TEXT SIZE:Increase Text SizeDecrease Text SizePRINT:Print This PageSHARE:bookmark and share
Accounts on the OBSSR e-Learning site enable you to save notes as you read the contents of the site.  Notes are a way for you to save a spot on the site with your own comments and title applied to it.  Think of it as putting a sticky note paper in a book to remember a place and leave a thought or two of your own for later reference.

Examples

This page provides links to all the examples that appear in the book.  Click a chapter title to view the examples in that chapter.
Show All

Examples By Chapter
'Science' in the Social Sciences

Example 1


I was born and raised in Liverpool, England. The personal significance (in this sense of ‘meaning’) of ‘Liverpool’ is wholly idiosyncratic to me (but also perhaps to many others): it would encompass having visited the Cavern Club where the Beatles first performed, it would encompass the arrival of African-American sailors at the docks holding vinyl records of Stax and Motown artists which they would sell to local record retailers, and so forth.

However, what ‘Liverpool’ means simpliciter is (roughly) that it is the name of a large port city in the upper northwest of England. In other words, we can distinguish two sense of ‘meaning’, one sense is that of ‘personal significance’ (of interest to biographers, but not to social scientists), and the other sense is that of, to borrow a phrase from phenomenological philosophy, ‘intersubjective’ intelligibility, which has nothing to do with idiosyncratic meaning but everything to do with socially-shared meaning. And it is the latter which alone concerns the social scientist. To put it bluntly, intersubjectivity is as close as we social scientists can approximate to the ‘objectivity’ of natural phenomena. Does this preclude us from the mantel of ‘science’? If so, from the mantel of which science?

Administrative Data Systems

Example 1: Use of Administrative Data

The Healthcare Cost and Utilization Project (HCUP) is an on-line query system that provides access to health statistics and information on hospital inpatient and emergency department utilization. Click on the following link, to access (HCUP) and create a set of data tables. As you do so, consider such questions as:

Do these data give you the rate of hospitalization in the population?

Would this database help you understand what is causing those admissions via the ED?

Additional information
To further explore the use of administrative data you can also view Dartmouth Atlas (level of data is hospital or region) to apply concepts presented in this chapter and determine how best to use administrative data.


Observational Studies

Example 1

The research of Galster and Temkin (2004):502 asks, how can one show whether "efforts by government, community development corporations (CDCs), and for-profit developers to revitalize distressed, inner-city neighborhoods make any demonstrable difference? Put differently, can a method be devised for persuasively quantifying the degree to which significant, place-based investments causally contributed to neighborhoods' trajectories, compared to what would have occurred in the absence of interventions."

A central conceptual concern is how to best define the counterfactual. But they also address a number of statistical issues. They favor a pooled cross-section time series design with neighborhoods as the observational units. An important issue is how best to take spatial dependence into account. Other things equal, neighborhoods close by one another will tend to be more alike than neighborhoods farther away. When the authors regress median neighborhood housing prices on a set of predictors, including a binary variable for an intervention, they use the inverse Euclidian distance between neighborhoods to weight their regressions (Galster and Temkin, 2004:516). But is this a good statistical summary of spatial proximity? It assumes that dependence declines linearly with distance and that the decline is smooth. Yet, the quality of neighborhoods can change sharply in just a few blocks, and breaks in neighborhood continuity caused by freeways, parks, and bodies of water can introduce abrupt changes in the degree of dependence.

Example 2

When troublesome adolescents are sent to special alternative schools where strict discipline is enforced, does the experience increase or decrease the likelihood of subsequent success in regular public schools? Wolf and Wolf (2008) report the results of a program meant to break the "school to prison pipeline" for a number of school-aged children from the Syracuse (New York) city school district. The program had seven components:

  1. Systematic support for students anticipating a transition from special alternative schools to mainstream schools;
  2. Out-of-school activities meant to improve social and academic skills;
  3. Promotion of "bonding" between the youth and "caring" adults.
  4. Counseling and referrals;
  5. Support groups for students with incarcerated loved ones.
  6. Regular contact with parents; and
  7. Collaborative training for teachers, administrators, and other school staff.

The students in the study were essentially a convenience sample of all students in the Syracuse city school district, and Syracuse itself is a convenience sample of large cities in the United States. Yet, the observational study was motivated by the desire to learn about the efficacy of such interventions in general. What would be the point of learning whether the intervention worked for the several hundred students in the study unless that information could inform future policy decisions? In this instance, the intervention did not seem to produce beneficial effects overall and may even have produced some undesirable effects. But what kinds of generalizations can be properly justified?

