Question.4703 - SPSS Assignment Instructions1. Begin by opening SPSS via the CUNY Server Next, start following the instructions shown in the following SPSS In Focus Videos Stats Screencast 5.6.1 and watch this video (https://www.youtube.com/watch?v=e6pT-GyT0hk ) for a more detailed explanation of crosstabulationStats Screencast 5.6.2 and watch this video to see how to interpret the values in a crosstabs table ( https://www.youtube.com/watch?v=MqksiPX46_I ). Stats Screencast 6.8To calculate z-scores and areas under the normal curve, try out these online z-score and normal distribution calculatorshttps://www.socscistatistics.com/tests/ztest/zscorecalculator.aspxhttps://www.calculator.net/z-score-calculator.htmlhttps://www.mathportal.org/calculators/statistics-calculator/z-score-calculator.php (This one is great because it will show you the hand calculations required to get the probabilities associated with different z-scores)2. For the discussion, we will make it very easy and short with no minimum word count and no requirement to reply to classmates:Please just list any questions you have about the SPSS or z-score calculator methods for this unit.Explain any insights about psychology or statistics which have occurred to you this weekResponses to classmates are optional for this DBThe reason this discussion is short is because it is rare to be directly calculating conditional probabilities and z-scores in an office or laboratory, and if you did need to do that, you can refer to your notes from this unit's methods and you would probably get training on the exact steps for how people would want that to be done. There is NO NEED to attach your SPSS files this, but you can if you like.Perspective: Why do we care about crosstabulations?One of the most important uses of crosstabulations is to start looking at the effects of two variables at once on an outcome of interest. We will use this concept in our final week as part of calculating the Chi-square statistic and Chi-square is used to tell us if the counts or percents per category are either different across the categories OR if our variables are dependent or independent. (There are two separate versions of the Chi-square test, the Chi-square goodness of fit and the Chi-square test of independence.) In our example of the relationship between the independent variable of Type of Hospital and the independent variable of Insurance Status, all we can currently see is that none of the "cell" counts are equal. However, when we get into the second part of our class which is all about detecting statistically significant differences or relationships, we will learn how to determine if those counts per category/cell are statistically significantly different. Remember, that right now all we see is that they are different, but because we are dealing with a sample, not a population, we do not have an estimate of whether or not those differences exceed what we would expect just due to sampling error. So, the work we do this unit to understand and generate crosstabulation tables, is going to be repeated and expand upon later in our class. The big advance of this cross tabulation method is that we are now looking at the combined effects of two variables. We live in a multiple causality world, so all of our previous examples that just look at the effect of one variable on one other variable, or just look at one variable period, are just the most simple cases we can look at. By using the crosstabs function and looking at two variables at once (type of hospital, Insurance status), our class moves one step closer to dealing with the real world, which is most often a world of multiple causality.I’m not disparaging the importance of looking at one or two variables at a time, because that is incredibly important, and it is typically the only perspective which people are able to easily understand. Instead, I want to point out that our very simple tutorials showing you how to compute a very simple example of conditional outcomes (counts per condition), is actually the backbone of been able to compute conditional probabilities, look at the combined effects of two variables on an outcome such as the counts per category, and determine if those variables are independent of each other, or not. This will lead us into statistical testing for nominal data, and other data which is not normally distributed. Why do we care about z-scores? That was part of our main discussion for the unit, so we will not repeat it here.Good luck!

Answer Below: