Part One Part One
Variables in Research Variables in Research
The purpose of all research is to describe and explain variance in the world. Variance The purpose of all research is to describe and explain variance in the world. Variance is simply the difference; that is, variation that occurs naturally in the world or change that we is simply the difference; that is, variation that occurs naturally in the world or change that we create as a result of a manipulation. Variables are names that are given to the variance we create as a result of a manipulation. Variables are names that are given to the variance we wish to explain.
wish to explain.
Continuous and Discontinuous Variables (“Research Methods,” n.d.) Continuous and Discontinuous Variables (“Research Methods,” n.d.)
Va
Variables have different properties riables have different properties and to these properties we and to these properties we assign numerical values.assign numerical values. If the val
If the valueues s of a of a vavaririablable e cacan ben be divided into fractionsdivided into fractions ththen wen we cae call ill it at a continuouscontinuous variable.
variable. Such a variable can Such a variable can take infinite nuber of valuestake infinite nuber of values.. !"a#les
!"a#les: Income, temperature, age, or a test score: Income, temperature, age, or a test score
These variables may tae on values within a given range or, in some cases, an infinite These variables may tae on values within a given range or, in some cases, an infinite set.
set.
!ny variabl
!ny variable that e that has a has a limitelimited number of d number of distindistinct values and ct values and whichwhich cannot be divided intocannot be divided into fractions
fractions, is a, is a discontinuous variablediscontinuous variable. Such a variable is also called as. Such a variable is also called as cate$oricacate$orical l variablevariable or
or classclassificaificator% tor% variavariable, ble, or or discdiscretrete e varivariableable. Some variables have only two values,. Some variables have only two values, reflecting the presence or absence of a property.
reflecting the presence or absence of a property.
"xample: employed#unemployed or male#female have two values "xample: employed#unemployed or male#female have two values
These variables are referred to as
These variables are referred to as dichotoousdichotoous. There are others that can . There are others that can tae addedtae added categories such as the demographic variables of race, religion.
categories such as the demographic variables of race, religion.
!n automotive variable, for example, where $%hevrolet$ is assigned a & and $'onda$ is !n automotive variable, for example, where $%hevrolet$ is assigned a & and $'onda$ is assigned a (, provides no option for a &.&)i.e. the values cannot be divided into fractions*. assigned a (, provides no option for a &.&)i.e. the values cannot be divided into fractions*. Continuous and Discontinuous Variables (continuation fro other source)
Cate$orical variables are also nown as discrete or &ualitative variables. %ategorical variables can be further categori+ed as either: nominal, ordinal or dichotomous.
'oinal variables are variables that have two or more categories, but which do not have an intrinsic order. or example, a real estate agent could classify their types of property into distinct categories such as houses, condos, co#ops or bungalows. So $type of property$ is a nominal variable with - categories called houses, condos, co#ops and bungalows. f note, the different categories of a nominal variable can also be referred to as groups or levels of the nominal variable. !nother example of a nominal variable would be classifying where people live in the /S! by state. In this case there will be many more levels of the nominal variable )&0 in fact*.
Dichotoous variables are nominal variables which have only two categories or levels. or example, if we were looing at gender, we would most probably categori+e somebody as either $male$ or $female$. This is an example of a dichotomous variable )and also a nominal variable*. !nother example might be if we ased a person if they owned a mobile phone. 'ere, we may categorise mobile phone ownership as either $1es$ or $2o$. In the real estate agent example, if type of property had been classified as either residential or commercial then $type of property$ would be a dichotomous variable.
Ordinal variables are variables that have two or more categories 3ust lie nominal variables only the categories can also be ordered or raned. So if you ased someone if they lied the policies of the 4emocratic 5arty and they could answer either $2ot very much,6 $They are 7$ or $1es, a lot$ then you have an ordinal variable. 8hy9 ecause you have categories, namely $2ot very much,6 $They are 7$ and $1es, a lot$ and you can ran them from the most positive )1es, a lot*, to the middle response )They are 7*, to the least positive
)2ot very much*. 'owever, whilst we can ran the levels, we cannot place a $value$ to them; we cannot say that $They are 7$ is twice as positive as $2ot very much$ for example.
