Causal-comparative research design can be defined as a research that permits researchers to study naturally taking place, cause and effect relationship through comparison of data from participant categories who show the variables appealing. Causal-comparative research can even be referred to as ex post facto, Latin for "after the simple fact" (Sowell, 2001). In other words, causal-comparative research can be studied in retrospect since it makes an attempt to ascertain reasons or causes for the prevailing condition between or among sets of individuals. This research design is often found in the domains of education, medicine and public sciences.
According to Sullivan (2001), "The belief that there exists order in the universe, that there are explanations why everything happens, which researchers, using the strategies of research, can discover what those reasons are" points out that experts usually go on to examine why the observed routine are present and what they suggest. For this reason, the basic aspect of causal-comparative strategy involves you start with an effect and seeking for possible causes or vice versa. The essential approach, which involves starting with effects and investigating triggers, is sometimes referred to as retrospective causal-comparative research. Retrospective causal-comparative studies are a lot more common in educational research. In the mean time, the variation which starts with triggers and investigates results is called possible causal-comparative research.
The cause and result relationships may effect how a problem is created and a research design developed. It could be said that the major reason for causal-comparative research is to investigate potential cause-and-effect human relationships that occur in a natural way without manipulation of factors. In this particular research design, researchers look for the reasons why certain forms of behaviour arise. To formulate this research design it needs at least two factors namely impartial and dependent adjustable to support the objective of the research. In this process, it could be said that some 3rd party variable (IV) is the factor, or one of the factors, that produces variance in a dependent variable (DV) (Sullivan, 2001). Consider, for instance a researcher made 3 groups of preschoolers consist of those who never viewed Sesame Neighborhood, those who viewed it sometimes, and those who observed it frequently. The 3 organizations were then analyzed by making contrast over a reading readiness test. Based on the mentioned case study, it demonstrates the independent changing affect the reliant variable. In this case, Sesame Streets is the independent variable (IV) while the preschoolers' reading performance is the based mostly varying (DV).
The Characteristics of Causal-comparative Research
According to Babbie (2013), there are three main characteristics for causal-comparative. Firstly, to infer the presence of a reason and effect romance, the causal-comparative research must display an association between the independent and centered adjustable. Therefore, it involves several organizations and one 3rd party variable. In addition, it determines the cause or effects of dissimilarities that already is present between or among groups of individuals. The teams are given to the treatments and the analysis is completed. The individuals are not randomly allocated to treatment groupings because they were already picked into groups before the research initiated.
In this research, it could be said that cause and impact depends on each other, whereby the reason may precedes the effect or vice versa. It's important to note that the unbiased variables in causal-comparative cannot be manipulated, shouldn't be manipulated, or simply not manipulated but could be manipulated because the independent variable has recently occurred. Thus, it is not possible to manipulate the independent varying.
Causal-comparative research requires the analysis to be non-spurious. In this particular context, non-spurious identifies a causal romance between two parameters. Corresponding to Babbie (2013), spurious relationship is a coincidental statistical correlation between two factors, shown to be triggered by some third variable. However, in causal-comparative research, only two variables are required and not brought on by the action of some third varying, it is therefore shown that causal-comparative research is non-spurious.
There are two types of causes that contribute to this research design, specifically necessary and sufficient triggers. Generally, the word 'cause' is assumed to imply something that produce an impact, result, or effect. A required cause represents an ailment that must be present for the effect to follow. For example, it is necessary that you should attend driving classes in order to get a driving permit. However, by only participating in driving a motor vehicle classes is not a sufficient reason behind getting a certificate. It is because it is required to pass the travelling test to have the driving permit.
On the other palm, an adequate cause represents a condition that, if it's present, guarantees the effect involved (Babbie, 2013). This is not to say a sufficient cause is the sole possible cause of a particular result. Take the circumstance of the traveling test mentioned before; not joining the test will be a sufficient cause for faltering it, though students could are unsuccessful it in different ways as well. Thus, a reason can be sufficient, but not necessary.
