Qaecologist Posts

COVID hotel quarantine failures – a hierarchical model

Sat, 05 Jun 2021 04:16:49 +0000

With another lockdown in Victoria, the media has been asking why Victoria has had a worse COVID experience than other Australian states. Much can be explained by the challenges of the second wave and an overwhelmed contact tracing system. Contact tracing is now much improved, with tens of thousands of contacts being identified and managed quickly during the current outbreak.

Another media focus has been rates of escape from hotel quarantine, which are now the main source of outbreaks in Australia. If you look at the raw numbers, it seems that some states might have better systems than others, especially when considering the number of travellers who have been quarantined. But how sure can we be of that? Can some states feel smug superiority, or have they just been lucky?

Leah Grout and colleagues examined the rate of failure of quarantine facilities in Australia and New Zealand, reporting the number of failures, the number of quarantined travellers, and (importantly) the number of those travellers who were COVID positive (as of early 2021). This latter number is one of the keys – you could have the worst quarantine system imaginable but you won’t have any failures if none of the travellers are COVID positive.

So what do the numbers tell us? New South Wales has processed the most COVID positive travellers of the jurisdictions in the database (1581) but it has also had the most identified failures (5 to that point). Victoria has had almost as many identified breaches (4) but many fewer positive cases in their quarantine system (462).

But when looking at these data, you might notice that the number of failures is low. The small numbers mean that any estimates of the rate of failure of hotel quarantine will be uncertain. How uncertain? Very uncertain!

Even in states/territories with zero breaches so far, the rate of failure might be no lower than in the jurisdictions that appear to be performing worst. Tasmania and the ACT are cases in point – both have had no recorded breaches of hotel quarantine but they have also processed very few COVID positive travellers (21 and 25 respectively).

Even the Northern Territory, with its much vaunted Howard Springs facility, had only 88 COVID cases in Grout et al.’s data. Consequently, the uncertainty around an estimate of the rate of failure of hotel quarantine is large.

To estimate the rate of failure, let’s first treat each of the COVID positive cases as a simply Bernoulli trial, with the probability of failure being the same for each person within the jurisdiction. You can see the estimates below. Do you notice the large intervals around the estimates for the NT, ACT and Tasmania? Using only the observed rates of failure, we can’t really be sure that those jurisdictions are better than any other.

Estimated probability of failure of COVID hotel quarantine for each infected traveller, based on the failures reported in Grout et al. (in review). The dots are the point estimates (failures divided by cases), and the bars are 95% credible intervals, assuming a uniform prior for the probability of failure.

The cabins at Howard Springs have the advantage of almost eliminating aerosol transmission between rooms, which appears to be a problem in the hotel systems that operate elsewhere. But we know, intuitively, that the hotel quarantine facilities in places like the ACT and Tasmania are likely to suffer similar risks to similar systems in other jurisdictions. Given that, the risks are unlikely to be as high as indicated by the upper bounds of the intervals above. But likewise, the probability of quarantine failure is unlikely to be zero.

How can we “borrow” information about rates of failure in other jurisdictions while at the same time allowing for some differences in rates of failure between jurisdictions? Well, let’s say hello to a hierarchical statistical model!

For our hierarchical statistical model of failure rates from COVID quarantine hotels, we assume that the rate of failure of each jurisdiction is drawn from a common pool of possible failure rates. This pool of possible failure rates is defined by a probability distribution – hierarchical modelling estimates this distribution. Each jurisdiction has its own particular failure rate – if the rates differ a lot between between jurisdictions, then the distribution that defines the pool of possible rates will be wide. If the rates are similar to each other, then the distribution will be narrow.

You can think about what such a hierarchical model might mean when estimating the failure rate in places like Tasmania and the ACT where data are scarce. If we look at the jurisdictions with more data, the rate of failure is unlikely to be larger than 0.02 or so (the upper bounds of the 95% intervals in the figure above). So, these more precisely estimated rates will tend to constrain the variation in the pool of possible rates.

