 Great. Okay. It looks like we've got most people back. So welcome back to the workshop everybody. I hope you all had a nice lunch break. So in this section of the workshop, we're going to be getting to grips with exploring the data a little bit more. But before we get started with that, I'd just like to introduce Nigel and Nadia, who you might have met in the chat earlier. Nigel and Nadia work on the UK Data Service user support and training team. They are here to help if you have any queries about R or status. Nigel, as he's popped in the chat, we'll help you with any status queries as we go through these activities and Nadia is our expert on R. Okay. Great. So I'll show you. Brilliant. Thank you. Okay. So now we're going to look like I said, exploring some of the data with some practical exercises. So I'm just going to run through the general aims for this session, talk about how it's all going to work, and then we'll get started. So in this session, we're going to do two separate Explore the Data activities. The first one, we are going to look at the Quarty Laberforce Survey October to December last year, and you should be able to access that data through the Dropbox link, the first one if you've completed the form that Sorcia sent. If you haven't done that yet, Sorcia, could you perhaps resend that form in the chat for anyone who needs it? Yeah, of course. So that's through to the Dropbox, and that will give you the data that you need. So throughout this session, our aim is going to be in each practical to recreate some ONS estimates. So in the first practical, we're going to produce some estimates of temporary employees, and then in the second one, we're going to look at some estimates for gross weekly earnings of full-time employees. And though the task is to make the estimates, the main aim we have is to help you get familiar with the data. So please just take your time with it. Ask us any questions as you're going through and let us know anything that you're not sure of. So the format of the exercises is pre-written or syntax or code files, which hopefully you've found by following that form in the first Dropbox. Again, I'll reiterate that if you are using SSS or Stata, you'll need to follow the updated syntax Dropbox link, which is the second one that I've put in the chat. That's just because we made some slight changes to the syntax. Also, the activity does require using C tables. I did have a conversation with someone yesterday who didn't have that plug-in for SPSS. So if you don't have that, there are some alternate options within the updated syntax for you to do that as well. So the format of the exercises, like I say, is that we've got these pre-written files and the set of files are different for each software. So there's a file for each practical for each software. So, and like I said, Nadja will be here to help with R and Nadja will be here to help with Stata. So I'm going to give a little demonstration and introduction in SPSS. And then you should be able to, we'll split off and we'll go and work on our separate softwares. So the first step is to open the data. So the code for the Stata and the an R both include code to help you read in the right file. So if you're using that, that's there for you to use. Within SPSS, just in case anyone's not familiar with it, you can open data by using file, open data, and then selecting the file that you want to open. So in this case, it's the October to December file. Okay, so let's just have a look at the data first. So here we can see this is variable view. This is what we're going to work in. So here you can see the names of all the variables, information with the labels and the values. And I will say for these activities, you want to in particular pay attention to these columns to help you answer the questions. And you can extend these if you need to as well for more information. So the second thing we're going to want to do is save the file with a new name. And we're going to work on it in the new version that we create. And this is just so that you have the original if something goes wrong. And this is really good practice for working with any data that you are. That's just my SPSS. So I'm going to go file, save as, and I'll just add practical one to the end. So I recommend that you do that with any files that you've got. Just let SPSS load for a second. Great. Now that we've got our data set all set up, the next thing I'm going to show you is the code files. So this is the syntax file for the SPSS part of the activity. And here you can see that we've written in the notes the different exercise instructions. So this tells you where to start. And this file is a mix of both commands which we have commands and syntax which we have written and also some review questions. So some of the questions will be pretty obvious, others will be less so, but they're just there to help you check you know what's going on as you go through. So you can type in and answer those questions as you go through. And there is an answer sheet in the original Dropbox as well. So like I say, the files did come to us in SPSS syntax and we've created Stata and R versions and they are similar enough that you should get something equivalent but if you're using those other software just be aware that they might be a little bit different. So what I'm going to do now is I'm going to just demo how to run some syntax in SPSS just in case anyone hasn't done it. And then what we'll be able to do is we'll move on to independent kind of working on this but we'll be here to help you if you have any issues. So to run this in SPSS, you just want to highlight the section that you want to run and then just press the green play arrow. It will open a second output window that looks like this and show you the information that you need to answer the questions. So that's the introduction to this section. If