Your literature review is missing the point. Qualitative and quantitative analysis have different objectives (e.g. understand the diversity versus model the population) and different approaches to sampling (e.g. saturation versus probability). Words can be used for both qualitative (what was in the words?) and quantitative (count the words) analysis.

Give a try at:

http://www.sagepub.com/upm-data/43454_10.pdf 

Your literature review is missing the point. Qualitative and quantitative analysis have different objectives (e.g. understand the diversity versus model the population) and different approaches to sampling (e.g. saturation versus probability). Words can be used for both qualitative (what was in the words?) and quantitative (count the words) analysis.

Thanks Sandro. The article says it.

Thanks John for the enlightenment.

A useful article:

http://www.hindawi.com/journals/jqre/2010/849043/

Abstract:

Gathered data is frequently not in a numerical form allowing immediate appliance of the quantitative mathematical-statistical methods. In this paper are some basic aspects examining how quantitative-based statistical methodology can be utilized in the analysis of qualitative data sets. The transformation of qualitative data into numeric values is considered as the entrance point to quantitative analysis. Concurrently related publications and impacts of scale transformations are discussed. Subsequently, it is shown how correlation coefficients are usable in conjunction with data aggregation constrains to construct relationship modelling matrices. For illustration, a case study is referenced at which ordinal type ordered qualitative survey answers are allocated to process defining procedures as aggregation levels. Finally options about measuring the adherence of the gathered empirical data to such kind of derived aggregation models are introduced and a statistically based reliability check approach to evaluate the reliability of the chosen model specification is outlined.

Yes, you can apply Nonparametric statistics.

For example, if you want the test the relationship between smoking and profession (or Economic status), you can apply the Chi-square test.

See this link please.

http://toolkit.pellinstitute.org/evaluation-guide/analyze/analyze-quantitative-data/

http://www.investopedia.com/terms/n/nonparametric-statistics.asp

I hope that be helpful for you.

In the attached chapter,  the framework developed by Miles and Huberman (1994) is adopted to describe the major phases of data analysis:

Miles, M.B, and Huberman, A.M. (1994). Qualitative Data Analysis, 2nd Ed., p. 10-12. Newbury Park, CA: Sage

Qualitative modes of data analysis provide ways of discerning, examining, comparing and contrasting, and interpreting meaningful patterns or themes. Meaningfulness is determined by the particular goals and objectives of the project at hand: the same data can be analyzed and synthesized from multiple angles depending on the particular research or evaluation questions being addressed. The varieties of approaches - including ethnography, narrative analysis, discourse analysis, and textual analysis - correspond to different types of data, disciplinary traditions, objectives, and philosophical orientations. However, all share several common characteristics that distinguish them from quantitative analytic approaches.

Throughout the course of qualitative analysis, the analyst should be asking and re asking the following questions:

• What patterns and common themes emerge in responses dealing with specific items? How do these patterns (or lack thereof) help to illuminate the broader study question(s)?
• Are there any deviations from these patterns? If yes, are there any factors that might explain these atypical responses?
• What interesting stories emerge from the responses? How can these stories help to illuminate the broader study question(s)?
• Do any of these patterns or findings suggest that additional data may need to be collected? Do any of the study questions need to be revised?
• Do the patterns that emerge corroborate the findings of any corresponding qualitative analyses that have been conducted? If not, what might explain these discrepancies?

Two basic forms of qualitative analysis, essentially the same in their underlying logic, will be discussed: intra-case analysis and cross-case analysis. A case may be differently defined for different analytic purposes. Depending on the situation, a case could be a single individual, a focus group session, or a program site (Berkowitz, 1996). In terms of the hypothetical project described in Chapter 2, a case will be a single campus. Intra-case analysis will examine a single project site, and cross-case analysis will systematically compare and contrast the eight campuses.