To formalise this idea, we need to define a model for that pool of possible failure rates. When dealing with probabilities, we know that the values are constrained to be between zero and one. However, probabilities can also be expressed as odds. The odds that an event will happen is the probability of it happening divided by the probability of it not happening. So if p is a probability of an event, then p/(1-p) is the odds of the event^*. Odds are constrained to be between 0 (when p = 0) and infinity (when p = 1).

Now, if we take the logarithm of the odds, then the resulting value is the log-odds, and this number can take any real value between minus infinity (when p = 0) and plus infinity (when p = 1)^**. This transformation is useful, because it is straightforward to define a distribution on this interval – we can use a normal distribution. Now our pool of possible failure rates can be defined by a normal distribution (with the values drawn from this distribution being back-transformed to become probabilities). The statistical model^*** then simply needs to estimate the mean and standard deviation of this underlying normal distribution.

So what do the results of the hierarchical model indicate? Well, that model suggests that differences between jurisdictions in the rate of hotel failure might be as large as an order of magnitude or so (e.g., compare the extreme upper limit of one jurisdiction to the lower limits of others). But equally, there is also not compelling evidence that the risks differ much at all (e.g., note the large overlap of the 95% intervals). So when I hear pundits declaring how one state’s quarantine system is better than another’s based on the rate of failure, I just roll my eyes – they don’t quite understand how variable chance can be, especially when estimating rates of rare events.

Estimated probability of failure of COVID hotel quarantine for each infected traveller, based on a hierarchical model of the failures reported in Grout et al. (in review). The dots are means of posterior distributions, and the bars are 95% credible intervals. The right hand value is the average over the Australian states and territories.

Since the preparation of Grout et al.’s paper, we’ve seen further escapes from hotel quarantine – Victoria’s current outbreak being a case in point. And there is a second possible escape too, although sequencing so far has been unable to pinpoint the source of the delta variant in Victoria. But Grout et al.’s data suggest that an escape will be identified for every 200 or so COVID-positive cases in hotel quarantine. With COVID cases continuing to be common around the world, we’ll see more COVID cases in hotel quarantine with more outbreaks expected.

Notes

* You will have seen odds in horse racing. These define the payout from the bookmaker. They are essentially the odds of the horse not winning (while also factoring a small margin to pay for the bookmaker’s investment portfolio and collection of fancy cars).

** This is the logit transformation and is the basis of logistic regression.

For those interested in the details, here is BUGS code for the hierarchical model:

model { for (i in 1:8) # for each of the 8 jurisdictions. { re[i] ~ dnorm(0, tau) # how the probability of failure for each jurisdiction varies logit(p[i]) <- logit(pav) + re[i] # the prob of failure for each jurisdiction fails[i] ~ dbin(p[i], cases[i]) # failures treated as a set of Bernoulli events } OzHQ <- mean(p[2:8]) # average probability of failure for Aust hotels pav ~ dunif(0, 1) # the prior for the average probability of failure tau <- 1 / (s * s) # BUGS defines variation of dnorm by precision = 1/variance s ~ dunif(0, 100) # the prior sd }

And here’s the data used (NT is excluded given it includes the non-hotel site of Howard Springs; the order is: NZ, ACT, NSW, Qld, SA, Tas, Vic, WA):

cases[] fails[] 758 10 25 0 1581 5 543 3 230 1 21 0 462 4 450 1 END

Welcome John!

Fri, 21 May 2021 16:38:55 +0000

Dr John Donohue recently joined our group as a Research Associate. John will be working on some of the mechanistic modelling aspects of our AlienImpacts project.

John was previously a post-doctoral researcher at the University of Limerick where his research focused on the mathematical modelling of soil biomass. Before that, he completed a PhD in Applied Mathematics at NUI Galway where he worked on the modelling of seasonally migrating populations.

We’re really excited to welcome John to the group and to see what cool research he will do.

A damp (mini-)lab walk in New Forest (and evidence of someone who is hopeless at taking selfies!)

