A Statistical Analysis Of Video Games Problem Description ✓ Solved

This report details the outcomes of the data analysis of a video game data set. The analysis involved carrying out various hypothesis tests to ascertain the validity of particular claims about the data. The data analysis was carried out using the statistical software for social sciences (SPSS). The statistical tests conducted were Student’s t-test for the difference in means between groups along with descriptive and visual analysis of the data.

The specific questions to be addressed were whether the number of video game visits varied with the type of video game on show and whether the amount of visit time in a video game is different for the type of video game on show. Additionally, questions of whether the number of video game visits and the time taken for each visit varied with whether or not an advertisement of the video game was carried out.

Hypotheses were formulated and tested to help answer the above research questions. Given that each independent/grouping variable was associated with two research questions, a total of 4 hypotheses were formulated.

Hypotheses

Video game type and number of video game visits:

  • H0: There is no difference in the mean number of video game visits for the two types of video games (police or thief).

  • H1: There is a difference in the mean number of video game visits for the two types of video games (police or thief).

Video game type and the amount of visiting time:

  • H0: There is no difference in the mean amount of visiting time for the two types of video games on offer (police or thief).

  • H1: There is a difference in the mean amount of visiting time for the two types of video games on offer (police or thief).

Advertising and the number of video games visits:

  • H0: Advertising has no influence on the number of times a video game is visited.

  • H1: Advertising has an influence on the number of times a video game is visited.

Advertising and the amount of visiting time for a video game:

  • H0: The amount of visiting time for a video game does not vary with whether or not an advertisement is carried out for the video game.

  • H1: The amount of visiting time for a video game does vary with whether or not an advertisement is carried out for the video game.

All the above hypotheses were tested at the 0.05 level of significance. This implies that the null hypothesis is rejected if the obtained p-value is less than 0.05 while we fail to reject it if the obtained p-value is greater than 0.05.

The Data

The data used for this analysis includes various aspects of video games such as type, advertisement status, number of visits, amount of visiting time, total visiting time on a particular day, and the day of visit. The dataset contains six variables with 44 observations each. Two variables were re-coded in SPSS for the analysis.

Descriptive statistics and visualizations were performed prior to undertaking hypothesis testing to understand the distribution and central tendencies of the variables. The results provided insights into visit frequencies and time spent on video games.

T-Tests Results and Discussion

The Independent sample t-tests were conducted to evaluate the formulated hypotheses. The findings indicated no significant difference in visit times between the game types, affirming H0. Conversely, the p-values for the advertising-related queries revealed significant differences in both visit times and frequencies, leading to the rejection of the null hypotheses.

In conclusion, the analysis demonstrated that advertisement influences visits and visit durations while the type of game did not affect these metrics.

References

  • Anderson, D. R., Burnham, K. P., & Thompson, W. L. (2000). Null hypothesis testing: problems, prevalence, and an alternative. The Journal of Wildlife Management.

  • Escalera, S., Pujol, O., & Radeva, P. (2010). Re-coding ECOCs without re-training. Pattern Recognition Letters.

  • Kim, T. K. (2015). T test as a parametric statistic. Korean Journal of Anesthesiology.

  • Rhemtulla, M., Brosseau-Liard, P. €, & Savalei, V. (2012). When can categorical variables be treated as continuous? Psychological Methods.

  • Wasserstein, R. L., & Lazar, N. A. (2016). The ASA statement on p-values: context, process, and purpose. The American Statistician.