QQ+political+data+lecture+2.pdf

Qualitative and Quantitative Analysis of Political Data Lecture 2: Comparative research and Overview on Quantitative and Qualitative Research Methodologies  Comparative Design The more the cases or examples that are studied, the more likely that common causes can be found and...

Qualitative and Quantitative Analysis of Political Data Lecture 2: Comparative research and Overview on Quantitative and Qualitative Research Methodologies  Comparative Design The more the cases or examples that are studied, the more likely that common causes can be found and generalizations made. Political events and processes are often clarified and illuminated by comparison with similar events and processes in other contexts. The major difficulty with comparative design is in finding comparable cases: that is, examples which are similar in large number of respects to the case which the researchers want to treat as constant but dissimilar in the variables that they wish to compare to each other  Comparative Design Comparative design has grown out of the desire both to understand better one’s own political system by comparing it with others, and also to make generalizations about political practices and processes. Loading… Comparative analysis sharpens our understanding of the context in which theoretical problems occur and enables causal inferences to be drawn. However, as comparative analysis usually involves only a relatively limited number of cases, caution has to be maintained about the levels of generalizations that can be made  Comparative Design Political science proceeds by imposing some sort of order on processes, events and phenomena that do not easily conform to any sort of order. The real difficulty of political science is to make convincing statements about the causation of political phenomena, given the complexity of interactions among the whole range of social phenomena and the number of external sources of variance The comparative method can help alleviate but rarely, if ever, resolve the fundamental problem of causal inference inasmuch as it can emulate the experimental method.  Comparative Design There are two basic comparative research designs: most similar designs and most different research designs. The most important aspect of formulating either the most similar or most similar or a most different research design is to Loading… select cases that make it possible to conclude something interesting about one’s research question. Comparative case selection should take place on the basis of three selection principles: cases should maximize experimental variance, minimize error variance and control extraneous variance  Comparative Design The logic behind most similar research designs is that by a basic process of elimination all the variables in the other category can be ruled out of the research. If they do have an effect on the dependent variable, they have the same effect on the dependent variable across all cases. This leaves the independent variable, which has a differential effect on the dependent variable in the two or more cases (which is the reason why the cases are selected in the first case).  Comparative Design This means that any observed differences between cases with respect to the dependent variable can be associated with the only variable that makes the cases different: the independent variable. In brief, the more the circumstances the selected cases have in common, the easier it is to locate the variables that do differ and which may thus be considered as the first candidates for investigation as causal or explanatory variables.  Comparative Design The primary advantages of the comparative method can be summarized under four headings: it allows us to contextualize knowledge; to improve classifications; to formulate and test hypothesis; and to make predictions. We make comparisons to contextualize knowledge almost without thinking about everyday life as well as in more formal political analysis, to integrate and make sense of newly acquired knowledge.  Comparative Design A related advantage of approaching a research question comparatively is that doing so has the potential to improve the classification we use to impose some sort of order on the diversity of the political world. Classification is the basic type of concept formulation, neither comparison (non metric ordering) nor measurement proper can take place without it, that is, classification is prior to comparison in the sense that typically we choose cases to compare because they belong to a particular classification.  Comparative Design Taking a comparative perspective on a research question also enables hypothesis testing and development. The comparative method can enable predictions about politics. If an empirical relationship between two or more variables has been observed in one temporal or spatial setting, then it can be inferred that the same relationship would hold in another temporal or spatial setting.  Comparative Design The too many variables, not enough cases problem of comparison arises because the political world that is the research environment of political science is too rich and varied (that is, it consists of too many variables) for the Loading… researcher to be able to find enough cases to control for all the effects of these variables: it thus becomes impossible to isolate the dynamics of the relationship of primary interest. There is no way to test how additional variable is related to the two original variables without additional cases that have all the attributes of the two original cases.  