00:10:31 Samantha Krutzfeldt: whe does this weeks quiz become available again? 00:10:40 Kelsey MacCuish: 5pm today 00:10:41 Ijeoma Uche: 5pm 00:10:47 Samantha Krutzfeldt: perfect thanks 00:11:45 Samantha Krutzfeldt: im struggling haha 00:11:56 Nikki Marucut: ^ LOL same 00:12:00 Ijeoma Uche: Confused and tired lol 00:12:00 Cristal Escamilla: ^^ 00:12:00 Lupita Ambriz: Carving pumpkins + scary movies 00:12:02 Sam Holland: Dixon corn maze! 00:12:03 Chitra Nambiar: would love to take a break 00:12:05 Aliza Adler: Studying for this midterm !!! 00:12:09 Nikki Marucut: I have a midterm too 00:12:14 Samantha Krutzfeldt: this class just got really hard for me 00:12:18 Samantha Krutzfeldt: and also midterms 00:12:33 Nikki Marucut: OMGOD so good 00:12:33 Sam Holland: I love that movie 00:12:36 Ala Koreitem: Omg I loveee that movie 00:12:42 Lupita Ambriz: Haven’t decided on a scary movie yet 00:12:43 Sam Holland: largest corn maze in Dixon lmao 00:12:47 Sam Holland: the city 00:12:48 Cristal Escamilla: It feels like we are about to finish round 1 of midterms and starting round 2...back to back lol 00:12:54 Nikki Marucut: I heard about the remake of candyman 00:13:05 Nikki Marucut: The original is problematic but I really want to see it 00:13:06 Sam Holland: sac area! 00:13:25 Gabriela Gonzalez: am i the only one who doesn’t enjoy scary movies LOL 00:13:32 Nadia Rojas: I’m with you! 00:13:33 Cheyenne Pritchard: @gabriela - I cry... can't watch them lol 00:13:40 Samantha Krutzfeldt: I don't either!!! haha 00:13:44 Aliza Adler: @ Gaby me tooo! I can’t even watch the previews for scary movies 00:13:47 Lupita Ambriz: I get nightmares but I’ll still watch lol 00:13:47 Samantha Krutzfeldt: i just end up covering my eyes 00:15:17 Samantha Krutzfeldt: random question: my last lab passed all the tests but when i looked on gradscope, it said it hadn't.. does this mean i get zero for that lab? has anyone else had this happen? 00:15:49 Alexis O'Connor: that happened to me on question 14 last lab^ 00:15:54 Samantha Krutzfeldt: ya same 00:16:00 Samantha Krutzfeldt: do we get 0 00:17:31 Kelsey MacCuish: make sure to check Gradescope after submitting via data hub - sometimes things pass in R but if you rerun the chunks from the top you 00:17:35 Kelsey MacCuish: ‘ll identify errors 00:18:03 Kelsey MacCuish: (a common issue people were having last week was that they were assigning objects after the question problem so that question didn’t pass in Gradescope) 00:18:18 Kelsey MacCuish: so ALWAYS make sure to check your submission on the Gradescope website after submitting via data hub :-) 00:18:34 Samantha Krutzfeldt: ok, i though i remember reading somewhere that for labs you had to pass all tests so will i get a score of zero for this lab? 00:19:20 Kelsey MacCuish: its all or nothing in the sense that if you get a previous question wrong and you end up getting all the qs wrong after that then you dont get any credit for those 00:19:30 Kelsey MacCuish: (i.e. the autograder doesnt take double jeopardy into account) 00:19:39 Kelsey MacCuish: you get credit for whatever tests you pass 00:19:43 Samantha Krutzfeldt: i just didn't pass the test for q 14 00:19:44 Kelsey MacCuish: and that show up as passed in GS 00:19:51 Samantha Krutzfeldt: ok 00:20:05 Gabriela Gonzalez: alameda_pop <- data.frame(L07_Alameda) 00:20:09 Gabriela Gonzalez: that’s all I got LOL 00:20:13 Cheyenne Pritchard: alameda_pop <- read_csv("./data/L07_Alameda.csv") head(alameda_pop) 00:20:27 Gabriela Gonzalez: it did 00:20:33 