Senior Editor role at Journal of Ecology

Wed, 07 Apr 2021 17:08:16 +0000

I’m super excited to be joining the Senior Editor team at Journal of Ecology this month!

I absolutely love the journal (and the British Ecological Society more generally), so delighted to have the opportunity to contribute to the journal, our science and our wonderful community of plant ecologists in this way. Let the fun begin!

Journal of Ecology is very excited to announce that Jane Catford will be joining our Senior Editor team! Jane has been an Associate Editor with our journal since 2016 and we’re thrilled to see her take on this new role.

Here we interview Jane about her current research, favourite plant species, ideal fictional lab partner & dream superpower!

My top easy ways to use a to-do list or task manager

Mon, 15 Mar 2021 01:18:40 +0000

Do you find that you always forget ‘all of the things’ you need to do? – and people are getting fed up with you because of it?

Are you finding yourself overwhelmed – just because you need to keep all these things in your head?

Well, hold on to your seat, because I’ll let you in on the top easy ways I use to-do lists and task managers for greater productivity!

Task managers in a nutshell

What is a task manager … you say?

Well, a task manager is a fancy way to say a ‘to-do list’.

It is a repository for all your tasks (big or small) that may also be ordered by category and/or date.

There are multiple options for your task manager, and I will go through the pros and cons of each super quick.

Paper to-do lists:

The ancestor of the task manager, probably around since the Bronze Age (or whenever organized people evolved). While it has that great tactile feel, the paper to-do list can easily become obsolete if you keep forgetting your notebook at home/work/at your boyfriend’s place.

It also has limited capacity for categorization by topic and/or dates, and limited capacity for updating (remember: any task manager is a living, breathing system).

Digital methods:

The app I use as a daily task manager is called Todoist.

What I love about is that you can use natural language to create a task. For example, ‘Decide on new kitchen benchtops #HomeReno by Monday’ is automatically filed to my Home Reno project and scheduled for Monday. Genius!

There are plenty of other tools out there, such as Asana, Trello, and even Google Keep.

What I would recommend is have a quick glance at which would suit you better, jump in, sign up, and stick to one.

An example of my marketing tasks in Todoist – note, at the top, the exact task I am doing right now!

Make it the repository for ALL the things

My top tip is to use your system for all (or nearly all) of your tasks.

The system is really here to prevent you from using your brain as a storage container (‘Oh I need to book my hairdresser appointment in 6 weeks! Oh this grant is due in a week!).

If you only use the system for 40% of your tasks (let’s say, your work tasks), your brain will be still be freaked out trying to remember the remaining 60%.

Your brain won’t trust the system as being complete, and so, will try to remember things on its own AND blame the system when things go awry.

Remember: a system’s value increases exponentially with the amount of stuff you put in it. A system with nothing in it has ZERO value.

Update your task manager regularly

The next most evil thing besides an empty task manager is …. An outdated task manager.

Like everything in your life, your task manager needs regular upkeep and loving.

Make time (every Sunday night or Monday morning) to clear the system of outdated tasks, moved deadlines, or irrelevant shit.

This is also a very good way to trick your brain into feeling ‘in control’ (i.e. if it is in the task manager, it will get done!).

Make your system clean-out a fun and relaxing routine, for example by putting some music on and sipping a delicious cup of coffee.

My current weekly reset routine in Todoist

Use your task manager daily

I use my Todoist daily.

It is the first thing I open on my computer in the morning (before emails). This means that my daily priorities are set by myself (I mean, yesterday’s Lucie), instead of other people. Try it, it will change your life!

What I see in the morning is a neat list of tasks I need to do that day. When I’m feeling fancy, I also put my meetings in it. Or you can use a calendar to remind yourself of your appointments.

This list becomes a mini time-blocking strategy (esp. if I add how long each task takes).

Using the ‘board’ function (for you visual thinkers out there), you can also visualize your whole week with time blocks.

If you need more inspiration to set up your day for maximum success, you can also watch this quick video I made.

Use your task manager for repeat tasks

To me, one of the most fantastic uses of a task manager is to put repeatable tasks on auto-pilot.