Comparative Design The first manifestation of the traveling problem is conceptual: does the meaning of the concept stay constant across time and space? The significance of this was discussed in the example of nation states in terms of how the comparative method can improve classifications and it follows from that discussion that mistaken assumptions about concepts and their meanings lead to confusion about what it is that is being compared. The second manifestation of the traveling problem concerns empirical measurement, the concern being that even if the meaning of the concept is constant across cases, if it is operationalized differently for different cases, then there is measurement inconsistency.  Comparative Design The Galton’s problem occurs when the expectation is not met that political outcomes are due to processes internal to each case in the research design. If some hypothesized empirical relationship under examination is really the result of an external or even global process, then studying more than one case will not in truth provide a comparative perspective because the cases will not be independent from each other. Comparative researchers are, in other words, stuck between Galton’s problem and the need to find cases that are comparable, the problem being that cases that are comparable often are comparable precisely because of being affected by some external process; that is, they are similar because of a Galton’s problem.  Quantitative Analysis Types of data: Nominal: this is the most basic data and the information is coded in terms of discrete categories (often mutually exclusive) for example, gender, party membership voters and non-voters in a particular election. It is clear that in relation to these two categories (gender and age), participants in the survey can only fit into one category for each variable. Ordinal: also referred to as ranked data, it accounts for data, which can place in some sort of comparative order. We can use this information about attitudes towards public spending; support of trade unionism and support for party leaders. Interval/ratio: this is often described as the most useful level of data because it also indicates some level of distance. Interval data may be used to calculate how far apart measures are: there are equal intervals or equal distances between each measure on the scale, however with interval data there is no absolute zero point.  Quantitative Analysis Probabilistic sampling: Random sampling: this implies that every member of the population has an equal and independent chance of being selected; this is not easy and is increasingly problematic when the population is large. People walking down any particular street at any particular time are not truly typical of the population because the types of people we would expect would vary and be influenced by the time of day. Systematic sampling is the selection of every nth case. For example, by sampling every thirteenth name on the electoral register we are unlikely to get two people from the same household or even their neighbors.  Quantitative Analysis Probabilistic sampling: Stratified sampling entails the division of the research population into sampling units, then applying random sampling to each unit. For example, if we wished to measure the political preference of a student body we might split students into age groups and then take a random sample from each age group. Cluster sampling can be useful if we do not have a sampling frame, this approach may be the only method which we can employ to survey particular groups, such as the unemployed and homeless.  Quantitative Analysis Non-probabilistic sampling: Quota sampling-the study identifies a number of respondents from particular social strata (sampling units), which proportionately reflect the number of cases in that unit. This method is widely used in market research. Convenience sampling-samples that are easily accessible Volunteer sampling-this takes the form of phone-ins on TV and radio and postal questionnaires, these are not likely to be representative samples, as participants might be personally motivated to become involved.  Quantitative Analysis Non-probabilistic sampling: Snowball sampling – a sampling technique employed when we might ask a small sub-group to identify others whom we could also study. Purposive sampling – the sample is handpicked because the participants are typical or interesting examples of what we are researching, more utilized in qualitative designs.  Quantitative Analysis Causality-the ability of a characteristic (or variable) to affect attitudes or behaviors, voting behavior (dependent variable) if affected by the age or gender (independent variable). A correlation measures the extent to which the changes, which occur in two variables or attributes, are related to one another. Increasing reliability in research: the ability to replicate Stability – by employing the test and re-test method we can measure the long term predictability of a given research, this may be useful for ascertaining factual types of information, for example we may ask some at six monthly intervals whether they voted in the last elections.  Quantitative Analysis Increasing reliability in research: the ability to replicate Internal consistency – we may use a homogenous set of questions in order to establish the consistency of attitudes. This might be necessary we were if we wee concerned that we are getting an artificial response. We are often involved in asking people to rate the importance of certain policies to which they may not pay a great deal of attention in their everyday lives. Inter judge reliability – it is important if we need to classify responses to open ended questions into quantifiable categories. As we are constantly dealing with fluid concepts, we might decide to employ several observers/judges in order to check the consistency of classification-a type of double marking.  