Others includes
Du% Variables fro uantitative Variables
<Types of Variables6 )=0>=* described that a &uantitative variable can be transfored into a cate$orical variable , called a dummy variable by recoding the values. %onsider the following example: the ?uantitative variable !ge can be classified into five intervals. The values of the associated categorical variable, called dummy variables, are >, =,,-,&:
• @/p to =&A > • @=&, -0 A = • @-0, &0A • @&0, (0A -• @!bove (0A &
Preference Variables
<Types of Variables6 )=0>=* described that preference variables are specific discrete variables, whose values are either in a decreasin$ or increasin$ order. or example, in a survey, a respondent may be ased to indicate the importance of the following nine sources of information in his research and development wor, by using the code @>A for the most important source and @BA for the least important source:
• Citerature published in the country • Citerature published abroad
• Scientific abstracts
• /npublished reports, material, etc.
• 4iscussions with colleagues within the research unit
• 4iscussions with colleagues outside the research unit but within institution • 4iscussions with colleagues outside the institution
• Scientific meetings in the country • Scientific meetings abroad
2ote that preference data are also ordinal. The interval distance from the first preference to the second preference is not the same as, for example, from the sixth to the
seventh preference.
Multi#le Res#onse Variables
<Types of Variables6 )=0>=* described that multiple response variables are those, which can assue ore than one value. ! typical example is a survey ?uestionnaire about the use of computers in research. The respondents were ased to indicate the purpose)s* for which they use computers in their research wor. The respondents could score ore than one cate$or%.
• Statistical analysis
• Cab automationD process control
• 4ata base management, storage and retrieval • Eodeling and simulation
• Scientific and engineering calculations • %omputer aided design )%!4*
• %ommunication and networing • Fraphics
Continuous variables are also nown as &uantitative variables. %ontinuous variables can be further categori+ed as either interval or ratio variables.
*nterval variables are variables for which their central characteristic is that they can be measured along a continuum and they have a numerical value )for example, temperature
measured in degrees %elsius or ahrenheit*. So the difference between =0% and 0% is the same as 0% to -0%. 'owever, temperature measured in degrees %elsius or ahrenheit is 2T a ratio variable.
Ratio variables are interval variables, but with the added condition that 0 )+ero* of the measurement indicates that there is none of that variable. So, temperature measured in degrees %elsius or ahrenheit is not a ratio variable because 0% does not mean there is no temperature. 'owever, temperature measured in 7elvin is a ratio variable as 0 7elvin )often called absolute +ero* indicates that there is no temperature whatsoever. ther examples of ratio variables include height, mass, distance and many more. The name $ratio$ reflects the fact that you can use the ratio of measurements. So, for example, a distance of ten metres is twice the distance of & metres.
Other include
Continuous Ordinal Variables
They occur when the measurements are continuous, but one is not certain whether they are on a linear scale, the only trustworthy information being the ran order of the observations. or example, if a scale is transformed by an exponential, logarithmic or any other nonlinear monotonic transformation, it loses its interval # scale property. 'ere, it would be expedient to replace the observations by their rans )<Types of Variables,6 =0>=*.
De#endent and *nde#endent Variables (“Research Methods,” n.d.)
Gesearchers who focus on causal relations usually begin with an effect, and then search for its causes. The cause variable, or the one that identifies forces or conditions that act on soethin$ else, i s the inde#endent variable. +his is also called e"#lanator% variable (“Variable +%#es,” -). The variable that is the effect or is the result or outcoe of another variable is the de#endent variable )also referred to as outcome variable or effect variable*. +his is also called res#onse variable (“Variable +%#es,” -). The independent variable is $independent of$ prior causes that act on it, whereas the dependent
variable $depends on$ the cause. It is not always easy to determine whether a variable is independent or dependent. Two ?uestions help to identify the independent variable.