Design and Procedure
The selection of the comparison categories is vital in causal-comparative process. Although the 3rd party variable is not manipulated, there are control strategies that may be exercised to increase the interpretation of results. The researcher chooses two sets of individuals, the experimental and control groupings, but more effectively referred to as comparison groups. These two groups may differ in two ways; whether one group has a characteristic that the other will not or each group has the characteristic, but they differ in conditions of certifications and volumes. The independent adjustable differentiating the groupings must be clearly and operationally identified, since each group represents a different people. In planning this research, the arbitrary sample is decided on from two already existing populations, rather than from an individual population.
A causal-comparative design is chosen, for example, when research workers want to study the possible influences of Montessori school enrolment on children's mathematical ability. Researchers find a population in which several degrees of mathematical potential are recognized to exist and then select a sample of members. The researchers accumulate data from all participants on options of mathematical ability and college enrolment. Once they have accumulated their data, researchers decide how many levels of mathematical ability they would like to study. In this case, suppose the research workers want two teams. They could classify the participants' scores consequently from highest to lowest, and then find the middle credit score of the list. Those participants whose steps are above the middle score are chosen as "high numerical ability" and the ones below it, "low mathematical ability".
Next, the experts compare process performance scores in each group to see whether Montessori institution enrolment seems to influence task performance. You will find three possibilities that can emerge from the study.
Montessori university children have higher scores than non-Montessori school children.
Montessori institution children have lower ratings than non-Montessori institution children.
No discernible structure shows in the ratings of Montessori and non-Montessori college children.
This shows that each statement suggests a possible marriage between the two variables that happen to be Montessori college enrolment and the children's numerical ability.
Measurement of second variable
Group B
Group A
Measurement of first adjustable determines group placements of participants
Participant selection
Generalized example
Montessori college children
Participant selection
Measurement of mathematical ability
Measurement of Montessori school enrolment
Non-Montessori university children
Example of institution enrolment and mathematical ability
FIGURE 1: Techniques in causal-comparative designs.
3. 1 Control Procedures
In other research design, random assignment of participants to groups is probably the best way to try to ensure equality of groups, but random assignment is not possible in causal comparative studies because the communities are naturally created before the start of study. There's a possibility to have extraneous changing in a causal comparative research that may affect the overall purpose of the study. Thus, control techniques are being used to compare the sample organizations equally. You will find three common control techniques you can use, namely matching, comparing homogenous groups or subgroups and research of covariance.
Matching can be explained as a technique for equating groups on one or more variables. If research workers identify a variable likely to influence performance on the dependent variable, they may control for this variable by pair-wise matching of participants. In other words, for each and every participant in one group, the researcher detects a participant in the other group with the same or very similar credit score on the control adjustable. If a participant in other group does not have the right match, the participant is taken away from the study. Thus, the producing match groups are equivalent or very similar with respect to the identified extraneous adjustable.
Another way to regulate extraneous variable is to compare groups that are homogenous with respect to the extraneous variable. The greater similar both groupings are on such variables, a lot more homogenous these are on everything however the variable of interest. This homogeneity makes a better study and reduces the amount of possible alternative, explanations of the study findings. And in addition, then, a number of control strategies correct for identified in equalities on such factors. This approach also enables the researcher to ascertain whether the goal grouping variable affects the dependent variable differently at different degrees of control variable. That's, the researcher can analyze whether the effect on the based mostly variable is different for every single subgroup.
Analysis of covariance is a statistical technique used to adapt initial group distinctions on variables used in causal comparative and experimental studies. Essentially, analysis of covariance adjusts results on a centered variable for primary differences on some other varying related to performance on the reliant variable. Analysis of covariance statistically adjusts the results of the group to remove the initial advantage so that at the end of the analysis, the results can be rather compared, as if the two groupings started similarly.
4. Data Analysis and Interpretation
Analysis of data in causal-comparative research involves a number of descriptive and inferential information. The mostly used descriptive statistics are signify and standard deviation. Mean reveals the average performance of a group on some measure of a variable. Standard deviation is a measure of the dispersion of a set of data from its mean. A lot more spread apart the data, the bigger the deviation. Standard deviation is computed as the square root of variance.