Example 3

Substance abuse is often a chronic problem for which several interventions are needed so that each responds to where in the life course an individual falls. One implication is a shift from an acute care paradigm to a chronic care paradigm.  Rush and his colleagues report on the results of an intervention called "Recovery Management Checkups" (RMC) designed to help "people with substance abuse disorders by level of co-occurring mental disorders..." (Rush et al., 2008:7). "The RMC intervention targets individuals who have previously participated in treatment and are now living in the community using substances. The intervention ... aims to provide immediate linkage back to substance abuse treatment on the basis of need, thus expediting the recovery process.  Key components include, for example, assessing eligibility for the intervention and need of treatment, transferring participants in need of treatment from the interviewer to a linkage manager for a brief intervention, linking participants to the intake assessment, and ultimately linking participants to treatment" (Rush et al., 2008:8). A key measurement issue is to determine who is in need of treatment. For this study, such a person was defined as a study participant living in the community (vs. incarcerated or in treatment) who was not already in treatment and answered yes to any of the following questions:

  1. During the past 90 days, have you used alcohol, marijuana, cocaine, or other drugs on 13 or more days?
  2. During the past 90 days, have you gotten drunk or been high for most of 1 or more days?
  3. During the past 90 days, has your alcohol or drug use caused you not to meet your responsibilities at work/school/home on 1 or more days?
  4. During the past month, has your substance use caused you any problems?
  5. During the past week, have you had withdrawal symptoms when you tried to stop, cut down, or control your use?
  6. Do you feel that you need to return to treatment?"

The alpha (measuring internal consistency) reported for these items was .85.

Example 4

Rubin defines a causal effect:

Intuitively, the causal effect of one treatment, E, over another, C, for a particular unit and an interval of time from t1 to t2 is the difference between what would have happened at time t2 if the unit had been exposed to E initiated at t1 and what would have happened at t2 if the unit had been exposed to C initiated at t1: 'If an hour ago I had taken two aspirins instead of just a glass of water, my headache would now be gone,' or because an hour ago I took two aspirins instead of just a glass of water, my headache is now gone.' Our definition of the causal effect of the E versus C treatment will reflect this intuitive meaning.

According to the RCM, the causal effect of your taking or not taking aspirin one hour ago is the difference between how your head would have felt in case 1 (taking the aspirin) and case 2 (not taking the aspirin). If your headache would remain without aspirin but disappear if you took aspirin, then the causal effect of taking aspirin is headache relief (Rubin, 1974:689).

Example 5

Domestic violence exacts a well-documented and costly toll on victims and their families. In the United States "on the average, 3.5 people are killed by intimate partners every day, and many others are injured" (Vigdor and Mercy, 2006:313). An important question, therefore, is whether laws restricting access to firearms for individuals with a history of domestic violence can reduce intimate partner homicides (IPH). Vigdor and Mercy try answer this question using states as the observational units.

"The states that have laws limiting access to guns by abusers passed their legislation at different times. We exploit this time variation by effectively comparing IPH rates before and after passage of the law in states that enacted these laws with those in states that did not pass such a law. Although we cannot be certain that we are isolating the impact of the laws, the time variation in the effective date of the laws reduces the likelihood that we are capturing the effect of an omitted shock affecting all IPH rates."

Fully appreciating states can vary on the other factors that can affect IPH, they use a negative binomial regression model that includes a large number of covariates. They find that restraining- order laws help to keep perpetrators and victims apart and reduce IPH. Other kinds of interventions, such as gun confiscation laws, had no demonstrable impact.

Example 6

Conducting survey interviews can be especially problematic in inner city areas. Residents may be suspicious of outsiders and even hostile if they suspect that they are just being used to advanced some purely academic agenda. Holbrook and her colleagues (2006) studied the use of indigenous interviewers in such circumstances. A key issue was the quality of the data compared to data collected by professional interviewers. To this end, they compared summary statistics from survey interviews conducted by local residents to those from survey interviews conducted by professional interviewers. They also built regression models to characterize how the backgrounds of interviewers might affect respondent answers to sensitive questions. The authors do not discuss how they conceptualized the sources of uncertainty. Well over 70 hypothesis tests were conducted. No discounting of p-values is mentioned. Moreover, p-values are typically not reported. Rather one is given the popular "starsystem:" one star for p < .10, two stars for p < .05, and three stars for p < .01.

Conversation Analysis

Example 8

The exchange goes as follows:

01 Doc: tch D'you smoke?, h
02 Pat: Hm mm.
03 (5.0)
04 Doc: Alcohol use?
05 (1.0)
06 Pat Hm:: moderate I’d say
07 (0.2)
08 Doc: Can you define that, hhhehh ((laughing outbreath))
09 Pat: Uh huh hah .hh I don’t get off my- (0.2) outta
10 thuh restaurant very much but [(awh:)
11 Doc:                                                        [Daily do you use
12 alcohol or:=h
13 Pat: Pardon?
14 Doc: Daily? or[:
15 Pat:                 [Oh: huh uh. .hh No: uhm (3.0) probably:
16 I usually go out like once uh week.
17 (1.0)
18 Doc: °'Kay.°

Example 8a

In what follows we can examine a series of sub-sequences in this passage of interaction.