Think of it … how many truly unique things do you do each month?

Probably not that many!

I use my task manager to list on-repeat personal and professional tasks such as:

Watering my plants (every 10 days)

Doing my bookkeeping on the 1^st of each month

Keeping up to date with my studies (weekly)

Going through my weekly ‘Project360’ method for each project I manage

Booking my dentist appointments (annually)

Imagine how great life would be if you never forgot to book your hairdresser, car services, or getting that birthday present.

Your peers would love you a whole lot more (now that you’ve stopped forgetting about everything you promised). And you would be a lot more beautiful and well kept!

Setting repeatable systems

OK, this is for the ninjas of the task manager users …

I call this …. The SYSTEMATIZER.

Imagine if you could streamline all the processes you repeat regularly (such as uploading blog posts, writing grant reports, or processing your uni expenses).

How much more efficient and faster would you be? You wouldn’t have to Google how to do it every time, that’s for sure.

Well, create a mini checklist for it in your task manager!

Let’s take the example of my bookkeeping. Each month, I do the same tasks (outlined below) and review the same types of expenses (office rent, office supplies etc.).

If I had to remember each category every time, I would lose so many receipts, and the ATO would be all over me.

Next time you complete a project that requires multiple steps, take the extra 10 min to create a checklist. Bonus to you if you add links to Youtube videos and articles on how to do what you need to do.

Even though it seems boring (well … it’s not to me), entire industries were built on repeatable procedures (salient examples include the army, surgeons, and automotive industries). There is even a book about it called the Checklist Manifesto!

Your turn

DECIDE on a paper to-do list or online task manager. Sign up and use it daily for a week. See your life transform!

The post My top easy ways to use a to-do list or task manager appeared first on Dr Lucie Bland | Managing Editor.

My top tips and tricks for time tracking

Thu, 04 Mar 2021 03:56:10 +0000

Have you ever been curious about time tracking, but not sure where to start? (or why do it?)

Well, I’ve been religiously time tracking for going onto four years, so I can share a few tips and tricks with you (as well as the dark side of time tracking).

What is time tracking?

Time tracking is the simple practice of making note of how you spend your time.

For example, you could simply use a notebook (e.g. 9-11 am Monday: Writing ARC grant).

The difference between time tracking and time blocking is that time blocking is usually done in advance of a task (e.g., as you are planning your week, like in my weekly planning series).

Time tracking is what you have ACTUALLY done. And it could be very different to what you have planned!

I use Toggl for my time tracking, and have been on the free plan for years. I’d recommend it to anyone wanting to time track (as I explain in this blog on free productivity apps).

Why time track?

There are multiple good reasons to time track; some are more superficial, and some are kind of psychological and very cool!

Someone might start time tracking if it is a requirement of their job. For example, they have been engaged under a casual or consultant contract, and need to report back on the time they spent on that specific work.

The first advantage of time tracking is that it forces you to define what you are doing: in Toggl’s timer, you can write down the task (e.g. ‘blogging’) and the project to which is belongs (e.g. ‘marketing’).

My Toggl timer at the time of writing (PS: some projects are confidential and were blacked out, soz!).

This first step is very valuable in itself, as it forces you to define ‘work’ more specifically. If you are browsing Twitter, then you have to admit you are doing this and write ‘social media’. If you are processing emails, then write ‘emails’.

This forces you to be intentional and more than once has prevented me from wasting my time (i.e. I could not bring myself to write ‘internet shopping’ in my Toggl!!!).

Using reports to plan your time

The second huge value in time tracking is that you can review and monitor how you’ve spent your time. At the end of the week, a beautiful pie chart will unveil exactly how you’ve spent your week.

Is it different from your perception of how you spent your time? I know that for me, it usually is (and please let me know in the comments your results!).

This can be a wonderful opportunity to re-decide and improve your processes.

Want to spend less time on emails? Then generate creative ideas to do so, and look at your email time decrease each week. Isn’t it motivating?