anyone has any issues, please do let me know and I'll be able to demonstrate for the SPSS version. I also want to flag that if anyone is particularly struggling we will be able to potentially facilitate a one to one and split off with the relevant expert if you need help with anything in particular but for now, please go ahead and have a go at the activity and any questions, please let me know. And I see that we've had a few people join late. So if anyone's not clear on what's happening do put a message in the chat and I'll be able to fill you in. So we've got about 25 minutes for this, I think. So we'll come back together at about 25 too and we'll do a review. Just quickly, Allie, there was a question. Oh, actually, I think Nadiya's answered it. Thank you, Nadiya. It was just about which set we're using first. Yes, so Nadiya's answered it. But just for anyone who's not clear, you'll see that there are two data files in the drop box. The one with the study number 8777 and one with 8778. So the first activity we're gonna use 8777 to do both the temporary employees and the growth weekly earnings. And then the other one is the longitudinal file which we'll move on to in the second explore the data. But for now, we'll start with the 8777. We've got another question. What is the difference between syntax and data? No, that's a really, really good question. Please don't apologize. So the data is, I'll demonstrate actually on the screen. So the data is the file that we are using that basically contains the data that was collected in the survey. So all of the information of the respondents answers to the questions. So that looks like this. The syntax is, so we call it syntax in SPSS and we call it code in programming. And it basically is the instructions that we run to get the instructions that we run to get the answers that we want to generate the tables and the outputs. So for example, this one here, I've typed frequencies and then the names of the variables that we want to get the frequencies for. So I run it, it analyzes the data and then generates an output. So the syntax just tells us, tells the program or the code tells the program and what we want to do. If your confusion is with the separate folders, the data files end with .sav, which tells you it's an SPSS data file and the syntax ends with .sps. So that will tell you it's the syntax file. So you need both to be able to do the activities. So the syntax one contains all of the instructions and the review questions and the data is just what you have to apply that syntax to to get the outputs like this. I hope that makes sense. Do you send another message? If not. There was another question with regards to the variable JBTP101, so basically what's the difference between the, with the one ending 101, 102, et cetera, et cetera. So that's basically the different answer options, but that's a multiple choice question and it captures the different answer options in each of these, I think, if I remember correctly. Great, thank you. Okay, so I can see that someone's saying that they're having trouble adding the weight. So what we want to do to add the weight is to just, like I said, highlight it. I'm still sharing my screen, aren't I? Yeah, so highlight it like this and then click the play button and then the weight will add. You will get a little output window that looks like this that says weight by PW20. And then how you can check that the weight is applied is by going back to your main screen and at the bottom here, it will say weight on. If you can't see that and for some reason the syntax isn't working, you can go to data at the top, then weight cases, weight cases by, and then you can select your variable from here. So that variable is the, what's it called? So you can switch it to make it alphabetical and you can scroll, not make it alphabetical, sorry. Sort by the variable names and then I'll remind myself what the weight is called, PWT. And then you can select it through here. We're trying to do this menu-driven, not syntax-driven, not menu-driven, but that's just another way of doing it if for some reason the syntax isn't working. If not, I would suggest, if you're still having trouble, Jamie, I would suggest just closing the file and trying to reopen it and run it again. Sometimes SPSS can be a little tricky about things. If your issue is adding the weight in the second practical, I would suggest again, opening the original file. So not the one that you've saved to be practical one, opening the original one and then saving that and titling it practical two because sometimes it doesn't reset properly between. So try all those things and if you're still having problems, send another message in the chat and we can pop into a breakout room to try and work it out. We've got a question just now. Why do we only include cases with a weight greater than zero? Should we always do this? Sorry, my Zoom is, my Teams is bugging. Is this, let me just double check this, sorry, one second. Which section of the analysis is this? Oh, it's where we, is it in the first one or the second one? Corinne, do you want to just put it in the chat? Is it in the first one? It's in the first one, great, okay. Let me just have a look. Okay, yeah, so we've selected those who have a weight of greater than zero. I assume and Martina and Simon, please correct me. If I'm wrong, we don't want to include those with a weight of zero because it means that they're not a valid case within the data. Is that correct? Yeah, I think that's correct because basically if someone has a zero and you multiply it by the variable, then you have a zero so they wouldn't be included anyway. So yeah, that's why we exclude them. But just which weight are we using there? Because depending on what weight you use, for example, in some of the datasets, not everyone gets a weight. For example, there's a non-proxy weight, et