Quantitative Analysis Common sources of unreliability: Varying sources – by using different samples of people we may produce very different results, we may decide to repeat a survey after a six month break and uncover very different responses. Random errors – This can be simple replication errors or errors due to ambiguity. For example, if we are entering large amounts of data into a computer, we may on occasion hit the wrong key.  Quantitative Analysis Common sources of unreliability: Problems with the research design – it is the usual practice when designing survey research to employ a pilot study in order to eradicate these sources of unreliability. Reliability errors can also be derived from badly phrased questions. Problems in data collection – interviewer/respondent effects: respondents may feel they have no reason to play the game and may tell the interviewer blatant lies; respondent replies may vary with their mood.  Quantitative Analysis Validity is the extent to which our measures correspond to the concepts they are intended to reflect. Construct validity – it is important as the study concerns measuring abstract traits such as social class or party identification. We must be clear about the meaning of the terminology we use. Content validity – we need to ensure that we reflect the range of the subject, for example, in order to establish party preference we should ask questions about all, not just one or two, parties.  Quantitative Analysis Types of information acquired by survey research Facts – where respondents live, their age, their academic qualifications Perceptions – what people know about the world Opinions – what people think about the world, e.g. judgments about the competencies of leaders Attitudes – these are relatively stable evaluations (support for wealth distributions, antipathy towards violence) Behavioral reports – how people act (does the respondent pay attention to the news)  Quantitative Analysis When carrying out survey work that we preplan and indeed it is often the case that we invest a great deal of time and energy in what is termed as pre-testing or pilot studies. An appropriate survey should 1) reflect relevant theoretical propositions in its construction; 2) use results from the sample to generalize about the population; and 3) be replicable. To design a good questionnaire one should: 1) read around the topic; 2) decide on the aims of the survey; 3) decide the population and sample groups; and 4) pilot the work to be undertaken.  Quantitative Analysis Advantage of employing survey research: Surveys may offer a feasible alternative to interviews if we are dealing with sensitive or contentious political issues. Cross-sectional surveys-we asks our respondents to complete the survey on one occasion only and as such these surveys provide a snapshot of a moving target. Longitudinal surveys – respondents are surveyed on more than one occasion to look for stability or changes in attitudes and opinions. This may be achieved via trend surveys, in which we survey different people from the same population.  Quantitative Analysis Disadvantages of employing survey research: First we may encounter a poor response rate or we may have wider worries about the appropriateness of the samples surveyed. Second, it may be an inappropriate tool for the subject matter, the responses may not be genuine but rather reflect the expectations of the survey. Surveys provide only limited information and we should not necessarily expect too much from the type of rather superficial data that surveys collect rather we should use various analytical methods if possible  Quantitative Analysis Survey research - Methodological Issues: Must have a clear-cut definition of our chosen research question and more importantly an awareness of the target population before we begin constructing our survey. Aside from the cost of the survey we have to consider the availability-that of your intended sample population, Avoid using complex terminologies/jargons as well as asking leading questions in the survey. Closed questions-in which we provide the respondents with a list of responses and ask them to pick the most appropriate, or do we ask open ended questions, in which we allow respondents to answer in their own words.  Quantitative Analysis The Value of Official Statistics: Census as a source of official statistics-established sources of data collection is crucial for contemporary research, partly because of their volume and depth. Official statistics cover Loading… themes such as the economy, labor market, welfare and populations and migration. Official statistics are particularly important for our understanding of demographics, which are patterns of stability and change in the study of human populations. Access to official statistics varies, some data are available free of charge, whereas other data have cost  Quantitative Analysis Underlying concerns surrounding official data: 1) who has sponsored the research? 2) How are the findings interpreted? 3) How are concepts defined? 4) Why are particular social and political issues prioritized over others? 