/irst, does it come before other variable in time9
0econd, if the variables occur at the same time, does the researcher suggest that one variable has an impact on another variable9
Independent variables affect or have an impact on other variables. 8hen independent variable is present, the dependent variable is also present, and with each unit of i ncrease in the inde#endent variable, there is an increase or decrease in the de#endent variable also .
In other words, the variance in dependent variable is accounted for by the independent variable. 4ependent variable is also referred to as criterion variable.
In the research vocabulary different labels have been associated with the independent and dependent variables lie:
*nde#endent variable De#endent variable 5resumed cause presumed effect
Stimulus Gesponse
5redicted from ... 5redicted to ...
!ntecedent %onse?uence
Eanipulated Eeasured outcome
5redictor %riterion
!"a#le
“Types of Variable” (n.d.) give example as such Imagine that a tutor asks !! students to complete a maths test. The tutor "ants to kno" "hy some students perform better
than others. #hilst the tutor does not kno" the ans"er to this$ she thinks that it might be because of t"o reasons% () some students spend more time revising for their test& and (') some students are naturally more intelligent than others. s such$ the tutor decides to
investigate the effect of revision time and intelligence on the test performance of the !! students. The dependent and independent variables for the study are%
De#endent Variable Test Ear )measured from 0 to >00*
*nde#endent Variables Gevision time )measured in hours* Intelligence )measured using IH score*
Moderatin$ Variable (“Research Methods,” n.d.)
! moderating variable is one that has a strong contin$ent effect on the inde#endent variable1de#endent variable relationshi#. That is, the presence of a third variable )the moderating variable* modifies the original relationship between the independent and the dependent variable.
!"a#le
strong relationship has been observed bet"een the uality of library facilities (*) and the performance of the students (+).
!lthough this relationship is supposed to be true generally, it is nevertheless contingent on the interest and inclination of the students. It means that only those students who have the interest and inclination to use the library will show improved performance in their studies. In this relationship interest and inclination is moderating variable i.e. which moderates the strength of the association between and 1 variables.
*ntervenin$ Variable (“Research Methods,” n.d.)
! basic causal relationship re?uires only independent and dependent variable. ! third type of variable, the intervening variable, appears in more complex causal relationships. It comes between the independent and dependent variables and sho2s the link or echanis bet2een the. !dvances in nowledge depend not only on documenting cause and effect relationship but also on specifying the mechanisms that account for the causal relation. In a
sense, the intervening variable acts as a de#endent variable 2ith res#ect to inde#endent variable and acts as an inde#endent variable to2ard the de#endent variable.
!"a#le
theory of suicide states that married people are less likely to commit suicide than single people. The assumption is that married people have greater social integration (e.g. feelings of belonging to a group or family). ,ence a ma-or cause of one type of suicide "as that people lacked a sense of belonging to group (family). Thus this theory can be restated as a threevariable relationship% marital status (independent variable) causes the degree of social integration (intervening variable)$ "hich affects suicide (dependent variable).
/pecifying the chain of causality makes the linkages in theory clearer and helps a researcher test complex relationships.
!"traneous Variables (“Research Methods,” n.d.)
!n almost infinite number of extraneous variables )"V* exist that might conceivably affect a given relationship. Some can be treated as independent or moderating variables, but most must either be assumed or excluded from the study. Such variables have to be identified by the researcher. In order to identify the true relationship between the independent and the
dependent variable, the effect of the e"traneous variables a% have to be controlled . This is necessary if we are conducting an experiment where the effect of the confounding factors has to be controlled. Confoundin$ factors is another name used for extraneous variables. Other e"#lanator% ters (“Variables in research,” -3)
4ttributes are sub#values of a variable, such as JmaleJ and JfemaleJ. !n exhaustive list contains all possible answers, for example gender could also include Jmale transgenderJ and Jfemale transgenderJ )and both can be pre# or post#operative*.