01 Doc: tch D'you smoke?, h
02 Pat: Hm mm.
03 (5.0)
04 Doc: Alcohol use?
05 (1.0)
06 Pat Hm:: moderate I’d say

The sequence begins with a ‘yes/no’ (or polar) question about smoking, to which the patient responds negatively with a brief headshake, and a dismissive "hm mm" (a minimized version of "no"). At this point, the clinician turns to the question of alcohol. His initial question "Alcohol use?" is devoid of a verb and is elliptical as between the polar question "Do you use alcohol?" and the more presupposing "How much alcohol do you use?" This design allows the clinician to circumvent the "yes/no" question, while permitting the patient to decide how to frame a response. After a one second silence (a substantial period of time in an engaged state of interaction) during which the patient assumed a 'thinking' facial expression, the patient articulates a sound which conveys pensiveness ("hm::"), and then offers an estimate ("moderate"), concluding her turn with "I'd say" which retroactively presents her response as an estimate, albeit a 'considered' one. Though presented as a 'considered opinion,' and in scalar terms, the patient's estimate is unanchored to any objective referent. The scene is now set for a pattern of questioning that will be familiar to primary care physicians: an attempt to extract a quantitative estimate from the patient.

Example 8b

06 Pat Hm:: moderate I’d say
07 (0.2)
08 Doc: Can you define that, hhhehh ((laughing outbreath))
09 Pat: Uh huh hah .hh I don’t get off my- (0.2) outta
10 thuh restaurant very much but [(awh:)

The physician begins this effort by inviting the patient to 'define' moderate (line 8). As he concludes his turn, he looks up from the chart and gazes, smiling, directly at the patient, and briefly laughs. Laughter in interaction is quite commonly associated with 'misdeeds' of various sorts (Jefferson 1985, Haakana 2001). Because the laughter in this case is not targeted at a single word or phrase (Jefferson 1985) but follows the physician's entire turn, it will, by default, be understood as addressing the entire turn. In this case, it appears designed to mitigate any implied criticism of the patient's turn as insufficient or even self-serving.

In her reply, the patient begins with responsive laughter (Jefferson 1979) but does not continue with a 'definition.' Instead she takes a step back from such a definition to remark: "I don't get....outta thuh restaurant very much but", and her subsequent development of this line is interdicted by the clinician. While this remark may be on its way to underwriting a subsequent estimate, its proximate significance is to convey the context of her alcohol use, or "how" she drinks. Specifically this remark purports to indicate that her drinking is ‘social’: she does not drink alone in her apartment, nor does she drink on the job. In this way, the patient introduces a little of her 'lifeworld' circumstances into the encounter, conveying that her drinking is 'healthy' or at least not suspect or problematic.

Example 8c

The next phase of this sequence will be easily recognizable to those who have read Elliot Mishler's The Discourse of Medicine (1984). In that study, Mishler elaborated a distinction between what he called the ‘voice of medicine’ preoccupied with objectivity and measurement, and the ‘voice of the lifeworld’ preoccupied with personal experience. Mishler depicted these two orientations as frequently in conflict, and so they are here. The clinician pursues a measurable metric for the patient's alcohol use by asking "Daily do you use alcohol or:=h". The question invites the patient to agree that she uses alcohol on a daily basis, thereby permitting her to take a step in the direction of acknowledging a 'worst case scenario' (Boyd and Heritage 2006). The movement of the word "daily" from its natural grammatical position at the end of the sentence to the beginning, has the effect of raising its salience, presenting a frequency estimate as the type of answer he is looking for. Finally, the 'or' at the end of the sentence, invites some other measure of frequency, and thereby reduces the physician's emphasis on 'daily' as the only possible (or most likely) response for the patient to deal with.

Example 8d

At this point in the interaction, the physician and patient are no more than two feet apart. Yet the patient's response to the question is to ask the physician to repeat it. In his analysis of these kinds of repeat requests, Drew (1997) observes that they are produced either when there is a hearing problem, or alternatively, when there is a problem in grasping the relevance of the talk to be responded to. A hearing problem is out of the question because of the objective circumstances of the participants, and it is subsequently ruled out by the conduct of both of them. However a 'relevance' problem is not out of the question. After all the patient's remark at lines 9 and 10 (that she didn't get out of the restaurant "very much") was most likely on its way to suggesting that she didn't have many opportunities to drink. The transition from this implication to an inquiry about whether she drinks on a "daily" basis may indeed have been somewhat jarring, and difficult to process.

Earlier it was suggested that the parties ruled out a 'hearing problem' as the basis for the patient’s request for repetition. The physician rules this out when, rather than fully repeating his previous question, he repeats a reduced form in which only the two most salient words are left: "daily" and "or." Only a full repeat would have been compatible with a belief that his patient had not heard him. A drastically reduced repeat like this one conveys, to the contrary, that he believes she heard him. For her part, the patient confirms this analysis when she proves fully able to respond to this abbreviated repeat, beginning before it is even concluded. Here then the objective circumstances of the interaction and the actual conduct of the parties is compatible with only one interpretation of the patient's "Pardon?": that it expressed a difficulty with the relevance of the question.

