Introduction To Research Methods and Study Statistics

Question 1

In what ways is research an ‘organised’ way of finding answers to questions?

Answer 1

Research is organised because there is a structure or method in going about research. It is a planned procedure, not a spontaneous one. It is focussed and limited to a specific scope.

Question 2

What is research?

Answer 2

Research is an organised and systematic way of finding answers to questions.

It is systematic because there is a definite set of procedures and steps which you will follow. There are certain things in the research process which are always done in order the get the most accurate result.

It is organised in that there is a structure or method in going about research. It is a planned procedure, not a spontaneous one. It is focused and limited to a specific scope.

Questions are central to research. If there is no questions, then the answer is of no use. Research is focused on relevant, useful and important questions. Without a question, research has no focus, drive or purpose.

Question 3

Why is it important that the research question is well defined?

Answer 3

A well defined research question is the key to undertaking good research. The question will determine many subsequent issues in protocol development, such as who we should study, what the control should be, what outcomes we should measure. If the research question is muddled, the whole project will likewise be muddled.

Question 4

Most research in medicine is quantitative rather than qualitative. True or false?

Answer 4

True.

Question 5

What is one useful approach that may be used in order to focus a research question?

Answer 5

The PICO approach.

Question 6

Describe the PICO approach of focussing a research question in order to ensure that it is well defined.

Answer 6

P - People, patients or population - who are you asking your question about?

I - Intervention - what intervention are you interested in?

C - Control or comparison - what are you comparing the intervention to?

O - Outcome - what outcome are you interested in?

Question 7

When might qualitative research be required?

Answer 7

Some research questions do not fit easily into the PICO categories, particularly if they involve an investigation area of healthcare about which very little is currently known, or if they are concerned with investigating complex psychological, social or cultural issues. In these situations qualitative research methods may be required and the ‘measuring’ or hypothesis testing approach will be inappropriate. To answer these question we would want to listen to what the people concerned have to say, and we could talk about their ideas and concerns with them. This is where qualitative research would be more useful.

Question 8

What types of data are qualitative?

Answer 8

Qualitative data are text, phrases or sentences spoken (or written) by a study subject recorded by a researcher.

Question 9

What types of data are quantitative?

Answer 9

Quantitative data tend to be collected in a highly standardised way, with the data usually being numerical or categorical.

Question 10

What type of research would be most useful for exprloring new topics, where the issues are not well established or complex?

Answer 10

Qualitative research.

Question 11

What type of research would be most useful for exploring issues that are fairly well understood, relatively simple and unambiguous, and amenable to valid and reliable measurement?

Answer 11

Quantitative research.

Question 12

In addition to defining and refining your research question what else about your research question might you want to consider?

Answer 12

It is also worth considering the relevance of your research question. Some questions are highly relevant to a particular institution or individual but of little relevance out side that setting. Other people are unlikely to be interested in your research findings if they are not relevant to their situation.

Question 13

Describe what studying the epidemiology of disease involves.

Answer 13

Studying the epidemiology of the disease involves the following:

1) . A quantitative description of the distribution of the disease. How much disease is there in any population? What is the distribution of the disease in time, place and person?
2) . Identification of the determinants of variation in disease distribution between and within populations. What factors are associated with an increased risk of disease? What factors seem to protect against disease?
3) . Testing of the hypothesis.

Question 14

What is a cross-sectional study?

Answer 14

A cross-sectional study is a study of population at a specified point in time, used to measure prevalence, and cross-sectional associations between disease prevalence and ‘exposure’.

Question 15

What is a case-controlled study?

Answer 15

In case-controlled studies the characteristics of people with disease (cases) are compared with people without diseases (controls). For example: a case control study of risk factors for lung cancer would compare cases (individuals with lung cancer) with controls (individuals without lung cancer).

Question 16

What is a follow up (longitudinal or cohort) study?

Answer 16

A follow-up study involves following up a defined population over a period of time, and can measure incidence and look prospectively at the association between exposure and onset of disease.

Question 17

What are intervention studies or randomised control trials?

Answer 17

Intervention studies or randomised control trials are trials in which some people receive a treatment or preventive measure, and others get a placebo or different treatment. Clinical trials of new drugs in medicine are an example of this.

Question 18

Rank the following types of study design based on the strength of evidence which each type provides us with for the association between exposure and disease from weakest to strongest: case-control studies, intervention studies, follow-up studies, cross-sectional studies.

Answer 18

1) . Cross-sectional studies
2) . Case-control studies
3) . Follow-up studies
4) . Intervention studies

This order reflects the strength of evidence which each type of study provides us with for the association between exposure and disease. Cross-sectional studies provide relatively weak evidence, whilst intervention studies provide the strongest form of evidence.