Dear Eddie Seva See,

Research may be quantitative or qualitative, most of the time data is numerical and statistical analysis can be done in both the researches in my view. Thanks

To minimize effects due to likely but not considered appropriately errors in measurements, use of statistical calculations and analysis helps in improving accuracy and approximating the calibration necessary in the process  

There are different ways in which people differentiate qualitative and quantitative data/research.

One is that quantitative is has a metric underlying it, while qualitative does not. This is a standard definition among many in statistics. From this perspective a table of the frequencies cross-tabulating two categorical variables is qualitative. The statistical techniques are typically applied are chi-squared and log-linear models, and are described in books like Goodman's Analyzing Qualitative/Categorical Data book (http://www.amazon.com/Analyzing-Qualitative-Categorical-Data-Goodman/dp/0819141054). This definition seems fairly straightforward and while there can be arguments about some classifications (and methods mapping between them), it is more straightforward in my opinion that the second way to distinguish the phrase.

In some circles the distinction refers to qualitative research having different goals and methods from quantitative research, and sometimes about different subject matters. For example, if someone were looking at political speeches, a "quantitative" approach might count times the phrase "climate change" were used, while a "qualitative" approach might have people judge themes. I am not sure where all the advances in text mining would fit. There will be more disagreements about what fits within each of these categories for this way of distinguishing the phrases.

The choice of whether to do "statistics" (and which procedures to use) on qualitative data for either of these conceptualizations will depend on your research questions. As such, I think you will get more direct and useful responses if you describe your research questions and data.

You can always convert your qualitative data in quantitative ones, by applying a simple number for every 'position' or answer. Then there are several tools in order to proceed.

But then the meaningful interpretation of the results can be difficult or misleading. It depends on how meaningful the numeric coding is.

Example:

You have "disease grades" A-E, where

A: perfectly healthy

B: feeingn a little unwell, lowered overall performance

C: cannot attend endurance sport

D: cannot work

E: needs full-time nursing care

This is kind of typical in medicine; the "stages" are defined by somehow measurable parameters, and the reasons for those may not be similar (physiologic problems, adding wrong behavior/nutrition, adding infection, adding reactions/side-effects of treatments of the former symptoms, adding renal failure, ...)

Say you have 100 patients, 20 in each group.

Drug X works perfectly on "B", making these 20 patients changing to "A".

Drug Y works perfectly on "D" and makes these patiens change to "C".

Drug Z works at all levels, making 20% of the patiens getting into the next better class.

All the drugs obviousely work on different "levels", probably on different "symptoms". If one would code the stages numerically with a score (say from 1-5), then each drug would decrease the "average score" by 0.2 (from 3 to 2.8). This may lead to the over-simplified (and wrong) conclusion that all drugs are similarily useful.

Also finding that the "average reduction in the score" is higher for X than for Y does not indicate that X might be "better" than Y. To define what is "equal" or "better" you need a measure that is related to some aim, to something that makes the stages comparable in "real life". This could be "days of hospitalization", "survival time", "time the patient can continue to work", "nursing costs", etc.

If the scores are defined according to such a measure, then all subsequent numerical calculations of quantitative measures make sense (in relation to what the measure is) indeed. But in reaserch, the stages/levels are usually simply substituted by their ranks (like 1-5), what usually makes little sense for any real-world research question (I would be thankful for getting a counter-exmaple here).

The question seems to suggest an either/or decision to be made. In my view it is important not to be hang up on differences between quantitative and qualitative analyses and consider them as tools that may provide more or less light to the issue at hand but also bearing in mind the 'ifs and buts'. This way there is no harm in combining both tools (mixed model?).

Of course giving to quantitative attributes a numeric is also a state of art, by the same logic that giving a name to a combined mix of factors in PCA is also an art.

Everything in life is art...

How can one make a sensible "either/or decision" when there is no quantitative measure of wins and losses?

Careful: "mixed model" is usually a model that contains both fixed and random effects. I do not understand how this should be related to the current topic.

@Demetris: so true!

