Vous êtes sur la page 1sur 6


1. Four types of experimental designs

Pre-experimental designs
Pre-experimental designs include:
-case study design
-one group pre-test/post-test design
-static group comparison design (cross-sectional study)
Quasi-experimental designs
Quasi-experimental designs include:
-time series design (may include panel design)
-equivalent time samples design
-equivalent materials design
-nonequivalent control group (comparison group) design
-counterbalanced design
-separate sample pre-test/post-test design
-separate sample pre-test/post-test control group design
-multiple time-series design
-recurrent institutional cycle design
-regression/discontinuity analysis
True experimental designs
True experimental designs include:
-Pre-test/post-test control group design
-Solomon four-group design
-post-test only control group design
Statistical designs
Statistical design is one of the oldest branches of statistics, its importance is ever increasing,
especially in the face of the data flood that often faces statisticians.
2. Concepts of Reliability, Validity and Sensitivity
Reliability reflects the amount of error inherent in any measurement.
Reliability is an estimation of the consistency or repeatability of a measurement.
It reflects the degree to which an instrument or scale measures the same way each time it is used under
the same condition with the same subjects .
A reliability coefficient is frequently used to report an estimate of reliability. There should be
compelling evidence that consistent results are achieved across raters (inter-rater reliability) and across
measurement occasions .
Two methods commonly used to estimate reliability are test/retest and internal consistency

Validity is a concept concerned with the extent to which an instrument actually measures what it is
supposed to measure.
It is assessed through different facets (content, construct, criterion, discriminant, and predictive
Validity is an indication of how well an instrument measures what it is truly supposed to measure.
There are numerous types or facets of validity.
Face validity is the easiest to establish. It reflects whether a test or scale appears to measure what it is
intended to measure.
Content validity is similar, but requires more rigorous testing to establish that the concept being
measured represents all essential aspects of the outcome measured (e.g., adherence takes into account
patient report and biomarkers if both are deemed necessary to define adherence).
Construct validity is a bit harder to establish. This means that a test or scale is really measuring the
construct it intends to measure. This is frequently used in psychometric testing and ensures that an
instrument designed to measure a construct such as breastfeeding self efficacy is truly measuring selfefficacy and not a similar construct such as outcome expectancy or motivation
Sensitivity to change corresponds to the property of an instrument to identify small but clinically
significant changes in attitude or practice.
Sensitivity or responsiveness to change is an important attribute of an M&E scale. It must be able to
detect small, but clinically significant changes in a phenomenon over time.
This may be done by comparing longitudinal measures of the same outcome i.e., at baseline and
discharge or a series of measures over time. A nutrition outcome indicator cannot have more than one
scale. For example, if a scale is designed to reflect significant improvement in plasma glucose,
implementation of the scale must be appropriate in both the ICU setting and with patients enrolled in a
diabetes self management clinic. The scale needs to be sensitive to changes in both situations.
3. Advantages and Disadvantages of the Questionnaire Method
Advantage of Questionnaire
It is Practical
Large amounts of information can be collected from a large number of people in a short period
of time and in a relatively cost effective way
Can be carried out by the researcher or by any number of people with limited affect to its
validity and reliability
The results of the questionnaires can usually be quickly and easily quantified by either a
researcher or through the use of a software package
Open-ended questions can generate large amounts of data that can take a long time to process
and analyze. One way of limiting this would be to limit the space available to students so their
responses are concise or to sample the students and survey only a portion of them.
When data has been quantified, it can be used to compare and contrast other research and may
be used to measure change
Positivists believe that quantitative data can be used to create new theories and / or test existing

Disadvantages of Questionnaire

Potentially information can be collected from a large portion of a group. This potential is not
often realized, as returns from questionnaires are usually low. However return rates can be
dramatically improved if the questionnaire is delivered and responded to in class time.
Phenomenologists state that quantitative research is simply an artificial creation by the
researcher, as it is asking only a limited amount of information without explanation
Lacks validity
There is no way to tell how truthful a respondent is being
The respondent may be forgetful or not thinking within the full context of the situation
People may read differently into each question and therefore reply based on their own
interpretation of the question - i.e. what is 'good' to someone may be 'poor' to someone else,
therefore there is a level of subjectivity that is not acknowledged

4. a) Data Editing
Data editing is defined as the process involving the review and adjustment of collected survey
data. The purpose is to control the quality of the collected data.[1] Data editing can be performed
manually, with the assistance of a computer or a combination of both. The editing of the data is not a
complex task but it requires an experienced, talented and knowledgeable person to do so.
Data Editing is the process of checking and adjusting data for omissions, consistency, and
legibility So, the editors task is to check for errors and omissions on questionnaires or other data
collection forms.
When the editor discovers a problem, adjusts the data to make them more complete, consistent,
or readable.
b)Significance - The purpose of data editing
Clarify responses
With editing the data the researcher makes sure that all responses are now very clear to understand.
Bringing clarity is important otherwise the researcher can draw wrong inferences from the data.
Sometimes the respondents make some spelling and grammatical mistakes the editor needs to correct
them. The respondents might not be able to express their opinion in proper wording.
The editor can rephrase the response, but he needs to be very careful in doing so. Any bias can be
introduced by taking the wrong meanings of the respondents point of view.
Make omissions
The editor may also need to make some omissions in the responses. By chance or by some mistake
some responses are left incomplete, the editor has to see what has been an oversight by the respondent.
It depends on the target population how well you get the questionnaires filled. An educated respondent
will fill the questionnaire in a better manner than a person who is not very educated. It also depends on
how much interested the respondent is in filling the questionnaire.

