In this episode, I speak with Anna Mosikian, a physician by training and Global Clinical Program Lead working at the intersection of clinical development and strategic marketing.

Anna brings a powerful perspective on how clinical data translates into real-world value—bridging evidence generation, regulatory expectations, and commercial impact. We dive into what clinical leaders truly expect from statisticians and how statisticians can move from technical contributors to strategic partners.

We explore what “good collaboration” really looks like in practice, why understanding the purpose of a study is critical, and how statisticians can elevate their impact through communication, proactiveness, and cross-functional thinking.

Why you should listen

  • Build real partnerships with clinical leaders
  • Increase your influence in decision-making
  • Communicate your work in a way that drives action
  • Think beyond analysis and into impact

Episode highlights with timestamps

  • 00:01:30 – Anna’s unique journey from physician to pharma leadership
  • 00:03:25 – A surprising expectation clinical leads have of statisticians
  • 00:04:21 – The one mindset shift that changes how you approach trials
  • 00:06:16 – How to create a culture where ideas actually get heard
  • 00:08:40 – A common blind spot in clinical trials you might overlook
  • 00:12:59 – Why waiting for the “perfect idea” can hold you back
  • 00:17:15 – A simple test to check if you truly understand your work
  • 00:20:39 – What really builds trust across teams
  • 00:22:32 – The question you should always ask—but most don’t
  • 00:25:49 – Why exploration matters more than you think
  • 00:26:19 – A major industry shift impacting how trials are designed
  • 00:30:35 – Final advice on becoming a standout statistician

Links and Resources:

🔗 Boehringer Ingelheim

🔗 EU Joint Clinical Assessment (JCA)

🔗 European Medicines Agency (EMA)

🔗 EUnetHTA

🔗 R Shiny – Interactive Data Visualization

🔗 Cochrane – Systematic Reviews and Evidence Synthesis

🔗 Learn more about PSI and become a member

🔗 The Effective Statistician Academy – I offer free and premium resources to help you become a more effective statistician.

🔗 My New Book: How to Be an Effective Statistician – Volume 1 – It’s packed with insights to help statisticians, data scientists, and quantitative professionals excel as leaders, collaborators, and change-makers in healthcare and medicine.

Join the Conversation:
Did you find this episode helpful? Share it with your colleagues and let me know your thoughts! Connect with me on LinkedIn and be part of the discussion.

Subscribe & Stay Updated:
Never miss an episode! Subscribe to The Effective Statistician on your favorite podcast platform and continue growing your influence as a statistician.

Never miss an episode!

Join thousends of your peers and subscribe to get our latest updates by email!

Get the shownotes of our podcast episodes plus tips and tricks to increase your impact at work to boost your career!

We won’t send you spam. Unsubscribe at any time. Powered by Kit

Learn on demand

Click on the button to see our Teachble Inc. cources.

Load content

Anna Mosikian

Oncology Asset & Portfolio Strategist | Driving Evidence into Value

Anna Mosikian is a physician-scientist and oncology leader with experience spanning clinical development, asset strategy, early commercial planning, and portfolio value creation.

Throughout her career, she has worked at the intersection of science, medicine, and business, helping translate clinical evidence into differentiated asset strategies, indication prioritization, target product profiles (TPPs), and long-term value creation.

In her current role at Boehringer Ingelheim, Anna combines global clinical development leadership with a strategic marketing assignment, partnering across clinical, commercial, regulatory, and forecasting functions to shape development and commercialization strategies for oncology assets.

Her experience ranges from leading global clinical programs and health authority interactions to developing TPPs, evaluating expansion opportunities, supporting asset positioning, and defining differentiated development pathways.

Her leadership philosophy emphasizes rigorous thinking, constructive challenge, and ownership of outcomes, with the goal of creating sustainable value for patients, healthcare systems, and organizations.

Transcript

00:00
You are listening to the Effective Statistician Podcast, the weekly podcast with Alexander Schacht and Benjamin Piske designed to help you reach your potential, great science and serve patients while having a great work-life balance.

00:21
In addition to our premium courses on the Effective Statistician Academy, we also have lots of free resources for you across all different topics within that Academy. Head over to theeffectivestatistician.com and find the Academy and much more for you to become an effective statistician.