This same difficulty is expressed in a different way when the patient begins to respond. The response includes "huh uh," a casual and minimizing version of "no" designed to indicate that "daily?" is far off the mark. It is also prefaced by “oh” which, as noted earlier, communicates that a question was irrelevant or inapposite (Heritage 1998).

Example 8e

After she rejects the physician's frequency proposal of “daily” as an estimate of her alcohol consumption, the patient finally comes up with an estimate of her own: "once a week." However she packages this as an estimate of how frequently she “goes out." This framing has two consequences. (i) It estimates her actual drinking in an implicit way, leaving it to clinician to draw the relevant inference. (ii) It renews her insistence on the social, and morally acceptable, nature of her drinking, implicitly ruling out, for example, solo drinking at work, or at night after work.

With lines 15-16, physician and patient have arrived at a compromise: the physician has a frequency estimate of the patient's drinking, while the patient has been able to retain her focus on "how" she drinks. At line 17, the physician turns to the patient's chart and starts to write, subsequently acknowledging the patient's response with a sotto voce "okay" and terminating the sequence.

Example 1

For example, in the following case, Ann's turn in line 1 is treated as an invitation by a response that 'accepts' it:

Dialogue Example

If, by contrast, Barbara had responded with an apology and an excuse:

Ann: Why don't you come and see me sometimes.
Bar: I'm sorry. I've been terribly tied up lately.

then it would have been apparent that Barbara had understood Ann's initial utterance as a complaint rather than an invitation (Heritage, 1984).

These two understandings are built into the design of the two different responses. They are apparent to observers but, and this is the important point, they are apparent to the participants: however the sequence plays out, Ann will find from Barbara's response how Barabara understood her and that, Barbara has, or has not, understood her correctly.

We can take this analysis a step further by recognizing that at this point, Ann knows how Barbara understood her turn, but Barbara does not know whether she understood it correctly. Continuation of the sequence allows Barbara to make this judgment (Schegloff, 1992):

Dialogue Example

Ann's 'accepting' response to Barbara's acceptance confirms Barbara in her belief that she understood Ann correctly. But it could have gone otherwise:

Dialogue Example

In this second scenario, Barbara would see that her understanding of Ann's first turn at talk as an invitation was mistaken. Ann's response, which renews and indeed escalates her complaint, conveys that her original utterance was in fact intended to have been just that.

Example 2


Here are three examples of conversational practices:


(a) Turn-initial address terms designed to select a specific next speaker to respond: (Lerner, 2003)

A: Gene, do you want another piece of cake?
(b) Elements of question design that convey an expectation favoring a 'yes' or a 'no' answer: in this case the word 'any' conveys an expectation tilted towards a 'no.' (Heritage et al., 2007) 

Doc: Do you have any other questions?

(c) Oh-prefaced responses to questions primarily conveying that the question was inapposite or out of place: (Heritage, 1998)

Ann: How are you feeling Joyce.=
Joy: Oh fi:ne.
Ann: 'Cause- I think Doreen mentioned that you weren't so well?
 

Example 3

For example, in the following pediatric history, the clinician treats the mother's initial response to his question as sufficient (line 4) but, following her elaboration, he does not intervene again until line 9 when he pursues the matter of how the child's cough sounds.

Dialogue Example as discussed in the text

After his subsequent question at line 12, he boundaries off the mother's inconclusive response (at line 17), and then resets the terms of his question at line 19, finally gaining a clear response.

Example 4

In a study of informing interviews with parents of children who have been tested for mental disabilities, Maynard (2003) describes the use of a 'perspective display' sequence in which clinicians begin by asking the parents for their view of their child's condition, as in the following example (Maynard, 1992). At line 1, the clinician asks the child's mother for her view of the child's condition, eliciting a response that acknowledges the existence of language difficulties (lines 3-7).

Dialogue Example as discussed in the text

The significance of this prefatory solicitation is that it enables clinicians to anticipate the stance that the parent has to the child's condition. Stances that may emerge in the form of resistance or denial can be anticipated and addressed. Moreover the perspective display sequence also allows physicians where possible, to build their clinical judgments as in agreement with the parent's conclusions (see lines 13-16 above). An important outcome of this process is that the parent may be better prepared for adverse conclusions (Maynard, 1996, 2003).

Example 5

Early in a British community nurse's first home visit to a primiparous mother, the nurse, apparently noticing the baby chewing on something, initiates the following exchange Drew and Heritage (1992):

Here the nurse's comment attracts very different responses from the child's parents. The father's turn is entirely occupied with agreeing with the nurse's observation. The mother's response however, by treating the nurse as implying that her child is hungry, embodies a defense against this implication and is infused with laugh particles which are often associated with such responses (Haakana, 2001).

