Jig-jiga Health Science College

Medical Laboratory Service

NTQF Level III

Learning Guide #10

Unit of Competence: Process and Interpret Data

Module Title: Processing and Interpreting Data

LG Code: HLT MLS3 LO1-05

TTLM Code: HLT MLS3TTLM 0414v1

TVET-PROGRAMME TITLE: Medical Laboratory Technology level III

MODULE TITLE: Processing and Interpreting Data

MODULE CODE: HLT MLS3M 10 0812

NOMINAL DURATION:

MODULE DESCRIPTION: This module describes the ability to retrieve data, evaluate formulae and
perform scientific calculations, present and interpret information
in tables and graphs and keep accurate records. The unit requires
personnel to solve problems of limited complexity where the
information may be less obvious, but not contradictory, and can
be determined by direct reasoning.

LEARNING OUTCOMES

At the end of this module the learner will be able to:

1. Retrieve and check data

2. Calculate scientific quantities

3. Present data in tables, charts and graphs

4. Interpret data in tables, charts and graphs

5. Keep accurate records and maintain confidentiality

MODULE CONTENTS

LO1. Retrieve and check data

1.1 introduction to data

1.2 quality of data

1.3 forms of data

1.4 correct errors in data collection

LO2. Calculate scientific quantities

2.1 analysis of data

 2.2 statistical test

2.3 reporting calculated data

LO3. Present data in tables, charts and graphs

3.1 methods of data presentation

LO4. Interpret data in tables, charts and graphs

4.1 interpretation and reporting of data

LO5 Keep accurate records and maintain confidentiality

5.1 verification of records

5.2 documentation and recording data

LEARNING METHODS

 Lecture
 Group discussion
 Demonstration
 Practical exercise
 Cooperative training

MODULE ASSESSMENT

 Assessment Methods
 Practical work
 Assignment
 Quiz/tests
 Written test(Exam)
. Oral questions

  Assessment Criteria
LO1. Retrieve and check data

1.1 Stored and retrieved data using appropriate files and/or application software.
1.2 Quality of data is verified using enterprise procedures.
1.3 Rectified errors in data using enterprise procedures

LO2. Calculate scientific quantities

2.1 Statistical values are calculated for given data.

 2.2 Scientific quantities are calculated using given formulae and data and estimated
uncertainties.
2.3 Ensured calculated quantities are consistent with estimations and expectations.
2.4 All calculated quantities using the appropriate units and correct number of significant
figures are reported.

LO3. Present data in tables, charts and graphs

3.1 Data in clearly labeled tables and charts is presented.

3.2 Data is graphed using appropriate scales to span the range of data or display trends.
3.3 all data are reported using the appropriate units and number of significant figures

LO4. Interpret data in tables, charts and graphs

4.1 Significant features of graphs, such as maximum and minimum values, and limit lines are
interpreted.
4.2 trends recognize & reported in data.

LO5. Keep accurate records and maintain confidentiality

5.1 Transcribed information accurately.

5.2 Verified the accuracy of records following enterprise procedures.
5.3 Workplace records are filed & stored in accordance with enterprise procedures.
5.4 All reference documents logically are filed and kept them up-to-date and secured.
5.5 Observed enterprise confidentiality standards.

LO1. Retrieve and check data

The term statistics is used to mean either statistical data or statistical methods
A. STATISTICAL DATA
- Refers to numerical descriptions of facts or figures.
- Are raw materials of statistics
NB: even though statistical data always denote figures (numerical descriptions) it must be
remembered that all numerical descriptions are not statistical data.
CHARACTERISTICS OF STATISTICAL DATA
In order that numerical descriptions may be called statistics, they must possess the
following characteristics
1. Statistical data should be in Aggregates form
 a single fact even though numerically expressed cannot be considered as
statistical data unless it expressed with other data
2. It should be Affected to a marked extent by multiplicity of causes:
Malaria epidemics is caused by - environmental factor
-parasitic load
- Anaphilous mosquito
3. Enumerated or estimated according to reasonable standard accuracy.
 This means that if aggregates of numerical facts are to be called ‘statistics’
they must be reasonably accurate b/c they are a base for statistical
investigation.
4. They must have been collected in a systematic manner for a predetermined
purpose.
5. They must be placed in relation to each other. I.E they must be comparable.
SOURCES OF DATA
 Routinely kept records
A. Registration book
 A document containing patient profile w/c includes
 patient name
 sex
 age
 address
Advantages of Registration book
 easily accessible
 cheap to use
Disadvantages Registration book
 may tear if improperly handled
 may worn out when extensively used for long time

B. electronic method
 computer
 hard disks
 flashes
Advantages
  holds large amount of data
 easy to search specific file/ data
 stays for long time
Disadvantages
 the entire data may be deleted when the computer infected by virus
 cost enough to purchase
 Surveys
 Experiments: direct observation
 External sources (e.g. published Reports, Research Papers)
B. STATISTICAL METHOD
Refers to a body of methods that are used for collecting, organizing, analyzing and
interpreting numerical data for understanding a phenomenon or making wise decisions.
This means of statistics is the one which refers to the study of statistics as a science.
It is a Scientific method which helps us to know better way the object under study
Two types
1. Descriptive statistics
- Includes summarizing, organizing and condensing set of data in to figures
numbers and tables
- It helps set of data to condense variable in to more measurable, simple and
more understood form
2. Inferential statistics
- Tries to answer about the general nature of all things using measurable,
simple and more understood picture and terms
- It estimates characteristics of the whole based on characteristics of apart
- It takes small sample size to determine the whole population
- Branch of modern statistics that is most relevant to public health and clinical
medicine.
- Deals with techniques of making conclusions about the population
- These are the types of statistics most commonly found in research
publication.
Statistical methods are used for research process, as such, descriptive and inferential
statistics helps us for decision making both deductively and inductively