Sam Holland: read.csv("./ph142-fa21/lab/lab07/data/L07_Alameda.csv") I tried this but it is saying it cannot open the connection 00:21:37 Nikki Marucut: For the second part: summary_means <- alameda_pop %>% summarize(mean(birth_loc), mean_sibs = mean(num_sibs), mean_num_hosp_vist = mean(hosp_visit), mean_num_height = mean(height)) summary_means 00:22:11 Samantha Krutzfeldt: does underscore csv work 00:22:19 Sam Holland: Mine said I was in /home/rstudio for my wd so that's why I did the whole thing 00:23:59 Kelsey MacCuish: in that case try taking away the ./ before ph142 00:24:06 Sam Holland: ah thank ya! 00:24:07 Kelsey MacCuish: read.csv("ph142-fa21/lab/lab07/data/L07_Alameda.csv") 00:24:25 Cheyenne Pritchard: bar? 00:24:38 Ijeoma Uche: The summarize all didn’t work for me 00:24:41 Annalisa Watson (she/her): birth_loc <- ggplot(alameda_pop,aes(x=birth_loc)) + geom_bar () birth_loc 00:24:46 Mariah Jiles (she/her): same Ijeoma 00:26:22 Olufunke Fasawe: Can you go a little bit slower 00:26:37 Annalisa Watson (she/her): It is a discrete variable 00:27:05 Cheyenne Pritchard: let's go to the bar (Chart)! 00:28:19 Ijeoma Uche: Would you mind sharing that code? 00:28:25 Ijeoma Uche: I can’t see it 00:28:54 Andriana Marijic Buljubasic (she/her): Ya same 00:28:58 Andriana Marijic Buljubasic (she/her): It looks good 00:28:59 Afroze Khan: looks fine 00:29:04 Nikki Marucut: It looks good for me 00:29:06 Phoenix Ding: Yeah looks good 00:29:07 Joyce Qiao: looks good 00:29:08 Hiruni Jayasekera (she/her): i can see 00:29:11 Yulan Xie: Looks good 00:29:13 Jiayi Zhu: Looks good 00:29:21 Samantha Krutzfeldt: yeah bigger is better, since i have my r window open yours has to be smaller 00:29:53 Aliza Adler: Histogram? 00:29:54 Maddy Griffith: histogram 00:32:00 Phoenix Ding: Right scew 00:32:02 Nikki Marucut: Right skewed 00:32:16 Maddy Griffith: Right 00:32:18 Ekua-Yaaba Monkah: skewed right 00:34:18 Jessica Fields (she/her/hers): Do we have to do height too? 00:34:31 Chitra Nambiar: or alameda_pop$num_sibs 00:35:55 Silvana Larrea: 10 00:37:46 Silvana Larrea: I did 00:37:51 Lian Hsiao: same 00:38:53 Nadia Rojas: Do we copy the code exactly or do we change the saved names? 00:39:46 Ijeoma Uche: ^^ 00:40:11 Samantha Krutzfeldt: ^^ yeah what are we suppose to be entering for our code? 00:40:48 Ijeoma Uche: So do we just run it 10 times 00:40:58 Andriana Marijic Buljubasic (she/her): Also if I not technically in this section do I copy and paste in this section or the one I am actually enrolled in 00:41:16 Andriana Marijic Buljubasic (she/her): Thank u 00:41:58 Sam Holland: bimodal? 00:42:51 Sam Holland: 0.75 and 1.3? 00:42:56 Maddy Griffith: 0.7 and 1.25 00:42:58 Maddy Griffith: Or so 00:42:59 Phoenix Ding: around 0.7 and 1.35 00:43:28 Phoenix Ding: 0 to 5 00:43:52 Leslie Giglio: Is the spread the same as the range? 00:43:52 Phoenix Ding: bimodel 00:43:55 Jessica Fields (she/her/hers): right-skewed 00:43:56 Sam Holland: can bimodal data be skewed right? 00:44:38 Nadia Rojas: Can you show the code in your screen again when you get a chance? I’m getting an error for some reason 00:44:54 Nadia Rojas: yes 00:45:11 Samantha Krutzfeldt: i think that code is for the next part no? 00:45:38 Cheyenne Pritchard: 1.189 is true mean I think 00:46:11 Chitra Nambiar: 1.13 00:47:00 Nikki Marucut: 5 becomes 50 00:47:01 Phoenix Ding: size_50 <- sample_n(alameda_pop, 50, replace = FALSE) size_50 %>% summarise(mean_numSibs=mean(num_sibs)) 00:49:19 Sam Holland: unimodal no outliers 00:49:26 Nikki Marucut: It’s normally distributed 00:49:28 Julia Hankin: A lot more symmetric 00:49:34 Nikki Marucut: 1.17 00:49:58 Phoenix Ding: 0 to 2.5 00:49:59 Silvana Larrea: From 0 to 2.5 00:50:37 Hiruni Jayasekera (she/her): narrower range 00:50:38 Leslie Giglio: Smaller range 00:50:38 Justin Nguyen: more normal 00:50:47 Ekua-Yaaba Monkah: I keep getting the same mean each time I run the code 00:52:01 Ekua-Yaaba Monkah: thank u 00:52:06 Maddy Griffith: About 1.2 ? 