Estimating Number of Canadians Who Moved Provinces Using Census Data

Q1: Proportion implied Frequency& Margin of Errorusing census data. Estimate the number of Canadianswho moved provinces over the last 5 years.The data has a variable called “pr” for province of residence. It’s coded with the standard StatsCan coding, from 10 for NL to 60for Yukon, NWT, and Nunavut. There’s another variable coded the same way called “pr5” which asks which province the person lived in five years ago. You will need to generate a new dummy variable for this and use the not equal operator (!= or ~=) to classify people into the movers and stayers categories. 1a.  Use your census dataset sample to estimate the NUMBER (not the percentage) of people who live in a different province from 5 years ago. So:first find the proportion of people who live in a different provinceand then turn it into a number of peopleusing the assumption that the total population of Canada is exactly 35 million. (You have no other source to help you estimate the number, just the proportion in your sample).  1b. Indicate how far away from the true number of people who moved provincesin the full population(i.e. not the percentage) that you would expect to be, 19 times out of 20. Say: ± ______ number of people. (NOT ± %) You can calculate this using the formula for the standard error of a proportion and then use that resulttocalculate the number of Canadians, as you will have done in question 1a. In Canvas, just enter one number for a)and another number forb). For this question you do not need to ‘write up’ the answers. Q2.Means from the census 

32a.  Compare the Government Transfers income (gtrfs) for people whose first language was English and whose first language was French (exclude the Both and Neither categories on that variable). Report the two means and the difference between them a smoothly worded paragraph that summarizes the findings for a reader. 2b.  Add a sentence reporting the standard error of the mean government transfer income for those whose first official language spoken was just English.Your report of this number should be in a sentence that says how close you expect to be to the population mean, in 95% of samples. Calculate this with the formula, using the mean, the standard deviation, and the number of cases (n) in the English category of that variable. Questions 3to 5: AmericanNational Election Study.Now switch to the 2016 American National Election Study (ANES2016)dataset. DO THIS FIRST: Draw a random sample of2,500cases from the dataset. You will all get different samples that we can replicateto check your answersbecause of the way random number generation works in computers.First:set the random number seed by typing: set seed courseidnumber(where you replace ‘courseidnumber’ with the same number as your course id (The number between 1 and 195,NOT your real student number).Then: use the command sample: sample 2500, countNow use the command called countto double check that you now have 2500 cases to work with: just type count and hit enterStata should simply report a number close to2500. (If it’s close, it’s ok).Q3.Americans’ interest in politics and feelings about groups We are going to look at the relationship between Americans’ voting intention (before the 2016 election) and their attitudes toward the Police and BLM. To start, use the lookforcommand to find the two variables that measure survey respondents’ 4evaluation of the POLICE and BLACK LIVES MATTER0-100 thermometer scale. Both of those variables have missing values that are strangely coded, so you’ll need to use this command to set all values outside 0 to 100 to missing. (You put in the variable names –actually numbers –where I have “varname”).replace varname=. if varname<0 | varname>100 Now that you have those variables only from 0 to 100 (check with summarize), create a new variable that indicates how much more positive the person is toward BLM compared to their feeling about the Police.I’ll call this BLMvsP for short here.Next, find the variable that measures“For whom does R intend to vote for President” [just type lookfor intendand find it in the list that comes up]. Create a new variable called something like “voteint” that has only 3categories: Clinton, Trump, and all other responses. In a single, concise, and engaging paragraph, report the mean score for BLMvsP variable for each of the three categories of the vote intention variable. Your audience is someone reading a newspaper article or op-ed. You’ll need to say howthe BLMvsPvariablemeasures what itmeasures, referring to the range of possible values it could be (i.e the extremes and neutral point).Give your Class ID number in parentheses at the start or end of your answer