1. Deductive reasoning
- Puts facts from general to specific idea
E.g.1 HIV AIDS is a pandemic disease
What are the factors causes HIV/AIDS?
- Sexual intercourse, stick needle injury, transplacental.
 E.g2 cholesterol level was reported as to be 250 mg/dl
Patients may ask what my chance of attacking heart disease is.
So that specific questions may be asked like Age, sex, and family history
2. Inductive reasoning
- Puts facts from specific to general idea
- Most common type of reasoning for health related cases
E.g. side effect of new drug for patients with particular disease
-do the side effect occurs in males and female equally
-are younger patient more likely to exhibit side effects
-are side effects are uniform from patient to patient
Inductive reasoning is achieved using scientific method which involves
1. Questioning - states the question to be researched
2. Observing – collecting, organizing, and interpreting available data
3. Formulating hypothesis – creating pleasable answer to the research
question
4. Designing the experiment – testing the hypothesis
5. Conducting the experiment – observing the outcome of the experiment
RATIONALE OF STUDYING STATISTICS
In medical/ clinical medicine statistical methods are used:
 To determine the accuracy of measurements
 To compare measurement techniques
 To asses diagnostic tests, to determine normal vales.
 To estimate prognosis and to monitor patients
BIOSTATISTICS/ HEALTH STATISTICS
When the different statistical methods are applied in biological, medical and public health
data, they constitute the discipline of biostatistics. It is an application of statistical method
to biological phenomena.
AIMS OF BIOSTATISTICS: IS concerned with three-fold purpose
 To generate the statistical data through experimental investigation and sample
surveys
 to organize and represent the data in suitable tables, diagrams, charts
 To draw valid inferences from the data collected put forth definite interpretations or
predict the future outcomes from the data.

LIMITATION OF STATISTICS
 It deals with only those subjects of inquiry that are capable of being quantitatively
measured and numerically expressed.
 It deals on aggregates of facts and no importance is attached to individual items-
Suited only if their group characteristics are desired to be studied.
 Statistical data are only approximately and not mathematically correct.
DEFINITION OF COMMON STATISTICAL TERMS
1. Variables
It is the characteristic that takes different values in different persons, places or things. E.g.
height, weight, blood pressure etc.
1.1 Qualitative variables
- Magnitude is absent or implicit
- Measurement made on qualitative variables convey information regarding attribute
E.g. Blood type, marital status, sex
1.2- Quantitative variables
- Variable that has magnitude
- Can be measured on a scale in some appropriate units
Quantitative variable may be further characterized as
a. Numerical Discrete
 Numerically Discrete (Discrete random variable)
 It can only have a finite number of values in any given interval.
 Characterized by gaps or interruptions in the values that can assume.
 That is the measurements are in integers.
b. Numerically Continuous (Continuous random Variable)
 It can have an infinite number of possible values in any given interval.
 Doesn’t possess the gaps or interruptions characteristic of a discrete random
variable
 measurements are resulting from the process of measuring rather than counting
 In continuous data the measurement is capable of being subdivided into smaller and
smaller units.
 Is with the greatest degree of quantification. Each observation theoretically falls
somewhere along a continuum.
2. Data: It is a set of facts expressed in quantitative form.
SCALES OF MEASUREMENT
Measurement – the assignment of numbers to objects or events according to a set of rules
Measuring scales are different according to the degree of precision involved.
Basically there are 4 types of measurement of scale (Data)
1. Nominal Scale
2. Ordinal scale
3. Interval scale and
4. Ratio scale
1. Nominal scale(data)
 Classifies data in to mutually exclusive categories in which no order or rank can be
imposed on the data
  Reflects classification of characteristics, but the characteristics do not indicate any
mathematical or qualitative difference
 It is measurement in which names, labels, or symbols are assigned to each
Measurement to one of a limited number of categories that cannot be ordered.
 We cannot infer any qualitative difference.
 Are discrete types of data?
 Is the lowest measurement scale e.g. b/d group, eye color, religion, sex, marital
status
A good example (involving numbers) is classifying people by ethnicity.
Two types of nominal scale/data
1. Dichotomous nominal scale
# contains only two categories
# is always mutually exclusive
#are an either- or category E.g. male/ female, boys/girls, smokers/nonsmokers etc..
2. Multichotomous nominal scale
# contains more than two categories
# is always mutually exclusive
# is an either- or category
E.g. -Marital status (single, married, divorced, widowed)
-Religion (orthodox, Muslim catholic, protestant)
-types of disease (malaria, tuberculosis, intestinal parasite, typhoid)
2- Ordinal scale (data)
 Classifies data into categories that can be ranked
 Are data which can have meaningful inequality?
 Assigns each measurement to one of a limited number of categories that are ranked
in terms of a graded order
 The spaces or intervals between the categories are not necessarily equal.
E.g. patient status, intelligence of children, socioeconomic status
Satisfaction level (categories may be very satisfied, moderately satisfied, unsatisfied
In the above situation (example), we only know that the data are ordered
3-Interval scale
 Assigns each measurement to one of an unlimited number of categories that are
equally spaced
 The distance between any two measurements is known
 It has no true zero point.
 The point of comparison is the arbitrarily chosen “zero degree”
 Unlike the nominal and ordinal scales is truly quantitative scale.
Example: temperature measured on Celsius or Fahrenheit
4-Ratio scale
 Measurement begins at a true zero point and the scale has equal space.
  Characterized by the fact that equality of ratios as well as equality of intervals may
be determined.
 Highest level of measurement
Example: height, weight, blood pressure
 In both interval and ratio scales, the distance between any two numbers on the scale
are known and are of equal size
 Both interval and ratio scale (data) involve measurement.
DATA COLLECTION METHODS
There are various techniques of data collection methods
1. Observation
2. Documentary sources
3. Questionnaire
3.1 Self-administered
3.2 Mailed
4. Interview
4.1 Face to face
4.2 Telephone
1. Observation
Involves systematically, selecting, watching and recording behaviors of people or other
phenomena for the purpose of getting specified information.
Includes all methods from simple visual observations to the use of high level machines, and
measurements, sophisticated equipment or facilities.
Outlining the guidelines for the observations prior to actual data collection is very useful
Advantages
 Gives relatively more accurate data on behavior and activities
Reduces the chance of incorrect data being recorded
Disadvantages
 Investigators or observer’s own biases, desires etc.
Need more resources and skilled human power during the use of high level machines.
2. Use of documentary sources
Clinical and other Personal records, death certificates, published mortality statistics,
census, publication etc.
Advantages
 Is less time consuming and relatively has low cost.