Question 19

The ways in which individual diseases are defined and diagnosed tend to fit into four groups. List these groups.

Answer 19

Clinical, statistical, prognostic and operational.

Question 20

Describe the clinical definition of disease.

Answer 20

The clinical definition of disease is based on the recognition of a characteristic pattern of history, current symptoms and physical signs on examination, often supplemented by data from clinical investigation. Thus a diagnosis of asthma might be based on a history of episodic wheezing and breathlessness, wheezing on examination of the chest, and objective evidence of variable airflow obstruction, either spontaneously or in response to treatment. The acquisition of the information necessary to come to this diagnosis may take some time, being an iterative process involving several consultations, and furthermore the diagnosis itself is often based on very subjective criteria that are virtually impossible to standardise. Despite this, many clinical diagnoses (asthma is a good example) are extremely repeatable - that is, they are recognised consistently and clearly by clinicians, even though they are difficult to define or standardise.

Question 21

Describe the statistical definition of disease.

Answer 21

A disease may be defined in terms of a particular attribute or objective measurement value that lies outside of a defined normal range. This is the standard practice in the definition abnormal results in many laboratory investigations, and conventionally 5% of the population tends to be arbitrarily defined as abnormal. An inevitable consequence of this approach to diagnosis is that many of those defined as abnormal by the test result have no clinical symptoms or signs of disease. Disorders of thyroid gland activity, which are now generally defined in terms of laboratory data, are examples of this approach to diagnosis.

Question 22

Describe the prognostic definition and diagnosis of disease.

Answer 22

Some diseases are defined in terms of a measurement, clinical finding, laboratory test result or other characteristic that carries prognostic significance. For example, diabetes mellitus was once a disorder characterised by clinical characteristics of thirst, dehydration and the passage of large amounts of sweet urine. Now the diagnosis of diabetes is based on the presence of raised fasting blood glucose, which is in itself not enough to cause the symptoms of diabetes (such as retinopathy or kidney failure) in the future. The definition of a diagnosis of diabetes has therefore evolved from a clinical to a purely prognostic diagnosis.

Question 23

Describe the operational definition and diagnosis of disease.

Answer 23

Operational definitions of disease are based on the identification of individuals in whom a different management or treatment policy is indicated. Hypertension is another example of a disease that was once recognised clinically, by the occurrence of heart failure, cerebral oedema or other manifestations of a profound and sustained elevation of blood pressure. However, hypertension is now commonly defined as the level of diastolic blood pressure at which doctors institute therapy. Antihypertensive therapy has been shown to reduce the risk of cardiovascular complications if given to patients with a diastolic blood pressure above a certain level; hypertension is therefore defined operationally as the level above which therapy is given.

Question 24

What are the two widely used basic measures of disease in populations?

Answer 24

The two widely used basic measures of disease in populations are prevalence and incidence.

Question 25

What is meant by the prevalence of a disease?

Answer 25

The prevalence of a disease is the number of people in a population with disease at any given time, divided by the total number of people in the population. It is a cross-sectional ‘snapshot’ of disease in a population.

For example, in a survey of eczema in nottingham schoolchildren, of 4643 primary school children surveyed a total of 692 reported that they currently had eczema. The prevalence of eczema is therefore 692/4643, or 14.9%.

Note that prevalence is a proportion, not a rate (it has no component of time in it).

Question 26

What two factors is the prevalence of a disease dependent upon?

Answer 26

Prevalence is dependent on two factors:

1) . The number of new cases (incidence) - the more new cases of the disease, the higher the prevalence.
2) . The duration of the disease - the longer the duration, the higher the prevalence. Duration is influenced by fatality, i.e. whether and how quickly people die from the disease, and recovery, i.e. Whether and how quickly people recover from the condition.

Question 27

What is meant by the incidence of disease?

Answer 27

The incidence of a disease is the number of people who develop a disease over a period of time. Measuring incidence therefore involves taking a population of people (which might be fixed or dynamic), following them for a period of time, and identifying all episodes of disease that occur in this population.

Incidence is a rate, expressing the development of disease per unit of time at risk. For example 10 per 1000 persons per year may be the incidence of death for a particular disease.

Question 28

If we are studying the effect of a new treatment compared to the standard treatment on the length of time to heal a knee injury, what is the ‘exposure’ and what is the ‘outcome’?

Answer 28

In the case the outcome is the length of time to heal for the knee injury, and the exposure is the new or standard treatment.

Question 29

In what way is research ‘systematic’ in finding answers to questions?

Answer 29

Research is systematic because there is a definite set of procedures and steps which you will follow. There are certain things in the research process which are always done in order to get the most accurate results.