The most commonly used inferential statistics are t assessments, analysis of variance (ANOVA) and chi square. T testing are used to determine whether the method of two communities are statistically not the same as one another. ANOVA is used to determine if there is significant difference among the list of means of three or more groupings. Babbie (2013) defined chi square as a frequently used test of relevance in social science. In other words chi square checks are used to determine whether there is an association between two or more categories. Chi square test clarifies that recognized frequencies of the things or events in categories are weighed against expected frequencies.
Similarities and Dissimilarities between Related Research Designs
Causal-comparative versus Correlational Research
It is way better to learn that the major purpose of correlational research is to determine the magnitude and course of organizations or relationships among variables. Despite having different goal, correlational research may also be mixed up with causal-comparative since both shortage manipulation of variables and requires extreme care in interpreting results. In addition, both researches seek to explore romantic relationships among variables, and when relationships are determined, both research designs are often studied at a later time by means of experimental research.
However, causal-comparative and correlational research still can be differentiated. Compared to correlational research, causal-comparative compare two or more groups of themes, whereas correlational research only give attention to one group. Furthermore, correlational research does not have any attempts to understand cause and impact whereas; causal-comparative studies' goal is to identify the reason and effect interactions between the parameters. Apart from that, correlational research includes several factors and one group while causal-comparative includes two or more teams and one 3rd party variable.
Causal-comparative versus Experimental Design
Causal-comparative can even be puzzled with experimental research both try to establish cause-effect human relationships between variables and both require group comparisons. In addition, both causal-comparative and experimental research can test hypotheses concerning the relationship between an unbiased varying and a based mostly variable.
The difference between the two researches is the fact in causal-comparative, the folks are already in groups before study commences, whereas in experimental design, individuals are randomly given to treatment or control teams. Moreover, the random sample studies for causal-comparative is picked from two already-existing populations, while in experimental research, the arbitrary sample is selected from only one human population. The researcher in experimental research manipulates the unbiased varying; that is, the researcher determines who's heading to get what treatment. In contrast, in causal-comparative research, folks are not randomly assigned to treatment categories because they're in established teams before the research commences. The example for the set up group can be male or female, school graduates or non-graduates. In causal-comparative research the groups are already formed and already are different in terms of the key variable involved. Quite simply, the independent varying in experimental research can be manipulated by the researcher to look for the research's effect, whereas the independent varying in causal-comparative cannot be manipulated because the independent variable has recently occurred.
Advantages of Causal-Comparative Research
Like other research designs, causal-comparative research has its power and weaknesses. One of the strengths is the fact that the causes are being studied after they presumably have applied their effect on another adjustable. The research workers might administer a questionnaire to review the causes or they can also do interviews and observation to find the cause or impact related with their research. For instance, a researcher may hypothesize that participant in preschool education is the major factor contributing to distinctions in the communal modification of first graders. To look at this hypothesis, the researcher would select a sample of first graders who had participated in pre-school education and an example of first graders who had not and would then compare the sociable adjustment of the two groups. If the kids who participated in pre-school education exhibited the higher level of public adjustment, the researcher's hypothesis would be backed. Thus, the basic causal-comparative approach entail starting with an impact (i. e. , social modification) and seeking possible causes (i. e. , performed pre-school affect it).
Another good thing about causal-comparative research method is that it allows us to study cause-and-effect human relationships under conditions where experimental manipulation is difficult or impossible. Unlike experimental research, the varying in causal comparative research is not manipulated because it has already occurred. For instance, a researcher might be enthusiastic about determining the effect of poor parenting on the issue of juvenile delinquency. Obviously it could not be honest to approach the parents and ask about how exactly they raise their children since it is too personal to go over family issues for an outsider. Thus, causal comparative research enables investigation on a number of parameters that cannot be researched experimentally.
In addition, causal-comparative studies help identify variables worth experimental investigation. Actually, causal comparative studies are conducted exclusively to recognize the probable result associated with an experimental study. Quite simply, many romantic relationships can be examined within a research study. Assume for example, a researcher were considering implementing computer helped terminology learning in the institution system. Before employing the mentioned program, the researcher might consider attempting it from an experimental basis for annually in several universities or classrooms. However, even such limited adoption would require costly new equipment and instructor training. Thus, as an initial measure, to see your choice, the researcher could carry out a causal comparative research to compare the British language achievements of students in institution who are using the instruction with the English language accomplishment who aren't using it. If the results mentioned that the students learning through computer helped language learning instruction were obtaining higher results, the researcher may possibly decide to go ahead with an experimental tryout of computer helped language learning instructions. If no differences were found, the researcher may possibly not go ahead with the experimental tryout to save lots of time, cost and work.
