Prior to beginning work on this discussion, please read the required articles by Skidmore (2008) and Henrich, Heine, & Norenzayan (2010). Carefully review the PSY635 Week Two Discussion ScenarioPrevie

Apply the scientific method to the information included within the scenario and develop a null and a research hypothesis based on it.

Martin and Bridgmon (2012) suggest the research hypothesis as the indication that something is occurring during the testing which is not the null hypothesis. The research hypothesis for the construct would suggest the use of an intervention may stimulate more effective use of the discussion boards during weekly class activities. Martin and Bridgmon (2012) explains the “null hypothesis as the “no change” hypothesis. Applied to the current study would suggest the null hypothesis as regardless of intervention the status of activity on the discussion boards would not change.

Using the hypotheses you have developed, compare the characteristics of the different experimental research designs discussed in the Skidmore (2008) article and choose the one that is most appropriate to adequately test your hypotheses.

Skidmore (2008) indicates there are three types of experimental research designs commonly used in statistical research. The group is the pretest-post-test design by which the individual are randomly sorted in either a control or experimental group (Skidmore, 2008). The control is provided no interventions, where the experimental group are supported with interventions which may initiate a response. During the testing both groups are provided a pretest to observe current equal activity and the experimental is given a post-test to measure activity following the intervention (Skidmore, 2008). The second test requires a post-test only design which still has all requirements of an experiment design. The test requires randomly selected candidates, an experimental group provided an intervention, and a post-test of the experimental group that was provided the intervention (Skidmore, 2008). The final experimental research design of the group referred to as the Solomon Four-Group Design. The test design provides the best combination of information and overall examination of the process. The experiment not only allows for an overall observation of the experiment but also provides examination of information for an experimental group not using the pre-test prior to intervention. The overall design of the test though well assembled would require a very large sample group to complete the experiment effectively. Given the general sample size of the test group in the scenario, the use of the pre-test/post-test would seem most useful. The post-test only would possibly succumb to questions of validity and the sample size may not be large enough for the Solomon Four-Group Design.

 Identify potential internal threats to validity and explain how you might mitigate these threats.

Skidmore (2008) indicates there are two kinds of specific validity threats internal and external.

Internal 

The internal threats begin with ambiguous precedence (AP), selection bias. The AP validity issue stems from not knowing which variable happened first the dependent variable or the independent variable thus leaving one unable to determine exact cause and effect pattern. The case of the study scenario indicate AP could provide a problem were the interventions not effective enough to illicit a response (Skidmore, 2008). Henrich, Heine,  Norenzayan (2010) suggest motivation among individuals across populations meets similar criteria. There must be a consideration of possible intervention options to find a balance. Forgetting such a consideration the experiment may then become invalid were the response to remain the same even after the incentive because those involved did not find the intervention appealing thus leaving no change to observe. Selection bias does not apply (as stated random selection criteria was implemented to assure a truly randomized grouping). History may play a part in the results of the testing as the classes being on-line are not truly controlled during the duration of the test (Skidmore, 2008). The best way to avoid such an issue would be to plan an interactive meeting online where the experimental group was provided and incentive during the interaction and responses could be tracked in real time. Maturation should be unaffected due to the duration of the test online.

Though were the test to be controlled over a duration of enrollment may affect experiment outcomes (Skidmore, 2008). Statistical regression should not become an issue as those in the experiment are selected at random and there is no mention of pretest. Were a pretest to be used it could not  impact the group selection process as any modification to group random selection would make the experiment invalid. Experimental mortality/attrition could become an issue were the intervention not appealing to entice interaction during the test (Skidmore, 2008). There are those participant that may not believe the experiment is worth the effort and choose not to involve themselves in the testing. Due to the nature of on-line testing there is not complete control over the actions or outside interactions of the test subjects. Validity could be argued if subjects are not timed during the test and were the test something they could research on-line the subjects may choose to effect the outcome making the test invalid (Skidmore, 2008). The actual testing procedure and use of computers would aid in the validation as the chance for human error is lessened by tallying via on-line or database software. Additive and effect of threats is also a possibility as with any other online test there is no control over the action of the subject. The use of login and set aside a specific amount of time may provide the subject ample time to prevent interference during the experiment (Skidmore, 2008).

External 

The Interaction of Casual participants – due to the online nature of the scenario not only could interaction with individuals outside the testing be possible, it may also prevent an issue were the participants to communicate electrically during the experiment (Skidmore, 2008). Limiting time and disabling connective email between students for the duration of the test may prevent interference. Interaction of the causal relationship over treatment variations may vary depending on the time which the experiment can be conducted. The length of the experiment may also reduce possible anomalies in the testing (Skidmore, 2008). Interaction of the causal relationships with outcomes suggests little if any variation would exist in the scenario regarding measurements and consistency of measuring components (Skidmore, 2008). Interactions of the causal relationship with settings indicate in online experiments settings may vary for those participating. The best way to resolve such an issue would be to present a suggested list of instructions prior to participation with the intent to limit setting changes. Context-dependent mediation may consider the experiment from a demographic perspective which may vary among students (Skidmore, 2008). Without specific considerations such as computer specifications and presenting a list of requirements, location suggestions, and a specific time for the interaction.

 Apply ethical principles to the proposed research and describe the implications of this type of research in terms of the population(s) and cultural consideration(s) represented in the sample(s) within the scenario

 The ethical considerations of the testing would fall under two specific areas of the APA code of conduct. Section 8.01, 8.02, 4.01, and 3.04 may be the most useful areas when considering ethical conduct (American Psychological Association, 2017). First and foremost, with area 8.01 there must be an approving institutional body to analyze and approve the research. Without proper approval the entire experiment may be considered invalid as it did not meet the appropriate approval criteria for a specific region or location (American Psychological Association, 2017). The next section 8.02 letter of informed consent is required for all participants in the study which coincides with 3.04 do no harm (American Psychological Association, 2017). The most important aspect of any human based research is to assure no harm will come to the participants. The final part of maintaining confidentiality section 4.01 is important as depending upon the culture, region, and population of the society confidentiality could be very important (American Psychological Association, 2017). The participant may wish to remain anonymous during and after the testing. Some of those involved may choose not to stay involved if they believe their confidentiality could be compromised