Test of Significance: One-tailed and Two-tailed

What is the difference between a one-tailed and a two-tailed test of significance? Under what circumstances would each be used?

According to Aron, Aron, & Coups (2009), a one – tailed test is a hypothesis – testing procedure where the region for rejection of the null hypothesis is on one side of the distribution. Also according to Aron, Aron, & Coups (2009), a two – tailed test is a hypothesis – testing procedure where the region for rejection of the null hypothesis is on both sides of the distribution. One – tailed tests are for directional hypothesis (predicting a particular difference); two – tailed tests are for non directional hypothesis (predicting no particular difference).

Suppose researchers are testing a new drug, Drug Z, and its effects. If the hypothesis was, “Drug Z is just as effective as similar drugs on the market.”, a one – tailed test would be appropriate. In testing this hypothesis, the researchers are concerned with whether or not Drug Z is at least equal to the other drugs. They are not concerned with the significance levels above or below the other drugs. However, if researchers were testing how Drug Z compared with other drugs a two – tailed test would be appropriate. In this study, the researchers would want to know how significantly above or below the effectiveness of other drugs that Drug Z was.

Aron, A., Aron, E. N., & Coups, E. J. (2009). Statistics for psychology (5th ed). Upper Saddle River, NJ: Pearson/Prentice Hall.

Plagiarism:

Using someone else's work without giving proper credit, is plagiarism. If you use my work, please reference it.

Comparison Distribution

What is the comparison distribution and why is it important in hypothesis testing?

According to Aron, Aron, & Coups (2009), comparison distribution represents the population situation if the null hypothesis is true. It is the distribution that you compare the score of your samples to. This distribution is the difference between means. In a t test for independent means, the distribution of differences is 0. Comparison distribution is important in hypothesis testing because the significance can help you reject or fail to reject the null hypothesis.

Aron, A., Aron, E. N., & Coups, E. J. (2009). Statistics for psychology (5th ed). Upper Saddle River, NJ: Pearson/Prentice Hall.

Plagiarism:

Using someone else's work without giving proper credit, is plagiarism. If you use my work, please reference it.

Null Hypothesis

What is the null hypothesis? How do researchers determine whether or not to reject the null hypothesis? Why is it said that hypothesis testing involves double negative logic?

Our text defines a null hypothesis as a statement about a relation between the two populations in a study (Aron, Aron, & Coups, 2009).  This hypothesis is the opposite of the research hypothesis. Researchers use z scores to determine whether to reject the null hypothesis. The actual samples’ z scores are compared to the cutoff z score. If the actual score exceeds the cutoff score, then the null hypothesis is rejected. Hypothesis testing involves double negative logic because the null hypothesis is never accepted only rejected. If research does not reject the null hypothesis, it is worded as “failure to reject the null hypothesis”. One never says they have accepted the null hypothesis.

Aron, A., Aron, E. N., & Coups, E. J. (2009). Statistics for psychology (5th ed). Upper Saddle River, NJ: Pearson/Prentice Hall.

Plagiarism:

Using someone else's work without giving proper credit, is plagiarism. If you use my work, please reference it.

The Five Steps of Hypothesis Testing

What is the five-step process for hypothesis testing? Explain each step.

According to Aron, Aron, & Coups (2009), there are five steps in the process of hypothesis testing .

Step 1: Restate the question as a research hypothesis and a null hypothesis about the populations.

A research hypothesis is a statement about the predicted relation between the two populations. The null hypothesis is opposite of the research hypothesis. If one of the hypothesis is true, the other cannot be. If I were to research the health of children who eat fresh vegetables versus children in general. My reseach hypothesis would be “Children who eat fresh vegetables are healthier than those who don’t.” My two populations would be children who eat fresh vegetables (population 1) and children in general (population 2).

Step 2: Determine the characteristics of the comparison distribution.

The comparison distribution represents population situation if the null hypothesis is true. This is the distribution that you compare the score based on your sample’s results. In my fresh vegetable example, the null hypothesis would be “There is no difference in the health of children who eat fresh vegetables than those who don’t.” The comparison distribution os the distribution of population 2.

Step 3: Determine the cutoff sample score on the comparison distribution at which the null hypothesis should be rejected.

The cutoff sample score is the point if reached or exceeded by the sample score that you reject the null hypothesis. In this step, you set the z score at a score that would be unlikely if the null hypothesis is true. For example, the researchers testing the vegetable hypothesis may decide that if a result were less than 3% then they would reject the null hypothesis.

Step 4: Determine your sample’s score on the comparison distribution.

This is the point where the study is carried out and the actual results for the sample are obtained.

Step 5: Decide whether to reject the null hypothesis.

Compare the actual sample’s z score to the cut off z score. If the actual score is higher than the cut off score, the null hypothesis would be rejected.