Similarly in the following sequence, which occurs less than a minute later in the encounter, the following occurs (Drew and Heritage, 1992):

While both husband and wife design their responses as agreements with the nurse at the arrowed turns, the design of those agreements is quite different. The father (lines 6 and 8) agrees with reference to their own child, and indicates that they have started to notice the rapid development that the nurse mentions. The mother is more guarded. She makes no reference to her own child, confining her agreement to the learning capacities of children in general.

It is tempting to suggest that a relatively conventional sex-role division of labor informs both of these sequences. The father, who may have little responsibility for the day to day care of the child, is inclined to agree in an open-hearted way with the nurse, and even to claim a little credit for having noticed things that the nurse – the accredited 'baby expert' – comments on. The mother, with overall responsibility for the child, may encounter the nurse's expertise as a threat to her own, and to resent the 'surveillance' that is the unavoidable concomitant of a series of home visits (Heritage and Sefi, 1992).

Example 6

In the following case the patient presented with upper respiratory symptoms:

Or whether, conversely, they anticipate the confirmation of adverse medical signs in sequences of questions which (Stivers, 2007) labels 'problem attentive' as in the following case in which the patient presented with flu symptoms:

In contrast to the previous example, each of these questions is geared towards an affirmative, and problematic, response and is sensitive to the symptoms with which the child presented.

Example 7

In the following well-known example, the patient has disclosed extensive and regular drinking prior to going to bed (Mishler, 1984):

Here the patient's use of a biographical reference point in her response to the physician's questions first question clearly implicates her marriage as a causal factor in her drinking, though without saying so explicitly. The clinician pursues a quantitative estimate in his second question, and the patient complies with a calendrical formulation ("Four years.").

Clinical Trials

Example 1

A cinnamon-based herbal oil reduced breast pain in women compared to evening primrose oil. Commercial oils were used for the study. The new cinnamon oil was provided free to all participants, while the primrose oil needed a prescription to be filled by the patient.

In this example, there are several sources of potential bias, including:

  • Trial not blinded;
  • New medications are appealing;
  • False safety impression;
  • Impressions based on age;
  • Patient drop out; and
  • Self-fulfilling prophecy.

Cluster Unit Randomized Trials

Example 1

Some examples include the following:

A. 450 villages in Indonesia were randomly assigned to either participate in a Vitamin A supplementation scheme or serve as a control. One-year childhood mortality rates were compared in the two groups (Sommer et al., 1986).

B. 98 families were randomly assigned to receive either treated nasal tissues or standard tissues. 24-week incidence of respiratory illness was compared in the two groups (Farr et al., 1988).

C. One member of each pair of 17 matched maternity hospitals in Belarus was randomly assigned to receive a breastfeeding promotion strategy, with the other member of the pair receiving a control condition based on usual practice (PROBIT trial). The rate of breastfeeding at 12 months was compared between the two groups (Kramer et al., 2001).

D. 207 general practices were randomized to receive either a structured group education program or standard care offered to patients with newly diagnosed type 2 diabetes. A variety of response variables, including biomedical, lifestyle, and psychosocial measurements were collected over a one-year follow-up period (Davies et al., 2008).

E. One member of each pair of 11 matched communities was randomly assigned to a city-wide intervention that promoted the hazards of smoking with the other member serving as a control. Five-year smoking cessation rates were compared in the two groups (COMMIT Research Group, 1995).

Example 2

Althabe et al., 2004 report on a matched-pair trial aimed at reducing the rate of caesarian section deliveries in Latin American maternity hospitals. The intervention in this trial required the obstetrician to seek a second opinion from a senior colleague before proceeding with the c-section, with outcomes recorded at the hospital level only.

Likewise, Diwan et al., (1995) evaluated a policy of “group detailing” on the prescribing of lipid-lowering drugs in a trial randomizing community health centers. A primary endpoint in this study was the number of appropriately administered prescriptions per month, with the health center serving as the unit of analysis.

Example 3

Consider a family randomized trial designed to evaluate the efficacy of a dietary intervention in lowering blood pressure. Data from previous trials performed in a similar population indicate that the intracluster correlation coefficient with respect to diastolic blood pressure may be taken as 0.20, while the mean and standard deviation of the corresponding family size distribution can be reasonably estimated as 2.2 and 0.65, respectively (cv=0.30). Previous experience also indicates that the between-subject standard deviation of diastolic blood pressure is approximately 10.0.

Assuming it is of interest to detect a mean difference of 4mm Hg with 80% power at the two-sided 5% level, the value of VIFA may be obtained as 1+[(0.302+1)2.2-1]0.2 =1.28 and the number of subjects required in each of two groups by

n= {(1.96+0.84)2 2(102)/42}{1+[(0.302+1)2.2 -1])0.2}=(98.75)(1.28)=127 or about 64 families per group.

