The leader intends to carry out a research to make an informed decision whether the organization shall start a new initiative.

1. How would the systematic sampling method be used to select 30 participants from 2700 employees for the study.

In order to select 30 participants from 2700 employees using the systematic sampling method, one has to determine the sampling interval (McMillan, 2012). The sampling interval is calculated by dividing the sampling frame (N) by a sample size (n) (McMillan, 2012). Thus, the sampling interval = N/n, and therefore, 2700/30 = 90. The participants denoted by "nth" are selected from the list of all 2700 employees in the sampling frame, starting with a randomly selected employee within the first (1st) name on the list and the ninetieth (90th) name on the list (McMillan, 2012). The leader will select the next participant after 90 names from the first case. Thus, in picking 30 participants, every "nth" participant would correspond to every 90th employee (McMillan, 2012). Suppose the first participant's name is listed 20th, the second participant will be the 110th, the next one will be the 200th. The process will go on till 30 members are selected.

2. The description of the sampling procedure that would yield participants that equally represent both genders in the study is the stratified sampling.

The sampling procedure that would yield participants that equally represent both genders in the study is the stratified sampling. One should first determine the required sample size (McMillan, 2012). Then the number of each gender is established, and percentages are calculated based on the whole. The next step is classifying the sampling frame into male and female strata. The predetermined percentages are used to calculate the number of employees to select in their respective strata. Finally, participants are selected from each stratum to constitute a sample. For instance, the population is 100, and there are 30 male and 70 female employees; the percentages of the genders will be 30% male and 70% female. Suppose the sample size required is 60 employees, the sample size of the male employees will be 30% of 60, which is 18 members. The sample size of the female employees will be 70% of 60, which is 42 members. 18 participants will be chosen from the male stratum and 42 from the female stratum. Both selections are done either through systematic sampling or simple random.

3. The possible threats to the internal validity of the design used.

The possible threats to the internal validity of the survey design that the leader used to evaluate the participants' attitudes towards the new initiative may include the following (McMillan, 2012):

1) Selection bias may lead to untrue results if the leader does not randomly select and assign the participants to the study groups.

2) The maturation threat may arise because the survey goes through a certain period, for example, two days. In that period, changes, such as mental, emotional, or perspective changes, may occur. These changes may influence post-test scores.

3) Subject effects may lead to internal validity threats if the participants alter their behaviour to respond more favourably. They may also want to present themselves in the most positive manner, and this would affect the results as well (McMillan, 2012).

4) The survey instrumentation may cause threats to internal validity. The threats may be due to changes in the instrument used, or if the instrument is not consistent in its measurement, and due to changing the procedures for obtaining data on employees’ attitudes.

5) Experimenter effects may be a threat to internal validity of the survey in two ways. First, the characteristics of the investigator, such as age, sex, race, status, hostility, authoritarianism, and physical appearance, may affect the results. These characteristics may influence the respondents to answer differently to certain characteristics. Second, the experimenter may also evaluate the results through his expectations and experiences (McMillan, 2012).

6) Subject attrition may occur if the participants systematically drop out of the survey and their absence affects the results (McMillan, 2012).

4. A description of how the leader should use a true experimental design to run a pilot study to examine the impact of the new initiative on the organization.

The leader will use a randomized-to-groups pretest-posttest experimental design to examine the impact of the new initiative on employees (McMillan, 2012). He will need to divide the employees randomly into two groups – A and B (McMillan, 2012). All the groups will carry out production using the old approaches, and the leader will calculate their productivity scores. The next phase will involve the two groups working with the use of different approaches. In the group A, the investigator will expose the employees with a new initiative before and during the production process. In group B, the investigator will not interfere in any way. He will let the employees perform production using the old approaches. At the end of the production process, the leader will take productivity mean scores to evaluate the success of the new initiative compared to the old methods. He will also make a comparison between the pretest and posttest. If it turns out that the change in productivity for group A is significantly different from that of group B, it can be argued that the new initiative results in a significant difference in productivity.

5. The statistical procedure that would be used to analyze the quantitative data collected from the pilot study (with a true experimental design) to address the research question.

The statistical procedure the leader would use to analyze the quantitative data collected from the pilot study is the inferential statistics, specifically t – tests (McMillan, 2012). Matched samples t-test determines if there is a significant difference between the average productivity scores of the groups under research (McMillan, 2012). The leader would also calculate gain scores (that is, the difference between pretest and posttest) and test the significance of the average gain scores with the matched samples t-test (McMillan, 2012).