Aron, A., Aron, E. N., & Coups, E. J. (2009). Statistics for psychology (5th ed). Upper Saddle River, NJ: Pearson/Prentice Hall.

Plagiarism:

Using someone else's work without giving proper credit, is plagiarism. If you use my work, please reference it.

Descriptive and Inferential Statistics

What is the difference between descriptive and inferential statistics?

Both descriptive and inferential statistics are both used in analysis of numeric data. Descriptive statistics are used to reveal patterns through this analysis. Descriptive statistics describe the group they belong to. Examples of descriptive statistics are frequency counts, ranges, means, median scores, modes, and standard deviations. A specific example would be: “The class had an average score of 90.2%”. Inferential statistics are used to draw conclusions and make predictions through this analysis. Inferential is about a larger group. Examples of inferential statistics are experiments, probability, population, sampling, and matching. A specific example is: “65% of Americans approve of the bill.”

Plagiarism:

Using someone else's work without giving proper credit, is plagiarism. If you use my work, please reference it.

Variance and Standard Deviation

What do the terms variance and standard deviation mean? How are these concepts related?

Both variance and standard deviation measure variability. Our textbook defines the variance as a measure of how spread out a set of scores is from the mean (Aron, Aron & Coups, 2009). It is the average of the squared deviations from the mean. The standard variation is the positive square root of the variance. The standard variation is a descriptive statistic whereas the variance is rarely used as descriptive. Standard variation is the most common descriptive statistic.

For example, while conducting research your numerical results are: 20, 14, 8, 5, and 3. First, you need to find the mean of these results. The mean is simply the average of these numbers.

(20+14+8+5+3)/5 = 50/5 = 10

The mean is 10. Next, subtract the mean from each number and square the result for each.

{[(20-10)²] + [(14-4)²] + [(8-10)²] + [(5-10)²] + [(3-10)²]}/ 5 = [100+16+4+25+49]/5

                                                                     = 194/5

                                                                  =38.8

The variance is 38.8.

Since the standard deviation is the square root of the variance.

√38.8 = 6.22

If rounded to the closest whole number, the standard deviation would be 6.

Aron, A., Aron, E. N., & Coups, E. J. (2009). Statistics for psychology (5th ed.). Upper Saddle River, NJ: Pearson/Prentice Hall.

Plagiarism:

Using someone else's work without giving proper credit, is plagiarism. If you use my work, please reference it.

Research, Statistics and Psychology

Research, Statistics and Psychology

Neil Armstrong once said “Research here is exploration and discovery. It’s investigating (something that) no one knows or understands. Research here is creating new knowledge.” (NASA, 2005). Although he was speaking about the space flight programs, his words are true for all types of research. Researchers use the scientific method to formulate his or her research. Then, researchers use statistics to help analyze some of the data collected. Data and statistics are used to help see the results of research as a whole.

The Scientific Method and Research

In the late nineteenth century, American researchers were introduced to the scientific method (Tang, Coffey, Elby,  & Levin, 2010). The scientific method is an approach to systematically acquire knowledge and data. Using this method, researchers typically follow a four step process (McGraw-Hill, 2011). First, a problem is identified and usually posed as a question. Next, an explanation is formed and a study is designed. The research is carried out, data is collected and analyzed. The data obtained can either support or refute the explanation formed. The researcher then communicates his or her findings.

The central component of the scientific method is research (McGraw-Hill, 2011). Research is the systematic inquiry used to discover new knowledge. There are two methods of research. The first is descriptive research, the collection of information about a person, group or pattern of behavior. Descriptive research is divided into five sub-methods. These include archival research, naturalistic research, survey research, case studies, and correlation research. The second main method of research is experimental research. This is the method where experiments are conducted and a variable is usually manipulated.

Primary and Secondary Data

Data, the factual information that is used as a basis for reasoning, discussion, or calculation, is the result of research (Merriam-Webster, 2012). Data can be primary or secondary. Primary data consists of facts and information collected first – hand for the intended investigation or study. Secondary data is facts and information collected by another person for another purpose. Primary data cannot be found in other places since the researcher is gathering it specifically for his or her current research project. Secondary data, however, can save the researcher time that would be spent conducting research but would not be collected for the current study only. Secondary data generally is found in published sources and is found to be useful in the current analysis. There are two main methods of gathering primary data (Rabianski, 2003). These methods are direct observation and questioning of individuals. There are more issues surrounding secondary data. These issues are accuracy, bias, validity, reliability and appropriateness. There are errors that can make some data unreliable. These errors are manipulation, contamination (by confusion, carelessness or by not showing proper judgment), and concept error. According to Rabianski (2003), concept error is error that arises because if there is a difference between the concept to be measured and the specific items used to measure the concept.