Disadvantages
 Incompleteness of data.
3. Questionnaire
Usually used and most useful means of collecting data in community survey and research.
The Quality of information Depends up on
 -The quality of your questionnaire and
-Type of your respondents
A questionnaire can be
1. Self administered questionnaires
2. Mailed questionnaires
1. Self Administered questionnaires.
-Is simpler and cheaper
-Can be administered to many respondents simultaneously
-Demand a certain level of education and skill on part of the respondents.
2. Mailed questionnaire
The questionnaires are sent by post to the informants/responses together with a polite
covering letter.
People of a low socio-economic status are less likely to respond to a mailed questionnaire.
The main Problems with postal questionnaire are that response rates tend to be relatively
low
There may be under representation by less literate subjects.
Interview questionnaire
Questions are asked and recorded by interviewers /enumerators.
They can be either face to face or telephone interviews
Advantages
 Give an opportunity to know the people /respondents on a personal basis. I.e.
observations can be made.
 The information obtained is likely to be more accurate
 Can be adopted even in the case where the informants are illiterate
 Reduces the problem of non-response
 Allows for clarification and an interviewer can remove the misinterpretation
Disadvantage
 Sometimes, the presence of interviewer hampers/make movement or progress
difficult the response when some sensitive questions are asked
 Skilled interviewer requires experience and training
 More time is required
 It is costly when the number of peoples to be interviewed is large and they are
spread over wide area

Types of questions
1. Open ended questions
-Respondent is free to use his /her own words to reply
-Respondent is not given any possible answers to choose from
-Are useful to obtain detail information about Facts with which the researcher is not very
familiar with Opinions, attitudes, and suggestions of informants
E.g. “what would you do if you noticed that your daughter (school) girl had a relationship
with a teacher “.
2. Closed questions
In these types, the respondent is provided with some fixed answers and is asked to choose
one out of a list of possible answers.
When designing closed questions one should try to
- Offer a list of option Keep the numbers of options as few as possible.
- Are useful if range of possible responses is known
- Saves Time
- Used to get respondents expression or opinion by choosing rating points on a scale.
Requirements of questions
1. Must have face Validity.
The way in which questions are worded can make or break a questionnaire.
Questions must be phrased in language that’s believed the respondent will understand, and
that all respondents will understand in the same way (unambiguous)
Each question should contain only one idea, “Double barreled” questions are difficult to
answer, and to interpret.
The question should not make unnecessary assumptions about the respondent.
E.g. what is your Present occupation? Assumes that the respondent has an actual
occupation and would not applicable to those unemployed.
Therefore: in this circumstance the “filter” or skip pattern in the Preparation of a
questionnaire is used. In these types of questions there are at least two parts.
The first part determines whether or not the respondent qualifies for further investigation,
while the second part will give more detailed information about those who qualify.
E.g. Question1
Do you have an occupation?
a. Yes
b. No (if no skip to Q.2)
If yes: What is /was your occupation?
2. Must not be offensive
It is wise to avoid questions that may offend (hurt some body’s feeling) the respondent
/e.g. intimate matters/

3. Should be fair.
Questions should not be phrased in a way that suggests a specific answer (leading) should
not be loaded.
Short questions are generally regarded as preferable to long ones.
4. Sensitive questions should be pose as late as possible
Though if may not be possible to avoid asking sensitive questions that may offend
respondents, they must be asked carefully and wisely and should be asked as late as
possible
STEPS IN DESIGING a QUESTIONNAIRE
Designing a good questionnaire always takes several drafts
STEP 1- Content
In the first draft, we should concentrate on the contents.
Consider your objectives and variables as a starting point
Decide what questions will be needed to measure or to define your variables and reach
your objectives.
Step 2- Formulating questions
In the 2nd draft, look critically at the information.
Formulate one or more questions that will provide the information needed for each
variable.
Questions should be specific and precise enough that different respondents do not
interpret them differently.
Cheek whether each question measures one thing at a time.
Avoid leading of questions.
Step 3- Sequencing of questions.
Design your interview schedule or questionnaire to be “consumer friendly”
To Ensure this:
The sequence of questions must be logical for the respondent.
Start with an interesting but non-controversial questions/preferably open/ that are
directly related to the subject of the study.
Use simple everyday Language.
Step 4- Formatting the questionnaire
When formatting a questionnaire, each questionnaire should have:-
Heading: Space to insert number, date of location of the interview.
It could be added the name of the interviewer to facilitate quality control.
Questions belonging together should appear together visually.
Sufficient space should be provided for answers to open-ended questions.
Step 5 translation
The questionnaire has to be translated to standardize the way questions will be asked.
And again retranslated it in to the original language for comparison.
Step 6- Pre-testing of the questionnaire.
Once the questionnaire has been assembled, it should be tried out with people similar to
those to whom it is to be administered, i.e. it should be administered to the people not
included in the sample.
Classification of method of data collection
 Primary data
 Secondary data
1. Primary data
Are collected from the items or individual respondents directly for the purpose of certain
study
- Are original in character
- Are more reliable and accurate
- Are 1st hand information
Advantages
- More reliable than secondary data
- More accurate than secondary data
Disadvantages
- are cost than secondary data
- More time consuming than secondary data
2. Secondary data
- Have been collected by certain people or agency and statistically treated
- Can be obtained from journals, reports, government publication, and other publications.
- are second hand information
Advantages
 Are less expensive to collect both in money and time.
Disadvantages
 Less accurate and reliable than primary data
In general the choice of methods of data collection is based on
Largely on the accuracy of the information they yield
The need for personnel, Skills, equipment etc
The urgency with which results are needed.
The acceptability of the Procedures to the subjects
The Probability that the method will provide a good coverage
The investigator’s familiarity with a study Procedure.
Common Problem in collecting data might include
Language barrier
Lack of adequate time
Expensiveness
Inadequately trained and experienced staff
Cultural Problem (norms /values/.)
Lo2.Calculate simple scientific quantities
METHODS OF DATA ORGANIZATION
 Collected data need to be organized in such a way as to condense the information
they contain in a way that will show patterns of variation clearly.
  Condensation can be done by grouping the data according to their similarity or
affinity
1. ORDERED ARRAY
- Serial arrangement of numerical data in an ascending or descending order.
- a first step in organizing data
- Enables one to determine quickly the value of the smallest measurement, the value
of the largest measurement,
- Other facts about the arranged data that might be needed in hurry.
- Enables us to know the range over which the items are spread and will also get an
idea of their general distribution.
- An appropriate way of Presentation when the data are small in size (usually less
than20)
E.g. A demographer, interested in the number of children a family may have, took a sample
of 30 families and obtained the following observation. Number of children in 30 families