00:49
I’m producing this podcast in association with PSI, a community dedicated to leading and promoting user statistics within the healthcare industry for the benefit of patients. Join PSI today to further develop your statistical capabilities with access to the ever-growing video-on-demand content library, free registration to all PSI webinars, and much, more. Head over to the PSI website at psirec.org.

01:17
Learn more about PSI activities and become a PSI member too.

01:30
Welcome to another episode of the Effective Statistician. And today I’m really, really looking forward speaking with Anna. And before we dive into the topic, Anna, maybe you can introduce yourself to the audience. Yeah. Thanks for having me. Happy to be here. So I’m Anna. I’m a physician by training and I started my career as a doctor and very fast moved to pharma industry.

01:58
where I’ve always wanted to work, so it was my dream job. And I worked across several therapeutic areas as a clinical program lead. So I’ve planned the trials and ensured that the trial results are interpreted correctly, also communicated with regulators and health authorities. So I worked across different therapeutic areas, as I said, in diabetes mellitus, in oncology, in stem cell transplantation, and currently I’m in Beringer Ingelheim oncology.

02:26
And I want to make a disclaimer for this conversation that everything I’m saying is reflecting solely my personal views and not the views of the AI. Very, very good. By the way, I’ve worked for Beringer Engel as well. It was actually my first company that had joined 2002 after my academic time and my PhD. yeah, still good close relationships, especially as the headquarter is just about an hour away.

02:56
from me, so that’s very nice. So today we want to talk a little bit about the expectations that physicians like you have on statisticians and quantitative scientists that work together with you as a physician, as a clinical program lead. Let’s talk a little bit about first maybe the typical challenges that you have seen in your career in terms of statisticians.

03:25
I have always been blessed working with beautiful colleagues in all the companies I’ve worked in. And I never could complain on the quality. But I was thinking like, what the main things I would expect in our work, which sometimes was a bit of flacking. So I would expect the real partnership. There is sometimes a bias in clinical trials that clinical program lead is responsible for everything and making the final decisions. This is true to some extent.

03:54
But I’m always very much enjoying when statisticians bring up the proposals, when they point on some of my mistakes or some white spaces that I don’t see. And we had fantastic collaborations with some of my colleagues who actually brought up the new trial designs. It was much better than I initially thought of. So kudos to these people. And another thing that I would have in mind.

04:21
The testicians are usually lacking the medical background, which is very expected and normal. But for me, it’s very important to have the end goal in mind. So why are we doing clinical trial? Not to tick the boxes, not to fill the database, but we do it to bring the drug to the patient and to bring a valuable drug to the patient. So I always try to speak more about why are we working, who is waiting on the other end.

04:52
and why all the data really matters. I cannot accept when some data is lost just because of some typos or incorrectness, incompleteness of CRF, because this is other people’s work, it’s other people’s life. And for me, it’s important that all the statisticians understand this, least to some extent, when they’re working. You brought up a couple of really, really important points. The first is to have this end in mind. What do we want to achieve?

05:20
with a study and be very, very clear about it. Is that study said to make an internal decision in terms of that we can move from phase two to phase three? Is it something that will be needed for filing? So is it a pivotal study? Is it a study that we need for HTA purposes or do we need the study to tick multiple boxes? And getting all of these very, very clear is

05:48
I think one of the main points because then you know how good looks like. And without that, it becomes really, really difficult to do all the other things that you mentioned. So how do you work together with statisticians so that there’s a very, very good alignment on understanding what good looks like? First of all, I try to set up our relationship at a high level from the meeting one. And I always start

06:16
from please challenge me. Because especially when you work across different geographic regions, especially if you think about colleagues from China, where it’s not okay in the culture to challenge someone who is considered a team lead, you need some special attention to that. And I adore when people challenge me because something great always happens after these conversations. Also, at the very first meetings, I try to set up the frame. So I try to explain the indication if the person is new to it.