Example 4

To illustrate one such approach, consider a trial evaluating the effect of tailored general practice guidelines on the proportion of patients with benign prostatic hyperplasia (BPH) that remained under specialist care at 12 months post-randomization (Mollison et al., 2000). Of main interest here is a comparison of event rates observed on 150 patients contributed by 23 experimental group practices to event rates observed on 142 patients contributed by 26 control group practices. Median cluster sizes in this completely randomized trial were 6 and 3.5 in the experimental and control groups, respectively, a difference that can reasonably be attributed to chance.

66 (44%) patients in the experimental group were still under specialist care at 12 months as compared to 77 (54.2%) patients in the control group. Application of the standard Pearson chi-square test with one degree of freedom to these data yields x2p =3.05(p=.08), indicating a difference that is statistically significant at the 10% level. However this test fails to account for the similarity of responses (clustering) among patients belonging to the same practice, and therefore overstates the true level of significance. We therefore compute the “adjusted chi-square statistic” x2A, obtained by dividing x2p by an appropriate estimate of VIF (Donner and Klar, 1994). Application of this procedure, based on an estimated value of ρ given by 0.077, yields x2A =1.684(p=.19, one degree of freedom), a result no longer statistically significant at any conventional level. Algebraic formulas for all results presented in this example are given in the Appendix.


Multilevel Modeling

Example 1

In an influential study of progress among primary school children, Bennett (1976), using single-level multiple regression analysis, claimed that children exposed to a ‘formal’ style of teaching exhibited more progress than those who were not. The analysis while recognizing individual children as units of analysis ignored their grouping into teachers/classes. In what was the first important example of multilevel analysis using social science data, Aitkin, Anderson et al., (1981) reanalyzed the data and demonstrated that when the analysis accounted properly for the grouping of children (at lower level) into teachers/classes (at higher levels), the progress of formally taught children could not be shown to significantly differ from the others.

Example 2

Individual 25 moved from neighborhood 1 to neighborhood 25 during the study time-period t1-t2, spending 20% of her time in neighborhood 1 and 80% in her new neighborhood. This multiple-membership panel design could allow control of changing context as well as changing composition, besides enabling a consideration of weighted effects of proximate contexts (Langford, Bentham et al., 1998). So, for example, the geographical distribution of disease can be seen not only as a matter of composition and the immediate context in which an outcome occurs, but also as a consequence of the impact of nearby contexts, with nearer areas being more influential than more distant ones. Goldstein, (2003) provides an elegant and comprehensive classification schema.

Patient-Reported Outcomes

Example 1

A 25 year old athlete is engaged in numerous sports, and does very well. For reasons he finds hard to understand, he finds his life unsatisfying and is generally not very happy. A diving accident results in quadriplegia, leaving him completely dependent. After a month of depression, he finds the meaning in life that had previously eluded him. When asked about his mood, he describes himself as satisfied with his limited life, and overall very happy.

Q: Was his quality of life better before, or after, his accident?
A: If one adopts this perspective strictly, no two measures of quality of life might look the same, as each measure would tap individual experience that may be constrained by the particular environment of the individual or by the moment in time. A scientist who completely rejects the nomothetic ideal of finding a general “law” or “pattern” might well find sympathy with the poem by e.e. cummings. In the end, all individuals have separate identities, physically, emotionally, and spiritually.

Example 2

Quality of Life is more than Health

The Intelligence Unit of the widely distributed publication, The Economist, recently developed a new “quality of life” index based on a methodology that links the results of subjective life-satisfaction surveys to the objective determinants of quality of life. Using life-satisfaction surveys as a starting point, the Unit used nine indicators that had a significant influence on life-satisfaction and turned these into an equation that explained more than 80% of the variation in country’s life-satisfaction scores. The main factor was income, but the others things were also important: health, freedom, unemployment, family life, climate, political stability and security, gender equality, and family and community life. Note that health is listed among many other aspects of life. Ireland came out top with the fourth-highest GDP per head in the work in 2005, low unemployment, and political liberties. The U.S. was ranked 13th.

These rankings do not match those for infant mortality or life expectancy, but represent the notion that quality of life is broader than health status.

Example 3

The World Health Organization Quality of Life (WHOQOL) group has defined quality of life as:
“individuals’ perceptions of their position in life in the context of the culture and value systems in which they live, and in relation to their goals, expectations, standards, and concerns” (The WHOQOL Group, 1994; The WHOQOL Group, 1995; Szabo, 1996).

This definition reflects the growing recognition that quality of life can be inherently subjective, although normative definitions have been proposed that include more objective standards as well as perceptions of objective conditions (Campbell et al., 1976; Calman, 1987).
Quality of life can be used as:

  • A descriptor, i.e., the presence or absence of a characteristic of life;
  • An evaluative statement, i.e., some value is attached to the characteristics of an individual, population, or kind of human life or;
  • A normative or prescriptive statement, i.e., certain norms indicate which characteristics must be present to have a life of quality.