Statistics in Research

Researchers use statistics to organize, analyze and summarize the data they have collected (Baltimore County Public Schools, 2012). Statistics is the science of collecting, analyzing and making inferences from data. Statistics is also used as a way of pursuing the truth (Aron, Aron,  & Coups, 2009). There are two branches of statistics: descriptive and inferential. Statistics is helpful in research in many ways. One way is that statistics help the researcher understand and describe the hypothesis in his or her study. Another way statistics is helpful is that it helps the researcher reach reliable conclusions about the study. Statistical methods are used psychology. These methods are used to help them make sense of the numerical data obtained during research.  

Conclusion

The words of Mr. Armstrong are true. Research is exploration and discovery. Research is investigating something that no one knows or understands. Research is creating new knowledge. Through the systematic procedure known as the scientific method, research and experiments are carried out. Data is collected and then analyzed using various methods including statistics. Research in Psychology is an exploration and discovery of new knowledge.

References

Aron, A., Aron, E. N., & Coups, E. J. (2009). Statistics for psychology (5th ed.). Upper Saddle River, NJ: Pearson/Prentice Hall.

Baltimore County Public Schools. (2012). The Role of Statistics in Research. Retrieved from http://www.bcps.org/offices/lis/researchcourse/statistics_role.html

McGraw-Hill (2011). Psychsmart. New York, NY: Author.

Merriam-Webster. (2012). Data. Retrieved from http://www.merriam-webster.com/dictionary/data

NASA. (2005, October 21). A long-overdue tribute. Retrieved from http://www.nasa.gov/centers/dryden/news/X-Press/stories/2005/102105_Wings_prt.htm

Rabianski, J. S. (2003). Primary and Secondary Data: Concepts, Concerns, Errors and Issues. Appraisal Journal, 71(1), 43-55.

Tang, X., Coffey, J. E., Elby, A., & Levin, D. M. (2010). The Scientific Method and Scientific Inquiry: Tensions in teaching and learning. Science Education, 94(1), 29-47. doi:10.1002/sce.20366

Plagiarism:

Using someone else's work without giving proper credit, is plagiarism. If you use my work, please reference it.

Primary and Secondary Data

Distinguishing between primary and secondary data is important to help make your research credible. Primary sources make more credible data than secondary sources.

Primary data is data gathered first hand and for the purpose of the investigation at hand. This data contains original materials gathered by the “investigator”. An example of primary data is medical charts; they are gathered by the doctor for the purpose of your office visit.

Secondary data is data gathered from other sources and initially gathered for another purpose. Secondary data describes, interprets, analyzes, evaluates or explains a primary source. An example of secondary data is a review article. This type of data describes, interprets, analyzes, evaluates or explains a primary source (whatever the article is about, for example an article reviewing a medical journal article).

Since primary data is gathered in the form of original documents or statistics, these are more credible than secondary data which is basically second-hand information.

There are several examples of data that can be primary in one case and secondary in another. The example from earlier, medical charts is one. As primary data, it is collected by your physician for your current visit. It can be used as secondary data when transferred to another physician. This second physician did not gather the information contained; therefore, making it secondary.

Source:

Rabianski, J. S. (2003). Primary and Secondary Data: Concepts, Concerns, Errors, and Issues. Appraisal Journal, 71(1), 43-55. 

Plagiarism:

Using someone else's work without giving proper credit, is plagiarism. If you use my work, please reference it. 

Quantitative vs Qualitative Data

The easiest way to define quantitative and qualitative data is to look at the root of the word. 

Quantitative à Quantity

Quantitative data deals with numbers. This type of data can be measured. For example, saying a picture on the wall is 8 inches by 13 inches. This data is measured. Methods of demonstrating this type of data include tables, charts, histograms and graphs.

Qualitative àQuality

Qualitative data deals with description. It usually groups information in categories. This type of data is observed but not measured. For example, saying the sofa is green. This data is observed but is not a unit of measure.

In regards to scientific research, quantitative data is usually preferred over qualitative data. This is because quantitative data is measured and usually more reliable than some qualitative data.

A research study can be an example that contains both quantitative and qualitative data. The quantitative data in this example is: “There are 20 participants in XYZ Study.” The qualitative data in this example is: “Each participant exhibits anxiety.”

An everyday example that can be described with both qualitative and quantitative data is a sheet of notebook paper. Qualitative data includes that there are lines on the paper. Quantitative data includes that a single sheet is 8.5 inches by 11 inches.

Plagiarism:

Using someone else's work without giving proper credit, is plagiarism. If you use my work, please reference it. 

FINALLY! Back to Psychology!

After having to spend 10 weeks in College Algebra, I am back to Psychology courses! 


I am glad to have those Maths out of the way and it was a hard, grueling process! I am also not pleased that my newest class, Statistical Reasoning in Psychology, contains Math as well. This is not my strong point.