4 2 4 3 2 8

3 4 4 2 2 8

5 3 4 5 4 5

4 3 5 2 7 3

3 6 7 3 8 4
Non- numerical information
can also be represented in a frequency distribution.
E.g. marital status of 60 adults
marital status Number of adults

Single 25

Married 20

Divorced 8

Widowed 7

Total 60

2. Frequency Distributions
Frequency is the number of times a certain value of the variables is repeated in the given
data.
A summarized presentation of the number of observation of the values of a variable
arranged to their magnitude either individually in the case of discrete variable or in classes
in the case of continuous variable.
Frequency distribution has two parts
 The values of the variable
 The number of observations (frequency) corresponding to the values of the
variable on the other hand.
Frequency distributions are tabular representations of a quantitatively classified data.
Frequency distributions are either discrete or continuous according to whether the
variable is discrete or continuous.
A table which involves a listing of all observed values of the variable being studied and how
many times each value is observed.
For data to be more early appreciated and to draw quick comparisons it is often useful to
arrange the data in the form of a table, or in one of a number of D/t graphical forms.

CUMULATIVE AND RELATIVE FREQUENCIES

RELATIVE FREQUENCY
 Express the frequency of each value or class as percentage to the total frequency.
 Is obtained by dividing the class frequency by the total frequency of the distribution.
 Are useful to compare two or more distributions of the same variables but having
different total frequencies.
 Is useful at time to know the proportion, rather than the number, of value falling
within a particular class interval.
CUMULATIVE FREQUENCY
 When frequency of two or more classes are added up.
 Helps to find the total number of item whose values are less than or greater than
some value.
 Is computed by successively cumulating the relative frequencies of each of the
various class intervals

Example: Frequency Distribution of weight (in ounces) of malignant tumors removes From
the Abdomen of 57 subjects

Weight Freq. Cum.Fre Relative

 q. Frequency (%)

10 5 5 0.0877

20 19 24 0.3333

30 10 34 0.1754

40 13 47 0.2281

50 4 51 0.0702

60 4 55 0.0702

70 2 57 0.0352

57 1.000

MEASURES OF CENTRAL TENDENCY

- is the tendency of a set of data to center around certain numerical values
- conveys information regarding the average value of a set of values.
The three common measures of central tendency are:
 MEAN
 MEDIAN
 MODE
1. THE MEAN (ARITHMETIC MEAN OR SIMPLE MEAN)
Is computed by summing all the observations in the sample and dividing the sum by the
number of observations
Is unique for a given set of data, there is one and only one arithmetic mean
There are other means, such as harmonic and geometric means, but in biostatistics we
usually apply arithmetic mean
Symbolically, the means is represented by.
X= x1+x2+x3+----x n or -------------------- for ungrouped data
n
n
∑ xi
X = i= 1
Where
n = total no of observation
X = sample means read as “x bar”
X1 +xi= the first and the ith observation in series of observations respectively.
∑ = is the upper case Greek letter sigma and denotes “the sum of”
x (Lower case) = indicates particular value of a function

x (Upper case) = denote a random variable. Thus

n
∑
i= 1

Indicates the sum is to begin with i=1 and increment by one up to and including the last
observation n.
The mean may be considered as the balance point, or fulcrum, in a distribution of
observations. It considers the magnitude of each observation and is the point that balances
the positive and negative deviations from the fulcrum.
Characteristics of the mean
 Uniqueness
 Simplicity
 Sensitivity to extreme values
ADVANTAGE OF MEAN
 it is easy to calculate and understand ( simplicity)
 It is most amenable to algebraic (mathematical) treatment.
DISADVANTAGES OF MEAN
 Sometimes it is influenced by abnormal values in the distribution i.e. large values
may influence the mean and may distort it so that it no longer is representative of
the typical values of a distribution.
 Sometimes it may even look ridiculous (amazing). E.g. the average No of children
per woman may be reported as 6.2 which never occur in reality.
2. THE MEDIAN
 Is the observation that divides the distribution in to equal parts
 doesn’t depend upon the sum total and the number of observations
 To obtain the median, the observations should be arranged in an array (a list ranked
according to size).
 Is unique, as is true with me the mean, there is only one median for a given set of
data.
 Is that value which divides the set in to two equal parts such that the number of
values equal to or greater than the median is equal to the number of values equal to
less the median
 Is the middle most value.
 For an even number of observations, the median is the average of the two middle
most values.
ADVANTAGE OF MEDIAN
 Is easy to calculate
 is not drastically affected by extreme (abnormal) values as is the mean
 The median is more nearer to the reality and more representative than the mean.
DISADVANTAGE OF MEDIAN
 It is determined mainly by the middle points in a sample and is less sensitive to the
actual numerical values of the remaining data points
THE MODE
 Is the observation that occurs most frequently
 If all the values are different, there is no mode; on the other hand, a set of values
may have more than one mode.
 May be used for describing qualitative data.
Advantages
 It is easy to understand and
 is not affected by extreme (abnormal) values
Disadvantages
 The exact location is often uncertain and often is not clearly defined. Therefore
mode is not frequently used in medical statistics.
 it is even less amenable (responsive) to mathematical treatment than the median
CHOOSING A MEASURE OF CENTRAL TENDENCY
The arithmetic mean is by far the most commonly used because knowing the mean of a
distribution permits one to compare different frequency distributions. I.e. for the purpose
of statistical analysis and inference mean is more likely to be used since it is more
amenable for mathematically manipulations.

Median is preferred when the data have the possibility of extreme values.
Mode is probably most useful when describing the qualitative data
Generally, modes are used for nominal scores, medians for ordinal scores and For the
interval and ratio scale all the 3 measures of central tendency (mean, median, and mode)
can be used

MEASURES OF VARIATION (DISPERSION)

Conveys information regarding the amount of variability present in a set of data (i.e. M of V
describes variability)
The most common measures of variation are:
 The range
 the mean deviation
  the standard deviation
1. THE RANGE
 is the simplest measure of variation
 Is defined as the difference in value between the highest (maximum) and lowest
(minimum) observation
Range= x max –x min.
If we have grouped data the range is taken as the d/ce between the mid points of the
extreme categories.
Advantage
 can be computed quickly
Disadvantage
 The range is not of practical importance because it indicates only the extreme values
and nothing about the dispersion of values between the two extreme values i.e.
Considers only the extremes and doesn’t take in to consideration the bulk of the
observations.
2. VARIANCE/ STANDARD DEVIATION, SD/S
Variance (V) s2
Measures of deviation or dispersion of observations around the mean of a distribution.
The variance is the mean squared difference of the observations from the mean
When the values of asset of observations lie close to their mean, the dispersion is less than
when they are scattered over a wide range.
Is computed by squaring each deviation from the mean, adding them up, and dividing their
sum by one less n, the sample size
Measures dispersion relative to the scatter of the value about their mean
The sample variance may thus be thought of as the mean squared deviation from the
mean, and the greater the deviations, the greater the variance.
STANDARD DEVIATION, SD/S
Variance didn’t represent in observations in their original units, so it is not an appropriate
measure of dispersion when units are required in their original form.
To obtain a measure of dispersion in their original units, we merely take the square root of
the variance which is the standard deviation
 Is also known as root mean square deviation
 Is the most widely used measure of variation?

