In: Operations Management
Write one question using a Likert scale to measure student attitudes toward eating at the campus Carl’s Jr. Next, define reliability and validity, and then discuss two ways you might test the reliability and two ways you might test the validity of the scale in the question you just created.
Likert scale to measure student attitudes toward eating
1. In the event that my suppers are postponed, I get tipsy
Strongly Disagree
Disagree
Neither Agree or Disagree
Agree
Strongly Agree
Reliability and Validity
Reliability alludes to how reliably a technique estimates something. On the off chance that a similar outcome can be reliably accomplished by utilizing similar techniques under similar conditions, the estimation is viewed as reliable.
You measure the temperature of a fluid example a few times under indistinguishable conditions. The thermometer shows a similar temperature inevitably, so the outcomes are reliable.
Validity alludes to how precisely a strategy estimates what it is proposed to quantify. On the off chance that examination has high validity, that implies it produces results that relate to genuine properties, attributes, and varieties in the physical or social world.
High reliability is one pointer that estimation is valid. On the off chance that a strategy isn't reliable, it most likely isn't valid.
Test the Reliability:
1. Inter-Rater Reliability
Numerous conduct measures include noteworthy judgment with respect to an eyewitness or a rater. Inter-rater reliability is the degree to which various spectators are predictable in their decisions. For instance, in the event that you were interested in estimating college understudies' social abilities, you could make video accounts of them as they interacted with another understudy whom they are meeting just because. At that point, you could have at least two spectators watch the recordings and rate every understudy's degree of social aptitudes. To the degree that every member does, in reality, have some degree of social abilities that can be identified by a mindful eyewitness, various spectators' evaluations ought to profoundly correspond with one another.
Inter-rater reliability would likewise have been estimated in Bandura's Bobo doll study. Right now, spectators' evaluations of what number of demonstrations of animosity a specific youngster submitted while playing with the Bobo doll ought to have been exceptionally emphatically associated. Interrater reliability is frequently evaluated utilizing Cronbach's α when the decisions are quantitative or a practically equivalent to a measurement called Cohen's κ (the Greek letter kappa) when they are straight out.
2. Test-Retest Reliability
At the point when specialists measure a build that they expect to be reliable across time, at that point the scores they acquire ought to likewise be predictable across time. Test-retest reliability is the degree to which this is really the situation. For instance, insight is, for the most part, thought to be steady across time. An individual who is profoundly insightful today will be exceptionally keen one week from now. This implies any great proportion of insight should deliver generally indistinguishable scores for this person one week from now from it does today. Plainly, a measure that produces profoundly conflicting scores after some time can't be an awesome proportion of a development that should be steady.
Test the Validity
1.Content Validity
Content validity is the degree to which a measure "covers" the build of intrigue. For instance, if an analyst reasonably characterizes test tension as including both thoughtful sensory system actuation (prompting apprehensive emotions) and negative musings, at that point his proportion of test nervousness ought to incorporate things about both anxious sentiments and negative considerations. Or then again consider that perspectives are typically characterized as including musings, sentiments, and activities toward something. By this theoretical definition, an individual has an uplifting mentality toward exercise to the degree that the individual in question considers working out, likes practicing and really works out. So to have great content validity, a proportion of individuals' perspectives toward exercise would need to mirror every one of the three of these angles. Like face validity, content validity isn't normally surveyed quantitatively. Rather, it is surveyed via cautiously checking the estimation strategy against the theoretical meaning of the build.
2. Criterion Validity
Criterion validity is the degree to which individuals' scores on a measure are associated with different factors (known as criteria) that one would anticipate that they should be related. For instance, individuals' scores on another proportion of test tension ought to adversely correspond with their exhibition on a significant school test. In the event that it was discovered that individuals' scores were in certainty contrarily corresponded with their test execution, at that point this would be a bit of proof that these scores truly speak to individuals' test tension. Be that as it may, in the event that it was discovered that individuals scored similarly well on the test paying little mind to their test tension scores, at that point this would provide a reason to feel ambiguous about the validity of the measure.
A criterion can be any factor that one has the motivation to think ought to be associated with the development being estimated, and there will normally be a considerable lot of them. For instance, one would expect test nervousness scores to contrarily correspond with test execution and course reviews and emphatically related to general tension and with circulatory strain during a test.