are developing their own definitions of the world. Characteristic 4: Qualitative methods. This method avoids the Problemof subject learning, which is encountered when the test-retest method isused by the researcher. These methodsinclude the researcher's using common sense; face validity (i.e., themeasure encompasses the total of elements thought to be a part of theconcept being measured); predictive validity (i.e., an indicator of thebehavior that the researcher is attempting to assess; and, constructvalidity (i.e., all elements of the construct are measured).
If this paper is not what you are looking for, you can search again:
or
We can write a Custom Essay just for you.
Browse Essays by Subject