SD= √ V= √∑ ( x1−x ) ---------------------sample SD

n-1
 SD is computed by extracting the square root of the variance.
Steps in the calculation of S.D
1. Take the deviation of each value from the arithmetic mean. ( x− x )
2. Square each deviation ((x- x )
3. Add up the squared deviations ( ∑ ( x−x ) 2)
4. Divide the result by the number of observations (n-1)
5. Take the square root w/h will be the standard deviation.
Example: If SD= 1.58, it indicates that on the average, observations fall 1.58 units from the
mean.
Both the variance and the standard deviation are measures of variation in a set of data. The
larger they are, the more heterogeneous the distribution (i.e. the larger the S.D, the greater
the variation of values around the mean).
As a measure of variation, standard deviation is much preferred over all other choices;
The units of the SD turn out to be the same as the units of the raw data. (e.g. inches,
Millimeters, kilograms), Whereas the units of variance are squared.
SD is arithmetically easy to handle and avoids the awkwardness of absolute values.
COEFFICIENT OF VARIATION (CV)
Since the SD is the Variability around the mean of the distribution, a direct comparison of
SDs for samples with d/t means would not be much informative. Even if the absolute
magnitudes of the deviations are equal, the degree of variability to each mean could be very
different.
The CV can be compared directly; when two distributions have means of d/t magnitudes a
comparison of their coefficient of variation is therefore much more meaningful than a
comparison of the respective SDs.
CV- is defined as the ratio of the SD as a percentage of the mean
sd
¿
CV = x/¿ X100%
- depicts the size of the standard deviation relative to its mean.
Since both SD and the mean represent the same units, the units cancel out and the
coefficient of variation becomes a pure number. That is, it is free of the measurement units
of the original data. Therefore, it is possible to use it to compare the relative variation of
even unrelated quantities.

LO3. Present data in tables, charts and graphs

METHODS OF DATA PRESENTATION AND SUMMARIZATION
Objectives of data presentation
- It is a step before analysis/ interpretation of the data.
- It involves reduction in the volume of the data. This facilitates better understanding.
 - When the data is presented in the form of tables, graphs or pictures it makes the
data interesting.
DATA PRESENTATION METHODS
The data can be presented fully/ partially in the form of text. Similarly it can be presented
in the form of centering consents, rates, ratios, proportions etc. However, traditionally
these are not considered as methods of data presentation.
The common methods of data presentation are
- Tabular method; frequency table
- Graphical method; bar diagram, line diagram, histogram,
- frequency polygon, pie diagram
SUMMARIZING DATA
Although frequency Distributions serve useful Purposes, there are many situations that
require other types of data summarization.
When data are summarized individual identity will lost b/c of this we make a certain
assumptions about the values when we compute a descriptive measure from grouped data.
Consequently, our results are approximated to the true value.
The Ability to summarize the data by means of a single number is called a descriptive
measure.
Descriptive measurers may be computed from the data of a sample or the data of a
population.
A descriptive measure computed from the data of a sample is called a statistic.
A descriptive measure computed from the data of a population is called a parameter.
There are several types of descriptive measures but the common ones are measures of
central tendency and measures of dispersion.
Statistical tables
An orderly and systematic presentation of numerical data in rows and columns. This
increases its attractiveness and facilitates comparison, analysis and further processing.
CONSTRUCTION OF TABLES
During construction tables the following general Principles should be addressed.
1. Tables should be as simple as possible
2. Tables should be self-explanatory.
 Title should be clear and to the Point
 Title is placed above the table.
 Each row and column should be labeled
 Numerical entities of zero should be explicitly Written rather than indicated by a
dash
 Dashed are reserved for missing or unobserved data.
 Totals should be shown either in the top row and the first column or in the
last row and last column.
3. If data are not original, their sources should be given in a foot note.
ANATOMY OF THE TABLE: the table has three parts. Title, body and foot note
1. The title; includes
- The unit of measurements for the data
- Number given to the table.
- Answer what (explain the content of the table briefly), where (explain the geographical
source of the population), when (define the time with reference to the population).
2. The body
Consists of columns (captions) are vertical arrangements; rows (stubs) are horizontal, cells
and totals Consisting numerical information.
Columns & rows indicate the demarcation of various groups/subgroups compiled out of
the data.
The totals are given in the cell of the last column & rows.
3. The foot note: Indicates the source of the data from where the data contained in the
table has been obtained.
It is a statement that clarifies some specific items given in the table, or explains the
omission thereof (e.g. explanation of any cods, abbreviations, or symbols used)
Example; table 2.1 deaths by sex for major causes, London 1989
(In thousands)
Gender

causes of death Male Female Total

Circulatory system 100 100 200

Neoplasm (cancer) 80 70 150

Respiratory system 30 30 60

Injury and poisoning 10 6 16

Digestive system 8 10 18

Others 20 20 40

Total 248 236 484

Types of tables
Based on the Purpose for W/h the table is designed and the complexity of the relationship,
a table could be either of simple frequency table or cross tabulation.
1. One-way table
Is used when the individual observations involve only a single variable.
The denominators for the Percentages are the sum of all observed frequencies.
Example: Table1 satisfaction level of students of Central Medical College up on their
hospital apparent ship, Addis Ababa feb, 1998 E.C
Satisfaction level Number Percentage (%)

Satisfied 175 175/366X100 = 47.8

Not satisfied 191 191/366X100=52.2

Total 366 100.00

Sources ……..
2. Two way table
- Is used to obtain the frequency Distribution of one variable by the subset of anther
variable.
- Shows two characteristics and is formed when either the caption or the stub is divided in
to two more parts

Example: Table 2.satisfaction level of Central Medical College, Students up on their

hospital apparentship Vs batch (year), Addis Ababa Feb, 1998 E.C

Satisfaction level

Year Satisfied Not satisfied Total

No % No %

35 35 65 65 100&

Year II 22 39.5 34 60.7 56(100%)

Year III 68 52.3 62 47.7 130(100%)

Year IV 50 62.5 30 37.5 80(100%)

Total 175 47.8 191 52.2 366

Sources ------

3. High order table

- Shows three or more characteristics in single table.