Mutuall% e"clusive attributes are those that cannot occur at the same time. Thus in a survey a person may be re?uested to select one answer from a list of alternatives )as opposed to selecting as many that might apply*.
5nits are the ways that variables are classified. These include: individuals, groups, social interactions and ob3ects.
Part +2o
Definin$ +ers in Research
It is important to define the different terms one uses in their research paper because the reader will have a better understanding of the topic )<!rt of %raftsmanship, =0>=*.
'ere are a few reasons why it is important to define <ey6 terms one uses in their research paper:
• Eust define <ey6 terms one uses in the research paper to ensure that the reader gets a
better understanding of the topic.
• 4efining the <ey6 terms in the research paper will help the readers now the
definition of words they may have never heard of.
• 4efining the <ey6 terms in the research paper gives the paper more credibility. • 4efining the <ey6 terms in the research paper maes the paper easier to read.
• 4efining the <ey6 terms in the research paper lets the reader now that the writer
understands what they wrote and there will be no confusion regarding the main topic of the research paper.
4 foral definition consists of three #arts. >. The term )word or phrase* to be defined
. The differentiating characteristics that distinguish it from all others of its class
6ere are the 7uidelines in definin$ ters in research (7lobio, -8)
>. nly terms, words, or phrases which have special or uni?ue meanings in the study are defined. or instance, the term non#teaching facilities may be used in the study of the teaching of science. 2on#teaching facilities may be defined as facilities needed by the students and teachers but are not used to explain the lesson or to mae instructions clearer. "xamples are toilets or comfort rooms, electric fans, rest rooms or lounges, and the lie. They may also be called non# instructional facilities.
=. Terms should be defined operationally, that is how they are used in the study. or instance, a study is made about early marriage. 8hat is meant by early marriage9 To mae the meaning clear, early marriage may be defined as one in which the contracting parties are both below eighteen years of age.
. The researcher may develop his own definition from the characteristics of the term defined. Thus, a house of light materials may be defined as one with bamboo or small wooden posts, nipa, buri, or nipa walls; split bamboo floor and cogon or nipa roof. This is also an operational definition.
-. 4efinitions may be taen from encyclopedias, boos, maga+ines and newspaper articles, dictionaries, and other publications but the researcher must acnowledge his sources. 4efinitions taen from published materials are called conceptual or theoretical definitions.
&. 4efinitions should aKbe brief, clear, and une?uivocal as possible.
(. !cronyms should always be spelled out fully especially if it is not commonly nown or if it is used for the first time
9asic Methods of Definin$ +ers (“Methods of Definin$ +ers,” --) The basic methods of defining terms are as follows:
>. !"a#le# Fiving an example is often an effective method of defining terms. Fiving your audience a specific example of the type of program you propose.
=. Coon 5sa$e# In the interest of accuracy and precision, debate propositions must sometimes contain technical terms. ften these terms can be defined effectively by referring to common usage. "stablish a definition clear to the audience. To ?ualify as common usage a term must be commonly understood across lines of gender, age, and culture.
. 4uthorit%# Some terms may be defined most effectively by referring to an authority ?ualified to state the meaning and usage of the term. 4ictionaries, encyclopedias, and boos or articles by recogni+ed scholars are often used as authority for a particular
definition.
-. O#eration1 Some terms are best defined if the advocate provides an operational definition and explains the function or special purpose represented by the terms in a specific context. The use of operation as a method of definition is often lined with the presentation of a plan and is a helpful way of explaining a complex matter.
&. 'e$ation# Sometimes a term may be defined effectively by indicating what it does not mean.
9asic Methods of Definin$ +ers (continuation for other source)
our categories of definitions are offered )<%hapter L: 4efining Terms,6 =0>*:
Parenthetical definition M /sed when defining a word that the reader will easily understand if shown a synonym or alterative phrase. It shows the synonym in parentheses immediately after the word.
!"a#le The software has received many reviewersJ accolades )praises*.
