Results 1 to 9 of 9

Thread: Salary surveys worthless?

  1. #1

    Thread Starter
    PowerPoster
    Join Date
    Feb 2006
    Posts
    24,482

    Salary surveys worthless?

    We see plenty of these, and you have to wonder.

    Do they throw out data they don't like? Intentionally or otherwise work from a selected/restricted survey population?

    Or are they just nuts?

    Tabs versus Spaces? Not Just Contentious But Economic

    The surprising finding that developers who use spaces for indentation make more money that those who use tabs comes from Stack Overflow's Data Scientist David Robinson in a blog post that also announces that the raw data for the Stack Overflow Developer Survey is available for download.

  2. #2
    Super Moderator jmcilhinney's Avatar
    Join Date
    May 2005
    Location
    Sydney, Australia
    Posts
    110,297

    Re: Salary surveys worthless?

    Even if that finding is 100% true, I very much doubt that anyone is going to improve their career prospects markedly by switching to using Tabs instead of spaces. Correlation does not inherently imply causation.

  3. #3
    Ex-Super Mod RobDog888's Avatar
    Join Date
    Apr 2001
    Location
    LA, Calif. Raiders #1 AKA:Gangsta Yoda™
    Posts
    60,710

    Re: Salary surveys worthless?

    Well they also state that it can be influenced by the language. Some dont use tabs and some do. Perhaps they skew the results a certain way to spark a debate which gives them more exposure
    VB/Office Guru™ (AKA: Gangsta Yoda®)
    I dont answer coding questions via PM. Please post a thread in the appropriate forum.

    Microsoft MVP 2006-2011
    Office Development FAQ (C#, VB.NET, VB 6, VBA)
    Senior Jedi Software Engineer MCP (VB 6 & .NET), BSEE, CET
    If a post has helped you then Please Rate it!
    Reps & Rating PostsVS.NET on Vista Multiple .NET Framework Versions Office Primary Interop AssembliesVB/Office Guru™ Word SpellChecker™.NETVB/Office Guru™ Word SpellChecker™ VB6VB.NET Attributes Ex.Outlook Global Address ListAPI Viewer utility.NET API Viewer Utility
    System: Intel i7 6850K, Geforce GTX1060, Samsung M.2 1 TB & SATA 500 GB, 32 GBs DDR4 3300 Quad Channel RAM, 2 Viewsonic 24" LCDs, Windows 10, Office 2016, VS 2019, VB6 SP6

  4. #4
    Super Moderator jmcilhinney's Avatar
    Join Date
    May 2005
    Location
    Sydney, Australia
    Posts
    110,297

    Re: Salary surveys worthless?

    Quote Originally Posted by RobDog888 View Post
    Well they also state that it can be influenced by the language. Some dont use tabs and some do. Perhaps they skew the results a certain way to spark a debate which gives them more exposure
    I think that most of us who use VS for .NET programming rely on the IDE to add the appropriate indentation whenever we hit Enter. I think that VS used to favour Tabs but now uses spaces by default. That said, that may just be the case for VB and it may always have been spaces for C#. Given that C# developers tend to make more than VB developers, the language being the important factor could well stand up in .NET development at least.

  5. #5
    Ex-Super Mod RobDog888's Avatar
    Join Date
    Apr 2001
    Location
    LA, Calif. Raiders #1 AKA:Gangsta Yoda™
    Posts
    60,710

    Re: Salary surveys worthless?

    Yea they needed to break it down by language and do comparisons from within each.
    VB/Office Guru™ (AKA: Gangsta Yoda®)
    I dont answer coding questions via PM. Please post a thread in the appropriate forum.

    Microsoft MVP 2006-2011
    Office Development FAQ (C#, VB.NET, VB 6, VBA)
    Senior Jedi Software Engineer MCP (VB 6 & .NET), BSEE, CET
    If a post has helped you then Please Rate it!
    Reps & Rating PostsVS.NET on Vista Multiple .NET Framework Versions Office Primary Interop AssembliesVB/Office Guru™ Word SpellChecker™.NETVB/Office Guru™ Word SpellChecker™ VB6VB.NET Attributes Ex.Outlook Global Address ListAPI Viewer utility.NET API Viewer Utility
    System: Intel i7 6850K, Geforce GTX1060, Samsung M.2 1 TB & SATA 500 GB, 32 GBs DDR4 3300 Quad Channel RAM, 2 Viewsonic 24" LCDs, Windows 10, Office 2016, VS 2019, VB6 SP6

  6. #6
    Smooth Moperator techgnome's Avatar
    Join Date
    May 2002
    Posts
    34,531

    Re: Salary surveys worthless?