06:47
explain the patient’s story, like what they feel, what all these terms mean, what they suffer from. And then I set up the context for this trial. So it’s very rarely isolated, as you said, it leads to something and it has a history, the background. So I try to always explain where this trial was born from, why is it conducted and what we aim to achieve and what may be the spin-offs of this trial in future. So this usually helps to set up the level of

07:16
scrutiny when we look at the data and the data cleaning. And I think it helps some meaningful collaboration. So people are more willing to work when they feel like they are contributing to something great. Yeah, absolutely. I was always feeling like if I know why I’m doing things, I’m much more willing to do them. And also it makes it more possible for myself to prioritize things. Yeah. So to ask like, okay, why do we have that?

07:45
part of the study design. Why do we need this in exclusion criteria? Why do we need this questionnaire? And also think about like, wouldn’t it be better to have a different design in any shape or form? Do we need an active comparotile? Do we need an external comparotile? Do we need anything so that we can do run an indirect comparison? Like maybe we have a typical questionnaire here in the study.

08:14
but all the external populations are run with a different questionnaire and would be much harder to do an indirect comparison that way. How long does the study need to be? There’s so many different things to think about and having that psychological safety so you can talk about these and ask about there’s a better way, that is really, really helpful. I would also add to that maybe missing data.

08:40
So working with the missing data, especially in oncology, you usually have different approaches and having the end in mind helps the statisticians together with the CPL to decide what’s the most optimal way. Yeah, so especially in oncology, also switching data, you need to understand how that impacts the safety analysis, what is the right estimate, explaining these estimates in a good way. One other thing you mentioned is

09:10
proactive behavior from the statistician. What do you think statisticians need to be more proactive? I think it should be the clear responsibility share. So when I was talking to my colleagues in biostatistics, I sometimes hear a sentiment that much more is expected in terms of proactiveness that is in the zone of control of this person.

09:38
And I’m very compassionate to that because of course the final decision on the end point lies at clinical program lead. And I feel like speaking about psychological safety, if a statistician understands that it will be not his or her final decision, they will feel much safer to propose different solutions. So not feeling this pressure to apply clinical filter, which people don’t have to have.

10:08
or not feeling this regulatory pressure and knowing that they always can consult with other colleagues and we can sometimes have shared responsibility or to perceive it as contribution, not as a final step. I think it helps proactiveness a lot. And what also helps is when the relationship are established in the way that you’re not only speaking that people must be proactive, but you really create this trust.

10:38
So the episode happens and you accept this, you welcome this feedback. Another time and another time and every time it becomes easier and easier. And sometimes my colleagues just came up with something I was not thinking about at all. For example, additional evaluation of probability of success of different scenarios or additional schema of endpoints analysis like the sequence.

11:04
and the alpha spreading. So it’s something not usually in my head as a clinical program lead, but these were very valuable discussions and we involved cross-functional colleagues, for example, what do you assess first, BFS or PROS? That’s actually a good question, right? And it doesn’t have sometimes the only one correct answer. Yeah, I think that’s a very, very good final sentence. There’s usually not black and white. There’s very lots of different things you can do.

11:33
And if you raise your proposal as an idea, even if maybe it’s really well thought through and you’re pretty sure about that it’s the right way to go, you can still raise it as an idea that it’s up for discussion. And that makes it much easier for everybody else to contribute. And then it becomes a much more of a team decision because many people will have different views on it. Yeah.

12:01
How feasible is it from an operational point of view? What will the regulators say about it? Will it be different in the US or in Europe? How will it be viewed from a access point of view? Or does that even matter for that study? What is the physician’s or patient’s point of view? So there’s always lots of lots of different considerations so that you can overall come up with a good solution. And from my personal perspective, I would even recommend to

12:30
bring this up earlier rather than later. You don’t need to bring up the polished and very well thought through decision. Just bring it as early as you have initial idea. Let’s challenge it. Let’s test its viability and we will co-create. We will make a common decision, which everyone will be happy with. And you will not have a frustration of spending plenty of time of something that would be denied. Yeah. I know that from

12:59
many of my trainings said this is a major topic. Yeah. So people participate in a meeting and it’s pretty fast paced discussion. And the statistician would have an idea of this is a different point to do it, but is hesitant to share it just because he may not have completely thought it through. Yeah. And then the discussion progresses and afterwards the statistician thinks like,

13:29
Maybe I should have said something, then it’s too late. So I encourage people to speak up, even if you’re not 100 % sure. And that is much easier in teen cultures that you have just discussed, where there’s a lot of trust, where there’s open debate, where everybody can contribute. Everybody is recognized and respected in such a culture.