00:52:26 Silvana Larrea: It is closer to the true mean 00:55:44 Nikki Marucut: Range = .94-1.486 00:56:16 Ijeoma Uche: Unimodal 00:56:18 Nikki Marucut: The shape is unimodal and and looks approximately normal 00:56:34 Nikki Marucut: 1.2? 00:56:36 Hiruni Jayasekera (she/her): approx 1.18? 00:58:02 Silvana Larrea: It approximates the normal distribution 00:58:03 Leslie Giglio: the sampling distribution of the mean becomes more normally distributed 00:59:09 Nikki Marucut: Thinking... 00:59:09 Cheyenne Pritchard: more samples mean that when we get a mean that's way off by chance it won't have as much of a pull for the overall sample mean 00:59:12 Justin Nguyen: central limit theorem? 00:59:13 Annalisa Watson (she/her): Less vulnerable to outliers 00:59:18 Cheyenne Pritchard: what annalisa said^ 00:59:35 Ekua-Yaaba Monkah: got it 01:00:08 Nikki Marucut: I guess more people = is closer to the population 01:00:30 Nikki Marucut: Or approximate the population better 01:01:33 Nikki Marucut: C ! 01:01:35 Lupita Ambriz: 500 01:01:36 Taylor Zehren: c 01:04:32 Aliza Adler: For question 1 (and the others), do we have to store our answers as a vector? If so, could you quickly go over that? 01:06:04 Aliza Adler: Ah got it! Thanks! 01:09:45 Phoenix Ding: height_mean_sd <- alameda_pop %>% summarize( mean_height = mean(height), sd_height = sd(height)) # YOUR CODE HERE height_mean_sd 01:11:01 Nikki Marucut: Hist? 01:11:34 Cheyenne Pritchard: p6 <- ggplot(alameda_pop, aes(height)) + geom_histogram() 01:11:38 Justin Nguyen: ggplot(alameda_pop, aes(x=height)) + geom_histogram() 01:11:48 Julia Hankin: ggplot(alameda_pop, aes(x= height)) + geom_histogram(binwidth = 1, col = "white") 01:12:07 Justin Nguyen: also why couldn't we use mutate for question #5? 01:13:01 Sam Holland: Could we use data.frame to complet #5? 01:13:04 Sam Holland: *complete 01:13:11 Justin Nguyen: ah got it ty 01:13:29 Sam Holland: I tried exactly the same code but got an error 01:14:31 Ijeoma Uche: Center at 70 01:14:40 Nikki Marucut: It looks unimodal, and symmetric 01:14:42 Maddy Griffith: Pretty symmetrical 01:14:52 Maddy Griffith: Spread ~ 60-80 01:15:08 Nikki Marucut: Yes 01:15:09 Maddy Griffith: Yes 01:15:10 Ijeoma Uche: Yea 01:15:13 Phoenix Ding: yes 01:15:23 Olufunke Fasawe: can you show the codeagain pls? 01:15:58 Cheyenne Pritchard: known_pop_sd <- 2.786314 01:16:11 Chitra Nambiar: height_mean_sd$sd_height 01:18:44 Nadia Rojas: Normal distribution 01:18:45 Annalisa Watson (she/her): SRS, normality, known SD 01:18:45 Nikki Marucut: Simple random 01:19:48 Annalisa Watson (she/her): Is there a symbol for sample standard deviation? 01:20:07 Annalisa Watson (she/her): thanks 01:20:23 Christopher Patterson: yes 01:25:57 Ijeoma Uche: SE 01:25:58 Leslie Giglio: Standard error? 01:25:58 Cheyenne Pritchard: standard error 01:25:59 Sam Holland: was that standard error? 