Nature of Biostatistics

Statistics

A science dealing with the collection, organization, analysis, and interpretation of numerical data

Public Health Statistics

Refer to quantitative data needed as basis for planning, monitoring, and evaluation of health services

Vital statistics

Births, deaths, marriage

Health Statistics

Data on morbidity, hospital and clinical statistics, and services statistics

Biostatistics

The scientific discipline focused with the application of statistical principles concerning biological problems

Descriptive statistics

Used to summarize and present data

• Central tendency

• Dispersion and location

• Tabular presentation

• Graphical presentation

Inferential statistics

Used to predictions, generalizations, and conclusions

• Estimation of parameters

• Hypothesis testing

Variable

Refers to measurement or characteristic of interest

Constant

A phenomenon whose value remains the same from person to person, from time to time, or from place to place

Does not have a scale of measurement

Measurement or role in the study

Basis of types of variables

Qualitative

Non-quantifiable categories; numerical representation as labels or codes only

ex. sex, education level, disease status, eye color

Quantitative

Values indicate quantity or amount

Divided into discreet and continuous

Discreet

Assume only integral values or whole numbers (e.g. no. of hospital beds, no. of vaccinated children, no. of HIV cases in Metro Manila)

Continuous

Attain any value including fractions and decimals (e.g. concentration of cholesterol in mg/dL, temperature, PTT results)

Dependent

It is a variable that are studied under the supposition or demand; basically it changes because of the control in the independent variable

Independent

It is a variable that stands alone and isn’t changed by other variables you are trying to measure

Nominal

A classificatory scale used only as labels; represent a set of mutually exclusive and exhaustive classes (e.g. sex, blood groups, gynecologic diagnosis)

Mutually exclusive

Describing two or more events that cannot happen simultaneously

Exhaustive

At least one of the events must occur; includes all

Ordinal

Classes can be ordered or ranked (e.g. disease severity, age groups, rating)

Interval

Distances between all adjacent classes are equal (e.g. Temperature in ^oC, calendar time, NCAE test, Standard IQ Test)

Does not have a true zero point (ARBRITARY)

Ratio

Meaningful zero point exists; Does have a zero point (ABSOLUTE)

Ratio of two values can be meaningfully computed and interpreted (e.g. blood pressure, number of doctor visits, weight and height)

Sampling

Act of studying only a segment of the population to represent the whole; generalizations were made from this sampling

Process of selecting representative number of elements from a population

Census

Complete enumeration of all item in the population

All items are covered and highest is obtained

Involves enormous amount of resources spent such as time, money, and energy

Difficult to apply

Elementary Unit/ Element

Object or person on which information is actually taken or observation is made

Sampling unit

Units which are chosen in selecting the sample and may be made up of non-overlapping collection of elementary units

May be an individual, a household, or a geographical area such as barangay, or a municipality

Sampling frame

A sort of listing or any other material like maps per aerial photographs, which shows the target population

Collection of all the sampling units

Comprehensive, correct, reliable, and appropriate

Sampling design

A definite plan for obtaining a sample from a given population

Type of universe/population

Can be finite or infinite

Sample size

Refers to the number of items to be selected from the universe to constitute a sample

Statistic

Numerical characteristic of a sample

Parameter

Numerical characteristic of a population

Probability/Random Sampling Methods

It gives equal choice of selecting elements in a population when drawing samples

Most used by scientific research

Non-probability/Non-Random Sampling Methods

Does not follow randomization or does not give equal chance of selecting the elements in a population

Selection probability of elementary units can be calculated

Elementary units has a known non-zero chance of being selected

REPRESENTATIVE and ADEQUATE

Convenience Sampling/ Accidental/ Haphazard Sampling

Researcher may use whatever may come at hand or whoever is available

Participant selection based on availability

Quota sampling

A method that follows identifying groups (age, sex, political affiliation, religious, etc.) and elements are sampled from each group at the interviewer’s discretion

Purposive or Judgement Sampling

Researches may implicitly choose a “representative” sample based on experts subjective judgement or some pre-specified criteria

Snowball sampling

Used when research is focused on participants with very specific characteristics

Sampling is not representative however is useful

Used for investigating hard-to-reach groups or hidden groups

Simple Random Sampling

Method of selecting n units out of N population units giving each element equal chance of being chosen

Drawn unit by unit, with or without replacement, from a population

Systematic Sampling

A method of sampling every k unit sample from regular or regular arranged units within the N population size

K = N/n

Stratified sampling

Method of selecting n units out of Ni sub-populations called strata

Variables are MUTUALLY EXCLUSIVE (e.g. urban/rural areas, economic categories, geographic regions, race, sex, etc.)

Equal allocation

Divide the number of sample units n equally among the K strata

Nh = n/K

Proportionate allocation

Make the proportion of each stratum sampled identical to the proportion of the population

f = n/N

Cluster sampling

Each sampling unit is a collection or cluster of elements, which are close together

The total population is divided into small subdivisions and then some of are randomly selected for inclusion in the overall sample

Multi-stage sampling

Sampling is done in more than one stage

Data processing

A systematic procedure ensuring that the information or data gathered are complete, consistent, and appropriate/suitable for data analysis and presentation

Data coding

Conversion of verbal or written information

Refers to grouping the responses from a question into categories and assigning codes and symbols to these categories

Close ended questions

• Field code

• Bracket code

• Factual or Listing code

• Pattern code

Open-ended questions

• Domains

• Numeric codes

Field code

The actual value or information given by the respondent is recorded or coded in the forms

Bracket code

The data are recorded as range of values rather than actual values

Factual or Listing Code

The codes are assigned to a list of categories of a given variable

Pattern code

Applicable for questions with multiple answers

Can be coded as a single numeric cluster containing single or combination responses

Open-ended code

Used for questions that do not have pre-specified answers or choices

Codes should be assigned in the answers before encoding

Classify the respondent’s answers into similar categories or domains

Data encoding

Process of transforming the data written in the questionnaire or form to electonic form

Field editing

Done while still on the field

Immediately done

May involve contacting respondents again

Central editing

Done at the office or meeting place of the research team

Done after data collection was finished

Usually automated