13:56
it is much easier to come up with, let’s say, a half-baked solution that you just put out there as a question. So if you think about the typical skills of statisticians, these are usually the quantitative skills, the well-trained methodological people. And we talked about a couple of, let’s say, attitudes that they need to have or things that they need to do differently in terms of, for example, being

14:25
more proactive, more willing to share ideas that are not completely thought through and to think about all the different things that they do, having the end in mind. What skills do you think statisticians need to accomplish these and be really effective in such team environments? I would not speak a lot about specific methodology skills.

14:52
So in my experience, and I personally am not very well familiar with all the theories that statisticians know, but what I personally challenge constantly, can we have analysis earlier? because time is money and time is rich to the patients. And honestly, if you’re working in late stage environment, let’s stage development, you will constantly be asked.

15:20
Can we incorporate interim analysis to get to result faster, to get approval faster? And so you will be asked a lot of details. What will be the power of this analysis? What’s the information rate? Why is this and why not that? What’s your previous experience with regulators? So the skill to summarize this experience and to explain it in a lay language to the people who are not deep in the start topics, this is very valuable skill.

15:49
If we’re speaking about the early stage development, so I’m speaking mostly in oncology first in human, maybe phase two in non-oncology, here the flexibility is gold. Sometimes I know that people, like mathematical environment, tend to be very detail-oriented and very data-driven, but the questions like what if happens all the time? And I would ask, for example, is

16:19
this model the best to describe what’s going on? Is this approach to dose escalation is the optimal one? Can we do faster? Can we do with more precision? If we discuss bias and statistics, I would challenge what we put into the prior. And I want explanation because I want to understand what I’m doing. I need to present it. I need to defend it. And I need explanation in lay language and I need the willingness

16:46
and readiness to explore all these multiple scenarios or explain why they are not worth exploring. But in early development, will never be the case when you have set up something and forgot about that for two years. It will be a constant challenge, constant protocol amendments, and this is pretty normal and very valuable when statistician could support you on this journey. hear first one thing, explain things in layman’s terms.

17:15
From my point of view, this is one of the most important things statisticians need to be doing. Whenever I interview statisticians or have interviewed statisticians for new jobs in the last 20 years, one question was, imagine I’m a physician and have no clue about statistics, please explain to me what a p-value is. And then getting something that is understandable for non-statistician.

17:45
and still mostly correct. It doesn’t need to be 100 % correct, but mostly correct is super valuable. And that usually defined for me, is that a statistician that really understood things and is able to explain them. And this P-value question comes up again and again and again over my career. Also being as a statistician being asked from all different people, from marketing and market access and…

18:14
Our favorite question is what hazard ratio is. Could you explain what is the hazard ratio and what is the critical hazard ratio? This is what every medical and marketing person would ask you. Yeah. Yeah. Very good. Even understanding what a hazard is, is already a big thing. then it’s a hazard ratio and then you have non-propersional hazard ratios and things like this. Oh my God. Yeah. So all the theory.

18:43
is worthless if we can’t communicate it clearly. My experience is, if you can explain these things to non-statisticians, to your colleagues, this is highly appreciated by everybody. And it builds a lot of trust, builds trust in your competence and builds trust in the other relationship, also because you can show that you actually care for all the other non-statisticians.

19:11
And this is actually those soft skills that make you outstanding because hard skills many people have, but this trust is built exactly when I’ve asked a simple question and received a simple answer, even slightly incorrect in a very detailed manner. But yeah, this is something what makes people want to work with you, what makes people to invite you to the meetings of the wider team and to let you present yourself, let you speak up more and more.

19:40
Yeah, for me, even went also to the point where the physician I was working with needed to present a findings to a QP in a leader advisory board or to upper management. He would take me along and send, we would present the data together. And whenever there was any tricky questions, like why didn’t you do that way of different way of alpha spending or did we use that stopping rule? You can directly explain to it.