5) What are the results going to be used for? 6) Who was studied? Government has been accused of manipulating figures in order to create desired  Quantitative Analysis Advantages of official statistics: 1. Produces a wealth of information relating to political, social and economic issues 2. Allows the examination of trends over time 3. May be the only source of information for some issues  Quantitative Analysis Disadvantages of official statistics: Prioritizes particular interests and thus sets an agenda The definition of some concepts will change over time: such concepts are diachronic The time taken to publish large sections of data may render such statistics out of date Data are quantitative and as such tell us rather than why. The data alone have little value unless we can relate them to theoretical understandings and expectations  Qualitative Analysis The origins of qualitative research methods lie in anthropology and sociology. It involves the researcher immersing himself/herself in the social setting in which he or she is interested, observing people in their usual setting and participating in their activities Qualitative interviews, in contrast, are useful because they allow people to talk freely and present their perspective in their terms. Qualitative research sampling is often guided by the search for contrasts, which are needed to clarify the analysis and achieve maximum identification of emergent categories  Qualitative Analysis Qualitative research tool-focus groups: can be employed at various research stages. It intends at formulating a research question, for developing relevant indicators for data collection. The advantages of focus groups include the following: They ensure that the research question is covered They can overcome the problem of wording that may be encountered with surveys and interviewer effects An explanation of answers can be requested It is possible to recognize how opinions are given relation to the answers and reactions of others  Qualitative Analysis The Ethnographic Approach in Qualitative Research: For ethnographers, ethnocentrism (cultural bias) is avoided by emphasizing the centrality of cultural relativism (the means by which a society is constructed and operates the rules of political behavior). The emphasis within ethnography is upon explanatory understandings rather than upon trying to make predictions about what might occur. It does not make prior assumptions about what is important or what to expect.  Qualitative Analysis Advantages of qualitative research Greater opportunity to explore beliefs and attitudes Can explain why and how rather than just what Greater reliance upon the respondents’ actions and thoughts  Qualitative Analysis Disadvantages of qualitative research Data are atypical: if any, ability to generalize Problem with interpretation, different researchers may interpret the same response in different ways Researcher involvement; may become involved in and be sympathetic towards particular participants Time consuming  Qualitative Analysis Observational methods in political research: for the purposes of research, observational research can be systematic (structured) or ethnographic (unstructured). The systematic approach is often associated with the positivist tradition of the social sciences; that is, we have precise definitions of observable behavior, which we can measure. The advantage of an observational research approach is that we are not relying, for example, purely upon a political actor to tell us what rules and responsibilities their job entails; we can actually witness this ourselves  Qualitative Analysis Perhaps the most challenging aspect of observational research is that of gaining access. Flexibility is also important in relation to other aspects of carrying out fieldwork. Observing decision makers may be very difficult if the researcher only has access to some meetings (due to issues of confidentiality). It may take a long period of observation to be able to recognize normal patterns and trends. Observation may take the form of preliminary research stage – a form of pilot research.  Qualitative Analysis Advantages of observational research: Directly recorded by the observer rather than relying on others Provides supplementary data to surveys and interviews Observer may see relevant factors, which the observed cannot Gleans information, which others cannot or may not wish to discuss  Qualitative Analysis Disadvantages of observational research: Accessibility may be difficult or impossible Reactivity Relies upon interpretations made by the observer Time-consuming, costly and potentially unrepresentative Cannot guide the discussion/behavior of those being studied Locating a suitable site  Qualitative Analysis Qualitative Research: Interview Method An interview is an encounter between a researcher and a respondent. In particular, the interview is a great vehicle for bringing a research topic to life. It is also an excellent method of obtaining data contemporary subjects which have not been extensively studied and for which there is little research The standardized interview-we ask every question in the same way, this is similar in principle to a survey and indeed produce data which can easily be turned into a quantifiable form.  Qualitative Analysis Semi-standardized interview combines quantitative questions (such as age, gender) but can generate more qualitative data as the interviewer seeks clarification and elaboration of answers. We are interested in knowing the whys, hows as well as the whats. Unstandardized interview also referred to as an informal, focused, unstructured or free interview. An unstandardized interview takes the form of a free flowing conversation, relying heavily on the quality of the social interaction between the investigator and informant, that can subtly redirected by the interviewer if it should stray too far off the track of the research study.  