Example 4

A Detailed Example of Construct Validation

The Inflammatory Bowel Disease Questionnaire (IBDQ) was designed to measure disease-specific HRQL and it includes 30 items directed at 4 domains: bowel symptoms, systemic symptoms, emotional function, and so­cial function. Investigators administered the IBDQ (along with global ratings of change in function, global ratings of change by the physician and a relative, a Disease Activity In­dex, and the emotional function domain of a generic HRQL measure) to 42 patients with inflammatory bowel disease on two occasions separated by 1 month. At the time the investigation was planned, the investigators made predictions about how change in the IBDQ score should relate to change in the other measures if this questionnaire was really measuring HRQL. Examples of the predictions and the results are as follows:

  • The patient's global rating of change in disease activity should relate closely (correlation ~ 0.5) with change in the bowel-symptoms dimension of the In­flammatory Bowel Disease Questionnaire.
    Correlation observed was 0.42.
  • Some relation (correlation ~ 0.3) should exist between change in the Disease Activity Index and change in the bowel-symptoms dimension of the In­flammatory Bowel Disease Questionnaire.
    Correlation observed was 0.33.
  • Some relation (correlation ~ 0.3) should exist between change in the Disease Activity Index and change in the systemic-symptoms dimension of the Inflammatory Bowel Disease Questionnaire.
    Correla­tion observed was 0.04.
  • Change in the emotional-function dimension of the Inflammatory Bowel Disease Questionnaire should relate closely (correlation ~ 0.5) with change in the emotional-function dimension of the generic questionnaire.
    Correlation observed was 0.76.

Example 5

  • In a domain with 6 items, changes of 3 or 4 represent small effects, changes of 5 or 6 represent moderate effects, and changes of 7 or more represent large effects. Investigators used this information to in­terpret a recent trial that showed use of bronchodilators results in a small but clinically important improvement in dyspnea, fatigue, and emotional function in patients with chronic airflow limitation (Guyatt et al., 1987).
  • In a study (Thompson et al., 1988) of patients with arthritis, a change of 0.02 points in the Quality of Well-Being utility instrument was equivalent to all treated patients improving from moving their own wheelchair without help to walking with physical limi­tations. The availability of data to improve the Interpretability of PROs is likely to increase exponentially in the next decade.

Heritage J. (1984). Garfinkel and ethnomethodology. Cambridge, UK: Polity Press.
Schegloff E. A. (1992). Repair after next turn: The last structurally provided defence of intersubjectivity in conversation. American Journal of Sociology 95(5): 1295-1345.
Heritage, John. 2008. Conversation Analysis as Social Theory. In Bryan Turner (Ed), The New Blackwell Companion to Social Theory. Oxford, Blackwell.

Lerner G. (2003). Selecting next speaker: The context sensitive operation of a context-free organization. Language in Society 32: 177-201.
Heritage J. (1998). Oh-prefaced responses to inquiry. Language in society 27(3): 291-334.

Schegloff, E.A. (2006). Interaction: The infrastructure for social institutions, the natural ecological niche for language and the arena in which culture is enacted. In: Enfield N.J., Levinson S.C.,Ed, The Roots of Human Sociality: Culture, Cognition and Interaction. New York: Berg, 70-96.
Heritage, John. 2008. Conversation Analysis as Social Theory. In Bryan Turner (Ed), The New Blackwell Companion to Social Theory. Oxford, Blackwell.

Stivers, T. (2007). Prescribing under pressure: Parent-physician conversations and antibiotics. New York: Oxford University Press.
Heath, C. (1992). The delivery and reception of diagnosis and assessment in the general practice consultation. In: Drew P., Heritage J., Ed, Talk at Work. Cambridge, UK: University Press, 235-267.
Peräkylä A. (1998). Authority and accountability: The delivery of diagnosis in primary health care. Social Psychology Quarterly 61(4): 301-320.

Maynard D. (2003). Bad news, good news: Conversational order in everyday talk and clinical settings. Chicago: University of Chicago Press.
Maynard D. (1992). On clinicians co-implicating recipients' perspective in the delivery of diagnostic news. In: Drew P., Heritage J., Ed,  Talk at work: Social interaction in institutional settings. Cambridge, UK: Cambridge University Press, 331-358.
Maynard D. (1996). On 'realization' in everyday life. American Sociological Review 60(1): 109-132.
Maynard D. (2003). Bad news, good news: Conversational order in everyday talk and clinical settings. Chicago: University of Chicago Press.

