Part 1: Mainstream Media

Part 1: Mainstream Media内容摘要：

STATISTICS IN EDUCATIONAL RESEARCH 1 EDTC 810 Statistics for Educational Research Gigi Mohamad New Jersey City University STATISTICS IN EDUCATIONAL RESEARCH 2 This assignment discusses two examples of statistical inferences in two articles about education in the media. The first article is published by Pew Research Center and titled “A Look at What the Public Knows and Does Not Know About Science” (Funk & Kehaulani Goo, 2015). The second article is titles “A study of student attitudes and performance in an online introductory business statistics class” (Schou, 2007). Part 1: Mainstream Media Pew Research Center (Funk & Kehaulani Goo 2015) had conducted a survey to examine Americans knowledge about several scientific terms and concepts. The researchers surveyed 3,278 adults using 12 multiple-choice questions. 2,923 responded digitally, and 355 responded by mail. The survey included questions about gender and level of education of participants. The questions were about different science topic, but were not meant to cover all the science knowledge. This is an observational study since there is no treatment or experimental units applied to the sample, the data was collected without experimentation. Findings The study found out that most Americans can answer questions about basic science such as the hottest of Earth’s layer (86%), and elements needed to make nuclear energy (82%). But fewer can identify the property of a sound wave that determines loudness or interpret a scatterplot chart. The median was eight correct answers out of 12 (mean 7.9). 27% answered eight or nine questions correctly, 26% answered ten or 11 items correctly, and just 6% of the participants got a perfect score. There was a strong positive correlation (see figure 1) between higher education and the number of correct answers. Those with higher education levels knew more answers to science questions (Funk & Kehaulani Goo 2015). STATISTICS IN EDUCATIONAL RESEARCH 3 Figure 1: The relationship between science knowledge and education. This figure illustrates the positive strong correlation between science knowledge and education. P-value One way to calculate a p-value, is to examine the relationship between the number of correct answers (x), and the level of education for the participants (y) following these steps: 1. 2. 3. 4. 5. 6. Establish the null hypothesis as H0: Pxy = 0 and the alternative hypothesis as H1: rxy ≠ 0. Set the level of significance as .05 (Type 1 error) Compute the Pearson correlation coefficient Determine the value needed for rejection of the null hypothesis. Compare the obtained value to the critical value Make a decision The article didn’t supply enough data to calculate the p-value, but since there is a strong relationship between the variables that would result in the rejection of the null hypothesis, then the p value (p) must be less than 0.05. A copy of the article is attached to the end of this document. STATISTICS IN EDUCATIONAL RESEARCH 4 Part 2: Scholarly Article The second article is a study titled “A study of student attitudes and performance in an online introductory business statistics class” (Schou, 2007). The purpose of the study is to find out how effective online learning is by comparing students’ learning outcomes in an online introductory business statistics course with students’ learning outcomes in a traditional face-toface introductory business statistics course at one doctoral granting institution in Western United States. The following hypothesis was evaluated to examine the comparability of learning outcomes: H0: µtraditional = µonline. The first null hypothesis stated that there is no difference between the mean score on the final examination between online and traditional course. To learn whether students improve their attitude toward statistics after online instruction, the following hypothesis was evaluated: H0: µpretest ≤ µpost-test. The second null hypothesis stated that the mean pre-test Survey of Attitudes Toward Statistics (SATS) score is lower than the mean post-test SATS. The conveniently chosen samples were 16 participants in the traditional course and 15 participants in the online course. College Algebra was a prerequisite for this course, and the researcher did not administer a pre-test assuming that it would be expected that the participants are at the same skill level. Such assumption might undermine the results of the study; the results would have been more valid if a pre-tes