# Answers to the Review Questions for the Final Exam

**View the full content.**View Full Document

0 0 18 views

**Unformatted text preview:**

Answers to the Review Questions for the Final Exam Vartanian Data II 1 Cell 1 Father s education has a more negative effect on the likelihood of growing up poor relative to growing up middle class That is the higher the level of education the less likely you are to be in category 1 relative to the excluded category Mother s education has a more negative effect on growing up poor relative to growing up middle class The higher the level of education of the mother the less likely you are to be in category 1 relative to the excluded category EDDADWF has more negative effect on growing up poor relative to growing up middle class The higher the education of the wife s dad the less likely you are to be in category 1 relative to the excluded category EDMOMWF has no effect Cell 5 The higher the level of education of the dad the more likely the person will have grown up rich relative to growing up middle class The higher the value of EDDAD the more likely you are to be in category 5 relative to the excluded group The higher the level of education of the mom the more likely the person will have grown up rich relative to growing up middle class The higher the value of EDMOM the more likely you are to be in category 5 relative to the excluded group The higher the level of education of the father of the wife the less likely the person grew up rich relative to growing up middle class The higher EDDADWF the less likely you are to be in category 5 relative to the excluded category EDMOMWF has no effect on the outcome From the second set of regressions we can determine the differences between category 5 Rich and category 1 Poor Cell 5 The higher the level of education the more likely you are to be in the rich group relative to the poor group The higher the level of mother s education the more likely you are to be in category 5 relative to category 1 The other variables are not related to differences in category 5 and category 1 B If the Hausman test showed significance this would indicate that we reject the null of iia and we would therefore need C WP60 LECT2 PHD FINALrev Review05 Answers wpd Page 1 to run another type of test 2 A If we have a relatively large number of observations with 0 hours of work our estimates for hours of work may be biased We run the selection model examining factors that may affect whether or not someone works and the correct for our estimates by this Heckman process In other words the Heckman selection model allows us to use information from non working women to improve the estimates of the parameters in the regression model The Heckman selection model provides consistent asymptotically efficient estimates for all parameters in the model b There seem to be slight differences in the models The Heckman model seems to show that the effects of being married are less than what the OLS model indicates It also shows that the effects of owning your own home is more negative than in the OLS model The biggest difference appears to be in the effects of health of the head The heckman models shows that the effects of having excellent health are quite a bit lower than the OLS model an additional 92 hours relative to those who don t have excellent health versus 104 in the OLS model for those with excellent health relative to those with less than excellent health C This tests to determine if the error terms in the two models are related to each other If they are not then the OLS regression estimates are unbiased If they are related to one another then the OLS regression estimates are biased The null hypothesis is that Rho 0 Here we reject the null hypothesis and state that Rho 0 in all likelihood and we have better estimates with our selection model 3 A C WP60 LECT2 PHD FINALrev Review05 Answers wpd Page 2 In other words there is a 31 chance that someone will buy a car B Thus with these characteristics the probability of buying a car increases from 31 to 77 C In other words people with 3 kids are 0578 1 as likely to buy a car as those people with 0 kids Or people with 0 kids are 1 0 0578 17 30 as likely to buy a car as those people with 3 kids D Females are 4 48 times as likely to buy a car as males controlling for the other variables within the model 5 A Logistic Regression is your best choice B DV likelihood of drug use IV Peer pressure either measured at the interval or nominal level Control Family income district income and whether or not the person smokes C WP60 LECT2 PHD FINALrev Review05 Answers wpd Page 3 C The null hypothesis is that peer pressure will have no effect on the likelihood of drug use D You ll accept the null hypothesis in the first model where peer pressure is measured at the nominal level In the second model where peer pressure is measured at the interval level you ll reject the null hypothesis at the 05 level E For people who experience peer pressure have 0 in family and district income and do not smoke the probability of drug use is The probability for those people who do not experience peer pressure but who smoke is 5 A and B Children with parents who drink a lot of caffeine are found to be more likely to throw rocks than children with parents who drink little or no caffeine You will thus accept your null hypothesis that there is no relationship between caffeine drinking parents and rock throwing since the relationship is in the opposite direction of your research hypothesis Those children who ride motor scooters to school are shown to be less likely to throw rocks at birds In fact this is C WP60 LECT2 PHD FINALrev Review05 Answers wpd Page 4 the best predictor we have of whether or not a child will throw rocks at birds Children who ride motor scooters are only 1 8 as likely to throw rocks are children who do not ride motor scooters This means that children who do not ride motor scooters are 54 598 times as likely to throw rocks as children who ride motor scooters 1 0 0183 As predicted Libras are more likely to throw rocks but unexpectedly Scorpios are less likely to throw rocks than non Scorpios Variable Null Hypothesis Caffeine Accept Scorpio Libra Scooter Accept Reject Reject Likelihood 49 more likely for those who drink 1 ounce versus those who drink 0 ounces of caffeine 13 53 as likely 7 389 times as likely 1 83 as likely C Yes You ve made a type II error This is when you accept the null hypothesis when there truly is a relationship between the variables D The likelihood of rock throwing …