Ars conjectandi !

http://books.google.de/books/about/Ars_conjectandi.html?hl=de&id=kD4PAAAAQAAJ

On creating quantities, one of the classics is Luce and Tukey (1964) which is available at:

http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=5524AF694B5E1330627DE0867D987F5B?doi=10.1.1.334.5018&rep=rep1&type=pdf

See Norman Denzin on qualitative analysis.  Moustakas as well for some insight into qualitative research.  There are categorical areas of analysis in qual that do not exist in quant, and so there are terminological confusions throughout when trying to mix the methodologies.  Understanding these confusions will help in determining if you can mix methods in your research.  Categories such as reliability, confirmability, transferability and so forth have interesting connotations for qualitative ventures.  As Barbara infers above: Quantitative tells you what occurred, qualitative tells you why something happened.

Hi Eddie - Another possible route for you to consider is Fuzzy Logic whose aim is to reflect qualitative dimensions in measurement. See for example: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.133.9943&rep=rep1&type=pdf

Cha, I have one question, in Fuzzy Logic application, will there also be an in-between between objectivity and subjectivity?

Daniel, an almost similar question, is subjectivity absent in simultaneous conjoint measurement especially for behavioral studies?

Huda, the guide is helpful in analyzing data, especially nominal data.

Behrouz, the article is meaningful read.

An example of statistical analysis of qualitative data

The technique of path analysis was then used to explore the relationship between the dependent variable and selected independent variables which had been significantly related to it.

This technique was used in the attached article to analyze the results of the study because it provided a tool to employ qualitative nutritional and social data in a rigorous, sophisticated manner. Path analysis is a statistical procedure used to make explicit the rationale underlying conventional regression techniques; it focuses on the problem of the interpretation of variables (Duncan, 1972). The purpose is to discover whether a proposed set of interpretations is consistent throughout (Wright, 1960).

The study sampled 113 preschool children from Tompkins County (Ithaca, New York) Well Baby Clinics and their families to investigate factors affecting the dietary and the nutritional status of the children. Twenty-two percent of this population were determined to be anemic; 31 percent of the childrens' weights and 27 percent of the heights fell below the twenty-fifth percentile of the Boston Growth Standards. Path analysis indicated that the variables exerting predictive influence of the dietary quality were those of sex, ordinal position, mother's employment status, education, and her nutrition education. The model developed accounted for greater than 50 percent of the variance in the dependent variable of dietary quality.

Ref:

Caliendo, M. A., Sanjur, D., Wright, J., & Cummings, G. (1976). Use of path analysis as a statistical technique for the analysis of qualitative nutritional data. Ecology of Food and Nutrition, 5(2), 75-81.

http://www.tandfonline.com/doi/abs/10.1080/03670244.1976.9990448#.VS9b9fmUdic

Behrouz, can we have a statistical (quantitative) research even if our data are "qualitative"?

yes, we can use statistical analysis for qualitative variables. 

I would answer-- It depends.  Statistics in qualitative research would probably be less inferential and more just descriptive, for after all, does that not fit with the purpose of one vs. the other?  In other words, qualitative research has a purpose of in-depth understanding, which is why words are used so much more-- text is very important.  I hesitate to even call words, the "unit of measure," as "measurement"  is not. primary in qual research, but rather, more description for understanding the topic at hand.

For qualitative research, descriptive explanation is important to explore the topic. Writing of text  must be based on in-depth understanding of the issue.

Eddie Seva See Be careful with the terminology, especially when you are writing.  Be clear on design, data collection and then, analysis.  "... can we have a statistical (quantitative) research even if our data are "qualitative"? Stick to quantitative research, as 'statistical' is NOT research and confuses the description/discussion.  If your data is qualitative, what makes the research quantitative?  Is it the design. I'd bet money that your project is actually mixed method using qualitative and quantitative in both the design, data collection, and thus, analysis. Yes?

Mary-Helen, thanks for the comment. Actually my question is a "hypothetical" one and not based on an actual or ongoing study. Eddie