EPIDEMIOLGY AND BIOSTATISTICS

CMT 05101

INTRODUCTION TO BIOSTATISTICS

Learning ObjectivesBy the end of this session students should be able to:• Define terms used in Biostatistics• Explain the significance for studying biostatistics in

medical field• Mention the application of statistics• Describe descriptive methods for qualitative data

INTRODUCTION

Biostatistics• Development and application of statistical

techniques to scientific research relating to life (Human, plant and Animal).

• But here the focus is on human life and health– Pharmacology– Medicine– Epidemiology– Anatomy and physiology, etc.

Statistics• Branch of mathematics concerned

with collection, classification, analysis, and interpretation of numerical facts or data, for drawing inferences on the basis of their quantifiable likelihood (probability).

• Statistics can interpret aggregates of data too large to be intelligible by ordinary observation because such data tend to behave in regular, predictable manner

INTRODUCTION

Statistics• A field which examines the collection,

organization, summarization and analysis of data, and draws inferences regarding that data for a population through observation of a sample.

INTRODUCTION

Data • A representation of facts, concepts or instructions

in a formalised manner suitable for communication, interpretation, or processing by humans or by automatic means. (Hicks [1993: 668] quoted by Checkland and Holwell [1998])

• The raw material of statistics, consisting of numbers of measurement or counting of a population sample.

INTRODUCTION

Population• The totality of individuals or units of interest.

For example, there could be a population of blood samples collected in a year. If the interest is restricted to only suspected cases of liver diseases, the population comprises blood samples of such cases only. If the interest is further restricted to the cases attending OPD in a group of hospitals, the population is also accordingly restricted.

INTRODUCTION

Sample• A set of data collected and/or selected from

a statistical population. It is therefore a part of a population obtained by a defined procedure.

INTRODUCTION

Parameter• A summary measure for any characteristic in

the target population, for example, percentage of cirrhosis patients with high Aspartate Aminotransferase, or rate of increase of systolic blood pressure in healthy subjects per year of age. The parameter pertains to the entire population of interest and not to the sample.

• A descriptive measure calculated from the data of a population.

INTRODUCTION

Variable• A characteristic that varies from person to

person, or from situation to situation. For example, Platelet count in different persons is variable but number of eyes or number of fingers is not a variable.

• There are two main types of variable– Qualitative variable– Quantitative variable

INTRODUCTION

Qualitative variable• Data that is not given numerically, e.g place of

birth, gender/sex, favorite of food, level of education etc

Quantitative variable• Given numerically. Subdivided into two types– Discrete variable —Take specific numeric value or

number of possible values, for example, Parity for a woman, number of patients are discrete variables.

INTRODUCTION

– Continuous variable — A variable that can theoretically have infinite number of possible values within a short range. Age is continuous since within 8 and 12, it can be 8.17, 10.874, 9.756 years, etc. Age can be measured in terms of days, hours and minutes, although practically there is no need to do this. Blood pressure is a continuous variable but measured in integers for convenience. Parity is not a continuous variable because there is no possibility of it being 2.75 or 1.6.

INTRODUCTION

Levels of Variable Measurement

• Four levels of measurement have been identified. These levels differ in how closely they approach the structure of the number system we use.

• Understanding the level of measurement of variables used in research is important because the level of measurement determines the types of statistical analyses that can be conducted.

• The conclusions that can be drawn from research depend on the statistical analysis used.

• Nominal level measurement uses symbols to classify observations into mutually exclusive and exhaustive categories. – Mutually exclusive means the categories must be

distinct so that no observation falls into more than one category.

– Exhaustive means sufficient categories must exist so that all observations fall into some category.

Levels of Variable Measurement

Levels of Measurement: Nominal• This is the most basic level of measurement. • At this level we can determine only whether

two observations are alike or different. • Example: In a survey of teachers, sex was

determined by a question. Observations were sorted into two mutually exclusive and exhaustive categories, male and female. Observations could be labeled with the letters M and F, or the numerals 0 and 1.

• In the same survey the variable of marital status could be measured by two categories, married and unmarried.

• But, these categories must each be defined so that all possible observations will fit into one category but no more than one: legally married, common-law marriage, religious marriage, civil marriage, living together, never married, divorced, informally separated, legally separated, widowed, etc

Levels of Measurement: Nominal

• In nominal measurement, all observations in one category are alike on some property and differ from the members in the other category on that property (e.g., sex, martial status).

• On ordering of categories exists. We cannot say one category is better or worse, or more or less than another.

Levels of Measurement: Nominal

• Ordinal level of measurement uses symbols to classify observations into categories that are not only mutually exclusive and exhaustive. In addition, the categories have some explicit relationship among them.

• Observations may be classified into categories such as taller and shorter, greater and lesser, faster and slower, harder and easier, and so forth.

• The categories must be exhaustive and mutually exclusive.

Levels of Measurement: Ordinal

• Most questionnaires use Likert type items. For example, we may ask teachers about their job satisfaction.

• Asking whether a teachers is very satisfied, satisfied, neutral, dissatisfied, or very dissatisfied is using an ordinal scale of measurement.

Levels of Measurement: Ordinal

Level of Measurement: Interval• The interval level of measurement classifies

observations into mutually exclusive and exhaustive categories that have some explicit relationship among them, and the relationship between the categories is known and exact. This is the first quantitative application of numbers.

• In the interval level of measurement, a common and constant unit of measurement is established between the categories. For example, measures of temperature are interval scales.

• A temperature of 75° is one degree cooler than a temperature of 76°; likewise, a temperature of 32° is one degree warmer than a temperature of 31°.

Level of Measurement: Interval

• Numbers may be assigned to observations because the relationship between any two categories is assumed to be the same as the relationship between numbers in the number system. For example, 76-1=75 and 31+1=32.

• Intervals between categories are equal but they originate from some arbitrary point of origin. No meaningful zero point exists.

Level of Measurement: Interval

Levels of Measurement: Ratio• The ratio level is the same as the interval level

with the addition of a meaningful and non-arbitrary zero point.

• Examples: Weight, area, speed, velocity. In education, budgets and number of students are measured on ratio scales.

Descriptive Methods for Qualitative DataFrequency distribution • A statistical distribution of subjects that displays

the number of subjects with different levels of measurement, e.g., how many have diastolic blood pressure <70 mmHg, how many between 70-74, 75-79, etc.

• It gives a picture of the shape of the distribution of the data.

Unimodal, Bimodal and Multimodal Distribution

• Distributions of data can have few or many peaks. Distributions with one clear peak are called unimodal, and distributions with two clear peaks are called bimodal. That with more than two peaks is called multimoda data

• Frequency distribution can be displayed as a table, bar chart, histogram or pie chat

What is the Role of Biostatistics in Modern Medicine?

• Helps to determine disease burden in the population

• Finding new drug treatment for diseases• Planning and allocation of resources• Used in research projects• Used in Quality Improvement programs• Used to measure performance outcome