Sometimes the respondents are very reluctant to fill it out. In case, you think that your respondents are
not very much interested, you should take an interview rather than submitting a questionnaire. In the
questionnaire, the respondents will leave blank spaces and you might get noreponse. On the other
hand, in an interview you can better assess what they want to tell and what they are trying to hide.
Avoid biased editing
The editor has a great responsibility to edit the surveyed data or other form of responses. The editor
needs to be very objective and should not try to hide or remove any information. He should not add
anything in the responses without any sound reason. He should have to be confident in making any
changes or corrections in the data. In short, least changes should be made like logical changes.
Make judgements
Sometimes the respondents leave something incomplete, to complete the sentence or a phrase the editor
has to make a judgement. He should have to have good judgement to do so. He should do it so well that
his personal bias do not involve in the responses.
Check handwriting
Handwriting issues needs also be resolved by the editor. Some people write very fast and in this way
they write so that comprehension of the text becomes difficult. In electronically sent questionnaires this
problem never arises.
Logical adjustments
Logical adjustments must be made or otherwise the data will become faulty. There might be need for
some logical corrections, for example, a respondent gives these three answers to the three questions
that have been asked form him;

5. a)Descriptive analysis
Descriptive research can be either quantitative or qualitative. It can involve collections of
quantitative information that can be tabulated along a continuum in numerical form,
such as scores on a test or the number of times a person chooses to use a-certain feature of a
multimedia program, or it can describe categories of information such as gender or patterns of
interaction when using technology in a group situation.
It is brief descriptive coefficients that summarize a given data set, which can be either a
representation of the entire population or a sample of it.
Descriptive analysis are broken down into measures of central tendency and measures of
variability, or spread. Measures of central tendency include the mean, median and mode, while
measures of variability include the standard deviation or variance
Descriptive statistics uses the data to provide descriptions of the population, either through numerical
calculations or graphs or tables. Inferential statistics makes inferences and predictions about a
population based on a sample of data taken from the population in question.

b)Inferential analysis
Inferential statistics is used to make inferences from our data to more general conditions.
Inferential statistics is used to make judgments of the probability that an observed difference between
groups is a dependable one or one that might have happened by chance in this study
Inferential statistics that are useful in experimental and quasi-experimental research design or in
program outcome evaluation
Inferential statistics arise out of the fact that sampling naturally incurs sampling error and thus a sample
is not expected to perfectly represent the population
For instance consider the example of statistics of exam marks of all students in the UK.
It is not feasible to measure all exam marks of all students in the whole of the UK so to measure a
smaller sample of students (e.g., 100 students), which are used to represent the larger population of all
UK students.
Properties of samples, such as the mean or standard deviation, are not called parameters, but statistics.
Inferential statistics are techniques that allow us to use these samples to make generalizations about the
populations from which the samples were drawn.
It is, therefore, important that the sample accurately represents the population. The process of achieving
this is called sampling (sampling strategies are discussed in detail here on our sister site)
6. a) Structure of the Research Report
The reporting requires a structured format and by and large, the process is standardized.
As stated above, the major difference amongst the types of reports is that all the elements that make a
research report would be present only in a detailed technical report.
Usage of theoretical and technical jargon would be higher in the technical report and visual
presentation of data would be higher in the management report.
The process of report formulation and presentation is present.
In the management report, the sequencing of the report might be reversed to suit the needs of the
decision-maker, as here the reader needs to review and absorb the findings.
Format of a Business Report

Title Section includes the Table of Contents and definitions of terms used. Optional details
like the writers name and date prepared on may be mentioned.

Summary an overview of all relevant information on major points, conclusions, and

recommendations. Its a good practice to write this at the end to include all the last minute

Introduction specifies the reason the report was written and the problem it addresses;
generally it is the first page of the report.

Body the main section of the report; it includes industry jargon. Information is arranged in
sections, in decreasing order of importance.

Conclusion this, along with Summary, is the most read section of the report, hence the
language should be simple and specific.

Recommendations actions to be followed in an increasing order of priority.

Appendices technical details and industry facts to support your conclusions.

b) Guidelines for effective report writing

Clear report mandate:
While writing the research problem statement and study background, the writer needs to be absolutely
clear in terms of why and how the problem was formulated. Clearly designed methodology,
Any research study has its unique orientation and scope and thus has a specific and customized
research design, sampling and data collection plan.
Clear representation of findings:
Complete honesty and transparency in stating the treatment of data and editing of missing or contrary
data is extremely critical.
Representativeness of study finding: A good research report is also explicit in terms of extent and
scope of the results obtained, and in terms of the applicability of findings.
Command over the medium: A correct and effective language of communication is critical in putting
ideas and objectives in the vernacular of the reader/decision-maker.
Phrasing protocol: There is a debate about whether or not one makes use of personal pronoun while
reporting. The use of personal pronoun such as I think.. or in my opinion.. lends a subjectivity
and personalization of judgement. Thus, the tone of the reporting should be neutral.
Simplicity of approach: Along with grammatically and structurally correct language, care must be
taken to avoid technical jargon as far as possible. In case it is important to use certain terminology,
then, definition of these terms can be provided in the glossary of terms at the end of the report.
Report formatting and presentation: In terms of paper quality, page margins and font style and size,
a professional standard should be maintained.
The font style must be uniform throughout the report. The topics, subtopics, headings and subheadings
must be construed in the same manner throughout the report. The researcher can provide data relief and
variation by adequately supplementing the text with graphs and figures.