cetera, et cetera. So only those that have responded in person basically have a valid weight. And the other ones that were interviewed by proxy basically then would have a zero because we wouldn't want them to be asked certain questions for the relevant variables. So it depends, that's why it's really important that you use the right weights for the right variables, which is what Simon mentioned earlier. Yeah, great. Thank you, Martina. Yeah, so in this case, we're using it, yeah, like Martina says, hope that clarifies. I'm muted. I'm just gonna give a quick recap of the session of the first couple of activities and I'll introduce the second Explore the Data activity. So just to recap this session, so just some important things to take away from it. So in the first exercise, it's really important to note that the weight that we use in the LFS is a grossing weight, which means it aims to scale to known population totals. So you might have noticed when you round the first frequency and then reround them, the frequencies are much higher when the weight is applied. We then used a filter to select those in non-permanent employment. So that's a really useful way for you to select the relevant population that you're interested in. But what we also see is that though the starting sample is about 74,000 people, by the time we get to like looking at those who fit in our population of temporary employees, there are only about 1,600, I think that's right. And then when you're looking at the second exercise that looks at earnings, the thing to take away from that is that we need to use a different weight when analyzing income. So that's just like Martina and Simon were saying it's super, super important to make sure you're using the correct weight. And again, we should note that estimates of things like the number of full-time employees depends on whether we use the standard weight or the income weight. So yeah, again, you just really need to be careful and be on top of what weight you should be using. So we now have time for a little bit more practical analysis. So it's your choice. You can continue with practical one and practical two, which like we said uses the quarterly file, but there's also a practical three that uses the two quarter longitudinal file. And the aim is to just get familiar with the data, a different sort of form of the LFS data. And so this practical helps you to explore different ways of looking at labor market flows. So that's changes in people's employment status between two different quarters. And the syntax and the code and everything for that is available in the same places. So if you want to have a go at that one as well, please, please go ahead, but there's no rush work through at your own pace and send us any questions as you need. Well, I can see we've got a question about in which guides can the weights be found? Gosh, like I said, there's 11 user guides. So I'm not sure I know off the top of my head. Let's have a look. So I can see that I can find waiting in some information on the background of waiting in the volume one guide, usually in section 10. I've come across it there. If you wanted specific info on the waiting variables, that would be in the variable guides like we discussed. Yeah, does Martina Simon, do you have anything else to add other than that? I recommend any other guides other than the volume one. The volume one is basically sort of the key one to get an overall overview of I guess the methodology, the history of how it all changed if you're interested in that. And yeah, that's what I would say as well. And all the others are more specific to variables and data sets depending on what you want to find, yeah. Great, thank you. Oh, yeah, so the question in the chat about getting the October data as well. So the code is just a specific number. I'll actually demonstrate this now because I think I've mentioned it a couple of times but I haven't been necessarily the most clear about it. So to address that question, if I just move this over and share my screen. Okay, so if you look at my screen here, we have what we call the study number, which is this is actually not the data that we're using, it's just a different one. So this is the study number and this is the code that you can use to basically make sure that you're using the data set that you want to use. When you download it, which is the zip file like you would find on the Dropbox, it will have UKDA followed by this code. So if I go to our find data and I want to look for the specific data set that we're using first of all, so the October to December one. And I know the code is 8777. If I search for it, it will take me straight to the search page that shows the result for this data. And this is the data set that we're using. So if you've ever got a data set and you're not entirely sure if it's the right one, you can just look up and double check the code. And you could also do this in reverse. So for example, you could search quarterly labor for survey October to December. And then once you're on this page, you can see the study number. And then if we look at say a different one, so if we look at 8778, which I think, yeah, so this is the other data set. This is the longitudinal data set. So this is just to make it really clear which data set is which basically. Okay, so if no one has any questions, I'm just gonna say thank you so much to Simon and Martina for coming and offering their expertise to us. Thank you to Nigel and Nadia for their software help. And thank you to everyone for attending. The workshop slides will be up. The workshop slides are already up online and the recording will be up in about a week, I think. And if you have any questions, you can contact us by emails or by the help desk. I'm gonna stick around for another 15 minutes if we've got any more software questions. But thank you all very much for attending.