Drew P., Heritage J., Eds. (1992). Talk at work: Language use in institutional and work-place settings. Cambridge, UK: Cambridge University Press.
Haakana M. (2001). Laughter as a patient's resource: Dealing with delicate aspects of medical interaction. Text 21(1): 187-219.
Drew P., Heritage J., Eds. (1992). Talk at work: Language use in institutional and work-place settings. Cambridge, UK: Cambridge University Press.
Heritage J., Sefi S. (1992). Dilemmas of advice: Aspects of the delivery and reception of advice in interactions between health visitors and first time mothers. In: Drew P., Heritage J.,Ed,  Talk at work. Cambridge, UK: Cambridge University Press, 359-4

Boyd E., Heritage J. (2006). Taking the history: Questioning during comprehensive history Taking. In:  Heritage J., Maynard D., Ed,  Communication in Medical Care: Interactions between Primary Care Physicians and Patients. Cambridge, UK: Cambridge Unive
Stivers, T. (2007). Prescribing under pressure: Parent-physician conversations and antibiotics. New York: Oxford University Press.

Mishler E. (1984). The discourse of medicine: Dialectics of medical interviews. Norwood NJ: Ablex.

Boyd E., Heritage J. (2006). Taking the history: Questioning during comprehensive history Taking. In:  Heritage J., Maynard D., Ed,  Communication in Medical Care: Interactions between Primary Care Physicians and Patients. Cambridge, UK: Cambridge Unive

Drew P. (1997). 'Open' class repair initiators in response to sequential sources of trouble in conversation. Journal of Pragmatics 28: 69-101.
Heritage J. (1998). Oh-prefaced responses to inquiry. Language in society 27(3): 291-334.

Mishler E. (1984). The discourse of medicine: Dialectics of medical interviews. Norwood NJ: Ablex.
Sacks H. (1984). On doing 'Being Ordinary'. In: Atkinson J.M., Heritage J., Ed,  Structures of social action. Cambridge UK: Cambridge University Press, 413-429.

Jefferson G. (1985). An exercise in the transcription and analysis of laughter. In: Teun A. Dijk (Ed),  Handbook of discourse analysis Volume 3. New York: Academic Press, 25-34.
Haakana M. (2001). Laughter as a patient's resource: Dealing with delicate aspects of medical interaction. Text 21(1): 187-219.
Jefferson G. (1985). An exercise in the transcription and analysis of laughter. In: Teun A. Dijk (Ed),  Handbook of discourse analysis Volume 3. New York: Academic Press, 25-34.
Jefferson G. (1979). A technique for inviting laughter and its subsequent acceptance/declination. In: Psathas G., Ed,  Everyday language: Studies in ethnomethodology. New York: Irvington Publishers, 79-96.

Subramanian, S. (2004) Multilevel methods, theory and analysis. In: N. Anderson (Ed.). Encyclopedia on Health and Behavior. Thousand Oaks, CA: Sage Publications. 602-608.
Subramanian, S., Jones, K., et al. (2003) Multilevel methods for public health research. In: I. Kawachi and L. Berkman (Eds.). Neighborhoods and Health. New York: Oxford Press. 65-111.
Diez Roux, A. V. (2002) A glossary for multilevel analysis. Journal of Epidemiology and Community Health 56(8): 588-594.

Jones, K., Gould, M. I., et al. (1998) Multiple contexts as cross-classified models: The labor vote in the British general elections of 1992. Geographical Analysis 30: 65-93.
Goldstein, H. (2003) Multilevel statistical models. London: Edward Arnold.
Goldstein, H. (1994) Multilevel cross-classified models. Sociological methods and research 22: 364-375.

Kahneman D., Diener E., Schwarz N. (Eds). (1999). Well-being: The Foundations of Hedonic Psychology. New York : Russell Sage.

Bennett, N. (1976) Teaching styles and pupil progress. London: Open Books.
Aitkin, M., Anderson, D., et al. (1981) Statistical modelling of data on teaching styles (with discussion). Journal of the Royal Statistical Society A 144: 148-161.

WHOQOL Group. (1994). WHOQOL Group, The Development of the World Health Organization Quality of Life Assessment Instrument. In: J. Orley and W. Kuyken, (Eds.) Quality of life assessment: International perspectives, Springer,Berlin (1994), pp. 41–57.
Szabo, S. (1996). On behalf of the WHOQOL Group The world health organization quality of life (WHOQOL) assessment instrument. In Spiker, B. Quality of Life and Phramacoeconomics in Clinical Trails. (2Ed.) Philadelphia: Lippincott-Raven Publishers.
Campbell A., Converse S.E., & Rodgers W.L. (1976). The Quality of American Life. New York : Russell Sage.
Campbell A., Converse S.E., & Rodgers W.L. (1976). The Quality of American Life. New York : Russell Sage.
Calman, K.C. (1987). Definitions and dimensions of quality of life. In Aaronson, N.K. & Beckman, J. (Eds.). The Quality of Life of Cancer Patients. Monograph series of the European Organization for Research on the Treatment of Cancer (EORTC). Vol 17. New York : Raven.
WHOQOL Group. (1994). WHOQOL Group, The Development of the World Health Organization Quality of Life Assessment Instrument. In: J. Orley and W. Kuyken, (Eds.) Quality of life assessment: International perspectives, Springer, Berlin (1994), pp. 41–57.