Definin$ #hrase 1 It is sometimes beneficial to use a term as it is used by the profession you are writing about, and to follow the term with a few words to explain it. !"a#le ! technical writer should as a colleague to proof each draft, to read through it for errors.
/oral sentence # ! formula is given for writing a definition in a sentence. Start with the word or phrase, state the class )the category the word belongs to*, and the distinguishing
characteristics that mae it different from other members of its class. "xample: !n operational definition )phrase* is the specific meaning of a word or phrase )class* given to it by the group of people who use the word in their specific context )distinguishing
characteristics*.
!"tended definition # This version of a definition is the longest, offering the freedom to provide insight into the origin of the term, additional meanings, synonyms and antonyms, and more. !dditional terms are defined here that may be used in definitions:
• Denotation # The most basic meaning of a term, usually the first meaning in a
dictionary entry
• Connotation # The most familiar meaning of a term to a user
• 0%non% # !nother word or phrase that has the same or almost the same meaning • 4nton% # !nother word or phrase that has the opposite meaning
• Descri#tion # !s used here, a longer, more detailed description than is provided by a
single formal sentence. This may include a description of each part of a device.
• Contrast # ! discussion of the term as it compares to a term that has a different
meaning
• Co#arison # ! discussion of the term as it relates to a term similar in meaning
• 4nalo$% 1 This method uses similes or metaphors to explain a thing as being lie
something else. "xample: a networ router is a device that wors lie an airport traffic controller, eeping networ signals moving toward their destinations, and avoiding collisions between them.
• Ori$in 1 !n explanation of where a term comes from, who first used it, or the
circumstances in which it was first used.
• !t%olo$% # ! more formal statement about the language roots of a word. Technical
terms may not have actual roots of this sort. The author explains that they are often acronyms that are better understood when the letters or parts of the word are explained.
Definition fallacies are errors a technical writer might mae when writing definitions. Eost are easily understood:
• too technical # the writer has not explained plainly enough;
• too broad # the writer has not focused on what the word means in context;
• too narro2 1 the writer has not given a definition that is general enough that the
reader might recogni+e other cases of the thing being defined; and
• circular 1 typically, the writer has defined a phrase using one of the words in the
phrase, or defined a word using another form of the same word.
9iblio$ra#h%
!rt of %raftsmanship. )=0>=*. Getrieved 4ecember >, =0>&, from http:DDwww.artofcraftsmanship.comDhow#to#define#terms#in#a#research#paper#an# academic#manual
%hapter L: 4efining Terms. )=0>*. Getrieved 4ecember >, =0>&, from http:DDstevevincent.infoDITS>>NL.htm
Flobio, ". )=0>*. Thesis and 4issertation Fuidelines: Thesis 8riting: 4efinition of Terms. Getrieved 4ecember >, =0>&, from http:DDthesisadviser.blogspot.comD=0>D0=Dthesis# writing#definition#of#terms.html
Eethods of 4efining Terms. )=0>0*. Getrieved 4ecember >, =0>&, from http:DDwww.angelfire.comDhi=DmangoDmet.html
Gesearch Eethod. )n.d.*. Getrieved 4ecember >, =0>&, from http:DDwww.+eepedia.comDread.php9
variablesNandNtypesNofNvariablesNmoderatingNvariablesNresearchNmethodsObPL>Oc P(
Types of Variable. )n.d.*. Getrieved 4ecember >, =0>&, from https:DDstatistics.laerd.comDstatistical#guidesDtypes#of#variable.php
Types of Variables. )=0>=*. Getrieved 4ecember >, =0>&, from http:DDwww.unesco.orgDwebworldDidamsDadvguideD%hapt>N.htm
Variable Types. )=0>>*. Getrieved 4ecember >, =0>&, from http:DDwww.oswego.eduDQsrpDstatsDvariableNtypes.htm
Variables in research. )=0>&*. Getrieved 4ecember >, =0>&, from http:DDchangingminds.orgDexplanationsDresearchDmeasurementDvariables.htm