Example 3 Distribution of student’s by satisfaction level, sex and year, Addis Ababa, Feb,
1998 E.C
Year Sex Satisfaction Level Total

Satisfied Not
 satisfied

Year I Male 15( ) 35 ( ) 50 ( )

Female 20 ( ) 30 ( ) 50 ( )

Year II Male 20 ( ) 26 ( ) 46 ( )

Female 2( ) 8( ) 10 ( )

Year III Male 55 ( ) 44 ( ) 99 ( )

Female 13 ( ) 18 ( ) ` 31 ( )

Year IV Male 28 ( ) 25 ( ) 53 ( )

Female 22 ( ) 5( ) 27 ( )

Total 175 191 366

(100.00) (100.00 (100.00)

2. DIAGRAMMATIC REPRESENTATION OF DATA

Appropriately Drawn Graph allows readers to obtain rapidly an overall graph of the data
Presented.
Well Designed graphs can be an incredibly powerful means of communicating a great deal
of information using visual techniques.
The relationship b/n number of various magnitudes can usually be seen more quickly and
early from a graph than from a table.
When graphs are poorly designed, they not only do not effectively convey message, but also
they often mislead and confuse.
Importance of diagrammatic Representation
They have grater attraction than figures. They give delight to the eye and add a spark of
interest.
They help in deriving the required information in less time and without any mental strain.
They facilitate comparison.
They may reveal unsuspected patterns in complex set of data and may suggest direction in
which changes are occurring. This makes us to take immediate action.
They have greater memorizing value than mere figures. This is so because the impression
left by the diagram is of a lasting nature.

Limitations of diagrammatic representation

Diagrammatic representation is usually useful for the purposes of comparison. It is not to
be used when comparison is either not possible or is not necessary.
Diagrammatic representation is not an alternative to tabulation.
It can give only an approximate idea and as such where greater accuracy is needed
Diagrams will not be suitable.
They fail to bring to light small differences
CONSTRUCTION OF GRAPHS
- The choice of the particular form among the different possibilities will depend on
personal choices and/or the type of data.
Bar charts and pie- charts are commonly used for qualitative and quantitative discrete data.
Histograms, frequency polygons are used for quantitative continuous data.
During construction of graphs, the following general point has to be considered.
Every graph should be self- explanatory and as simple as possible.
Titles are usually placed below the graph and it should again question what? Where? How
classified.
Keys should be used to differentiate variables of more than one is shown.
The units in to w/h the scale is divided should be clearly indicated.
The axes label should be placed to read from the left side and from the bottom.
COMMON TYPES OF DIAGRAMMATIC REPRESENTATIONS
1. BAR CHART (DIAGRAMS)
Are used to represent and compare the frequency distribution of discrete variables and
attributers or categorical services.
The categories are represented on the base-line (x- axis) at regular interval and the
corresponding values of frequencies or relative frequencies represented on the y-axis is
(ordinal) in the case of vertical bar diagram and vis-versa in the case of horizontal bar
diagram.
Methods of constructing bar graph
All bars drawn in a single study should be of the same width.
The different bars should be separated by equal distances
All the bars should rest on the same line called the base
It is better to construct a diagram on a graph paper.
Types of bar chart (Diagram)
There are d/t types of bar diagrams, the most important ones are:
a) Simple bar chart
Is a one –dimensional diagrams in w/h the bar represented the whole of the magnitude.
The height or length of each bar indicates the size (frequency) of the figure represented.
 % HIV prevalence 30
25
20
15
10
5
0
Female sex Men who have Injecting drug Prisoners Refugees
workers sex with men users

Population

b) Multiple bar charts

Represents the relationships among more them two variables.
Component figures (bars) are shown as separate bars adjoining each other.
The height of each bar represents the Actual value of the component figure.
Example: multiple Bar Charts
Figure 8.3. HIV prevalence rate among pregnant 15- to 19-year-olds at 4 clinic sites, City X,
Country Y, years 1 – 3

c) Component (or sub-divided) bar Diagram

Bars are subdivided in to component parts of the figure.
Are constructed when each total is built up from two or more compo

2. Pie- chart
Useful for qualitative or quantitative discrete data
Shows the relative frequency for each category by dividing a circle in to sectors, the angle
of which is proportional to the relative frequency.
Steps to construct a pie-chart
Construct a frequency table
Change the frequency in to percentage (p)
Change the percentages in to degrees
Where Degree= percentage X360
Draw a circle and divided it accordingly
Example: Pie Chart

3. Histograms (a special kind of bar graph)

Useful for quantitative continuous data
Are frequency distributions with continuous class intervals that have been turned in to
graphs
To construct a histogram, draw the interval boundaries on the horizontal line and the
frequency’s on a vertical line
It is constructed on the bars of the following principles.
a) The horizontal axis
Is continuous scale running from one extreme end of the distribution to the other.
It should be labeled with the name of the variable and the units of measurement.
b) For each class in the distribution a vertical rectangle is drawn with.
i) Its vase on the horizontal axis extending from one class boundary of the class to the other
class boundary.
There will never be any gap b/n the histogram rectangles.
ii) Are bases of all rectangles will be determined by the width of the class intervals.

Figure 8.4. Children living with HIV, District X, 2002

4. Frequency polygon.
To draw a frequency polygon- connect the mid-point of the tops of adjacent rectangles
(cells) of the histogram by a straight line.
When the polygon is continued down to the horizontal axis at the ends at points that would
be the mid points if there were an additional call at each end of the corresponding
histogram. This alones for the total area to be closed. The total area under the frequency
polygon is equal to the area under the histogram.
It is not essential to draw histogram in order to obtain frequency polygon.
It call be drawn without erecting rectangles of histogram as follows.
The scale should be marked in the numerical values of the mid-points of intervals.