20:09
Especially when they are coming from another company and used to being doing it in a different way. Or maybe they have read a competitor publication and they have done it in a different way. If you can explain why you did it your way and not the other way on the spot, this is incredibly helpful. And your physician usually is really thankful that he or she doesn’t need to answer these technical questions. So people skills.

20:39
Soft skills are really, really important. In terms of SET, which soft skills do you see being most important? So a SET ability to explain, ability to ask question and understand what’s exactly needed, because the lay person sometimes cannot explain you in statistical terms what’s needed. for example,

21:03
I would come and say I need to show superiority in several subgroups. And I would be so much happier if you propose me something and show some schemes and explain why this is and that would work. And maybe say that a few subgroups I don’t need, it’s too much for the trial and propose another way to approach this. Maybe some exploratory endpoints, maybe some sensitivity analysis. So this skill to get what exactly is behind the question.

21:33
And sometimes answer to the questions that was not asked. This is very valuable. Or at least making me to come to the clear question to you. Maybe it will be not the first question. I love that point. I have seen that again and again and again in discussions. Yeah. There’s an initial question, but this is not the actual questions. This is just the, maybe the things that a certain person is used to getting or something like this and understanding.

22:02
The why behind it makes things so much easier. What will you do with it? Who will use it? Who’s the decision maker? What are the rules? Things like that. I once had a student in my leadership program and he was preparing safety results and Excel spreadsheets to go back to the physician. It was also some early phase studies. And through my program, he got encouraged to speak with a safety physician, him

22:32
What are you doing with it? And then the safety physicians showed him what he’s doing with it and how he’s exploring these Excel spreadsheet and how he’s comparing data. And the statistician said, well, these Excel spreadsheets are really a suboptimal tool to do all of that and programmed a Ashani application to display the data. And that reduced the working time for that physician that was on ongoing basis from one day to

23:01
10 minutes. Fantastic. And then he recommended that to all the other physicians doing similar tasks on similar studies and it got rolled out across the company. So just because someone dare to say, what do you need this for and what are the tasks behind so that you can come up with a tool that fits much better than it. We actually love the visual tools so much.

23:27
I was so happy when my beautiful colleagues introduced the visual tool for plenty of my exploratory analysis so that I stopped pinging them for each and every question. And it saved all of us so much time and I could do so much exploration on myself. It was so valuable. Yeah. I think every study at the end needs some interactive data visualization because exactly

23:54
for the exploring subgroups, exploring additional analysis, and that speeds up time like nothing. And also it saves a lot of additional programming time and all these other things. And in this topic, I usually come up with some hesitance. I meet some hesitance about this exploratory analysis is not validated. You cannot publish it. You cannot bring it to the regulator, but this is not the point.

24:24
All this exploratory analysis are purely for internal understanding. What went wrong? What are the signals? Where could we look next? What can we utilize for our real-world evidence studies? And there are very different goals and very different understanding of all this regulatory stuff and the pure creativity and exploration stuff. So I hope there is an understanding of that and a bit of less hesitance.

24:52
to provide these unregulated tools for unregulated exploration. Yeah, and very often you have, let’s say, 20 different endpoints. You have 10 different subgroups, and then you have a couple of different populations that you actually look into. That creates a huge pile of tables. Understanding these tables is not that straightforward. Even putting all these numbers in the tables into a good tool will help you a lot.

25:21
And also understanding how data has changed. Like you have mentioned oncology, have the different data cuts. How did the data change across the different data cuts? Are there any new things? Things like that. Safety, always a great tool for data exploration to understand what’s going on so that you can get a sense of what is happening in the data again and again and again. The more you get

25:49
beyond the regulatory things, it’s really, really important to explore your data and understand your data. Absolutely. Talking about this, given that you’re also working in oncology and we are now in 2026, I think there’s one topic we can’t really avoid and that is the EUJCA and how that impacts all our work and also the statistics work, especially. So in your environment,

26:19
How has the EUJCA process impacted you? Yeah, I’ve actually experienced that already. And I would say mostly with our HR manager rather than statisticians, but I would say it requires a new way of working. Maybe one of the main problems is that now we need to acknowledge all the different standards of care in different countries.

