Paper Topic:

Research Desing and experiments for M5

According to McBurney and White (2003 , an experiment can be defined as a research procedure in which the scientist must select subjects for different conditions from pre-existing groups (qtd . in Marks , 2006 This experiment appears to fall into the category of quasi-experiment and two of the main contributors to this are the seeming lack of randomization and the internal validity threat posed by the limited testing variables . In addition to this , the design for this experiment appears to lack detail , so that several other areas could exist in which internal and external

validity might be compromised . Such details that are lacking include sample size and protocol , which do have a direct effect on the validity of any experiment

Although Rafael 's hypothesis appears acceptable , the experiment would fail to be a true one because of the fact that he mentions nothing about the randomization of his subject . Though the initial selection of children might be a random one , this information is not given in his design . If , for example , these children are chosen randomly ' from the park , a certain amount of bias might already have been introduced into the experiment , as it might already be selecting children who have experience playing (formally or informally ) on teams . In any case , it is important to specify how the initial sample of children will be selected

However , it is clear that the assignment of children to different testing groups will not be random at all , as it will be based on the students ' answers to the self-efficacy measure . If this self efficacy measure is to be the actual experiment , then this would have to be termed a quasi-experiment because of the lack of a control group . If however , the self-efficacy measure is used to separate the groups into testing and control group , then the experiment might already be biased True experiments randomize not just the initially selected group of participants , but also their placements into testing and control groups (Chevalier , 2003 Losh , 2002

It might be that Rafael has chosen on purpose to assign these groups based on their differences as a method of somehow testing those differences . However , what also makes this a quasi-experiment is the fact that Rafael has made no allowance for the possibility (or rather the probability ) that these children differ according to other variables that have not been made a part of the experiment . Whenever prior information is known about existing differences between the testing and control groups , researchers are expected to put into place statistical controls for these differences (Losh , 2002 Marks , 2006 . For example some students might have low efficacy for baseball because they have not been exposed enough to it , but be highly interested in playing for a team because they love the game and would like to learn . Yet , these same children might not be able to do this because of prior engagements , lack of parental support , or any number of other reasons . Rafael 's experiment lacks detail on how to deal with these...

4 pages

35.0 KB

Free sing-up