5. The line diagram (graph)

Is especially useful for the study of some variables according to the passage of time.
The time, in weeks, months or years is marked along the horizontal axis; and the value of
the quantity that is being studied is marked on the vertical axis.
Points are plotted and joined by line segments in order.
Sometimes two or more graphs are drawn on the same graph paper taking the same scale
so that the plotted graphs are comparable.
LO5. Keep accurate records and maintain confidentiality
Record keeping and confidentiality
Confidentiality requires safe keeping of records
Increasingly, service providers are expected to keep records of interventions with clients.
While this can seem time-consuming and arduous, good record keeping is key to an
effective service, and can help in monitoring and improvement of your service delivery.
Records can also help you in obtaining funding - they are a way of demonstrating the work
you do and the successes you have. This chapter will help you think about your record
keeping process and consider important aspects such as confidentiality, knowledge
management and the Data Protection Act

Minimum Standards
 The provider has policies and procedures for handling information about clients,
including confidentiality and data protection
 Record keeping systems are maintained and regularly monitored
 Staff are trained in the operation of recording systems and understand the scope of
their authority to access information
 Staff understand and work in line with the requirements of the Data Protection Act
 Clients are aware of their rights to access information and are enabled to exercise
these rights
 There are policies and procedures for sharing information with external agencies
and clients are made aware of this on admission.
 Records are written in a clear, concise and impartial manner and are dated and
signed by the author
 Statistical data is made available to inform development of local homelessness
strategy

Introduction: Most service providers keep records in order to:

 manage the daily operation of their projects
 provide better support to clients
 inform the project’s longer term development

Increasingly, recording statistical information about your clients and services is necessary
to satisfy funders and to demonstrate equality of access and non-discriminatory practice.
Remember that although it can seem onerous, recording such information need not be time
consuming and may provide information to back up your funding bids and demonstrate
outcomes.

The systems employed and what information is recorded varies between organizations.
The present trend, however, is towards local co-ordination of recording, for example
common needs assessment, common referral forms, etc.

There are a number of legal and good practice considerations in relation to record keeping.
Therefore the collection and storage of this information needs careful planning, training,
implementation and monitoring.
This section specifically addresses clients’ records. Good practice on records relating to
staffing, finance or other matters can be found in publications such as NCVO guides and
Housing Corporation regulations.

Types of records: Service providers keep a large quantity of information relating to

individual clients, often of a sensitive nature, contained in all or any of the following
records:

 referral and admission forms

 key working notes, agreements, needs assessments, and plans
 resettlement agreements and plans
 needs assessments
 risk assessments and management plans
 minutes of meetings with clients
 records of warnings, exclusions and bans
 Correspondence on behalf of or about clients.

These records are usually combined to form a ‘client file’. Some services have
revolutionized the system of the client or client file by allowing people to look after their
own file. In day centers this system is probably best administered where the worker takes
copies for a central 'staff' file, but this is with the consent and sign off of the client. This
system is felt to be empowering to the clients, and encourage real partnership working on
keywork/support plans.

It is common for larger providers to make use of electronic means of storing data. This
allows information about client to be available across several projects and prevents the
need to duplicate information gathering as the client moves on. These systems also allow
for statistical analysis of data concerning past and present client, which can be useful, for
example, in identifying trends around changing profile of clients and their needs. Even
smaller providers could use computers to develop basic databases of information and to
generate statistics.

As well as client’s records, other records need to be kept of daily operations in:

 log book (day book)

 diary
 hand-over records
 medication records
 accident book (health and safety)
 Incident reporting file.

Confidentiality and recording sensitive information

“Nothing that detracts from the dignity or worth of the client should be included”
Confidentiality: Confidentiality is about who knows what about whom. In service
it involves monitoring who has access to information, what is written about people, and
what information is passed on to external agencies.

There are many different approaches to confidentiality within the sector and there remains
some confusion about confidentiality. Clients and staff need to be clear about the limits to
confidentiality. In other words, under what circumstances staff will pass information to
others without the expressed permission of the client.

Organizations collect and hold a lot of information about clients in order to provide
effective support. Much of this information will be of a sensitive and personal nature. It is
therefore not surprising that some clients feel very uneasy about disclosing information.
They will only be reassured if they are confident that the information will be treated
confidentially.

Unfortunately, there is scope for misunderstanding between staff and clients over what
confidentiality means and the limits to it.

It is important, therefore, that all service providers have a confidentiality policy that
addresses:

 what the organization means by “confidentiality” and why it is important

 what information will be collected
 how it will be recorded
 who will have access to it
 how will it be used
 informed consent – how clients will be asked for consent
 sharing of information within the organization
 sharing of information outside the organization
 circumstances in which information may be shared without the client’s express
consent
 security of electronically stored data (e.g. against hacking)

Principles: Some practitioners prefer to refer to the 'professional use of information'.

This is to say that information on an individual of a personal nature is (only) disclosed
where it is important professionally to do so, in order to provide a better, more joined-up
service or to minimize and be aware of risks.

Confidentiality generally means information is kept within the project. This means that
information given to one member of staff may be shared with other members of staff.
Where the provider has several projects, the policy may state that confidentiality is within
the organization.

The policy should set out under what conditions staff will share information outside the
organization without the consent of the client. This may involve situations where not
divulging information will create serious risk to the client or someone else, or where the
provider is obliged to divulge the information by law to the police or other agency.
Providers should be proactive in working with the local police to ensure mutual
understanding about confidentiality and legal requirements. Clients should be aware of
how information will be disclosed to the police.

The policy should be clear on staff responsibility around handling personal information to
keeping records up-to-date. For example, staff need to be mindful of the environment in
which they are collecting, receiving or viewing sensitive information. Letters, records, and
files (both paper and electronic) should not be written or left where people without
authority can see them. Confidential telephone calls should be conducted in private.

Access to records: The organization’s procedures should make clear who should
have access to each type of record. The main principle is that clients have a right to see
everything recorded about them. However, not every member of staff will need to have
access to every piece of information.

It is important that staff:

 are aware that clients have a right to access the information about them
 Enable clients to exercise this right.

Each organization should have a procedure for enabling clients to view their records.
Access to records is a fundamental right and guaranteed by the Data Protection Act. The
procedure should make accessing records as straightforward as possible.

The procedure may include the following guidelines:

 Find out why the client wants to see the records. they may want to see something
specific, such as the record of a particular incident, and not their whole file
 make an appointment to meet the client with their records
 collate the records, removing all information relating to other people
 Present the records to the client and offer to take them through it. when necessary,
explain how the different records are used and be prepared to answer any questions
clients may have
 Give copies of the records to the client if requested.