    I'd also wonder if experience plays a role in it too.... years ago I was all about the tabs... now... I prefer the spaces.

    -tg
    * I don't respond to private (PM) requests for help. It's not conducive to the general learning of others.*
    * I also don't respond to friend requests. Save a few bits and don't bother. I'll just end up rejecting anyways.*
    * How to get EFFECTIVE help: The Hitchhiker's Guide to Getting Help at VBF - Removing eels from your hovercraft *
    * How to Use Parameters * Create Disconnected ADO Recordset Clones * Set your VB6 ActiveX Compatibility * Get rid of those pesky VB Line Numbers * I swear I saved my data, where'd it run off to??? *

  7. #7
    Super Moderator Shaggy Hiker's Avatar
    Join Date
    Aug 2002
    Location
    Idaho
    Posts
    38,988

    Re: Salary surveys worthless?

    This study is nuts. For one thing, there are no error bars around anything. All they are reporting is a simple mean about which the error bars would have to be HUGE. Heck, they are comparing across countries. Even within the US any such comparison would be rendered absurd by the differences in cost of living around the country. This would result in very large error bars that would greatly overlap and pretty much ruin the reliability of the statistics, such as they are.

    The study does say that the difference held true across languages, but doesn't back that up. It does have this quote:

    The model estimated that using spaces instead of tabs leads to a 8.6% higher salary
    That's clearly false. The model estimated that there was a correlation between spaces and higher salary. The statement explicitly says that it's a causal relationship, which is absurd. That would mean that somebody using tabs could switch to using spaces and receive an 8.6% raise, which everybody knows is not true. At the very best, it's just an artifact of auto-correlation.
    My usual boring signature: Nothing

  8. #8
    You don't want to know.
    Join Date
    Aug 2010
    Posts
    4,578

    Re: Salary surveys worthless?

    I think it's a goofy false correlation. Here's a few of my favorites, like "More people drown in years with more Nicholas Cage films". JMC and Shaggy Hiker are right here.

    The data suggests, interestingly, people who use spaces are paid more. That could lead to some fun further questions to figure out if it's survey bias or some strange correlation that other data would expose. It most definitely does not imply "using spaces gets you a higher salary". Try pitching that to your boss. You'll be making the same next month you're making this month.

    My going theory is:

    • The sample group consists of "people who post on Stack Overflow".
    • The SO post editor is a web text entry.
    • Pressing Tab in the entry box unavoidably switches focus, rather than adding a tab.
    • People who answer SO questions with regularity tend to be more experienced, skilled developers.
    • "Self-selecting" surveys are widely known for bias: only people passionate about the topic provide answers.

    So the group of people most likely to take a StackOverflow survey are a group of passionate developers most likely to be used to using spaces or "both", not tabs exclusively, and are more likely to be making an above-median salary when compared to a larger universe of developers. Which means the survey is likely to have a bias towards space-using higher-paid developers, and the data reflects the bias.

    It's hard to get disinterested people to respond to surveys, but that's the only way to make sure you adequately represent all parties. There's a reason it costs money to get good data. It's work.
    This answer is wrong. You should be using TableAdapter and Dictionaries instead.

  9. #9
    Super Moderator Shaggy Hiker's Avatar
    Join Date
    Aug 2002
    Location
    Idaho
    Posts
    38,988

    Re: Salary surveys worthless?

    Lies, damn lies, and statistics.

    I remember an example from a statistics class I took back in college: The number of bars in a city is directly correlated with the number of Baptist ministers.

    Not only is this true, it's a very good correlation. Of course, it's also meaningless. The larger the population, the more of pretty nearly everything, so any two items would be correlated.
    My usual boring signature: Nothing

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •  



Click Here to Expand Forum to Full Width