Qualitative Analysis Elite interview: If we wish to discover how political institutions operate, how important decisions are made and how political power is attained, we are not likely to ask the public at large, but rather those individuals who have access to this level of information – those referred to as political elites. These are people who occupy important positions. Advantages-they may help with the interpretation of documents and reports, they may help with the interpretation of personalities; they provide information, which may not be recorded elsewhere, and they help in establishing contact networks and access to others  Qualitative Analysis However, we must also bear in mind that the limitations of access affect the overall representativeness of any research findings, while the reliability of the information gleaned may be questioned. Perhaps the most challenging issue we confront when conducting elite interviews is where to start or put in another way who to interview and when.  Qualitative Analysis In conducting qualitative research it is important that the researcher should control access through gatekeepers-are the sponsors, officials and significant others who have the power to grant or block access to and within a setting. Maintaining objectivity is important, as the nature of the interview usually means that the interviewer is not as distant from the interviewee as in quantitative research.  Qualitative Analysis The phrasing of questions is just as important in qualitative research as we have shown it to be when conducting surveys. The language we use should be objective as possible and interviewer bias can mean that particular opinions are seen as desirable. The purpose of the interview should be made clear. In an ideal situation we should be completely honest about the reasons of the interview.  Qualitative Analysis It is crucial that we maintain interest in the interview. Questions of validity in an interview-the limitations of memory, especially in relation to factual information, in comparison, interviews held too soon after the event may be clouded by personal impressions. Qualitative interviewing can be time consuming and costly. The most laborious part of the research process is the transcription process. Ideally, this should be done while the interview is still fresh in your head, while you can still read the notes you made during the interview  Qualitative Analysis Resources for qualitative data: Mass media: Newspapers in particular tend to be politically partisan and even broadcast media are accused of presenting news values rather than plain facts. Despite the existence of bias this does not mean that media sources are of no value in political research and we need to appreciate that the media are the primary, if not the only source of political information for many people.  Qualitative Analysis Political party resources: Parties attempt to contact voters using a variety of sources from local leaflets and personal canvassing to advertising on billboards and in national newspapers. Manifestos provide the fullest official statement of each party’s policy proposals and have been widely used to analyze their position across the left-right political spectrum. Biography, autobiography and political memoirs: are personal accounts of political events and experiences whilst biographies are written by a second person, often through the use of interviews or access to personal papers. Both offer interpretations of politics and are obviously open to a great deal of subjectivity and personal opinions.  Qualitative Analysis The Internet: can be employed at various stages in the research process, but is particularly useful in providing book reviews, online journal articles and similar articles, discussion groups, statistics and on line media resources. While access to the Internet is growing at a rapid rate, it is still more likely to be used by the middle class and is often aimed at a younger, rather than elderly audience Historical and Archival Resources: any research involving historical material is likely to be overshadowed by objectivity and lack of first hand experience. In reality our understanding of political history is informed by a selective reading of documents.  Qualitative Analysis Substantive Content Analysis: is basically a systematic literature search that involves identifying key words or phrases. Content analysis provides us a method by which we may summarize fairly rigorously certain direct physical evidences of the behavior of and the relationships between, various types of political actor. Documentary analysis and research requires more than just descriptive analysis rather critical analysis in social sciences involves an examination of the assumptions that underpin any account and a consideration of what other prospects are concealed or ruled out.  Qualitative Analysis Structural content analysis: here we are less concerned with what is said than how it is said. We are less concerned with the subtleties of meaning than with styles of presentation. Rather than counting the number of times a word or phrase appears we instead concentrate upon the amount of space or time given to a topic (such as election stop watching), substantive differences such as an accompanying photograph or illustration, the size of news headline, the page placement of a story or the type of reference.  Qualitative Analysis The soundness of a document may also be challenged when different versions of the same document exist (if two different documents pertain to the same thing) or the authenticity of a document can be challenged when it is inconsistent in relation to similar documents. The credibility of the document should be considered. For a document to be credible, we need to be aware of the purpose of the document, was it produced to describe events, to persuade or to self protect. Thank You