Sometimes a client may disagree with what is written about them, for example when they
believe that is not factually accurate. When appropriate, information should be corrected or
deleted. If there is a disagreement about changes then this should be noted on the file and
the matter referred to a manager for review. If there is no agreement then the client should
be able to use the complaints procedure.
Some records may be difficult to share since they contain a lot of information about other
clients. An example is the log book (sometimes called the ‘day book’). The policy should be
clear about how a client may be able to see information relating to them in the log book.
This may have to involve photocopying the parts with relevant information, blanking out
sections referring to other clients.

Good practice for a log book or day book is to record only non-sensitive information about
individuals in it, but refer the reader to the personal files of the individuals concerned,
where they can find more information.

There are rare occasions when a provider may decide to deny a client access from certain
information in their records when revealing it would create a serious risk to a client, staff
or another person. In such cases, staff make a judgment to deny someone one their
fundamental rights. Such decisions should be:

 allowed for in policy and procedures

 agreed by senior managers
 considered in the light of the legal duty under the Data Protection Act
 Recorded appropriately.

Recording information in service and access by clients creates challenges for staff and
managers. Staff may be reluctant to record information about a particularly difficult client if
that person can access the file. These issues need to be addressed by management through
team meetings and supervision.

The Data Protection Act:. It sets down requirements for the transmission and use
of data, and the rights of the individual to access and protect information about themselves.

Staff should be aware of the requirements of the Data Protection Act as:

 they affect their responsibilities and duties;

 they affect the rights of clients

Writing records: Writing records is a professional skill that develops with

experience. Managers should assist their staff to see good record keeping as part of their
professional development.

Extra care should be taken when recording information about clients: all information
recorded should be

 legible
 accurate
 indicate the source of the information
 in plain, jargon-free English
Generally, providers should only record information based on disclosure by the client
themselves, agreed between staff and the client or from direct observation. Great care
should be exercised in situations of uncertainty. Staff should avoid presenting opinion as
fact. If it is necessary to record an opinion, the entry should be clear that it is an opinion
and whose opinion it is. Information provided by other services or individuals should also
be attributed. All entries should be signed / initialed by the person making the entry and
dated.

Staff should bear in mind that anything they write in files may later be made accessible to
an inquiry or court. They should not write anything they would not be prepared to justify
in these situations.

When a client has been in the project for some time, new or locum staff will find it helpful if
the main points / issues and progress is summarized on a sheet near the front of the file.

Systems and Storage: Service providers use many different systems of record-
keeping, paper and electronic, which are often developed over time drawing on the
experiences of staff.

In this section the records are assumed to belong to the organization. However, in some
projects clients keep their own file, which might include copies of their licence agreement,
needs assessment and resettlement plan. They can then take this with them if they move to
another project, preventing the need to start again from scratch. If client’s have their own
file they should be able to have a secure place to keep it.

Accessible: Systems should be as simple as possible and should be designed with the
user in mind. They should aid the daily operation of the project and the support provided
for clients, as well as the longer-term monitoring requirements of the organization.
Standardizing the collection of information through standard forms or (pro formas) helps
ensuring accessibility, consistency and easy maintenance.

Systems should be periodically evaluated taking into account feedback from all users. Staff
will feel happier about using a system when they have been properly consulted on
designing or improving it.

Maintenance: A system only operates effectively if it is regularly maintained and

updated. Policies and job descriptions should make it clear what responsibility each staff
member has with regards the upkeep of records. Systems should be flexible enough so that
they can adapt to meet the needs of project development and organizational change.

Training: New staff should be trained in the use of the organization’s records systems,
including:

 the various records and systems

  their responsibilities in recording information
 the confidentiality policy
 client access to records
 Responsibilities under the Data Protection Act 1998.

Monitoring: Recording systems and procedures should be continually monitored to

ensure that they meet the needs of staff, managers and the requirements of the law. This
could include a regular review cycle as well as random checks. A considerable amount of
staff time is wasted if systems are not maintained, and the daily operation and support
provided to clients undermined.

Sharing Information: Most information that is recorded about clients will be kept
confidential within the project and access only authorized to those who have a need to
know within the staff team. However, there will be occasions when sharing information
with outside agencies is necessary or in the interest of the client. Confidentiality policies
should allow for this, and procedures devised to ensure that the rights of individuals are
upheld.

Clients should give their informed and express consent before information is shared
outside of the project. Informed consent means that the client understands and agrees
what information will be passed on and to whom. They should understand when
information will be shared and the possible consequences.

In certain situations, for example where a client presents a danger to themselves or others,
information may have to be released without their knowledge or consent. This should be
explained at admission and made clear in the house rules or client’s handbook.

In addition, organizations will have arrangements with local police and other organizations
and may disclose information as part of this. Ultimately, files can be legally scrutinized by
law enforcement agencies following the issue of a warrant. Staff and clients should be
aware of when this is appropriate, and the procedures that are followed when this occurs.

In some areas, for example in Birmingham, protocols of information sharing exist in the
network of organizations delivering services to homeless people. These protocols aim to
ensure homeless people receive a good service and do not have to repeatedly face long
interviews giving the same information.

Where these protocols do exist, staff should explain carefully at admission what and how
information will be shared so that the client has some choice in what information he or she
decides to disclose. Where a service is conditional on disclosure of information this also
needs to be clearly stated and the reasons made clear.

If the project is involved in client case conferences involving other agencies, the
organization’s confidentiality policy should cover this and clients should be informed.
Statistical information: Service projects can gather, collate and make available
valuable evidence about the local homelessness situation. Providers should:

 ensure their systems are designed to streamline the collection of relevant data
 Ensure staffs are aware of the importance of this function.

Staff has a responsibility to ensure that they record statistical information accurately and
consistently.

Information from service will be vital in terms of mapping needs for Supporting People and
homelessness strategies:

Disposal of records: Most organizations will keep records for a period after a client
leaves the project. It is good practice to keep all records for at least two years. Some types
of records may need to be kept for longer under legal specifications, for example records
relevant to financial auditing.

The organization’s policy should outline when and how records are to be destroyed. Even
old records contain sensitive information and steps should be taken to ensure they are not
disposed of carelessly. Whenever possible old records should be shredded.