Assessment, Statistics, and Research

  Graphic from  Pewresearch 2021 Pew Researchers have a great deal of experience in asking people questions. Formulating a good question for a survey is an important place to begin. However, another lesson from Pew is the additional data they gather. I noticed a large graphic illustrating how people in different groups answered one question. When conducting survey research it is critical to consider what we need to know about the people responding to a question or item to understand the meaning of their response. Consider Pew's survey item with two choices: "most things in society...      Can be pretty clearly divided into good and evil      Are too complicated to be divided into good and evil The graphic shows how different groups responded and allows for comparisons on the two ways to respond. Later, in the article, they compare political affiliations, which in the US means Republican and Democrat. This is worth studying as well. The article is worth reading to learn more ab

  S cale name: Belief in Good Luck (BIGL) Scale overview: The scale presents 12-items, which are rated based on degree of agreement. The authors wanted to reliably assess irrational beliefs about luck and examine the beliefs in relationship to expectations of success. Early psychometric properties support the scale as a useful assessment of luck. Authors: Peter R. Darke and Jonathan L. Freedman   Response Type: 4-point agree-disagree scale Subscales: None Sample items b) Some people are consistently lucky, and others are unlucky. o) Luck is nothing more than random chance. (reverse scored) Reliability: Factor analysis yielded one factor. Items were selected from the original list based on factor loadings. Alpha   values were .85 in studies 1 and 3; .78 in study 2. Validity: The article includes correlation values with other measures. Total BIGL score was significantly positively correlated with the chance subscale of the Locus of Control scale. Availability:

  The concept of average intelligence is sometimes difficult to appreciate because the two words, average and intelligence, are sometimes not defined. Average   To psychologists and counselors who administer tests of intelligence, a person who scores at the 50th Percentile has average intelligence as defined by the number of correct answers to test tasks compared to others in their age group. Many tests set the middle score at 100 thus, 100 = average intelligence on many tests. All test scores vary from time to time so, a person may earn more or less points on another day. This fluctuation is estimated and can range for example by plus or minus 3-5 IQ points depending on the test and age group.  If you retake the test in a month or so, you may score better because of the “practice effect”—you’ve seen the items recently so you will probably do better. There is an average range so examiners will not focus on the obtained score but consider a broader range. For example, some may consider