Hi there. In this simulation, we're assuming that "log returns" are normally distributed. So, if your historical data is "log returns", and you believe the data follows a normal distribution, you can directly use the mean and standard deviation without transformation. You can have a look at our blog post (especially the section titled "Normal distribution of log returns") for further details: www.initialreturn.com/simulating-stock-price-paths-with-random-walks-in-excel Hope this helps!

Great to hear the refresher was helpful:) Thanks for watching!

Not sure exactly what you mean by the "weighted average". Are you referring to the investment weights? In this tutorial, we're assuming an equally-weighted portfolio, but you can pick any weight you like.

@@initialreturnsorry I meant to ask how did you find the returns for the last x months?

@@has9629 Oh, ok. You can download historical prices from Yahoo! finance and compute the returns. Have a look at these two tutorials where we explain how to do that: kzbin.info/www/bejne/q528l3mKd9p4qbM (downloading prices), kzbin.info/www/bejne/f2LMiopjnZqLsM0 (computing returns).

You can estimate the expected return by either using the average of historical returns or calculating betas (learn more here: kzbin.info/www/bejne/paqcpGhspqp2qtE ) and applying the CAPM equation (details here: kzbin.info/www/bejne/m5und5iMhqqfd8k ).

If you mean the investment weights, the investor chooses them based on how much he wants to invest in each stock. If you're interested in finding the optimal risky portfolio with optimal investment weights, we've got a separate tutorial on that here: kzbin.info/www/bejne/fIjUmpR-f9aLndU

Thank you for your encouraging comment! Much appreciated!

Thank you for the positive feedback! Great to hear you found this tutorial useful!

Great to hear that you found the tutorial helpful! And, thanks for watching it until the end!

Strange. Try different initial values of investment weights to see if any of them changes at all when solver finds a solution.

Thank you! 😊 It's always great to hear that viewers appreciate our content.

That's great to hear! Thanks for watching our videos!

Do you want to construct an efficient frontier based on 5 stocks? If that's what you mean, we have a separate tutorial on that here: kzbin.info/www/bejne/hWqyYoSmgtqsqdE

You're right: It's conventional (but not always a must) to annualize returns and standard deviations. For standard deviation, you can multiply the monthly standard deviation by the square root of 12 to get an annualized figure. And, for monthly returns, you can either multiply by 12 (that would ignore the effect of compounding) or compound for 12 months as follows: (1+return)^12 - 1.

Sure. A secondary offering is a type of seasoned equity offering whereby the shares are sold by existing shareholders. This means the company doesn't raise any proceeds from such an issue, and all the proceeds go to those shareholders who sold shares. Hope this helps!

@@initialreturn so if may get the point right, SEO is where the existing shareholders issue their share to the public and the proceeds go the company whiles the secondary offering, the proceeds goes shareholders who issue their shares

Not quite. Basically, an SEO can feature new shares issued by the company AND/OR existing shares sold by current shareholders. If it's existing shares ONLY, such an SEO is known as a secondary offering.

@@initialreturn perfectly understood sir.. Thank you You have really helped me in my academics and work life

Hello there. It seems the confusion arises from the date format, which is day/month/year in this video. For example, 01/06/2018 is June 1st, 2018 and 01/07/2018 is July 1st, 2018. You can get adjusted prices from Yahoo! Finance for free. We have a separate video on that titled "downloading stock price data". Hope this helps!

Hi there, thanks for the comments! The index is based on 157 countries, and the remaining countries are left out... If you follow the link in the video description to the original story, you can see the full list of rankings.

There's a recent, relevant speech on this by a Bank of England economist here: www.bankofengland.co.uk/speech/2023/november/jonathan-haskel-panellist-at-the-boe-watchers-conference-labour-market-dynamics

@@initialreturn None of them is a monetarist. They get everything wrong! Their Governor is a historian, btw.! Watch Milton Friedman or Steve Hanke, who had accurately forecast 9% peak CPI 1.5 years in advance, while those neo-Keynesians were on the team transitory!

They're doing well as far as this index is concerned. But, of course, that doesn't necessarily mean it is the best place to live!

thanks for showing your appreciation!

For the Indian market, the conventional choices are Nifty 50 and BSE Sensex as you mentioned. It's unlikely that the beta estimates would be too different when you use one rather than the other.

That's great to hear! Good luck with your work.

Hi there, it depends on your objectives. For example, if you'd like to compute portfolio risk & return to evaluate performance over a specific period, you'd use daily returns covering that entire period. Or, if it's for forecasting future returns, you'd typically need at least one year's worth of daily data.

Thank You so much for your response..

Can i take data from the day that i have made investment ??

Daily returns are typically small. So, starting your sample period one day before or after would normally make very little practical difference in your results. Ideally, you'd like to use the price you paid as the starting point. So, if you bought your shares, say, on Jan 1 you can use either the closing price on that day or the exact price you paid during that day as your starting point.

@@initialreturn 🙏🏻🙏🏻

One potential source is Yahoo! Finance. If you search for ^IRX, it gives you the 13-week T-bill rates. Alternatively, you can download it from Ken French's (as in Fama-French) data library.

Great to hear your positive feedback! It's always a big motivation for us. And, thanks for watching too!

Thank you so much! Some videos are pretty recent uploads, so here's hoping KZbin will give us more exposure in the coming months:)) And, great to see viewers like you appreciate our efforts!

Hi there, we have a tutorial on that here: kzbin.info/www/bejne/q528l3mKd9p4qbM

Delighted to hear this and thanks for watching!

A larger dataset would help in general as it would decrease the standard error of your estimates. But, the aim shouldn't be to "engineer" a statistically significant alpha. Ultimately, you'd like to know whether alpha was zero or not. An alpha estimate not statistically different than zero is also useful information...

Hi there. Here's how we do it: (1) download stock prices from Yahoo! Finance, and (2) use the "Adj Close", which stands for "adjusted closing prices", column to compute stock returns. Don't use the "Close" column because those are raw prices that don't account for stock splits and dividends. We have a separate video on downloading stock prices from Yahoo! Finance, which may be helpful for you. It's the first video in our "Analyzing stock returns" playlist.

Hi there! Great to hear you find our content helpful!

Hi there. One way to do that would be to go to the "Chart Design" tab (the plot needs to be selected) and click on "Select Data." You'd then see a popup menu with the title "Select data source". There, you can add multiple stocks by clicking the "Add" button. Each stock would be a "series" in the plot. The problem is that, though, some of these plots may not look great with multiple stocks. So, you might have to do some formatting... Hope this helps!

Thanks for watching and glad to hear it was useful for you!