Disadvantages of Causal-Comparative Research
Despite its many advantages, causal comparative research has some serious limitations to be extreme care of. In causal comparative research, the researcher has limited control over the study and extreme caution must be employed in interpreting results. It is because the groups already are formed at the start of the study. An visible cause-effect relation may well not be as it seems. The alleged reason behind an observed impact may in reality be the effect itself, or, a 3rd variable may have induced both the obvious cause and the effect. Quite simply, an observed relationship between changing A and B can mean that A triggers B, B causes B, or a 3rd variable C triggers both A and B.
A
causes
C
causes
B
A
B
causes
B
B
causes
Figure 2: Relationships of variables
For example, suppose a researcher hypothesized that enrolment to preschool is a determinant of reading accomplishment. The researcher would compare the achievement of two communities, one comprising individuals with children who went to preschool and children who didn't go to preschool. If those who went to preschool performed better on reading options, the researcher could be enticed to summarize that going to preschool influences reading accomplishment. However, this summary would be groundless. As the participants arrived at the start of the study with an established group of children who went to preschool and children who did not, and a recognised level of reading achievement, it isn't possible to determine which came first and which influence the other. Additionally, it is very plausible that some third varying, such as parental frame of mind, is the main affect on both reading achievement and pre-schooling. For instance, parents who directed their children to preschool and encourage their children may have children who've higher reading success.
Analysis of Studies Using Causal-comparative Research Design
"One of the major studies within the field of Second Terms Acquisition (SLA) research is the different rates of success with which children and parents achieve nativelike effectiveness in another dialect (L2)". () It is also common in SLA studies that largely L2 learners do not attain nativelike effectiveness because of their first language maintenance. In a study report entitled "Does first words maintenance hamper nativelikeness in a second terms?" by Bylund, Abrahamsson and Hyltensam of Stockholm University or college, they try to treat the role of L1 skills in L2 attainment. In such a study, the experts hypothesized that the second dialect learners do not attain nativelike skills because of their first dialect maintenance. It really is identified that the self-employed changing in this research is the first dialect maintenance, whereas, the centered variable is the nativelikeness in another language. It implies that there is plainly an association between the two variables because the independent variable (IV), which is the first terminology maintenance might probably have an impact on the dependent changing, which is the next language.
To look at the hypothesis, the researchers decide on a sample population contains Spanish-speaking immigrant community in Sweden, where residents of Chilean origins are locally. 30 L1 Spanish-and L2 Swedish residents participated in the study where they acquire their second terms before the years of twelve. The bilinguals originated from countries throughout Latin America with a specific concentration in Chile. The members were either university students or degree-holder. A common denominator of the members was that they exhibited a generally high level of L2 proficiency. For the second group, fifteen local sound system of Spanish and fifteen native speaker systems of Swedish were recruited as monolingual adjustments. The experts choose small test populations to signify the study populations. The control categories were matched to the bilingual participants by educational level. Along the way of coordinating the variables and groups, it could be said that 100 % pure monolingualism had not been a criterion for participation, and a lot of the participants had foreign language skills such as English language. In addition, none of the control individuals had lived in foreign countries for just about any significant amount of time in a setting in which their spanish skills could be employed. These two categories will be referred to as Spanish-speaking control and Swedish-speaking controls participants.
Bilingual individuals were tested individually in each terminology on two different events. The bilinguals and the Swedish-speaking control buttons were analyzed in the same setting and teachers and the Spanish-speaking controls were analyzed in another setting with another teacher. The language proficiency of the individuals were looked into by piloting a grammaticality wisdom test (GJT) to learn about the sample's grammatical intuition. Furthermore, in order to gauge the members' semantic and grammatical inferencing skills, a cloze test was piloted to all participants.