26:46
And my yet limited experience with the UGCA, I would say that Germany sometimes have strange standard of care in their official documents. It doesn’t match with the guidelines. So I’m not sure what the logic is behind, but we need to respect that and acknowledge while trial planning. And it creates additional difficulties when you plan the global trial across different regions with very different standard of care.

27:15
And actually you cannot just put everything into your control arm. Here it’s quite a cross-functional effort to decide what exactly you would put to the control arm. What would be statistical assumptions for the control so that we don’t underestimate the control performance at the end. And also we would need to plan additional comparisons, indirect comparisons, literature research, I don’t know, some meta-analysis or real-world studies to satisfy.

27:45
the regulator at the end. And for me, this is the major challenge. The other thing I was involved in is preparing for the dossier submission much in advance. So actually you have to do this at risk. You have to invest effort and time when you don’t know yet if you submit your drug for approval at all. This is what I don’t like about this process because it blocks a lot of colleagues for some time.

28:13
But this is the reality we have to work with. Maybe it will change sometime in the future. Yeah. Yeah. Completely agree. You need to do a lot of work at risk, starting with the comparator scene that you mentioned, understanding what is the guideline, but also understanding what is the typical standard of care in the different markets. We are, example, also, Rebilled Evidence can help you quite a lot. You can run a Rebilled

28:41
retrospective analysis on German claims data to understand what treatment is used and is there maybe some treatments that the GBA thinks about is important but is not that important and then you maybe can exclude these things. What are the different doses that are managed there? How long are they treated? What are the patient populations? There’s another really, really interesting point, making sure that you have outcomes that are accepted across all these different countries.

29:10
So in a sense, also what’s called Pico statement have said clear and they are both targeted as well as systematic literature reviews are really important, which will help you to inform your trial design, but also help with indirect proposals, network meta analysis, all these things you need to basically have prepared. Last year I was in some APF meeting here in Germany that was all about

29:39
that new part and one of the key messages was you can’t start early enough with all the work because it’s a huge amount of work. And my takeaway is also the statisticians that work on these HTA things needs to work hand in hand with the people that work on the studies and the clinical submissions. And I understand it’s a very different skill set for the statistician.

30:09
to work on the dose here and to work on the trial design. Yeah. Yeah. It’s a very, very different skill set. You usually also come from a very, very different thought process. And of course it would be optimal to have someone that knows everything, but I have not yet come across such a unicorn statistician that knows both worlds inside out. Any final point Anna that you would like to keep the listener with? I would recap on the partnership. So.

30:37
It’s so much important when we work and this is like ability to have some ownership and ability to communicate with the other colleagues at the eye level is something that makes outstanding statistical leaders versus those who stay as contributors. So if you want to develop into the leadership, the soft skills, communication, translation from start language to a language person.

31:06
understanding the why’s behind the questions and discussions. This is all so crucial. And I cannot judge on the hard skills which are needed to become the beautiful expert, but definitely people who are mastering both the hard and the soft skills are such a gem in our organizations and it’s such a great pleasure working with them. Thanks so much, Anna. I can only reiterate what you have said. Thanks so much for having you.

31:34
Thank you, my pleasure.

31:41
This show was created in association with PSI. Thanks to Rain and her team at VVS. Well, put the show in the background and thank you for listening. Read your potential, great signs and serve patients. Just be an effective statistician.

Join The Effective Statistician LinkedIn group

I want to help the community of statisticians, data scientists, programmers and other quantitative scientists to be more influential, innovative, and effective. I believe that as a community we can help our research, our regulatory and payer systems, and ultimately physicians and patients take better decisions based on better evidence.

I work to achieve a future in which everyone can access the right evidence in the right format at the right time to make sound decisions.

When my kids are sick, I want to have good evidence to discuss with the physician about the different therapy choices.

When my mother is sick, I want her to understand the evidence and being able to understand it.

When I get sick, I want to find evidence that I can trust and that helps me to have meaningful discussions with my healthcare professionals.

I want to live in a world, where the media reports correctly about medical evidence and in which society distinguishes between fake evidence and real evidence.

Let’s work together to achieve this.