Want to spend more time writing? Then challenge yourself to spend X more hours next week on it.

You’ll thank your time tracker for being your best boss!

My time tracking journey

When I was working part-time as a postdoc and continued my editing gig, I used time tracking to make sure I was giving sufficient attention to each job. If you hold multiple jobs, I would always recommend to try and do them on different days, but if you can’t, time tracking is a great way to be accountable for your time.

This is when I realized the power of time tracking for keeping ‘naughty’ tasks in check. I got a very good idea of how much of my postdoc time was dedicated to ‘emails’ (20%) and ‘meetings’ (20%). This put me in a very good position to negotiate a reduction in my responsibilities with my boss, as it was clear my research time was being cannibalized (despite my best efforts to be productive).

With the help of a timer (or the Pomodoro function in Toggl), I also realized the power of time tracking to tackle ‘important but difficult’ tasks (i.e. the ones you procrastinate on).

For example, I used to struggle dedicating time to writing my email newsletter. Thanks to time tracking, I could get to work on that specific task AND feel proud when I saw I had clocked the hours I needed (YAY to the sense of completion!).

The dark side of time tracking

I then ramped up my time tracking to epic proportions when I launched my business full time. I would track every single editing project to get an idea of my editing speed for each job type (e.g. paper editing vs. grant editing). This was a fabulous resource as I could quote very accurately (i.e. I knew exactly how long a 100,000-word book edit would take me).

However, I was also getting to face the dark side of time tracking, in that it can make you feel rushed all the time (like the clock is ticking).

It can also make you feel resentful of ‘waste of time’ tasks, such as re-booting your computer, updating your software, or writing a delicate email.

Indeed, it’s a slim margin between being productive versus obsessive.

After 3 years of tracking, I got into a conversation with my business coach, where I let her know how overwhelmed and rushed I felt constantly.

She had a look at my system, and thought it was more of a hindrance than help. She challenged me to stop time tracking for two weeks.

It was a weird change of habits, but I immediately felt immense relief. I didn’t need to monitor each second of my day and billed my clients for half-day blocks of work.

While I’ve kept some aspects of this system, I went back to ‘light’ tracking, because of the advantages explored above.

But this venture in the dark side of time tracking definitely helped me get a full perspective on it!

The advantages of time tracking

Time tracking forces you to define your tasks specifically (e.g. ‘email’, ‘admin’, ‘meeting’, ‘writing’, ‘project A’).

Time tracking gives you an accurate measure of how you ACTUALLY spend your time (rather than how you plan your time or wished/perceived your time)

Time tracking is great to help you monitor, learn, and improve on your work habits.

You get an accurate idea of how long tasks REALLY take, helping you with accurate weekly planning.

Time tracking can get you out of spending too much time on ‘naughty tasks’ (e.g. emails, admin).

Along with Pomodoro timers, time tracking can create motivation for difficult tasks.

Your time track reports are great evidence for discussions with your boss on your work tasks, responsibilities, performance evaluation etc.

You can link your time tracking with the results of specific projects, linking your time inputs to work outputs.

As you can see, all the above advantages are related to planning your time intentionally and having evidence (rather than unfounded beliefs) on how you spend your time.

The cons of time tracking

Tracking your whole life can lead you to feel under pressure or ‘rushed’ for all tasks.

Top tip: think about the specific tasks you would like to time track, and don’t track the rest. For example, I no longer track emails as I have those under control.

Tracking is only as good as the categories you use to track your time.

Top tip: spend 10 min thinking about the categories that would serve your particular life. For example, you might need to separate ‘finances’ from ‘admin’ to get the information you need.

Tracking can underestimate your true work time.

Top tip: keep the timer running if you find yourself thinking about work tasks during your lunch or coffee breaks. If you only track time at your desk, make sure you understand this is a LOW estimate of the true effort expanded (and round up your time if needed).

I hope you found this blog post useful. I can’t wait to share more tracking tips with you!

The post My top tips and tricks for time tracking appeared first on Dr Lucie Bland | Managing Editor.