01:25:59 Andriana Marijic Buljubasic (she/her): Standard error 01:26:00 Julia Hankin: Standard error 01:26:50 Cheyenne Pritchard: omg idk if this is news to anyone else but you can now do ANY emoji as a zoom response 01:27:08 Kelsey MacCuish: 😄 01:27:14 Leslie Giglio: Game changing^^ 01:28:37 Annalisa Watson (she/her): We don’t have instructions to do n=500 in our lab 01:28:54 Kelsey MacCuish: 1 01:31:31 Ijeoma Uche: Can we go over the code for 8 01:31:43 Hiruni Jayasekera (she/her): ^^ 01:31:46 Maddy Griffith: Still workin 01:32:34 Lupita Ambriz: I also would like to go over #8 01:33:54 Sam Holland: yes 01:33:56 Sam Holland: and yes 01:33:59 Andriana Marijic Buljubasic (she/her): yes 01:33:59 Lupita Ambriz: yeah 01:34:00 Nikki Marucut: yes 01:34:04 Nikki Marucut: We see both 01:38:02 Annalisa Watson (she/her): Does anyone get object 'mean_heights' not found 01:41:19 Cheyenne Pritchard: ^ I got N/A 01:44:42 Annalisa Watson (she/her): I’ll try that thanks 01:45:01 Jessica Fields (she/her/hers): Are we supposed to create 3 samples each with sample size 500 or not? (In the RMD it doesn’t seem like we have to, right?) 01:45:10 Cristal Escamilla: I got an Error: unexpected symbol in: " p8" 01:46:11 Cristal Escamilla: p8 <- size_10 %>% summarise(mean_heights = mean(height)) %>% mutate(lower_CI = mean_heights - critical_value*known_pop_sd/sqrt(sample_size), upper_CI = mean_heights + critical_value*known_pop_sd/sqrt(sample_size) 01:47:56 Ijeoma Uche: Im confused about this question :What proportion of the confidence intervals contain the mean 01:48:18 Samantha Krutzfeldt: does anyone else need to see the whole code from beginning to end? 01:48:21 Jessica Fields (she/her/hers): All except one of the CIs include the population mean 01:48:41 Samantha Krutzfeldt: I've been sending you messages Kelsey, not sure if you aren't getting them 01:48:52 Cristal Escamilla: i figured it out 01:49:02 Cristal Escamilla: thank you! 01:50:11 Samantha Krutzfeldt: pleeeease help hahah😂 01:50:14 Maddy Griffith: 95/100 01:50:30 Sam Holland: I am going to ask her for help after the lab Samantha ^ I am confused as well 01:50:52 Maddy Griffith: Not sure why, can you explain? 01:51:28 Samantha Krutzfeldt: i have another class but i guess im skipping lol 01:54:08 Julia Hankin: Sorry Kelsey, I’m confused about what represents the population mean on this plot, is that the black dot? 01:54:19 Jessica Fields (she/her/hers): Any chance you could show the plot of the CIs for n=50? 01:54:51 Julia Hankin: Ohhh got it, thank you! 01:55:16 Justin Nguyen: so even with small sample size we will get the true mean 95% of time given we repeat the process many times? 01:55:36 Ala Koreitem: So is 95% the proportion of CIs that contain the mean? 01:56:05 Julia Hankin: The confidence interval will be larger? 01:56:05 Nikki Marucut: It will be wider 01:56:15 Hiruni Jayasekera (she/her): ^that’s with a smaller n right? 01:59:13 Hiruni Jayasekera (she/her): they are narrower? 01:59:21 Ijeoma Uche: 95% 01:59:21 Olufunke Fasawe: The CIs are narrower 01:59:23 Olufunke Fasawe: 95% 01:59:54 Hiruni Jayasekera (she/her): larger n 02:01:09 Ijeoma Uche: Random but When is the midterm review? 02:02:32 Phoenix Ding: 1: Removed 89 rows containing non-finite values (stat_bin). 2: Removed 2 rows containing missing values (geom_bar). 02:02:38 Phoenix Ding: May I ask a question 02:02:39 Jessica Fields (she/her/hers): Thank you! 02:02:43 Maddy Griffith: Thank yoU! 02:02:47 Nikki Marucut: Thanks Kelsey 02:02:51 Genesis Navarrete: thanks Kelsey 02:03:08 Ekua-Yaaba Monkah: thank you kelsey 02:03:25 Joyce Qiao: thanks so much Kelsey 02:03:25 Michele Ko (she/her): Thank you Kelsey! 02:03:28 Julia Hankin: Thank you so much, Kelsey! :)