solved Discussion 1 Chapter #8 points out that scores from an

Discussion 1
Chapter #8 points out that scores from an instrument should be reliable ( that is the results would be similar over time, if the test were repeated) and valid, that is an accurate and specific measure of the variable.   How can reliability and validity be measured? 
Discussion 2
Name ONE way a researcher could minimize threats to internal validity.
Student 1 
(Question 1-Antoine)The common methods of measurements of reliability are internal consistency and test-retest.Internal consistency looks at the consistency of the score of individual items on an instrument. Using a survey to collect data on overall satisfaction should yield the same response for similar questions in your data collections. If the answers are not the same that may be an indication that the survey may be worded poorly. Test-retest is simply that of what it says, using an instrument and then testing again after an interval of time without administering any treatment or intervention.Common methods of testing validity are content validity and construct validity.Content validity means that the test measures appropriate content, while construct validity refers to the test measuring the skills/abilities that should be measured. An good example of content validity would be the administering of an EOY mathematics exam that properly asks questions on what students have been taught throughout the year. Construct validity example would be establishing a construct, such as depression, and developing a test that measures symptoms and indicators of depression.Student 2(Question 1-Tanya)Reliability can be measured several ways. The ones that stood out to me is the test-retest method. It is given to the same group of people after an appropriate time lapse. The higher the reliability coefficient, the more reliable  the tests are. The equivalent-forms method entails using two different forms that get to the heart of the same issue, given to the same group of individuals during the same time period. They are only constructed differently, everything else is the same. The idea is that we are measuring the same sort of performance but with different questions to the same group of people at the same time. Validity can be measured three ways. Content-related evidence of validity determines the appropriateness and how understandable the content of the instrument is. The questions should accurately represent the things that are being assessed in the study. Validity can be measured several ways. Criterion-related evidence of validity  is when there is a strong relationship between scores of more than one instrument. Construct-related evidence of validity deals with a characteristic that an instrument is measuring. I think of the MBTI as an example of this. It is a psychological test that is used to measure different personalities and temperaments. The questions are the same, but the results are specialized to each person identifying their temperament. 
Question 2 (Student 1-Lawrence)
Since I was in middle school, having a control group was required for a project to be considered for the science fair. Science is not really my jam, but I do know that, and it seems to be echoed in the text and scientific community as well. If control groups are compared to experimental ones, all observations and scores are more likely to be accepted if variables outside of anyone’s control begins to affect any group.
Question 2(Student2-Tundra)
Changing the experimental design is one method the researcher could reduce challenges to internal validity. This can help counteract a number of dangers to internal authenticity. Questionnaires or filler tasks can be used to conceal the study’s aim, hence reducing testing risks. Testing is also thwarted by having a big sample size. This is due to the fact that when the sample size is large, the results are considerably more sensitive to any variation in the outcomes. The lower the chances or threats, the shorter the maturation and history. Instrumentation hazards, on the other hand, can be mitigated through method control and even rigorous specification.